From ee08e5796f798c56acb2e55ffaa290bfaf81efcf Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Wed, 20 Sep 2023 17:44:29 +0200 Subject: [PATCH 01/25] Added a copy of the ENA templates for the upload tool --- .../library construction_v1.3.0.json | 249 +++++++ .../nucleic acid extraction_v1.2.0.json | 57 ++ .../nucleic acid sequencing_v1.3.0.json | 171 +++++ .../sample_collection_v1.0.0.json | 45 ++ .../sequence assembly_v1.2.0.json | 66 ++ .../source_all_organisms_v1.1.0.json | 656 ++++++++++++++++++ 6 files changed, 1244 insertions(+) create mode 100644 templates/ena_upload_tool/library construction_v1.3.0.json create mode 100644 templates/ena_upload_tool/nucleic acid extraction_v1.2.0.json create mode 100644 templates/ena_upload_tool/nucleic acid sequencing_v1.3.0.json create mode 100644 templates/ena_upload_tool/sample_collection_v1.0.0.json create mode 100644 templates/ena_upload_tool/sequence assembly_v1.2.0.json create mode 100644 templates/ena_upload_tool/source_all_organisms_v1.1.0.json diff --git a/templates/ena_upload_tool/library construction_v1.3.0.json b/templates/ena_upload_tool/library construction_v1.3.0.json new file mode 100644 index 0000000..5833f64 --- /dev/null +++ b/templates/ena_upload_tool/library construction_v1.3.0.json @@ -0,0 +1,249 @@ +{ + "metadata": { + "name": "library construction", + "group": "ena modified for upload tool", + "group_order": 4, + "temporary_name": "4_ena_library_construction", + "version": "1.3.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "library construction", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "SEEK Sample Multi", + "required": "true", + "isaTag": null + }, + { + "iri": null, + "name": "library construction", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "library_construction_protocol", + "description": "Free form text describing the protocol by which the sequencing library was constructed.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "Title", + "description": "Short text that can be used to call out experiment records in searches or in displays.", + "required": true, + "ontology": null, + "dataType": "String", + "CVList": null, + "isaTag": "otherMaterial_characteristic" + }, + { + "iri": null, + "name": "design_description", + "description": "The design of the library including details of how it was constructed. ", + "required": true, + "ontology": null, + "dataType": "String", + "CVList": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library source", + "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced. (SRA 1.2 documentation)", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "GENOMIC", + "GENOMIC SINGLE CELL", + "TRANSCRIPTOMIC", + "TRANSCRIPTOMIC SINGLE CELL", + "METAGENOMIC", + "METATRANSCRIPTOMIC", + "SYNTHETIC", + "VIRAL RNA", + "OTHER" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library strategy", + "description": "Sequencing technique intended for this library (SRA 1.2 documentation)", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "WGS", + "WGA", + "WXS", + "RNA-Seq", + "ssRNA-seq", + "miRNA-Seq", + "ncRNA-Seq", + "FL-cDNA", + "EST", + "Hi-C", + "ATAC-seq", + "WCS", + "RAD-Seq", + "CLONE", + "POOLCLONE", + "AMPLICON", + "CLONEEND", + "FINISHING", + "ChIP-Seq", + "MNase-Seq", + "DNase-Hypersensitivity", + "Bisulfite-Seq", + "CTS", + "MRE-Seq", + "MeDIP-Seq", + "MBD-Seq", + "Tn-Seq", + "VALIDATION", + "FAIRE-seq", + "SELEX", + "RIP-Seq", + "ChIA-PET", + "Synthetic-Long-Read", + "Targeted-Capture", + "Tethered Chromatin Conformation Capture", + "OTHER", + "NOMe-Seq", + "ChM-Seq", + "GBS" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library selection", + "description": "Whether any method was used to select for or against, enrich, or screen the material being sequenced. (SRA 1.2 documentation)", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "RANDOM", + "PCR", + "RANDOM PCR", + "RT-PCR", + "HMPR", + "MF", + "repeat fractionation", + "size fractionation", + "MSLL", + "cDNA", + "cDNA_randomPriming", + "cDNA_oligo_dT", + "PolyA", + "Oligo-dT", + "Inverse rRNA", + "Inverse rRNA selection", + "ChIP", + "ChIP-Seq", + "MNase", + "DNase", + "Hybrid Selection", + "Reduced Representation", + "Restriction Digest", + "5-methylcytidine antibody", + "MBD2 protein methyl-CpG binding domain", + "CAGE", + "RACE", + "MDA", + "padlock probes capture method", + "other", + "unspecified" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library layout", + "description": "specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", + "dataType": "Controlled Vocabulary", + "required": false, + "ontology": null, + "CVList": [ + "SINGLE", + "PAIRED" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "insert size", + "description": "Insert size for paired reads.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library name", + "description": "Name given to the generated library", + "dataType": "String", + "title": true, + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "otherMaterial" + }, + { + "iri": null, + "name": "submission date", + "description": "Date in which experiment was submitted to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "otherMaterial_characteristic" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "release", + "released" + ], + "isaTag": "otherMaterial_characteristic" + }, + { + "iri": null, + "name": "accession", + "description": "ENA experiment accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "otherMaterial_characteristic" + } + ] +} diff --git a/templates/ena_upload_tool/nucleic acid extraction_v1.2.0.json b/templates/ena_upload_tool/nucleic acid extraction_v1.2.0.json new file mode 100644 index 0000000..8eff559 --- /dev/null +++ b/templates/ena_upload_tool/nucleic acid extraction_v1.2.0.json @@ -0,0 +1,57 @@ +{ + "metadata": { + "name": "nucleic acid extraction", + "group": "ena modified for upload tool", + "group_order": 3, + "temporary_name": "3_ena_nucleic_acid_extraction", + "version": "1.2.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "nucleic acid extraction", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "SEEK Sample Multi", + "required": "true", + "isaTag": null + }, + { + "iri": null, + "name": "nucleic acid extraction", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": , //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "sample volume or weight for DNA extraction", + "description": "Volume (mL) or weight (g) of sample processed for DNA extraction", + "required": false, + "ontology": null, + "dataType": "String", // Original regex "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?", + "unit": null, //Original unit options ["mL","g"], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "Extract Name", + "description": "User-defined names for each portion of extracted material.", + "dataType": "String", + "title": true, + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "otherMaterial" + } + ] +} diff --git a/templates/ena_upload_tool/nucleic acid sequencing_v1.3.0.json b/templates/ena_upload_tool/nucleic acid sequencing_v1.3.0.json new file mode 100644 index 0000000..3d9d6af --- /dev/null +++ b/templates/ena_upload_tool/nucleic acid sequencing_v1.3.0.json @@ -0,0 +1,171 @@ +{ + "metadata": { + "name": "nucleic acid sequencing", + "group": "ena modified for upload tool", + "group_order": 5, + "temporary_name": "5_ena_nucleic_acid_sequencing", + "version": "1.3.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "nucleic acid sequencing", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "SEEK Sample Multi", + "required": true, + "isaTag": null + }, + { + "iri": null, + "name": "nucleic acid sequencing", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "sequencing instrument", + "description": "a parameter to report the sequencing instrument model and make", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + " 454 GS", + " 454 GS 20", + " 454 GS FLX", + " 454 GS FLX+", + " 454 GS FLX Titanium", + " 454 GS Junior", + " HiSeq X Five", + " HiSeq X Ten", + " Illumina Genome Analyzer", + " Illumina Genome Analyzer II", + " Illumina Genome Analyzer IIx", + " Illumina HiScanSQ", + " Illumina HiSeq 1000", + " Illumina HiSeq 1500", + " Illumina HiSeq 2000", + " Illumina HiSeq 2500", + " Illumina HiSeq 3000", + " Illumina HiSeq 4000", + " Illumina iSeq 100", + " Illumina MiSeq", + " Illumina MiniSeq", + " Illumina NovaSeq 6000", + " NextSeq 500", + " NextSeq 550", + " PacBio RS", + " PacBio RS II", + " Sequel", + " Ion Torrent PGM", + " Ion Torrent Proton", + " Ion Torrent S5", + " Ion Torrent S5 XL", + " AB 3730xL Genetic Analyzer", + " AB 3730 Genetic Analyzer", + " AB 3500xL Genetic Analyzer", + " AB 3500 Genetic Analyzer", + " AB 3130xL Genetic Analyzer", + " AB 3130 Genetic Analyzer", + " AB 310 Genetic Analyzer", + " MinION", + " GridION", + " PromethION", + " BGISEQ-500", + " DNBSEQ-T7", + " DNBSEQ-G400", + " DNBSEQ-G50", + " DNBSEQ-G400 FAST", + " unspecified" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "file type", + "description": "The run data file model.", + "dataType": "String", + "required": true, + "ontology": null, + "CVList": [ + "bam", + "cram", + "fastq", + "oxfordnanopore_native", + "pacbio_hdf5", + "sff" + ], + "isaTag": "dataFile_comment" + }, + { + "iri": null, + "name": "file checksum", + "description": "The MD5 checksum of the file.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "dataFile_comment" + }, + { + "iri": null, + "name": "Raw Data File", + "description": "Name (or URI) of the raw data file generated by an assay.", + "dataType": "String", + "title": true, + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "dataFile" + }, + { + "iri": null, + "name": "submission date", + "description": "Date in which run was submitted to ENA.Date of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "dataFile_comment" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "release", + "released" + ], + "isaTag": "dataFile_comment" + }, + { + "iri": null, + "name": "accession", + "description": "ENA run accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "dataFile_comment" + } + ] +} diff --git a/templates/ena_upload_tool/sample_collection_v1.0.0.json b/templates/ena_upload_tool/sample_collection_v1.0.0.json new file mode 100644 index 0000000..3089d3f --- /dev/null +++ b/templates/ena_upload_tool/sample_collection_v1.0.0.json @@ -0,0 +1,45 @@ +{ + "metadata": { + "name": "sample collection", + "group": "ena modified for upload tool", + "group_order": 2, + "temporary_name": "2_ena_sample_collection", + "version": "1.0.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": null, + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "sample collection", + "repo_schema_id": "ERC000011.xml 2021", + "organism": "any", + "level": "study sample" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "SEEK Sample Multi", + "required": true, + "isaTag": null + }, + { + "iri": null, + "name": "sample collection", + "description": "type of assay or experimental step performed.", + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "required": true, + "ontology": null, + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "Sample Name", + "description": "Name of the major output resulting from the application of the protocol.", + "dataType": "String", + "title": true, + "required": true, + "isaTag": "sample" + } + ] +} diff --git a/templates/ena_upload_tool/sequence assembly_v1.2.0.json b/templates/ena_upload_tool/sequence assembly_v1.2.0.json new file mode 100644 index 0000000..73c1686 --- /dev/null +++ b/templates/ena_upload_tool/sequence assembly_v1.2.0.json @@ -0,0 +1,66 @@ +{ + "metadata": { + "name": "sequence assembly", + "group": "ena modified for upload tool", + "group_order": 6, + "temporary_name": "6_ena_sequence_assembly", + "version": "1.2.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "sequence assembly", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "seek sample multi", + "required": "true", + "isaTag": null + }, + { + "iri": null, + "name": "sequence assembly", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": , //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "Normalization Name", + "description": "User-defined name for each normalization applied", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "Data Transformation Name", + "description": "a data transformation", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "Derived Data File", + "description": "derived data such as an assembly file", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "dataFile" + } + ] +} diff --git a/templates/ena_upload_tool/source_all_organisms_v1.1.0.json b/templates/ena_upload_tool/source_all_organisms_v1.1.0.json new file mode 100644 index 0000000..a70317b --- /dev/null +++ b/templates/ena_upload_tool/source_all_organisms_v1.1.0.json @@ -0,0 +1,656 @@ +{ + "metadata": { + "name": "source all organisms", + "group": "ena modified for upload tool", + "group_order": 1, + "temporary_name": "1_ena_source_all_organisms", + "version": "1.1.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": null, + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": null, + "repo_schema_id": "ERC000011.xml 2021", + "organism": "any", + "level": "study source" + }, + "data": [ + { + "iri": null, + "name": "Source Name", + "description": "Sources are considered as the starting biological material used in a study.", + "dataType": "String", + "title": true, + "required": true, + "isaTag": "source" + }, + { + "iri": null, + "name": "Title", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "dataType": "String", + "required": true, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "Description", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "dataType": "String", + "required": true, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "tax_id", //First field on an ENA sample file. It is the number ID + "description": "NCBI Taxonomy Identifier number ID. This is appropriate for individual organisms and some environmental samples.", + "dataType": "String", + "required": true, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "organism", + "description": "Provide a taxonomic information associated to the Source Biological material (for example, Species, genus, strain,....). Ideally, provide NCBI TaxID or NEWT identifier", //Changed to the description from ENA + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "cell_type", + "description": "cell type from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "dev_stage", + "description": "if the sample was obtained from an organism in a specific developmental stage, it is specified with this qualifier", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "germline", + "description": "the sample described presented in the entry has not undergone somatic genomic rearrangement as part of an adaptive immune response; it is the unrearranged molecule that was inherited from the parental germline", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "tissue_lib", + "description": "tissue library from which sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "tissue_type", + "description": "tissue type from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "collection_date", + "description": "The date of sampling, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.", + "dataType": "String", //original Regex "^[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "isolation_source", + "description": "describes the physical, environmental and/or local geographical source of the biological sample from which the sample was derived", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "lat_lon", + "description": "geographical coordinates of the location where the specimen was collected", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "collected_by", + "description": "name of persons or institute who collected the specimen", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "geographic location (country and/or sea)", + "description": "The geographical origin of the sample as defined by the country or sea. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", + "dataType": "Controlled Vocabulary", + "required": false, + "ontology": null, + "CVList": [ + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "not applicable", + "not collected", + "not provided", + "restricted access" + ], + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "geographic location (region and locality)", + "description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "identified_by", + "description": "name of the expert who identified the specimen taxonomically", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "environmental_sample", + "description": "identifies sequences derived by direct molecular isolation from a bulk environmental DNA sample (by PCR with or without subsequent cloning of the product, DGGE, or other anonymous methods) with no reliable identification of the source organism", + "dataType": "Controlled Vocabulary", + "required": false, + "ontology": null, + "CVList": [ + "No", + "Yes" + ], + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "mating_type", + "description": "mating type of the organism from which the sequence was obtained; mating type is used for prokaryotes, and for eukaryotes that undergo meiosis without sexually dimorphic gametes", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "sex", + "description": "sex of the organism from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "lab_host", + "description": "scientific name of the laboratory host used to propagate the source organism from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "host scientific name", + "description": "Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "bio_material", + "description": "identifier for the biological material from which the sample was obtained, with optional institution code and collection code for the place where it is currently stored.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "culture_collection", + "description": "institution code and identifier for the culture from which the sample was obtained, with optional collection code.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "specimen_voucher", + "description": "identifier for the specimen from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "cultivar", + "description": "cultivar (cultivated variety) of plant from which sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "ecotype", + "description": "a population within a given species displaying genetically based, phenotypic traits that reflect adaptation to a local habitat.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "isolate", + "description": "individual isolate from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "sub_species", + "description": "name of sub-species of organism from which sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "variety", + "description": "variety (= varietas, a formal Linnaean rank) of organism from which sample was derived.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "sub_strain", + "description": "name or identifier of a genetically or otherwise modified strain from which sample was obtained, derived from a parental strain (which should be annotated in the strain field; sub_strain from which sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "cell_line", + "description": "cell line from which the sample was obtained", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "serotype", + "description": "serological variety of a species characterized by its antigenic properties", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "serovar", + "description": "serological variety of a species (usually a prokaryote) characterized by its antigenic properties", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "strain", + "description": "Name of the strain from which the sample was obtained.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "submission date", + "description": "Date in which sample was submitted to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "release", + "released" + ], + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "accession", + "description": "ENA sample accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "source_characteristic" + } + ] +} From 2d262fcc6a4f2c27632f8fa4506556c204b82be6 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:01:40 +0200 Subject: [PATCH 02/25] Renamed the template files --- ...library construction_v1.3.0.json => library construction.json} | 0 ...c acid extraction_v1.2.0.json => nucleic acid extraction.json} | 0 ...c acid sequencing_v1.3.0.json => nucleic acid sequencing.json} | 0 .../{sample_collection_v1.0.0.json => sample collection.json} | 0 .../{sequence assembly_v1.2.0.json => sequence assembly.json} | 0 ...source_all_organisms_v1.1.0.json => source all organisms.json} | 0 6 files changed, 0 insertions(+), 0 deletions(-) rename templates/ena_upload_tool/{library construction_v1.3.0.json => library construction.json} (100%) rename templates/ena_upload_tool/{nucleic acid extraction_v1.2.0.json => nucleic acid extraction.json} (100%) rename templates/ena_upload_tool/{nucleic acid sequencing_v1.3.0.json => nucleic acid sequencing.json} (100%) rename templates/ena_upload_tool/{sample_collection_v1.0.0.json => sample collection.json} (100%) rename templates/ena_upload_tool/{sequence assembly_v1.2.0.json => sequence assembly.json} (100%) rename templates/ena_upload_tool/{source_all_organisms_v1.1.0.json => source all organisms.json} (100%) diff --git a/templates/ena_upload_tool/library construction_v1.3.0.json b/templates/ena_upload_tool/library construction.json similarity index 100% rename from templates/ena_upload_tool/library construction_v1.3.0.json rename to templates/ena_upload_tool/library construction.json diff --git a/templates/ena_upload_tool/nucleic acid extraction_v1.2.0.json b/templates/ena_upload_tool/nucleic acid extraction.json similarity index 100% rename from templates/ena_upload_tool/nucleic acid extraction_v1.2.0.json rename to templates/ena_upload_tool/nucleic acid extraction.json diff --git a/templates/ena_upload_tool/nucleic acid sequencing_v1.3.0.json b/templates/ena_upload_tool/nucleic acid sequencing.json similarity index 100% rename from templates/ena_upload_tool/nucleic acid sequencing_v1.3.0.json rename to templates/ena_upload_tool/nucleic acid sequencing.json diff --git a/templates/ena_upload_tool/sample_collection_v1.0.0.json b/templates/ena_upload_tool/sample collection.json similarity index 100% rename from templates/ena_upload_tool/sample_collection_v1.0.0.json rename to templates/ena_upload_tool/sample collection.json diff --git a/templates/ena_upload_tool/sequence assembly_v1.2.0.json b/templates/ena_upload_tool/sequence assembly.json similarity index 100% rename from templates/ena_upload_tool/sequence assembly_v1.2.0.json rename to templates/ena_upload_tool/sequence assembly.json diff --git a/templates/ena_upload_tool/source_all_organisms_v1.1.0.json b/templates/ena_upload_tool/source all organisms.json similarity index 100% rename from templates/ena_upload_tool/source_all_organisms_v1.1.0.json rename to templates/ena_upload_tool/source all organisms.json From 7cf4e521c61454e57a530e73318a49125ad62e01 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:10:48 +0200 Subject: [PATCH 03/25] Updated the mandatory information of the sources template --- templates/ena_upload_tool/source all organisms.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/templates/ena_upload_tool/source all organisms.json b/templates/ena_upload_tool/source all organisms.json index a70317b..1766725 100644 --- a/templates/ena_upload_tool/source all organisms.json +++ b/templates/ena_upload_tool/source all organisms.json @@ -4,7 +4,7 @@ "group": "ena modified for upload tool", "group_order": 1, "temporary_name": "1_ena_source_all_organisms", - "version": "1.1.0", + "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": null, "isa_technology_type": "nucleotide sequencing", @@ -25,7 +25,7 @@ }, { "iri": null, - "name": "Title", + "name": "title", "description": "Short text that can be used to call out sample records in search results or in displays.", "dataType": "String", "required": true, @@ -33,7 +33,7 @@ }, { "iri": null, - "name": "Description", + "name": "description", "description": "Free-form text describing the sample, its origin, and its method of isolation.", "dataType": "String", "required": true, @@ -42,9 +42,9 @@ }, { "iri": null, - "name": "tax_id", //First field on an ENA sample file. It is the number ID + "name": "taxon_id", //First field on an ENA sample file. It is the number ID "description": "NCBI Taxonomy Identifier number ID. This is appropriate for individual organisms and some environmental samples.", - "dataType": "String", + "dataType": "Integer", "required": true, "ontology": null, "isaTag": "source_characteristic" From 2da57de9e3bf84c57425e999fdf7e45aec59566b Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:29:45 +0200 Subject: [PATCH 04/25] Remove all the optional attributes from the sources template --- .../ena_upload_tool/source all organisms.json | 603 ------------------ 1 file changed, 603 deletions(-) diff --git a/templates/ena_upload_tool/source all organisms.json b/templates/ena_upload_tool/source all organisms.json index 1766725..ef692c5 100644 --- a/templates/ena_upload_tool/source all organisms.json +++ b/templates/ena_upload_tool/source all organisms.json @@ -48,609 +48,6 @@ "required": true, "ontology": null, "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "organism", - "description": "Provide a taxonomic information associated to the Source Biological material (for example, Species, genus, strain,....). Ideally, provide NCBI TaxID or NEWT identifier", //Changed to the description from ENA - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "cell_type", - "description": "cell type from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "dev_stage", - "description": "if the sample was obtained from an organism in a specific developmental stage, it is specified with this qualifier", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "germline", - "description": "the sample described presented in the entry has not undergone somatic genomic rearrangement as part of an adaptive immune response; it is the unrearranged molecule that was inherited from the parental germline", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "tissue_lib", - "description": "tissue library from which sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "tissue_type", - "description": "tissue type from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "collection_date", - "description": "The date of sampling, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.", - "dataType": "String", //original Regex "^[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "isolation_source", - "description": "describes the physical, environmental and/or local geographical source of the biological sample from which the sample was derived", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "lat_lon", - "description": "geographical coordinates of the location where the specimen was collected", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "collected_by", - "description": "name of persons or institute who collected the specimen", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "geographic location (country and/or sea)", - "description": "The geographical origin of the sample as defined by the country or sea. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", - "dataType": "Controlled Vocabulary", - "required": false, - "ontology": null, - "CVList": [ - "Afghanistan", - "Albania", - "Algeria", - "American Samoa", - "Andorra", - "Angola", - "Anguilla", - "Antarctica", - "Antigua and Barbuda", - "Arctic Ocean", - "Argentina", - "Armenia", - "Aruba", - "Ashmore and Cartier Islands", - "Atlantic Ocean", - "Australia", - "Austria", - "Azerbaijan", - "Bahamas", - "Bahrain", - "Baker Island", - "Baltic Sea", - "Bangladesh", - "Barbados", - "Bassas da India", - "Belarus", - "Belgium", - "Belize", - "Benin", - "Bermuda", - "Bhutan", - "Bolivia", - "Borneo", - "Bosnia and Herzegovina", - "Botswana", - "Bouvet Island", - "Brazil", - "British Virgin Islands", - "Brunei", - "Bulgaria", - "Burkina Faso", - "Burundi", - "Cambodia", - "Cameroon", - "Canada", - "Cape Verde", - "Cayman Islands", - "Central African Republic", - "Chad", - "Chile", - "China", - "Christmas Island", - "Clipperton Island", - "Cocos Islands", - "Colombia", - "Comoros", - "Cook Islands", - "Coral Sea Islands", - "Costa Rica", - "Cote d'Ivoire", - "Croatia", - "Cuba", - "Curacao", - "Cyprus", - "Czech Republic", - "Democratic Republic of the Congo", - "Denmark", - "Djibouti", - "Dominica", - "Dominican Republic", - "East Timor", - "Ecuador", - "Egypt", - "El Salvador", - "Equatorial Guinea", - "Eritrea", - "Estonia", - "Ethiopia", - "Europa Island", - "Falkland Islands (Islas Malvinas)", - "Faroe Islands", - "Fiji", - "Finland", - "France", - "French Guiana", - "French Polynesia", - "French Southern and Antarctic Lands", - "Gabon", - "Gambia", - "Gaza Strip", - "Georgia", - "Germany", - "Ghana", - "Gibraltar", - "Glorioso Islands", - "Greece", - "Greenland", - "Grenada", - "Guadeloupe", - "Guam", - "Guatemala", - "Guernsey", - "Guinea", - "Guinea-Bissau", - "Guyana", - "Haiti", - "Heard Island and McDonald Islands", - "Honduras", - "Hong Kong", - "Howland Island", - "Hungary", - "Iceland", - "India", - "Indian Ocean", - "Indonesia", - "Iran", - "Iraq", - "Ireland", - "Isle of Man", - "Israel", - "Italy", - "Jamaica", - "Jan Mayen", - "Japan", - "Jarvis Island", - "Jersey", - "Johnston Atoll", - "Jordan", - "Juan de Nova Island", - "Kazakhstan", - "Kenya", - "Kerguelen Archipelago", - "Kingman Reef", - "Kiribati", - "Kosovo", - "Kuwait", - "Kyrgyzstan", - "Laos", - "Latvia", - "Lebanon", - "Lesotho", - "Liberia", - "Libya", - "Liechtenstein", - "Lithuania", - "Luxembourg", - "Macau", - "Macedonia", - "Madagascar", - "Malawi", - "Malaysia", - "Maldives", - "Mali", - "Malta", - "Marshall Islands", - "Martinique", - "Mauritania", - "Mauritius", - "Mayotte", - "Mediterranean Sea", - "Mexico", - "Micronesia", - "Midway Islands", - "Moldova", - "Monaco", - "Mongolia", - "Montenegro", - "Montserrat", - "Morocco", - "Mozambique", - "Myanmar", - "Namibia", - "Nauru", - "Navassa Island", - "Nepal", - "Netherlands", - "New Caledonia", - "New Zealand", - "Nicaragua", - "Niger", - "Nigeria", - "Niue", - "Norfolk Island", - "North Korea", - "North Sea", - "Northern Mariana Islands", - "Norway", - "Oman", - "Pacific Ocean", - "Pakistan", - "Palau", - "Palmyra Atoll", - "Panama", - "Papua New Guinea", - "Paracel Islands", - "Paraguay", - "Peru", - "Philippines", - "Pitcairn Islands", - "Poland", - "Portugal", - "Puerto Rico", - "Qatar", - "Republic of the Congo", - "Reunion", - "Romania", - "Ross Sea", - "Russia", - "Rwanda", - "Saint Helena", - "Saint Kitts and Nevis", - "Saint Lucia", - "Saint Pierre and Miquelon", - "Saint Vincent and the Grenadines", - "Samoa", - "San Marino", - "Sao Tome and Principe", - "Saudi Arabia", - "Senegal", - "Serbia", - "Seychelles", - "Sierra Leone", - "Singapore", - "Sint Maarten", - "Slovakia", - "Slovenia", - "Solomon Islands", - "Somalia", - "South Africa", - "South Georgia and the South Sandwich Islands", - "South Korea", - "Southern Ocean", - "Spain", - "Spratly Islands", - "Sri Lanka", - "Sudan", - "Suriname", - "Svalbard", - "Swaziland", - "Sweden", - "Switzerland", - "Syria", - "Taiwan", - "Tajikistan", - "Tanzania", - "Tasman Sea", - "Thailand", - "Togo", - "Tokelau", - "Tonga", - "Trinidad and Tobago", - "Tromelin Island", - "Tunisia", - "Turkey", - "Turkmenistan", - "Turks and Caicos Islands", - "Tuvalu", - "USA", - "Uganda", - "Ukraine", - "United Arab Emirates", - "United Kingdom", - "Uruguay", - "Uzbekistan", - "Vanuatu", - "Venezuela", - "Viet Nam", - "Virgin Islands", - "Wake Island", - "Wallis and Futuna", - "West Bank", - "Western Sahara", - "Yemen", - "Zambia", - "Zimbabwe", - "not applicable", - "not collected", - "not provided", - "restricted access" - ], - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "geographic location (region and locality)", - "description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "identified_by", - "description": "name of the expert who identified the specimen taxonomically", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "environmental_sample", - "description": "identifies sequences derived by direct molecular isolation from a bulk environmental DNA sample (by PCR with or without subsequent cloning of the product, DGGE, or other anonymous methods) with no reliable identification of the source organism", - "dataType": "Controlled Vocabulary", - "required": false, - "ontology": null, - "CVList": [ - "No", - "Yes" - ], - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "mating_type", - "description": "mating type of the organism from which the sequence was obtained; mating type is used for prokaryotes, and for eukaryotes that undergo meiosis without sexually dimorphic gametes", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "sex", - "description": "sex of the organism from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "lab_host", - "description": "scientific name of the laboratory host used to propagate the source organism from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "host scientific name", - "description": "Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "bio_material", - "description": "identifier for the biological material from which the sample was obtained, with optional institution code and collection code for the place where it is currently stored.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "culture_collection", - "description": "institution code and identifier for the culture from which the sample was obtained, with optional collection code.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "specimen_voucher", - "description": "identifier for the specimen from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "cultivar", - "description": "cultivar (cultivated variety) of plant from which sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "ecotype", - "description": "a population within a given species displaying genetically based, phenotypic traits that reflect adaptation to a local habitat.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "isolate", - "description": "individual isolate from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "sub_species", - "description": "name of sub-species of organism from which sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "variety", - "description": "variety (= varietas, a formal Linnaean rank) of organism from which sample was derived.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "sub_strain", - "description": "name or identifier of a genetically or otherwise modified strain from which sample was obtained, derived from a parental strain (which should be annotated in the strain field; sub_strain from which sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "cell_line", - "description": "cell line from which the sample was obtained", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "serotype", - "description": "serological variety of a species characterized by its antigenic properties", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "serovar", - "description": "serological variety of a species (usually a prokaryote) characterized by its antigenic properties", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "strain", - "description": "Name of the strain from which the sample was obtained.", - "dataType": "String", - "required": false, - "ontology": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "submission date", - "description": "Date in which sample was submitted to ENA.", - "dataType": "String", - "required": false, - "ontology": null, - "CVList": null, - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "status", - "description": "Status of submission to ENA.", - "dataType": "String", - "required": false, - "ontology": null, - "CVList": [ - "add", - "added", - "modify", - "modified", - "cancel", - "cancelled", - "release", - "released" - ], - "isaTag": "source_characteristic" - }, - { - "iri": null, - "name": "accession", - "description": "ENA sample accession code. Provided by ENA after submission.", - "dataType": "String", - "required": false, - "ontology": null, - "CVList": null, - "isaTag": "source_characteristic" } ] } From 3bb2e56c65c3ae4aaf099930ffad441509719ee1 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:29:58 +0200 Subject: [PATCH 05/25] Change Name of the source template --- templates/ena_upload_tool/source all organisms.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/templates/ena_upload_tool/source all organisms.json b/templates/ena_upload_tool/source all organisms.json index ef692c5..77bf043 100644 --- a/templates/ena_upload_tool/source all organisms.json +++ b/templates/ena_upload_tool/source all organisms.json @@ -1,9 +1,9 @@ { "metadata": { - "name": "source all organisms", + "name": "source ENA Upload Tool", "group": "ena modified for upload tool", "group_order": 1, - "temporary_name": "1_ena_source_all_organisms", + "temporary_name": "1_ena_custom_source", "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": null, From 75e5e653cdfb6eafbe2f80f4ed94bf98aea625e4 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:34:02 +0200 Subject: [PATCH 06/25] Change the name of the sample collection template --- templates/ena_upload_tool/sample collection.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/templates/ena_upload_tool/sample collection.json b/templates/ena_upload_tool/sample collection.json index 3089d3f..61aecf6 100644 --- a/templates/ena_upload_tool/sample collection.json +++ b/templates/ena_upload_tool/sample collection.json @@ -1,9 +1,9 @@ { "metadata": { - "name": "sample collection", + "name": "sample collection ENA Upload Tool", "group": "ena modified for upload tool", "group_order": 2, - "temporary_name": "2_ena_sample_collection", + "temporary_name": "2_ena_custom_sample_collection", "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": null, From 60783824b66564a7ed474c7fe94eb094fde34185 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:42:12 +0200 Subject: [PATCH 07/25] Change name and level of the nucleic extraction template --- templates/ena_upload_tool/nucleic acid extraction.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/templates/ena_upload_tool/nucleic acid extraction.json b/templates/ena_upload_tool/nucleic acid extraction.json index 8eff559..cc81296 100644 --- a/templates/ena_upload_tool/nucleic acid extraction.json +++ b/templates/ena_upload_tool/nucleic acid extraction.json @@ -1,17 +1,17 @@ { "metadata": { - "name": "nucleic acid extraction", + "name": "nucleic acid extraction ENA Upload Tool", "group": "ena modified for upload tool", "group_order": 3, - "temporary_name": "3_ena_nucleic_acid_extraction", - "version": "1.2.0", + "temporary_name": "3_ena_custom_nucleic_acid_extraction", + "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": "genome sequencing", "isa_technology_type": "nucleotide sequencing", "isa_protocol_type": "nucleic acid extraction", "repo_schema_id": "ENA General experiment information 2021", "organism": "any", - "level": "assay" + "level": "assay - material" }, "data": [ { From a50c6ab5eeb6fd4001ae3cdbb6d5be4b5a7d8317 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 08:51:00 +0200 Subject: [PATCH 08/25] Change metadata of the Library preparation template --- templates/ena_upload_tool/library construction.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/templates/ena_upload_tool/library construction.json b/templates/ena_upload_tool/library construction.json index 5833f64..037deaf 100644 --- a/templates/ena_upload_tool/library construction.json +++ b/templates/ena_upload_tool/library construction.json @@ -1,17 +1,17 @@ { "metadata": { - "name": "library construction", + "name": "library construction ENA Upload Tool", "group": "ena modified for upload tool", "group_order": 4, - "temporary_name": "4_ena_library_construction", - "version": "1.3.0", + "temporary_name": "4_ena_custom_library_construction", + "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": "genome sequencing", "isa_technology_type": "nucleotide sequencing", "isa_protocol_type": "library construction", "repo_schema_id": "ENA General experiment information 2021", "organism": "any", - "level": "assay" + "level": "assay - material" }, "data": [ { From 8606b699e76e19e8fef23212f2dcd67371fa2622 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 10:42:34 +0200 Subject: [PATCH 09/25] change attribute names of the library construction template --- .../ena_upload_tool/library construction.json | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/templates/ena_upload_tool/library construction.json b/templates/ena_upload_tool/library construction.json index 037deaf..bdc2e2f 100644 --- a/templates/ena_upload_tool/library construction.json +++ b/templates/ena_upload_tool/library construction.json @@ -43,7 +43,7 @@ }, { "iri": null, - "name": "Title", + "name": "title", "description": "Short text that can be used to call out experiment records in searches or in displays.", "required": true, "ontology": null, @@ -63,7 +63,7 @@ }, { "iri": null, - "name": "library source", + "name": "library_source", "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced. (SRA 1.2 documentation)", "dataType": "Controlled Vocabulary", "required": true, @@ -83,7 +83,7 @@ }, { "iri": null, - "name": "library strategy", + "name": "library_strategy", "description": "Sequencing technique intended for this library (SRA 1.2 documentation)", "dataType": "Controlled Vocabulary", "required": true, @@ -133,7 +133,7 @@ }, { "iri": null, - "name": "library selection", + "name": "library_selection", "description": "Whether any method was used to select for or against, enrich, or screen the material being sequenced. (SRA 1.2 documentation)", "dataType": "Controlled Vocabulary", "required": true, @@ -175,7 +175,7 @@ }, { "iri": null, - "name": "library layout", + "name": "library_layout", "description": "specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", "dataType": "Controlled Vocabulary", "required": false, @@ -188,7 +188,7 @@ }, { "iri": null, - "name": "insert size", + "name": "insert_size", "description": "Insert size for paired reads.", "dataType": "String", "required": false, @@ -197,7 +197,7 @@ }, { "iri": null, - "name": "library name", + "name": "library_name", "description": "Name given to the generated library", "dataType": "String", "title": true, From 31736cfb7b57bd02cdc2d210b1125b95ef44e46d Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 10:45:17 +0200 Subject: [PATCH 10/25] Update metadata of the nucleic acid sequencing template --- templates/ena_upload_tool/nucleic acid sequencing.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/templates/ena_upload_tool/nucleic acid sequencing.json b/templates/ena_upload_tool/nucleic acid sequencing.json index 3d9d6af..020277d 100644 --- a/templates/ena_upload_tool/nucleic acid sequencing.json +++ b/templates/ena_upload_tool/nucleic acid sequencing.json @@ -1,17 +1,17 @@ { "metadata": { - "name": "nucleic acid sequencing", + "name": "nucleic acid sequencing ENA Upload Tool", "group": "ena modified for upload tool", "group_order": 5, - "temporary_name": "5_ena_nucleic_acid_sequencing", - "version": "1.3.0", + "temporary_name": "5_ena_custom_nucleic_acid_sequencing", + "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": "genome sequencing", "isa_technology_type": "nucleotide sequencing", "isa_protocol_type": "nucleic acid sequencing", "repo_schema_id": "ENA General experiment information 2021", "organism": "any", - "level": "assay" + "level": "assay - data file" }, "data": [ { From 8247f590162bd61f98000ad5fe40365a7d27a850 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 10:46:26 +0200 Subject: [PATCH 11/25] Change attributes of the nucleic acid sequencing template --- .../nucleic acid sequencing.json | 117 ++++++++++-------- 1 file changed, 68 insertions(+), 49 deletions(-) diff --git a/templates/ena_upload_tool/nucleic acid sequencing.json b/templates/ena_upload_tool/nucleic acid sequencing.json index 020277d..f993440 100644 --- a/templates/ena_upload_tool/nucleic acid sequencing.json +++ b/templates/ena_upload_tool/nucleic acid sequencing.json @@ -34,65 +34,84 @@ }, { "iri": null, - "name": "sequencing instrument", + "name": "platform", "description": "a parameter to report the sequencing instrument model and make", "dataType": "Controlled Vocabulary", "required": true, "ontology": null, "CVList": [ - " 454 GS", - " 454 GS 20", - " 454 GS FLX", - " 454 GS FLX+", - " 454 GS FLX Titanium", - " 454 GS Junior", - " HiSeq X Five", - " HiSeq X Ten", - " Illumina Genome Analyzer", - " Illumina Genome Analyzer II", - " Illumina Genome Analyzer IIx", - " Illumina HiScanSQ", - " Illumina HiSeq 1000", - " Illumina HiSeq 1500", - " Illumina HiSeq 2000", - " Illumina HiSeq 2500", - " Illumina HiSeq 3000", - " Illumina HiSeq 4000", - " Illumina iSeq 100", - " Illumina MiSeq", - " Illumina MiniSeq", - " Illumina NovaSeq 6000", - " NextSeq 500", - " NextSeq 550", - " PacBio RS", - " PacBio RS II", - " Sequel", - " Ion Torrent PGM", - " Ion Torrent Proton", - " Ion Torrent S5", - " Ion Torrent S5 XL", - " AB 3730xL Genetic Analyzer", - " AB 3730 Genetic Analyzer", - " AB 3500xL Genetic Analyzer", - " AB 3500 Genetic Analyzer", - " AB 3130xL Genetic Analyzer", - " AB 3130 Genetic Analyzer", - " AB 310 Genetic Analyzer", - " MinION", - " GridION", - " PromethION", - " BGISEQ-500", - " DNBSEQ-T7", - " DNBSEQ-G400", - " DNBSEQ-G50", - " DNBSEQ-G400 FAST", - " unspecified" + "LS454", + "Illumina", + "HiSeq", + "NextSeq", + "PacBio", + "Themo Fisher Scientific", + "MGI Tech", + "unspecified" ], "isaTag": "parameter_value" }, { "iri": null, - "name": "file type", + "name": "instrument_model", + "description": "a parameter to report the sequencing instrument model and make", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "454 GS", + "454 GS 20", + "454 GS FLX", + "454 GS FLX+", + "454 GS FLX Titanium", + "454 GS Junior", + "HiSeq X Five", + "HiSeq X Ten", + "Illumina Genome Analyzer", + "Illumina Genome Analyzer II", + "Illumina Genome Analyzer IIx", + "Illumina HiScanSQ", + "Illumina HiSeq 1000", + "Illumina HiSeq 1500", + "Illumina HiSeq 2000", + "Illumina HiSeq 2500", + "Illumina HiSeq 3000", + "Illumina HiSeq 4000", + "Illumina iSeq 100", + "Illumina MiSeq", + "Illumina MiniSeq", + "Illumina NovaSeq 6000", + "NextSeq 500", + "NextSeq 550", + "PacBio RS", + "PacBio RS II", + "Sequel", + "Ion Torrent PGM", + "Ion Torrent Proton", + "Ion Torrent S5", + "Ion Torrent S5 XL", + "AB 3730xL Genetic Analyzer", + "AB 3730 Genetic Analyzer", + "AB 3500xL Genetic Analyzer", + "AB 3500 Genetic Analyzer", + "AB 3130xL Genetic Analyzer", + "AB 3130 Genetic Analyzer", + "AB 310 Genetic Analyzer", + "MinION", + "GridION", + "PromethION", + "BGISEQ-500", + "DNBSEQ-T7", + "DNBSEQ-G400", + "DNBSEQ-G50", + "DNBSEQ-G400 FAST", + "unspecified" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "file_type", "description": "The run data file model.", "dataType": "String", "required": true, From 1d3447acf127f4abdcbf2e7635995a56253cf4d5 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 10:47:21 +0200 Subject: [PATCH 12/25] Change the metadata of the sequence assembly template --- templates/ena_upload_tool/sequence assembly.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/templates/ena_upload_tool/sequence assembly.json b/templates/ena_upload_tool/sequence assembly.json index 73c1686..512f1b3 100644 --- a/templates/ena_upload_tool/sequence assembly.json +++ b/templates/ena_upload_tool/sequence assembly.json @@ -1,17 +1,17 @@ { "metadata": { - "name": "sequence assembly", + "name": "sequence assembly ENA Upload Tool", "group": "ena modified for upload tool", "group_order": 6, - "temporary_name": "6_ena_sequence_assembly", - "version": "1.2.0", + "temporary_name": "6_ena_custom_sequence_assembly", + "version": "1.0.0", "isa_config": "genome_seq_default_v2015-07-02", "isa_measurement_type": "genome sequencing", "isa_technology_type": "nucleotide sequencing", "isa_protocol_type": "sequence assembly", "repo_schema_id": "ENA General experiment information 2021", "organism": "any", - "level": "assay" + "level": "assay - data file" }, "data": [ { @@ -29,7 +29,7 @@ "required": true, "ontology": null, "dataType": "String", //need to be autofilled with name of selected SOP for that block - "CVList": , //SOPtittle + "CVList": null, //SOPtittle "isaTag": "protocol" }, { From 0a277127f7506d34cfcabeb56945bf54b1c12f9e Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 21 Sep 2023 17:15:52 +0200 Subject: [PATCH 13/25] Archiving the `nucleic extraction` and `sequence assembly` template --- .../ena_upload_tool/{ => archive}/nucleic acid extraction.json | 0 templates/ena_upload_tool/{ => archive}/sequence assembly.json | 0 2 files changed, 0 insertions(+), 0 deletions(-) rename templates/ena_upload_tool/{ => archive}/nucleic acid extraction.json (100%) rename templates/ena_upload_tool/{ => archive}/sequence assembly.json (100%) diff --git a/templates/ena_upload_tool/nucleic acid extraction.json b/templates/ena_upload_tool/archive/nucleic acid extraction.json similarity index 100% rename from templates/ena_upload_tool/nucleic acid extraction.json rename to templates/ena_upload_tool/archive/nucleic acid extraction.json diff --git a/templates/ena_upload_tool/sequence assembly.json b/templates/ena_upload_tool/archive/sequence assembly.json similarity index 100% rename from templates/ena_upload_tool/sequence assembly.json rename to templates/ena_upload_tool/archive/sequence assembly.json From b58e555b4e687e571c770d25fb4ad456e1c710aa Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Fri, 22 Sep 2023 08:06:10 +0200 Subject: [PATCH 14/25] Merge all separate templates into one aggregated template json Fix errors. --- .../{ => archive}/library construction.json | 0 .../nucleic acid sequencing.json | 0 .../{ => archive}/sample collection.json | 0 .../{ => archive}/source all organisms.json | 0 .../ena_upload_tool_aggregated.json | 541 ++++++++++++++++++ 5 files changed, 541 insertions(+) rename templates/ena_upload_tool/{ => archive}/library construction.json (100%) rename templates/ena_upload_tool/{ => archive}/nucleic acid sequencing.json (100%) rename templates/ena_upload_tool/{ => archive}/sample collection.json (100%) rename templates/ena_upload_tool/{ => archive}/source all organisms.json (100%) create mode 100644 templates/ena_upload_tool/ena_upload_tool_aggregated.json diff --git a/templates/ena_upload_tool/library construction.json b/templates/ena_upload_tool/archive/library construction.json similarity index 100% rename from templates/ena_upload_tool/library construction.json rename to templates/ena_upload_tool/archive/library construction.json diff --git a/templates/ena_upload_tool/nucleic acid sequencing.json b/templates/ena_upload_tool/archive/nucleic acid sequencing.json similarity index 100% rename from templates/ena_upload_tool/nucleic acid sequencing.json rename to templates/ena_upload_tool/archive/nucleic acid sequencing.json diff --git a/templates/ena_upload_tool/sample collection.json b/templates/ena_upload_tool/archive/sample collection.json similarity index 100% rename from templates/ena_upload_tool/sample collection.json rename to templates/ena_upload_tool/archive/sample collection.json diff --git a/templates/ena_upload_tool/source all organisms.json b/templates/ena_upload_tool/archive/source all organisms.json similarity index 100% rename from templates/ena_upload_tool/source all organisms.json rename to templates/ena_upload_tool/archive/source all organisms.json diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json new file mode 100644 index 0000000..c30d62c --- /dev/null +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -0,0 +1,541 @@ +{ + "data": [ + { + "metadata": { + "name": "source ENA Upload Tool", + "group": "ena modified for upload tool", + "group_order": 1, + "temporary_name": "1_ena_custom_source", + "version": "1.0.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": null, + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": null, + "repo_schema_id": "ERC000011.xml 2021", + "organism": "any", + "level": "study source" + }, + "data": [ + { + "iri": null, + "name": "Source Name", + "description": "Sources are considered as the starting biological material used in a study.", + "dataType": "String", + "title": true, + "required": true, + "isaTag": "source" + }, + { + "iri": null, + "name": "title", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "dataType": "String", + "required": true, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "description", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "dataType": "String", + "required": true, + "ontology": null, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "taxon_id", //First field on an ENA sample file. It is the number ID + "description": "NCBI Taxonomy Identifier number ID. This is appropriate for individual organisms and some environmental samples.", + "dataType": "Integer", + "required": true, + "ontology": null, + "isaTag": "source_characteristic" + } + ] + }, + { + "metadata": { + "name": "sample collection ENA Upload Tool", + "group": "ena modified for upload tool", + "group_order": 2, + "temporary_name": "2_ena_custom_sample_collection", + "version": "1.0.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": null, + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "sample collection", + "repo_schema_id": "ERC000011.xml 2021", + "organism": "any", + "level": "study sample" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "Registered Sample (multiple)", + "required": true, + "isaTag": null + }, + { + "iri": null, + "name": "sample collection", + "description": "type of assay or experimental step performed.", + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "required": true, + "ontology": null, + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "Sample Name", + "description": "Name of the major output resulting from the application of the protocol.", + "dataType": "String", + "title": true, + "required": true, + "isaTag": "sample" + } + ] + }, + { + "metadata": { + "name": "library construction ENA Upload Tool", + "group": "ena modified for upload tool", + "group_order": 4, + "temporary_name": "4_ena_custom_library_construction", + "version": "1.0.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "library construction", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay - material" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "Registered Sample (multiple)", + "required": true, + "isaTag": null + }, + { + "iri": null, + "name": "library construction", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "library_construction_protocol", + "description": "Free form text describing the protocol by which the sequencing library was constructed.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "title", + "description": "Short text that can be used to call out experiment records in searches or in displays.", + "required": true, + "ontology": null, + "dataType": "String", + "CVList": null, + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "design_description", + "description": "The design of the library including details of how it was constructed. ", + "required": true, + "ontology": null, + "dataType": "String", + "CVList": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library_source", + "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced. (SRA 1.2 documentation)", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "GENOMIC", + "GENOMIC SINGLE CELL", + "TRANSCRIPTOMIC", + "TRANSCRIPTOMIC SINGLE CELL", + "METAGENOMIC", + "METATRANSCRIPTOMIC", + "SYNTHETIC", + "VIRAL RNA", + "OTHER" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library_strategy", + "description": "Sequencing technique intended for this library (SRA 1.2 documentation)", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "WGS", + "WGA", + "WXS", + "RNA-Seq", + "ssRNA-seq", + "miRNA-Seq", + "ncRNA-Seq", + "FL-cDNA", + "EST", + "Hi-C", + "ATAC-seq", + "WCS", + "RAD-Seq", + "CLONE", + "POOLCLONE", + "AMPLICON", + "CLONEEND", + "FINISHING", + "ChIP-Seq", + "MNase-Seq", + "DNase-Hypersensitivity", + "Bisulfite-Seq", + "CTS", + "MRE-Seq", + "MeDIP-Seq", + "MBD-Seq", + "Tn-Seq", + "VALIDATION", + "FAIRE-seq", + "SELEX", + "RIP-Seq", + "ChIA-PET", + "Synthetic-Long-Read", + "Targeted-Capture", + "Tethered Chromatin Conformation Capture", + "OTHER", + "NOMe-Seq", + "ChM-Seq", + "GBS" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library_selection", + "description": "Whether any method was used to select for or against, enrich, or screen the material being sequenced. (SRA 1.2 documentation)", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "RANDOM", + "PCR", + "RANDOM PCR", + "RT-PCR", + "HMPR", + "MF", + "repeat fractionation", + "size fractionation", + "MSLL", + "cDNA", + "cDNA_randomPriming", + "cDNA_oligo_dT", + "PolyA", + "Oligo-dT", + "Inverse rRNA", + "Inverse rRNA selection", + "ChIP", + "ChIP-Seq", + "MNase", + "DNase", + "Hybrid Selection", + "Reduced Representation", + "Restriction Digest", + "5-methylcytidine antibody", + "MBD2 protein methyl-CpG binding domain", + "CAGE", + "RACE", + "MDA", + "padlock probes capture method", + "other", + "unspecified" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library_layout", + "description": "specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", + "dataType": "Controlled Vocabulary", + "required": false, + "ontology": null, + "CVList": [ + "SINGLE", + "PAIRED" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "insert_size", + "description": "Insert size for paired reads.", + "dataType": "String", + "required": false, + "ontology": null, + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "library_name", + "description": "Name given to the generated library", + "dataType": "String", + "title": true, + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "other_material" + }, + { + "iri": null, + "name": "submission date", + "description": "Date in which experiment was submitted to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "release", + "released" + ], + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "accession", + "description": "ENA experiment accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + } + ] + }, + { + "metadata": { + "name": "nucleic acid sequencing ENA Upload Tool", + "group": "ena modified for upload tool", + "group_order": 5, + "temporary_name": "5_ena_custom_nucleic_acid_sequencing", + "version": "1.0.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "nucleic acid sequencing", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay - data file" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "Registered Sample (multiple)", + "required": true, + "isaTag": null + }, + { + "iri": null, + "name": "nucleic acid sequencing", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "platform", + "description": "a parameter to report the sequencing instrument model and make", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "LS454", + "Illumina", + "HiSeq", + "NextSeq", + "PacBio", + "Themo Fisher Scientific", + "MGI Tech", + "unspecified" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "instrument_model", + "description": "a parameter to report the sequencing instrument model and make", + "dataType": "Controlled Vocabulary", + "required": true, + "ontology": null, + "CVList": [ + "454 GS", + "454 GS 20", + "454 GS FLX", + "454 GS FLX+", + "454 GS FLX Titanium", + "454 GS Junior", + "HiSeq X Five", + "HiSeq X Ten", + "Illumina Genome Analyzer", + "Illumina Genome Analyzer II", + "Illumina Genome Analyzer IIx", + "Illumina HiScanSQ", + "Illumina HiSeq 1000", + "Illumina HiSeq 1500", + "Illumina HiSeq 2000", + "Illumina HiSeq 2500", + "Illumina HiSeq 3000", + "Illumina HiSeq 4000", + "Illumina iSeq 100", + "Illumina MiSeq", + "Illumina MiniSeq", + "Illumina NovaSeq 6000", + "NextSeq 500", + "NextSeq 550", + "PacBio RS", + "PacBio RS II", + "Sequel", + "Ion Torrent PGM", + "Ion Torrent Proton", + "Ion Torrent S5", + "Ion Torrent S5 XL", + "AB 3730xL Genetic Analyzer", + "AB 3730 Genetic Analyzer", + "AB 3500xL Genetic Analyzer", + "AB 3500 Genetic Analyzer", + "AB 3130xL Genetic Analyzer", + "AB 3130 Genetic Analyzer", + "AB 310 Genetic Analyzer", + "MinION", + "GridION", + "PromethION", + "BGISEQ-500", + "DNBSEQ-T7", + "DNBSEQ-G400", + "DNBSEQ-G50", + "DNBSEQ-G400 FAST", + "unspecified" + ], + "isaTag": "parameter_value" + }, + { + "iri": null, + "name": "file_type", + "description": "The run data file model.", + "dataType": "String", + "required": true, + "ontology": null, + "CVList": [ + "bam", + "cram", + "fastq", + "oxfordnanopore_native", + "pacbio_hdf5", + "sff" + ], + "isaTag": "data_file_comment" + }, + { + "iri": null, + "name": "file checksum", + "description": "The MD5 checksum of the file.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "data_file_comment" + }, + { + "iri": null, + "name": "Raw Data File", + "description": "Name (or URI) of the raw data file generated by an assay.", + "dataType": "String", + "title": true, + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "data_file" + }, + { + "iri": null, + "name": "submission date", + "description": "Date in which run was submitted to ENA.Date of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "data_file_comment" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "release", + "released" + ], + "isaTag": "data_file_comment" + }, + { + "iri": null, + "name": "accession", + "description": "ENA run accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "data_file_comment" + } + ] + } + ] +} From e52ac083b3393df7be08eade9e6fd103d5eca89b Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Tue, 3 Oct 2023 13:56:13 +0200 Subject: [PATCH 15/25] Updated the templates for ENA Upload --- .../ena_upload_tool_aggregated.json | 93 ++++++++++--------- 1 file changed, 51 insertions(+), 42 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index c30d62c..3518654 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -25,14 +25,6 @@ "required": true, "isaTag": "source" }, - { - "iri": null, - "name": "title", - "description": "Short text that can be used to call out sample records in search results or in displays.", - "dataType": "String", - "required": true, - "isaTag": "source_characteristic" - }, { "iri": null, "name": "description", @@ -95,6 +87,53 @@ "title": true, "required": true, "isaTag": "sample" + }, + { + "iri": null, + "name": "title", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "dataType": "String", + "required": true, + "isaTag": "source_characteristic" + }, + { + "iri": null, + "name": "accession", + "description": "ENA experiment accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "submission date", + "description": "Date in which experiment was submitted to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "Controlled Vocabulary", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "release", + "released" + ], + "isaTag": "data_file_comment" } ] }, @@ -306,21 +345,11 @@ "CVList": null, "isaTag": "other_material" }, - { - "iri": null, - "name": "submission date", - "description": "Date in which experiment was submitted to ENA.", - "dataType": "String", - "required": false, - "ontology": null, - "CVList": null, - "isaTag": "other_material_characteristic" - }, { "iri": null, "name": "status", "description": "Status of submission to ENA.", - "dataType": "String", + "dataType": "Controlled Vocabulary", "required": false, "ontology": null, "CVList": [ @@ -334,16 +363,6 @@ "released" ], "isaTag": "other_material_characteristic" - }, - { - "iri": null, - "name": "accession", - "description": "ENA experiment accession code. Provided by ENA after submission.", - "dataType": "String", - "required": false, - "ontology": null, - "CVList": null, - "isaTag": "other_material_characteristic" } ] }, @@ -462,7 +481,7 @@ "iri": null, "name": "file_type", "description": "The run data file model.", - "dataType": "String", + "dataType": "Controlled Vocabulary", "required": true, "ontology": null, "CVList": [ @@ -487,7 +506,7 @@ }, { "iri": null, - "name": "Raw Data File", + "name": "file_name", "description": "Name (or URI) of the raw data file generated by an assay.", "dataType": "String", "title": true, @@ -510,7 +529,7 @@ "iri": null, "name": "status", "description": "Status of submission to ENA.", - "dataType": "String", + "dataType": "Controlled Vocabulary", "required": false, "ontology": null, "CVList": [ @@ -524,16 +543,6 @@ "released" ], "isaTag": "data_file_comment" - }, - { - "iri": null, - "name": "accession", - "description": "ENA run accession code. Provided by ENA after submission.", - "dataType": "String", - "required": false, - "ontology": null, - "CVList": null, - "isaTag": "data_file_comment" } ] } From a695e9f1394de7ca182b52e21952d90910f68d9f Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Sat, 21 Oct 2023 15:53:53 +0200 Subject: [PATCH 16/25] Adjusting templates --- .../ena_upload_tool_aggregated.json | 508 +++++++++++++++--- 1 file changed, 422 insertions(+), 86 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index 3518654..5aa537a 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -27,11 +27,292 @@ }, { "iri": null, - "name": "description", - "description": "Free-form text describing the sample, its origin, and its method of isolation.", - "dataType": "String", + "name": "geographic location (country and/or sea)", + "description": "The geographical origin of the sample as defined by the country or sea. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", + "dataType": "Controlled Vocabulary", "required": true, "ontology": null, + "CVList": [ + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "not applicable", + "not collected", + "not provided", + "restricted access" + ], "isaTag": "source_characteristic" }, { @@ -94,7 +375,25 @@ "description": "Short text that can be used to call out sample records in search results or in displays.", "dataType": "String", "required": true, - "isaTag": "source_characteristic" + "isaTag": "sample_characteristic" + }, + { + "iri": null, + "name": "sample_description", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "dataType": "String", + "required": true, + "ontology": null, + "isaTag": "sample_characteristic" + }, + { + "iri": null, + "name": "collection date", + "description": "Date of the sample collection", + "dataType": "ENA collection date", + "required": true, + "ontology": null, + "isaTag": "sample_characteristic" }, { "iri": null, @@ -104,17 +403,17 @@ "required": false, "ontology": null, "CVList": null, - "isaTag": "other_material_characteristic" + "isaTag": "sample_characteristic" }, { "iri": null, - "name": "submission date", + "name": "submission_date", "description": "Date in which experiment was submitted to ENA.", "dataType": "String", "required": false, "ontology": null, "CVList": null, - "isaTag": "other_material_characteristic" + "isaTag": "sample_characteristic" }, { "iri": null, @@ -130,10 +429,9 @@ "modified", "cancel", "cancelled", - "release", "released" ], - "isaTag": "data_file_comment" + "isaTag": "sample_characteristic" } ] }, @@ -166,10 +464,11 @@ "name": "library construction", "description": "type of assay or experimental step performed.", "required": true, + "title": true, "ontology": null, "dataType": "String", //need to be autofilled with name of selected SOP for that block "CVList": null, //SOPtittle - "isaTag": "protocol" + "isaTag": "other_material" }, { "iri": null, @@ -194,12 +493,22 @@ "iri": null, "name": "design_description", "description": "The design of the library including details of how it was constructed. ", - "required": true, + "required": false, "ontology": null, "dataType": "String", "CVList": null, "isaTag": "parameter_value" }, + { + "iri": null, + "name": "library_name", + "description": "Name given to the generated library", + "dataType": "String", + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + }, { "iri": null, "name": "library_source", @@ -317,7 +626,7 @@ "name": "library_layout", "description": "specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", "dataType": "Controlled Vocabulary", - "required": false, + "required": true, "ontology": null, "CVList": [ "SINGLE", @@ -334,72 +643,6 @@ "ontology": null, "isaTag": "parameter_value" }, - { - "iri": null, - "name": "library_name", - "description": "Name given to the generated library", - "dataType": "String", - "title": true, - "required": true, - "ontology": null, - "CVList": null, - "isaTag": "other_material" - }, - { - "iri": null, - "name": "status", - "description": "Status of submission to ENA.", - "dataType": "Controlled Vocabulary", - "required": false, - "ontology": null, - "CVList": [ - "add", - "added", - "modify", - "modified", - "cancel", - "cancelled", - "release", - "released" - ], - "isaTag": "other_material_characteristic" - } - ] - }, - { - "metadata": { - "name": "nucleic acid sequencing ENA Upload Tool", - "group": "ena modified for upload tool", - "group_order": 5, - "temporary_name": "5_ena_custom_nucleic_acid_sequencing", - "version": "1.0.0", - "isa_config": "genome_seq_default_v2015-07-02", - "isa_measurement_type": "genome sequencing", - "isa_technology_type": "nucleotide sequencing", - "isa_protocol_type": "nucleic acid sequencing", - "repo_schema_id": "ENA General experiment information 2021", - "organism": "any", - "level": "assay - data file" - }, - "data": [ - { - "iri": null, - "name": "Input", - "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", - "required": true, - "isaTag": null - }, - { - "iri": null, - "name": "nucleic acid sequencing", - "description": "type of assay or experimental step performed.", - "required": true, - "ontology": null, - "dataType": "String", //need to be autofilled with name of selected SOP for that block - "CVList": null, //SOPtittle - "isaTag": "protocol" - }, { "iri": null, "name": "platform", @@ -477,6 +720,101 @@ ], "isaTag": "parameter_value" }, + { + "iri": null, + "name": "accession", + "description": "ENA experiment accession code. Provided by ENA after submission.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "submission_date", + "description": "Date in which run was submitted to ENA.", + "dataType": "String", + "required": false, + "ontology": null, + "CVList": null, + "isaTag": "other_material_characteristic" + }, + { + "iri": null, + "name": "status", + "description": "Status of submission to ENA.", + "dataType": "Controlled Vocabulary", + "required": false, + "ontology": null, + "CVList": [ + "add", + "added", + "modify", + "modified", + "cancel", + "cancelled", + "released" + ], + "isaTag": "other_material_characteristic" + } + ] + }, + { + "metadata": { + "name": "nucleic acid sequencing ENA Upload Tool", + "group": "ena modified for upload tool", + "group_order": 5, + "temporary_name": "5_ena_custom_nucleic_acid_sequencing", + "version": "1.0.0", + "isa_config": "genome_seq_default_v2015-07-02", + "isa_measurement_type": "genome sequencing", + "isa_technology_type": "nucleotide sequencing", + "isa_protocol_type": "nucleic acid sequencing", + "repo_schema_id": "ENA General experiment information 2021", + "organism": "any", + "level": "assay - data file" + }, + "data": [ + { + "iri": null, + "name": "Input", + "description": "Existing Samples in DataHub that represent input for this protocol.", + "dataType": "Registered Sample (multiple)", + "required": true, + "isaTag": null + }, + { + "iri": null, + "name": "nucleic acid sequencing", + "description": "type of assay or experimental step performed.", + "required": true, + "ontology": null, + "dataType": "String", //need to be autofilled with name of selected SOP for that block + "CVList": null, //SOPtittle + "isaTag": "protocol" + }, + { + "iri": null, + "name": "Raw Data File", + "description": "Name (or URI) of the raw data file generated by an assay.", + "dataType": "String", + "title": true, + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "data_file" + }, + { + "iri": null, + "name": "file_name", + "description": "Name (or URI) of the raw data file generated by an assay.", + "dataType": "String", + "required": true, + "ontology": null, + "CVList": null, + "isaTag": "data_file_comment" + }, { "iri": null, "name": "file_type", @@ -506,19 +844,18 @@ }, { "iri": null, - "name": "file_name", - "description": "Name (or URI) of the raw data file generated by an assay.", + "name": "accession", + "description": "ENA experiment accession code. Provided by ENA after submission.", "dataType": "String", - "title": true, - "required": true, + "required": false, "ontology": null, "CVList": null, - "isaTag": "data_file" + "isaTag": "data_file_comment" }, { "iri": null, - "name": "submission date", - "description": "Date in which run was submitted to ENA.Date of submission to ENA.", + "name": "submission_date", + "description": "Date in which run was submitted to ENA.", "dataType": "String", "required": false, "ontology": null, @@ -539,7 +876,6 @@ "modified", "cancel", "cancelled", - "release", "released" ], "isaTag": "data_file_comment" From 55c8ccefa534d1af0eb1858e2d2c842860184fd4 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Wed, 8 Nov 2023 18:01:29 +0100 Subject: [PATCH 17/25] changed 'submission_date' to 'submission date' --- .../ena_upload_tool_aggregated.json | 566 +++++++++--------- 1 file changed, 283 insertions(+), 283 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index 5aa537a..570eb7a 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -33,285 +33,285 @@ "required": true, "ontology": null, "CVList": [ - "Afghanistan", - "Albania", - "Algeria", - "American Samoa", - "Andorra", - "Angola", - "Anguilla", - "Antarctica", - "Antigua and Barbuda", - "Arctic Ocean", - "Argentina", - "Armenia", - "Aruba", - "Ashmore and Cartier Islands", - "Atlantic Ocean", - "Australia", - "Austria", - "Azerbaijan", - "Bahamas", - "Bahrain", - "Baker Island", - "Baltic Sea", - "Bangladesh", - "Barbados", - "Bassas da India", - "Belarus", - "Belgium", - "Belize", - "Benin", - "Bermuda", - "Bhutan", - "Bolivia", - "Borneo", - "Bosnia and Herzegovina", - "Botswana", - "Bouvet Island", - "Brazil", - "British Virgin Islands", - "Brunei", - "Bulgaria", - "Burkina Faso", - "Burundi", - "Cambodia", - "Cameroon", - "Canada", - "Cape Verde", - "Cayman Islands", - "Central African Republic", - "Chad", - "Chile", - "China", - "Christmas Island", - "Clipperton Island", - "Cocos Islands", - "Colombia", - "Comoros", - "Cook Islands", - "Coral Sea Islands", - "Costa Rica", - "Cote d'Ivoire", - "Croatia", - "Cuba", - "Curacao", - "Cyprus", - "Czech Republic", - "Democratic Republic of the Congo", - "Denmark", - "Djibouti", - "Dominica", - "Dominican Republic", - "East Timor", - "Ecuador", - "Egypt", - "El Salvador", - "Equatorial Guinea", - "Eritrea", - "Estonia", - "Ethiopia", - "Europa Island", - "Falkland Islands (Islas Malvinas)", - "Faroe Islands", - "Fiji", - "Finland", - "France", - "French Guiana", - "French Polynesia", - "French Southern and Antarctic Lands", - "Gabon", - "Gambia", - "Gaza Strip", - "Georgia", - "Germany", - "Ghana", - "Gibraltar", - "Glorioso Islands", - "Greece", - "Greenland", - "Grenada", - "Guadeloupe", - "Guam", - "Guatemala", - "Guernsey", - "Guinea", - "Guinea-Bissau", - "Guyana", - "Haiti", - "Heard Island and McDonald Islands", - "Honduras", - "Hong Kong", - "Howland Island", - "Hungary", - "Iceland", - "India", - "Indian Ocean", - "Indonesia", - "Iran", - "Iraq", - "Ireland", - "Isle of Man", - "Israel", - "Italy", - "Jamaica", - "Jan Mayen", - "Japan", - "Jarvis Island", - "Jersey", - "Johnston Atoll", - "Jordan", - "Juan de Nova Island", - "Kazakhstan", - "Kenya", - "Kerguelen Archipelago", - "Kingman Reef", - "Kiribati", - "Kosovo", - "Kuwait", - "Kyrgyzstan", - "Laos", - "Latvia", - "Lebanon", - "Lesotho", - "Liberia", - "Libya", - "Liechtenstein", - "Lithuania", - "Luxembourg", - "Macau", - "Macedonia", - "Madagascar", - "Malawi", - "Malaysia", - "Maldives", - "Mali", - "Malta", - "Marshall Islands", - "Martinique", - "Mauritania", - "Mauritius", - "Mayotte", - "Mediterranean Sea", - "Mexico", - "Micronesia", - "Midway Islands", - "Moldova", - "Monaco", - "Mongolia", - "Montenegro", - "Montserrat", - "Morocco", - "Mozambique", - "Myanmar", - "Namibia", - "Nauru", - "Navassa Island", - "Nepal", - "Netherlands", - "New Caledonia", - "New Zealand", - "Nicaragua", - "Niger", - "Nigeria", - "Niue", - "Norfolk Island", - "North Korea", - "North Sea", - "Northern Mariana Islands", - "Norway", - "Oman", - "Pacific Ocean", - "Pakistan", - "Palau", - "Palmyra Atoll", - "Panama", - "Papua New Guinea", - "Paracel Islands", - "Paraguay", - "Peru", - "Philippines", - "Pitcairn Islands", - "Poland", - "Portugal", - "Puerto Rico", - "Qatar", - "Republic of the Congo", - "Reunion", - "Romania", - "Ross Sea", - "Russia", - "Rwanda", - "Saint Helena", - "Saint Kitts and Nevis", - "Saint Lucia", - "Saint Pierre and Miquelon", - "Saint Vincent and the Grenadines", - "Samoa", - "San Marino", - "Sao Tome and Principe", - "Saudi Arabia", - "Senegal", - "Serbia", - "Seychelles", - "Sierra Leone", - "Singapore", - "Sint Maarten", - "Slovakia", - "Slovenia", - "Solomon Islands", - "Somalia", - "South Africa", - "South Georgia and the South Sandwich Islands", - "South Korea", - "Southern Ocean", - "Spain", - "Spratly Islands", - "Sri Lanka", - "Sudan", - "Suriname", - "Svalbard", - "Swaziland", - "Sweden", - "Switzerland", - "Syria", - "Taiwan", - "Tajikistan", - "Tanzania", - "Tasman Sea", - "Thailand", - "Togo", - "Tokelau", - "Tonga", - "Trinidad and Tobago", - "Tromelin Island", - "Tunisia", - "Turkey", - "Turkmenistan", - "Turks and Caicos Islands", - "Tuvalu", - "USA", - "Uganda", - "Ukraine", - "United Arab Emirates", - "United Kingdom", - "Uruguay", - "Uzbekistan", - "Vanuatu", - "Venezuela", - "Viet Nam", - "Virgin Islands", - "Wake Island", - "Wallis and Futuna", - "West Bank", - "Western Sahara", - "Yemen", - "Zambia", - "Zimbabwe", - "not applicable", - "not collected", - "not provided", - "restricted access" + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "not applicable", + "not collected", + "not provided", + "restricted access" ], "isaTag": "source_characteristic" }, @@ -407,7 +407,7 @@ }, { "iri": null, - "name": "submission_date", + "name": "submission date", "description": "Date in which experiment was submitted to ENA.", "dataType": "String", "required": false, @@ -732,7 +732,7 @@ }, { "iri": null, - "name": "submission_date", + "name": "submission date", "description": "Date in which run was submitted to ENA.", "dataType": "String", "required": false, @@ -854,7 +854,7 @@ }, { "iri": null, - "name": "submission_date", + "name": "submission date", "description": "Date in which run was submitted to ENA.", "dataType": "String", "required": false, @@ -883,4 +883,4 @@ ] } ] -} +} \ No newline at end of file From 8fd1787625c2baf5e066bb07019cab0827c97ea5 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Sun, 19 Nov 2023 20:31:21 +0100 Subject: [PATCH 18/25] Change submission date back to submission_date --- templates/ena_upload_tool/ena_upload_tool_aggregated.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index 570eb7a..1c74cec 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -407,7 +407,7 @@ }, { "iri": null, - "name": "submission date", + "name": "submission_date", "description": "Date in which experiment was submitted to ENA.", "dataType": "String", "required": false, @@ -732,7 +732,7 @@ }, { "iri": null, - "name": "submission date", + "name": "submission_date", "description": "Date in which run was submitted to ENA.", "dataType": "String", "required": false, @@ -854,7 +854,7 @@ }, { "iri": null, - "name": "submission date", + "name": "submission_date", "description": "Date in which run was submitted to ENA.", "dataType": "String", "required": false, @@ -883,4 +883,4 @@ ] } ] -} \ No newline at end of file +} From d3711d3804c517b81c1f3624b9600b3f544e7aa0 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Sun, 19 Nov 2023 20:32:05 +0100 Subject: [PATCH 19/25] Add seed file for DataHub extended metadata --- seek_seed_files/016_ena_upload.seeds.rb | 57 +++++++++++++++++++++++++ 1 file changed, 57 insertions(+) create mode 100644 seek_seed_files/016_ena_upload.seeds.rb diff --git a/seek_seed_files/016_ena_upload.seeds.rb b/seek_seed_files/016_ena_upload.seeds.rb new file mode 100644 index 0000000..b363518 --- /dev/null +++ b/seek_seed_files/016_ena_upload.seeds.rb @@ -0,0 +1,57 @@ +# General functionalities +def create_sample_controlled_vocab_terms_attributes(array) + attributes = [] + array.each do |type| + attributes << { label: type } + end + attributes +end + +existing_study_types = ['Whole Genome Sequencing', 'Metagenomics', 'Transcriptome Analysis', 'Resequencing', + 'Epigenetics', 'Synthetic Genomics', 'Forensic or Paleo-genomics', 'Gene Regulation Study', + 'Cancer Genomics', 'Population Genomics', 'RNASeq', 'Exome Sequencing', + 'Pooled Clone Sequencing', 'Transcriptome Sequencing', 'Other'] + +disable_authorization_checks do + # Study + unless ExtendedMetadataType.where(title: 'ENA Sample Metadata', supported_type: 'Study').any? + study_emt = ExtendedMetadataType.new(title: 'ENA Sample Metadata', supported_type: 'Study') + study_emt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'ena_sample_alias_prefix', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), + label: 'ENA sample alias prefix') + study_emt.save! + end + + study_type_cv = SampleControlledVocab.where(title: 'ENA Study Types').first_or_create!(sample_controlled_vocab_terms_attributes: create_sample_controlled_vocab_terms_attributes(existing_study_types)) + + # Assay + unless ExtendedMetadataType.where(title: 'ENA Study metadata', supported_type: 'Assay').any? + assay_cmt = ExtendedMetadataType.new(title: 'ENA Study metadata', supported_type: 'Assay') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'ena_study_title', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), label: 'ENA study title', + description: 'Title of the study as would be used in a publication.') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'study_type', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'Controlled Vocabulary'), + sample_controlled_vocab: study_type_cv, + description: 'The STUDY_TYPE presents a controlled vocabulary for expressing the overall purpose of the study.', + label: 'ENA Study Type') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'new_study_type', required: false, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), label: 'New Study Type', + description: 'Specify a new Study Type here if "Other" was chosen as "ENA Study Type".') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'ena_study_abstract', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'Text'), label: 'ENA study abstract', + description: 'Briefly describes the goals, purpose, and scope of the Study. This need not be listed if it can be inherited from a referenced publication.') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'assay_stream', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), + description: 'This is the name that will be transferred to the ISA JSON. Example: "My assay" will be defined as "a_my_assay.txt" in the ISA JSON', + label: 'Name Assay Stream') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'ena_study_alias_prefix', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), label: 'ENA study alias prefix') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'ena_experiment_alias_prefix', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), label: 'ENA experiment alias prefix') + assay_cmt.extended_metadata_attributes << ExtendedMetadataAttribute.new(title: 'ena_run_alias_prefix', required: true, + sample_attribute_type: SampleAttributeType.find_by(title: 'String'), label: 'ENA run alias prefix') + assay_cmt.save! + end +end +puts 'Seeded ENA extended metadata' From 72c2b6b0347ccd09d302a9171b5f4ff80735f3ac Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Sun, 19 Nov 2023 20:32:20 +0100 Subject: [PATCH 20/25] Change data type --- templates/ena_upload_tool/ena_upload_tool_aggregated.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index 1c74cec..d6b01df 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -390,7 +390,7 @@ "iri": null, "name": "collection date", "description": "Date of the sample collection", - "dataType": "ENA collection date", + "dataType": "ENA custom date", "required": true, "ontology": null, "isaTag": "sample_characteristic" From 3f4d92f24bd58e53e6a72d207bc6399511be68e7 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 30 Nov 2023 07:54:46 +0100 Subject: [PATCH 21/25] Change datatype name to "Registered Sample List" --- templates/arrayexpress/array_express_aggregated.json | 8 ++++---- templates/ena/ena_aggregated.json | 12 ++++++------ .../ena_upload_tool/ena_upload_tool_aggregated.json | 6 +++--- templates/ilvo/ilvo_aggregated.json | 8 ++++---- templates/isa test/isa_test_aggregated_v1.1.0.json | 12 ++++++------ templates/isa test/minimalistic_isa_test_v1.0.1.json | 8 ++++---- 6 files changed, 27 insertions(+), 27 deletions(-) diff --git a/templates/arrayexpress/array_express_aggregated.json b/templates/arrayexpress/array_express_aggregated.json index 35d4a02..eb37019 100644 --- a/templates/arrayexpress/array_express_aggregated.json +++ b/templates/arrayexpress/array_express_aggregated.json @@ -20,7 +20,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -213,7 +213,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -285,7 +285,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -432,7 +432,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, diff --git a/templates/ena/ena_aggregated.json b/templates/ena/ena_aggregated.json index a8503ac..21cdf88 100644 --- a/templates/ena/ena_aggregated.json +++ b/templates/ena/ena_aggregated.json @@ -20,7 +20,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -269,7 +269,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -325,7 +325,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -496,7 +496,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -610,7 +610,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -655,7 +655,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index d6b01df..e2b289f 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -346,7 +346,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -455,7 +455,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -780,7 +780,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, diff --git a/templates/ilvo/ilvo_aggregated.json b/templates/ilvo/ilvo_aggregated.json index 0bbc735..f92f4cf 100644 --- a/templates/ilvo/ilvo_aggregated.json +++ b/templates/ilvo/ilvo_aggregated.json @@ -20,7 +20,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -283,7 +283,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -603,7 +603,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -661,7 +661,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, diff --git a/templates/isa test/isa_test_aggregated_v1.1.0.json b/templates/isa test/isa_test_aggregated_v1.1.0.json index 629a6eb..b5ea17a 100644 --- a/templates/isa test/isa_test_aggregated_v1.1.0.json +++ b/templates/isa test/isa_test_aggregated_v1.1.0.json @@ -85,7 +85,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -208,7 +208,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -331,7 +331,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -454,7 +454,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -577,7 +577,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -700,7 +700,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, diff --git a/templates/isa test/minimalistic_isa_test_v1.0.1.json b/templates/isa test/minimalistic_isa_test_v1.0.1.json index 23aeeec..302f411 100644 --- a/templates/isa test/minimalistic_isa_test_v1.0.1.json +++ b/templates/isa test/minimalistic_isa_test_v1.0.1.json @@ -57,11 +57,11 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, - { + { "iri": null, "name": "sample collection", "description": "type of assay or experimental step performed.", @@ -112,7 +112,7 @@ "iri": null, "name": "Input", "description": "Existing Samples in DataHub that represent input for this protocol.", - "dataType": "Registered Sample (multiple)", + "dataType": "Registered Sample List", "required": true, "isaTag": null }, @@ -158,4 +158,4 @@ ] } ] -} \ No newline at end of file +} From cf9ddffc71783947ced0963892bf82c8e09dd79b Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Thu, 30 Nov 2023 09:16:15 +0100 Subject: [PATCH 22/25] Replace "ontology" dataType by "Controlled Vocabulary" --- .../array_express_aggregated.json | 44 ++++----- .../arrayexpress/source_plant_v1.2.0.json | 96 +++++++++---------- templates/ena/ena_aggregated.json | 10 +- .../ena/sample_collection_plant_v1.0.0.json | 24 ++--- templates/ena/source_plant_v1.1.0.json | 6 +- templates/ilvo/ILVO Sample plant.json | 12 +-- templates/ilvo/ILVO Source plant.json | 28 +++--- templates/ilvo/ilvo_aggregated.json | 16 ++-- .../isa test/isa_test_aggregated_v1.1.0.json | 26 ++--- 9 files changed, 131 insertions(+), 131 deletions(-) diff --git a/templates/arrayexpress/array_express_aggregated.json b/templates/arrayexpress/array_express_aggregated.json index eb37019..c6f7070 100644 --- a/templates/arrayexpress/array_express_aggregated.json +++ b/templates/arrayexpress/array_express_aggregated.json @@ -510,7 +510,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0100026", "name": "organism", "description": "A material entity that is an individual living system, such as animal, plant, bacteria or virus, that is capable of replicating or reproducing, growth and maintenance in the right environment. An organism may be unicellular or made up, like humans, of many billions of cells divided into specialized tissues and organs. E.g Drosophila melanogaster.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -524,7 +524,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000635", "name": "organism part", "description": "The part of organism's anatomy or substance arising from an organism from which the biomaterial was derived, excludes cells. E.g. tissue, organ, system, sperm, blood or body location (arm).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -538,7 +538,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000399", "name": "developmental stage", "description": "A developmental stage is spatiotemporal region encompassing some part of the life cycle of an organism, e.g. blastula stage", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -552,7 +552,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000246", "name": "age", "description": "A temporal measurement of the time period elapsed since an identifiable point in the life cycle of an organism. If a developmental stage is specified, the identifiable point would be the beginning of that stage. Otherwise the identifiable point must be specified such as planting (e.g. 3 days post planting).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -566,7 +566,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000513", "name": "genotype", "description": "The total sum of the genetic information of an organism that is known and relevant to the experiment being performed, including chromosomal, plasmid, viral or other genetic material which has been introduced into the organism either prior to or during the experiment.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -588,7 +588,7 @@ "iri": "http://purl.obolibrary.org/obo/CL_0000010", "name": "cultured cell", "description": "A cell in vitro that is or has been maintained or propagated as part of a cell culture.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -602,7 +602,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000324", "name": "cell type", "description": "A cell type is a distinct morphological or functional form of cell. Examples are epithelial, glial etc.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -616,7 +616,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000352", "name": "clinical history", "description": "Is an information entity about the material's (i.e., the patient's) medical record as background information relevant to the experiment.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -630,7 +630,7 @@ "iri": "http://purl.obolibrary.org/obo/CHEBI_24431", "name": "chemical entity", "description": "A drug, solvent, chemical, etc., with a property that can be measured such as concentration. A molecular entity consisting of two or more chemical elements.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -644,7 +644,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0002755", "name": "diet", "description": "The customary allowance of food and drink taken by a person or an animal from day to day, particularly one especially planned to meet specific requirements of the individual, including or excluding certain items of food; a prescribed course of eating and drinking in which the amount and kind of food, as well as the times at which it is to be taken, are regulated for therapeutic purposes or selected with reference to a particular state of health. Regular course of eating and drinking adopted by a person or animal. This does not include DIET THERAPY, a specific diet prescribed in the treatment of a disease.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -658,7 +658,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000408", "name": "disease", "description": "A disease is a disposition to undergo pathological processes that exists in an organism because of one or more disorders in that organism. [ OGMS:0000031 ]", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -672,7 +672,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000410", "name": "disease staging", "description": "The stage or progression of a disease in an organism. Includes pathological staging of cancers and other disease progression. E.g. Dukes C stage describing colon cancer.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -694,7 +694,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000434", "name": "ecotype", "description": "A biotype resulting from selection in a particular habitat, e.g. the A. thaliana Ecotype Ler.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -732,7 +732,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000510", "name": "genetic modification", "description": "A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. Examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -746,7 +746,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000523", "name": "growth condition", "description": "A role that a material entity can play which enables particular conditions used to grow organisms or parts of the organism. This includes isolated environments such as cultures and open environments such as field studies.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -760,7 +760,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000541", "name": "immunoprecipitate", "description": "The precipitate antibody bound target molecules generated when precipitating an antigen out of a solution during the process of immunoprecipitation.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -798,7 +798,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000546", "name": "injury", "description": "Damage inflicted on the body as the direct or indirect result of an external force, with or without disruption of structural continuity. [ NCIT:C3671 ]", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -828,7 +828,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000651", "name": "phenotype", "description": "The observable form taken by some character (or group of characters) in an individual or an organism, excluding pathology and disease. The detectable outward manifestations of a specific genotype.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -850,7 +850,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000683", "name": "replicate", "description": "A role played by a a biological sample in the context of an experiment where the intent is that biological or technical variation is measured.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -864,7 +864,7 @@ "iri": "http://purl.obolibrary.org/obo/PATO_0000047", "name": "sex", "description": "The assemblage of physical properties or qualities by which male is distinguished from female; the physical difference between male and female; the distinguishing peculiarity of male or female. An organismal quality inhering in a bearer by virtue of the bearer's ability to undergo sexual reproduction in order to differentiate the individuals or types involved. Term applied to any organism able to undergo sexual reproduction in order to differentiate the individuals or types involved. Sexual reproduction is defined as the ability to exchange genetic material with the potential of recombinant progeny.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -886,7 +886,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0001472", "name": "specimen with known storage state", "description": "A specimen for which it is known whether it has been subjected to storage of a specified type.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -916,7 +916,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0600002", "name": "tumor grading", "description": "An assay that determines the grade (severity/stage) of a tumor sample, used in cancer biology to describe abnormalities/qualities of tumor cells or tissues. Values can be described by terms from NCI Thesaurus. Determination of the grade (severity/stage) of a tumor sample, used in cancer biology to describe abnormalities/qualities of tumor cells or tissues. Values can be described by terms from NCI Thesaurus.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { diff --git a/templates/arrayexpress/source_plant_v1.2.0.json b/templates/arrayexpress/source_plant_v1.2.0.json index daf1ec3..a3a9314 100644 --- a/templates/arrayexpress/source_plant_v1.2.0.json +++ b/templates/arrayexpress/source_plant_v1.2.0.json @@ -26,7 +26,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0100026", "name": "organism", "description": "A material entity that is an individual living system, such as animal, plant, bacteria or virus, that is capable of replicating or reproducing, growth and maintenance in the right environment. An organism may be unicellular or made up, like humans, of many billions of cells divided into specialized tissues and organs. E.g Drosophila melanogaster.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -35,12 +35,12 @@ "description": "Experimental Factor Ontology", "rootTermURI": "http://purl.obolibrary.org/obo/OBI_0100026" } - }, + }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000635", "name": "organism part", "description": "The part of organism's anatomy or substance arising from an organism from which the biomaterial was derived, excludes cells. E.g. tissue, organ, system, sperm, blood or body location (arm).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -48,13 +48,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000635" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000399", "name": "developmental stage", "description": "A developmental stage is spatiotemporal region encompassing some part of the life cycle of an organism, e.g. blastula stage", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -62,13 +62,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000399" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000246", "name": "age", "description": "A temporal measurement of the time period elapsed since an identifiable point in the life cycle of an organism. If a developmental stage is specified, the identifiable point would be the beginning of that stage. Otherwise the identifiable point must be specified such as planting (e.g. 3 days post planting).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -76,13 +76,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000246" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000513", "name": "genotype", "description": "The total sum of the genetic information of an organism that is known and relevant to the experiment being performed, including chromosomal, plasmid, viral or other genetic material which has been introduced into the organism either prior to or during the experiment.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -90,7 +90,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000513" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0005136", @@ -104,7 +104,7 @@ "iri": "http://purl.obolibrary.org/obo/CL_0000010", "name": "cultured cell", "description": "A cell in vitro that is or has been maintained or propagated as part of a cell culture.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -112,13 +112,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://purl.obolibrary.org/obo/CL_0000010" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000324", "name": "cell type", "description": "A cell type is a distinct morphological or functional form of cell. Examples are epithelial, glial etc.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -127,12 +127,12 @@ "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000324" } - }, + }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000352", "name": "clinical history", "description": "Is an information entity about the material's (i.e., the patient's) medical record as background information relevant to the experiment.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -140,13 +140,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000352" - } + } }, { "iri": "http://purl.obolibrary.org/obo/CHEBI_24431", "name": "chemical entity", "description": "A drug, solvent, chemical, etc., with a property that can be measured such as concentration. A molecular entity consisting of two or more chemical elements.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -154,13 +154,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://purl.obolibrary.org/obo/CHEBI_24431" - } + } }, - { + { "iri": "http://www.ebi.ac.uk/efo/EFO_0002755", "name": "diet", "description": "The customary allowance of food and drink taken by a person or an animal from day to day, particularly one especially planned to meet specific requirements of the individual, including or excluding certain items of food; a prescribed course of eating and drinking in which the amount and kind of food, as well as the times at which it is to be taken, are regulated for therapeutic purposes or selected with reference to a particular state of health. Regular course of eating and drinking adopted by a person or animal. This does not include DIET THERAPY, a specific diet prescribed in the treatment of a disease.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -168,13 +168,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0002755" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000408", "name": "disease", "description": "A disease is a disposition to undergo pathological processes that exists in an organism because of one or more disorders in that organism. [ OGMS:0000031 ]", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -182,13 +182,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000408" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000410", "name": "disease staging", "description": "The stage or progression of a disease in an organism. Includes pathological staging of cancers and other disease progression. E.g. Dukes C stage describing colon cancer.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -196,7 +196,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000410" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000428", @@ -210,7 +210,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000434", "name": "ecotype", "description": "A biotype resulting from selection in a particular habitat, e.g. the A. thaliana Ecotype Ler.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -218,7 +218,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000434" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0004444", @@ -248,7 +248,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000510", "name": "genetic modification", "description": "A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. Examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -256,13 +256,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000510" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000523", "name": "growth condition", "description": "A role that a material entity can play which enables particular conditions used to grow organisms or parts of the organism. This includes isolated environments such as cultures and open environments such as field studies.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -270,13 +270,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000523" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000541", "name": "immunoprecipitate", "description": "The precipitate antibody bound target molecules generated when precipitating an antigen out of a solution during the process of immunoprecipitation.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -284,7 +284,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000541" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000542", @@ -300,7 +300,7 @@ "description": "The state of being infected such as from the introduction of a foreign agent such as serum, vaccine, antigenic substance or organism.", "dataType": "String", "required": false, - "isaTag": "source_characteristic" + "isaTag": "source_characteristic" }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0010196", @@ -314,7 +314,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000546", "name": "injury", "description": "Damage inflicted on the body as the direct or indirect result of an external force, with or without disruption of structural continuity. [ NCIT:C3671 ]", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -322,7 +322,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000546" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000554", @@ -344,7 +344,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000651", "name": "phenotype", "description": "The observable form taken by some character (or group of characters) in an individual or an organism, excluding pathology and disease. The detectable outward manifestations of a specific genotype.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -352,7 +352,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000651" - } + } }, { "iri": "http://purl.obolibrary.org/obo/GO_0016246", @@ -366,7 +366,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000683", "name": "replicate", "description": "A role played by a a biological sample in the context of an experiment where the intent is that biological or technical variation is measured.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -374,13 +374,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000683" - } + } }, { "iri": "http://purl.obolibrary.org/obo/PATO_0000047", "name": "sex", "description": "The assemblage of physical properties or qualities by which male is distinguished from female; the physical difference between male and female; the distinguishing peculiarity of male or female. An organismal quality inhering in a bearer by virtue of the bearer's ability to undergo sexual reproduction in order to differentiate the individuals or types involved. Term applied to any organism able to undergo sexual reproduction in order to differentiate the individuals or types involved. Sexual reproduction is defined as the ability to exchange genetic material with the potential of recombinant progeny.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -388,7 +388,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://purl.obolibrary.org/obo/PATO_0000047" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0010197", @@ -402,7 +402,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0001472", "name": "specimen with known storage state", "description": "A specimen for which it is known whether it has been subjected to storage of a specified type.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -410,7 +410,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://purl.obolibrary.org/obo/OBI_0001472" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0005135", @@ -432,7 +432,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0600002", "name": "tumor grading", "description": "An assay that determines the grade (severity/stage) of a tumor sample, used in cancer biology to describe abnormalities/qualities of tumor cells or tissues. Values can be described by terms from NCI Thesaurus. Determination of the grade (severity/stage) of a tumor sample, used in cancer biology to describe abnormalities/qualities of tumor cells or tissues. Values can be described by terms from NCI Thesaurus.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -440,17 +440,17 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://purl.obolibrary.org/obo/OBI_0600002" - } + } }, { "iri": null, "name": "material type", "description": "Used as an attribute column following Source Name, Sample Name, Extract Name, or Labeled Extract Name. This column contains terms describing the type of each material, for examples: whole organism, organism part, cell, total RNA.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": null, "CVList": ["whole organism", "organism part", "RNA", "DNA", "cell"] } ] -} \ No newline at end of file +} diff --git a/templates/ena/ena_aggregated.json b/templates/ena/ena_aggregated.json index 21cdf88..e5c79ce 100644 --- a/templates/ena/ena_aggregated.json +++ b/templates/ena/ena_aggregated.json @@ -523,7 +523,7 @@ "iri": null, "name": "sample material processing", "description": "Any processing applied to the sample during or after retrieving the sample from environment. This field accepts OBI, for a browser of OBI (v 2013-10-25) terms please see http://purl.bioontology.org/ontology/OBI", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "OBI", @@ -1421,7 +1421,7 @@ "iri": null, "name": "ploidy", "description": "The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). It has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). For terms, please select terms listed under class ploidy (PATO:001374) of Phenotypic Quality Ontology (PATO), and for a browser of PATO (v 2013-10-28) please refer to http://purl.bioontology.org/ontology/PATO. Mandatory for MIGS of eukaryotes.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "ontology": { "name": "PATO", @@ -1824,7 +1824,7 @@ "iri": null, "name": "environment (biome)", "description": "Biomes are defined based on factors such as plant structures, leaf types, plant spacing, and other factors like climate. Biome should be treated as the descriptor of the broad ecological context of a sample. Examples include: desert, taiga, deciduous woodland, or coral reef. EnvO (v 2013-06-14) terms can be found via the link: www.environmentontology.org/Browse-EnvO", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "ENVO", @@ -1882,7 +1882,7 @@ "iri": null, "name": "plant structure", "description": "name of plant structure that the sample was obtained from; for Plant Ontology (PO) terms see http://purl.bioontology.org/ontology/PO, e.g. petiole epidermis (PO_0000051); if an individual flower is sampled the sex of it can be recorded here", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "ontology": { "name": "PO", @@ -1896,7 +1896,7 @@ "iri": null, "name": "plant developmental stage", "description": "developmental stage at the time of sample collection; for Plant Ontology (PO) (v 20) terms, see http://purl.bioontology.org/ontology/PO, e.g. hypocotyl emergence stage (PO_0007043)", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "ontology": { "name": "PO", diff --git a/templates/ena/sample_collection_plant_v1.0.0.json b/templates/ena/sample_collection_plant_v1.0.0.json index 1835796..0a1bb51 100644 --- a/templates/ena/sample_collection_plant_v1.0.0.json +++ b/templates/ena/sample_collection_plant_v1.0.0.json @@ -21,14 +21,14 @@ "dataType": "SEEK Sample Multi", "required": true, "isaTag": null - }, + }, { "iri": null, "name": "sample collection", "description": "type of assay or experimental step performed.", "dataType": "String", "required": true, - "ontology": null, + "ontology": null, "CVList": null,//SOPtittle "isaTag": "protocol" }, @@ -39,20 +39,20 @@ "dataType": "String", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, "name": "sample material processing", "description": "Any processing applied to the sample during or after retrieving the sample from environment. This field accepts OBI, for a browser of OBI (v 2013-10-25) terms please see http://purl.bioontology.org/ontology/OBI", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "OBI", "version": "", "description": "Ontology for Biomedical Investigations", "rootTermURI": "http://purl.obolibrary.org/obo/OBI_0000094"}, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, @@ -61,7 +61,7 @@ "dataType": "String", // original Regex "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, @@ -70,7 +70,7 @@ "dataType": "String", // original Regex "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, @@ -79,7 +79,7 @@ "dataType": "String", // original Regex "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, @@ -88,7 +88,7 @@ "dataType": "String", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, @@ -97,7 +97,7 @@ "dataType": "String", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "parameter_value" }, { "iri": null, @@ -107,6 +107,6 @@ "required": true, "title": true, "ontology": null, - "isaTag": "sample" + "isaTag": "sample" } -] \ No newline at end of file +] diff --git a/templates/ena/source_plant_v1.1.0.json b/templates/ena/source_plant_v1.1.0.json index 5b91c6e..1d96e51 100644 --- a/templates/ena/source_plant_v1.1.0.json +++ b/templates/ena/source_plant_v1.1.0.json @@ -465,7 +465,7 @@ "iri": null, "name": "environment (biome)", "description": "Biomes are defined based on factors such as plant structures, leaf types, plant spacing, and other factors like climate. Biome should be treated as the descriptor of the broad ecological context of a sample. Examples include: desert, taiga, deciduous woodland, or coral reef. EnvO (v 2013-06-14) terms can be found via the link: www.environmentontology.org/Browse-EnvO", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "ENVO", @@ -522,7 +522,7 @@ "iri": null, "name": "plant structure", "description": "name of plant structure that the sample was obtained from; for Plant Ontology (PO) terms see http://purl.bioontology.org/ontology/PO, e.g. petiole epidermis (PO_0000051); if an individual flower is sampled the sex of it can be recorded here", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "ontology": { "name": "PO", @@ -535,7 +535,7 @@ "iri": null, "name": "plant developmental stage", "description": "developmental stage at the time of sample collection; for Plant Ontology (PO) (v 20) terms, see http://purl.bioontology.org/ontology/PO, e.g. hypocotyl emergence stage (PO_0007043)", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "ontology": { "name": "PO", diff --git a/templates/ilvo/ILVO Sample plant.json b/templates/ilvo/ILVO Sample plant.json index b7cf2bc..ee3fd9b 100644 --- a/templates/ilvo/ILVO Sample plant.json +++ b/templates/ilvo/ILVO Sample plant.json @@ -31,7 +31,7 @@ "isaTag": "protocol", "ontology": null, "CVList": null - }, + }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000688", "name": "sampling site", @@ -52,7 +52,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000635", "name": "organism part", "description": "The part of organism's anatomy or substance arising from an organism from which the biomaterial was derived, excludes cells. E.g. tissue, organ, system, sperm, blood or body location (arm).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "sample_characteristic", "ontology": { @@ -60,7 +60,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000635" - } + } }, { "iri": null, @@ -71,7 +71,7 @@ "isaTag": "sample_characteristic", "ontology": null, "CVList": ["whole organism", "organism part", "RNA", "DNA", "cell"] - }, + }, { "iri": null, "name": "Sample Name", @@ -109,6 +109,6 @@ "isaTag": "sample_characteristic", "ontology": null } - + ] - } \ No newline at end of file + } diff --git a/templates/ilvo/ILVO Source plant.json b/templates/ilvo/ILVO Source plant.json index 1176ab1..0d2cc9b 100644 --- a/templates/ilvo/ILVO Source plant.json +++ b/templates/ilvo/ILVO Source plant.json @@ -26,7 +26,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0100026", "name": "organism", "description": "A material entity that is an individual living system, such as animal, plant, bacteria or virus, that is capable of replicating or reproducing, growth and maintenance in the right environment. An organism may be unicellular or made up, like humans, of many billions of cells divided into specialized tissues and organs. E.g Drosophila melanogaster.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -56,7 +56,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000399", "name": "developmental stage", "description": "A developmental stage is spatiotemporal region encompassing some part of the life cycle of an organism, e.g. blastula stage", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -64,13 +64,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000399" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000246", "name": "age", "description": "A temporal measurement of the time period elapsed since an identifiable point in the life cycle of an organism. If a developmental stage is specified, the identifiable point would be the beginning of that stage. Otherwise the identifiable point must be specified such as planting (e.g. 3 days post planting).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -78,13 +78,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000246" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000513", "name": "genotype", "description": "The total sum of the genetic information of an organism that is known and relevant to the experiment being performed, including chromosomal, plasmid, viral or other genetic material which has been introduced into the organism either prior to or during the experiment.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -92,7 +92,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000513" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0005136", @@ -106,7 +106,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000510", "name": "genetic modification", "description": "A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. Examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -114,13 +114,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000510" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000523", "name": "growth condition", "description": "A role that a material entity can play which enables particular conditions used to grow organisms or parts of the organism. This includes isolated environments such as cultures and open environments such as field studies.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -128,13 +128,13 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000523" - } + } }, { "iri": "http://www.ebi.ac.uk/efo/EFO_0000683", "name": "replicate", "description": "A role played by a a biological sample in the context of an experiment where the intent is that biological or technical variation is measured.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -142,7 +142,7 @@ "version": "1", "description": "Experimental Factor Ontology", "rootTermURI": "http://www.ebi.ac.uk/efo/EFO_0000683" - } + } } ] - } \ No newline at end of file + } diff --git a/templates/ilvo/ilvo_aggregated.json b/templates/ilvo/ilvo_aggregated.json index f92f4cf..5493449 100644 --- a/templates/ilvo/ilvo_aggregated.json +++ b/templates/ilvo/ilvo_aggregated.json @@ -54,7 +54,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000635", "name": "organism part", "description": "The part of organism's anatomy or substance arising from an organism from which the biomaterial was derived, excludes cells. E.g. tissue, organ, system, sperm, blood or body location (arm).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "sample_characteristic", "ontology": { @@ -142,7 +142,7 @@ "iri": "http://purl.obolibrary.org/obo/OBI_0100026", "name": "organism", "description": "A material entity that is an individual living system, such as animal, plant, bacteria or virus, that is capable of replicating or reproducing, growth and maintenance in the right environment. An organism may be unicellular or made up, like humans, of many billions of cells divided into specialized tissues and organs. E.g Drosophila melanogaster.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -172,7 +172,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000399", "name": "developmental stage", "description": "A developmental stage is spatiotemporal region encompassing some part of the life cycle of an organism, e.g. blastula stage", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -186,7 +186,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000246", "name": "age", "description": "A temporal measurement of the time period elapsed since an identifiable point in the life cycle of an organism. If a developmental stage is specified, the identifiable point would be the beginning of that stage. Otherwise the identifiable point must be specified such as planting (e.g. 3 days post planting).", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -200,7 +200,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000513", "name": "genotype", "description": "The total sum of the genetic information of an organism that is known and relevant to the experiment being performed, including chromosomal, plasmid, viral or other genetic material which has been introduced into the organism either prior to or during the experiment.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": true, "isaTag": "source_characteristic", "ontology": { @@ -222,7 +222,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000510", "name": "genetic modification", "description": "A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. Examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -236,7 +236,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000523", "name": "growth condition", "description": "A role that a material entity can play which enables particular conditions used to grow organisms or parts of the organism. This includes isolated environments such as cultures and open environments such as field studies.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { @@ -250,7 +250,7 @@ "iri": "http://www.ebi.ac.uk/efo/EFO_0000683", "name": "replicate", "description": "A role played by a a biological sample in the context of an experiment where the intent is that biological or technical variation is measured.", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "isaTag": "source_characteristic", "ontology": { diff --git a/templates/isa test/isa_test_aggregated_v1.1.0.json b/templates/isa test/isa_test_aggregated_v1.1.0.json index b5ea17a..b223585 100644 --- a/templates/isa test/isa_test_aggregated_v1.1.0.json +++ b/templates/isa test/isa_test_aggregated_v1.1.0.json @@ -52,7 +52,7 @@ "iri": null, "name": "Source Characteristic 3", "description": "A characteristic of the source. With terms from an Ontology as accepted values", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "ENVO", @@ -127,7 +127,7 @@ "iri": null, "name": "sample collection parameter value 3", "description": "Parameter value 3 for sample collection", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "PATO", @@ -175,7 +175,7 @@ "iri": null, "name": "sample characteristic 3", "description": "sample characteristic 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "FOODON", @@ -250,7 +250,7 @@ "iri": null, "name": "Assay 1 parameter value 3", "description": "Parameter value 3 for Assay 1", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "BAO", @@ -298,7 +298,7 @@ "iri": null, "name": "other material characteristic 3", "description": "other material characteristic 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "FOODON", @@ -373,7 +373,7 @@ "iri": null, "name": "Assay 2 parameter value 3", "description": "Parameter value 3 for Assay 2", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "OMIT", @@ -421,7 +421,7 @@ "iri": null, "name": "other material 2 characteristic 3", "description": "other material characteristic 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "SNOMED", @@ -496,7 +496,7 @@ "iri": null, "name": "Assay 3 parameter value 3", "description": "Parameter value 3 for Assay 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "AFO", @@ -544,7 +544,7 @@ "iri": null, "name": "other material 3 characteristic 3", "description": "other material characteristic 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "SNOMED", @@ -619,7 +619,7 @@ "iri": null, "name": "Assay 4 parameter value 3", "description": "Parameter value 3 for Assay 4", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "ERO", @@ -667,7 +667,7 @@ "iri": null, "name": "comment 3", "description": "data file comment 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "MS", @@ -742,7 +742,7 @@ "iri": null, "name": "Assay 5 parameter value 3", "description": "Parameter value 3 for Assay 5", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "EDAM", @@ -790,7 +790,7 @@ "iri": null, "name": "comment 3", "description": "data file 2 comment 3", - "dataType": "Ontology", + "dataType": "Controlled Vocabulary", "required": false, "ontology": { "name": "NCIT", From 22a4bc04cb0e9f29feab5d4d5e625ac094990594 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Fri, 16 Feb 2024 11:15:28 +0100 Subject: [PATCH 23/25] Fix template --- templates/ena_upload_tool/ena_upload_tool_aggregated.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index e2b289f..215ed22 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -468,7 +468,7 @@ "ontology": null, "dataType": "String", //need to be autofilled with name of selected SOP for that block "CVList": null, //SOPtittle - "isaTag": "other_material" + "isaTag": "parameter_value" }, { "iri": null, @@ -477,7 +477,7 @@ "dataType": "String", "required": false, "ontology": null, - "isaTag": "parameter_value" + "isaTag": "protocol" }, { "iri": null, From 1f128572b6967f86f78a7e7ff2266c7bec970b14 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Fri, 16 Feb 2024 15:16:06 +0100 Subject: [PATCH 24/25] Clean-up ena templates --- .../ena_upload_tool_aggregated.json | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index 215ed22..3707b89 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -462,13 +462,24 @@ { "iri": null, "name": "library construction", - "description": "type of assay or experimental step performed.", + "description": "Type of assay or experimental step performed.", "required": true, - "title": true, + "title": false, "ontology": null, "dataType": "String", //need to be autofilled with name of selected SOP for that block "CVList": null, //SOPtittle - "isaTag": "parameter_value" + "isaTag": "protocol" + }, + { + "iri": null, + "name": "library", + "description": "Name of the genereal output of this assay in DataHub.", + "required": true, + "title": true, + "ontology": null, + "dataType": "String", + "CVList": null, + "isaTag": "other_material" }, { "iri": null, @@ -502,7 +513,7 @@ { "iri": null, "name": "library_name", - "description": "Name given to the generated library", + "description": "Name of the library to be published in ENA", "dataType": "String", "required": true, "ontology": null, From 12d7d4b85c9b0611e2387ea81ee0a119f413a471 Mon Sep 17 00:00:00 2001 From: Kevin De Pelseneer Date: Tue, 7 Jan 2025 10:25:47 +0100 Subject: [PATCH 25/25] Remove duplicate 'protocol' ISA tag --- .../ena_upload_tool/ena_upload_tool_aggregated.json | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/templates/ena_upload_tool/ena_upload_tool_aggregated.json b/templates/ena_upload_tool/ena_upload_tool_aggregated.json index 3707b89..82ac0e3 100644 --- a/templates/ena_upload_tool/ena_upload_tool_aggregated.json +++ b/templates/ena_upload_tool/ena_upload_tool_aggregated.json @@ -468,17 +468,6 @@ "ontology": null, "dataType": "String", //need to be autofilled with name of selected SOP for that block "CVList": null, //SOPtittle - "isaTag": "protocol" - }, - { - "iri": null, - "name": "library", - "description": "Name of the genereal output of this assay in DataHub.", - "required": true, - "title": true, - "ontology": null, - "dataType": "String", - "CVList": null, "isaTag": "other_material" }, {