Merge pull request #124 from drpatelh/fixes

Fix #114
nf-core · Nov 7, 2022 · 44901cf · 44901cf
2 parents 42aeaf3 + 12e8b85
commit 44901cf
Showing 3 changed files with 71 additions and 46 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Enhancements & fixes
 
+- [#111](https://github.com/nf-core/fetchngs/issues/111) - Change input mimetype to csv
+- [#114](https://github.com/nf-core/fetchngs/issues/114) - Final samplesheet is not created when `--skip_fastq_download` is provided
+- [#118](https://github.com/nf-core/fetchngs/issues/118) - Allow input pattern validation for csv/tsv/txt
+- [#121](https://github.com/nf-core/fetchngs/issues/121) - Add `tower.yml` to render samplesheet as Report in Tower
 - Fetch `SRR` and `DRR` metadata from ENA API instead of NCBI API to bypass frequent breaking changes
 - Updated pipeline template to [nf-core/tools 2.6](https://github.com/nf-core/tools/releases/tag/2.6)
 
@@ -26,7 +30,6 @@ This downloads a text file called `SRR_Acc_List.txt` that can be directly provid
 
 ### Enhancements & fixes
 
-- [#121](https://github.com/nf-core/fetchngs/pull/123) - Add `tower.yml` to render Reports in Tower
 - [#97](https://github.com/nf-core/fetchngs/pull/97) - Add support for generating nf-core/taxprofiler compatible samplesheets.
 - [#99](https://github.com/nf-core/fetchngs/issues/99) - SRA_IDS_TO_RUNINFO fails due to bad request
 - Add `enum` field for `--nf_core_pipeline` to parameter schema so only accept supported pipelines are accepted

diff --git a/modules/local/sra_to_samplesheet.nf b/modules/local/sra_to_samplesheet.nf
@@ -6,9 +6,9 @@ process SRA_TO_SAMPLESHEET {
     memory 100.MB
 
     input:
-    tuple val(meta), path(fastq)
-    val   pipeline
-    val   mapping_fields
+    val meta
+    val pipeline
+    val mapping_fields
 
     output:
     tuple val(meta), path("*samplesheet.csv"), emit: samplesheet
@@ -20,19 +20,19 @@ process SRA_TO_SAMPLESHEET {
     //
 
     //  Remove custom keys needed to download the data
-    def meta_map = meta.clone()
-    meta_map.remove("id")
-    meta_map.remove("fastq_1")
-    meta_map.remove("fastq_2")
-    meta_map.remove("md5_1")
-    meta_map.remove("md5_2")
-    meta_map.remove("single_end")
+    def meta_clone = meta.clone()
+    meta_clone.remove("id")
+    meta_clone.remove("fastq_1")
+    meta_clone.remove("fastq_2")
+    meta_clone.remove("md5_1")
+    meta_clone.remove("md5_2")
+    meta_clone.remove("single_end")
 
     // Add relevant fields to the beginning of the map
     pipeline_map = [
         sample  : "${meta.id.split('_')[0..-2].join('_')}",
-        fastq_1 : "${params.outdir}/fastq/${fastq[0]}",
-        fastq_2 : meta.single_end ? '' : "${params.outdir}/fastq/${fastq[1]}"
+        fastq_1 : meta.fastq_1,
+        fastq_2 : meta.fastq_2
     ]
 
     // Add nf-core pipeline specific entries
@@ -43,7 +43,7 @@ process SRA_TO_SAMPLESHEET {
             pipeline_map << [ fasta: '' ]
         }
     }
-    pipeline_map << meta_map
+    pipeline_map << meta_clone
 
     // Create a samplesheet
     samplesheet  = pipeline_map.keySet().collect{ '"' + it + '"'}.join(",") + '\n'

diff --git a/workflows/sra.nf b/workflows/sra.nf
@@ -80,19 +80,27 @@ workflow SRA {
         .splitCsv(header:true, sep:'\t')
         .map {
             meta ->
-                meta.single_end = meta.single_end.toBoolean()
-                [ meta, [ meta.fastq_1, meta.fastq_2 ] ]
+                def meta_clone = meta.clone()
+                meta_clone.single_end = meta_clone.single_end.toBoolean()
+                return meta_clone
         }
         .unique()
-        .branch {
-            ftp: it[0].fastq_1  && !params.force_sratools_download
-            sra: !it[0].fastq_1 || params.force_sratools_download
-        }
-        .set { ch_sra_reads }
+        .set { ch_sra_metadata }
     ch_versions = ch_versions.mix(SRA_RUNINFO_TO_FTP.out.versions.first())
 
     if (!params.skip_fastq_download) {
 
+        ch_sra_metadata
+            .map { 
+                meta -> 
+                    [ meta, [ meta.fastq_1, meta.fastq_2 ] ] 
+            }
+            .branch {
+                ftp: it[0].fastq_1  && !params.force_sratools_download
+                sra: !it[0].fastq_1 || params.force_sratools_download
+            }
+            .set { ch_sra_reads }
+
         //
         // MODULE: If FTP link is provided in run information then download FastQ directly via FTP and validate with md5sums
         //
@@ -109,33 +117,47 @@ workflow SRA {
         )
         ch_versions = ch_versions.mix(SRAFASTQ.out.versions.first())
 
-        //
-        // MODULE: Stage FastQ files downloaded by SRA together and auto-create a samplesheet
-        //
-        SRA_TO_SAMPLESHEET (
-            SRA_FASTQ_FTP.out.fastq.mix(SRAFASTQ.out.reads),
-            params.nf_core_pipeline ?: '',
-            params.sample_mapping_fields
-        )
+        SRA_FASTQ_FTP
+            .out
+            .fastq
+            .mix(SRAFASTQ.out.reads)
+            .map { 
+                meta, fastq ->
+                    def reads = meta.single_end ? [ fastq ] : fastq
+                    def meta_clone = meta.clone()
+                    meta_clone.fastq_1 = reads[0] ? "${params.outdir}/fastq/${reads[0].getName()}" : ''
+                    meta_clone.fastq_2 = reads[1] && !meta.single_end ? "${params.outdir}/fastq/${reads[1].getName()}" : ''
+                    return meta_clone
+            }
+            .set { ch_sra_metadata }
+    }
 
-        //
-        // MODULE: Create a merged samplesheet across all samples for the pipeline
-        //
-        SRA_MERGE_SAMPLESHEET (
-            SRA_TO_SAMPLESHEET.out.samplesheet.collect{it[1]},
-            SRA_TO_SAMPLESHEET.out.mappings.collect{it[1]}
-        )
-        ch_versions = ch_versions.mix(SRA_MERGE_SAMPLESHEET.out.versions)
+    //
+    // MODULE: Stage FastQ files downloaded by SRA together and auto-create a samplesheet
+    //
+    SRA_TO_SAMPLESHEET (
+        ch_sra_metadata,
+        params.nf_core_pipeline ?: '',
+        params.sample_mapping_fields
+    )
 
-        //
-        // MODULE: Create a MutiQC config file with sample name mappings
-        //
-        if (params.sample_mapping_fields) {
-            MULTIQC_MAPPINGS_CONFIG (
-                SRA_MERGE_SAMPLESHEET.out.mappings
-            )
-            ch_versions = ch_versions.mix(MULTIQC_MAPPINGS_CONFIG.out.versions)
-        }
+    //
+    // MODULE: Create a merged samplesheet across all samples for the pipeline
+    //
+    SRA_MERGE_SAMPLESHEET (
+        SRA_TO_SAMPLESHEET.out.samplesheet.collect{it[1]},
+        SRA_TO_SAMPLESHEET.out.mappings.collect{it[1]}
+    )
+    ch_versions = ch_versions.mix(SRA_MERGE_SAMPLESHEET.out.versions)
+
+    //
+    // MODULE: Create a MutiQC config file with sample name mappings
+    //
+    if (params.sample_mapping_fields) {
+        MULTIQC_MAPPINGS_CONFIG (
+            SRA_MERGE_SAMPLESHEET.out.mappings
+        )
+        ch_versions = ch_versions.mix(MULTIQC_MAPPINGS_CONFIG.out.versions)
     }
 
     //