Merge pull request #155 from pinin4fjords/parameterise_coverage

Add new meta_min_reads CLI param

ribotricer/cli.py

@@ -197,6 +197,13 @@ def prepare_orfs_cmd(
     help=("Whether output all ORFs including those " "non-translating ones"),
     is_flag=True,
 )
+@click.option(
+    "--meta-min-reads",
+    type=int,
+    default=META_MIN_READS,
+    show_default=True,
+    help="Minimum number of reads for a read length to be considered",
+)
 def detect_orfs_cmd(
     bam,
     ribotricer_index,
@@ -210,6 +217,7 @@ def detect_orfs_cmd(
     min_valid_codons_ratio,
     min_read_density,
     report_all,
+    meta_min_reads,
 ):
     if not os.path.isfile(bam):
         sys.exit("Error: BAM file not found")

ribotricer/const.py

@@ -29,3 +29,5 @@
 # Minimum read density over ORF
 # defined as the number of reads per unit length of the ORF
 MINIMUM_DENSITY_OVER_ORF = 0.0
+# Minimum number of reads for a read length to be considered
+META_MIN_READS=100000

ribotricer/detect_orfs.py

@@ -344,6 +344,7 @@ def detect_orfs(
     min_valid_codons_ratio,
     min_density_over_orf,
     report_all,
+    meta_min_reads=100000,
 ):
     """
     Parameters
@@ -371,6 +372,8 @@ def detect_orfs(
     report_all: bool
                 Whether to output all ORFs' scores regardless of translation
                 status
+    meta_min_reads: int
+                    minimum number of reads for a read length to be considered. Passed to metagene_coverage().
     """
     now = datetime.datetime.now()
     print(now.strftime("%b %d %H:%M:%S ..... started ribotricer detect-orfs"))
@@ -416,7 +419,7 @@ def detect_orfs(
             "started calculating metagene profiles. This may take a long time...",
         )
     )
-    metagenes = metagene_coverage(annotated, alignments, read_length_counts, prefix)
+    metagenes = metagene_coverage(annotated, alignments, read_length_counts, prefix, meta_min_reads = meta_min_reads)
 
     # plot metagene profiles
     now = datetime.datetime.now()