Merge branch 'CW-3247_1' into 'dev'

Fix build tables defect where sample was not taken into account when calculating bases mapped

Closes CW-3247

See merge request epi2melabs/workflows/wf-cas9!52

CHANGELOG.md

@@ -4,6 +4,11 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v1.0.1]
+### Fixed
+- Overestimation of kbases mapped values.
+- Target coverage plots showing only one sample.
+
 ## [v1.0.0]
 ### Added
 - Memory and CPU requirements for each process.

bin/workflow_glue/build_tables.py

@@ -59,8 +59,8 @@ def main(args):
     read_stats_df = pd.read_csv(args.aln_summary, sep='\t', index_col=False)
 
     df_read_to_target = df_read_to_target.merge(
-        read_stats_df[['name', 'read_length']],
-        left_on='read_id', right_on='name')
+        read_stats_df[['sample_id', 'name', 'read_length']],
+        left_on=['sample_id', 'read_id'], right_on=['sample_id', 'name'])
 
     df_target_summary = pd.read_csv(
         args.target_summary, sep='\t', names=header, index_col=False)
@@ -93,7 +93,8 @@ def main(args):
         # Deletions and insertions within the reads will mean the actual value may
         # vary slightly
         kbases = (
-            df_read_to_target[['target', 'align_len']]
+            df_read_to_target[
+                df_read_to_target.sample_id == id_][['target', 'align_len']]
             .groupby(['target']).sum() / 1000
         )
         kbases.columns = ['kbases']

lib/ingress.nf

@@ -307,14 +307,18 @@ process bamstats {
     input:
         tuple val(meta), path("reads.bam")
     output:
-        tuple val(meta), path("reads.bam"), path("bamstats_results")
+        tuple val(meta),
+              path("reads.bam"),
+              path("bamstats_results")
     script:
         def bamstats_threads = Math.max(1, task.cpus - 1)
     """
     mkdir bamstats_results
     bamstats reads.bam -s $meta.alias -u \
         -f bamstats_results/bamstats.flagstat.tsv -t $bamstats_threads \
+        --histograms histograms \
     | bgzip > bamstats_results/bamstats.readstats.tsv.gz
+    mv histograms/* bamstats_results/
 
     # extract the run IDs from the per-read stats
     csvtk cut -tf runid bamstats_results/bamstats.readstats.tsv.gz \
@@ -451,7 +455,9 @@ process fastcat {
         tuple val(meta), path("input")
         val extra_args
     output:
-        tuple val(meta), path("seqs.fastq.gz"), path("fastcat_stats")
+        tuple val(meta),
+              path("seqs.fastq.gz"),
+              path("fastcat_stats")
     script:
         String out = "seqs.fastq.gz"
         String fastcat_stats_outdir = "fastcat_stats"
@@ -461,10 +467,12 @@ process fastcat {
             -s ${meta["alias"]} \
             -r >(bgzip -c > $fastcat_stats_outdir/per-read-stats.tsv.gz) \
             -f $fastcat_stats_outdir/per-file-stats.tsv \
+            --histograms histograms \
             $extra_args \
             input \
             | bgzip > $out
 
+        mv histograms/* $fastcat_stats_outdir
         # extract the run IDs from the per-read stats
         csvtk cut -tf runid $fastcat_stats_outdir/per-read-stats.tsv.gz \
         | csvtk del-header | sort | uniq > $fastcat_stats_outdir/run_ids

main.nf

@@ -511,6 +511,7 @@ workflow pipeline {
             align_reads.out.bed)
 
         tar_cov_tsv = target_coverage.out.target_coverage
+            .map {meta, target_cov -> target_cov}
             .collectFile(name: 'target_coverage', keepHeader: true)
 
         tile_cov = background.out.tiles_coverage.collectFile(name: 'tile_cov', keepHeader: true)

nextflow.config

@@ -42,7 +42,7 @@ params {
         ]
 
       container_sha = "shaa7b95018145dc9c753d6092309ac6be5166a491a"
-      common_sha = "sha91452ece4f647f62b32dac3a614635a6f0d7f8b5"
+      common_sha = "sha399b89c275a4d8eac477a415691cb93180661be6"
     }
 }
 
@@ -53,7 +53,7 @@ manifest {
     description     = 'Summarise the results of Cas9 enrichment sequencing.'
     mainScript      = 'main.nf'
     nextflowVersion = '>=23.04.2'
-    version         = 'v1.0.0'
+    version         = 'v1.0.1'
 
 }