Parse quast report to csv (#16)

* Parse quast report to csv * Update README, fix version parsing
BCCDC-PHL · Dec 2, 2021 · f8a6416 · f8a6416
1 parent 7b2c6f6
commit f8a6416
Show file tree

Hide file tree

Showing 4 changed files with 46 additions and 21 deletions.
diff --git a/README.md b/README.md
@@ -62,10 +62,9 @@ sample-01
 ├── sample-01_20211125165316_provenance.yml
 ├── sample-01_fastp.csv
 ├── sample-01_fastp.json
-├── sample-01_prokka.gbk
-├── sample-01_prokka.gff
-├── sample-01_quast.json
-├── sample-01_quast.tsv
+├── sample-01_shovill_prokka.gbk
+├── sample-01_shovill_prokka.gff
+├── sample-01_shovill_quast.csv
 ├── sample-01_shovill.fa
 └── sample-01_shovill.log
 ```
@@ -76,16 +75,16 @@ Including the tool name suffixes to output files allows re-analysis of the same
 sample-01
 ├── sample-01_20211125165316_provenance.yml
 ├── sample-01_20211128122118_provenance.yml
-├── sample-01_bakta.gbk
-├── sample-01_bakta.gff
-├── sample-01_bakta.json
-├── sample-01_bakta.log
+├── sample-01_unicycler_bakta.gbk
+├── sample-01_unicycler_bakta.gff
+├── sample-01_unicycler_bakta.json
+├── sample-01_unicycler_bakta.log
 ├── sample-01_fastp.csv
 ├── sample-01_fastp.json
-├── sample-01_prokka.gbk
-├── sample-01_prokka.gff
-├── sample-01_quast.json
-├── sample-01_quast.tsv
+├── sample-01_shovill_prokka.gbk
+├── sample-01_shovill_prokka.gff
+├── sample-01_shovill_quast.csv
+├── sample-01_unicycler_quast.csv
 ├── sample-01_shovill.fa
 ├── sample-01_shovill.log
 ├── sample-01_unicycler.fa
@@ -104,7 +103,7 @@ For each pipeline invocation, each sample will produce a `provenance.yml` file w
 - tool_name: prokka
   tool_version: 1.14.5
 - tool_name: quast
-  tool_version: v5.0.2
+  tool_version: 5.0.2
 - input_filename: sample-01_R1.fastq.gz
   sha256: 4ac3055ac5f03114a005aff033e7018ea98486cbebdae669880e3f0511ed21bb
 - input_filename: sample-01_R2.fastq.gz

diff --git a/bin/parse_quast_report.py b/bin/parse_quast_report.py
@@ -4,6 +4,7 @@
 import collections
 import csv
 import json
+import sys
 
 
 def parse_transposed_quast_report(transposed_quast_report_path):
@@ -92,8 +93,35 @@ def main():
     parser.add_argument('transposed_quast_report')
     args = parser.parse_args()
 
+    output_fieldnames = [
+        'assembly_id',
+        'total_length',
+        'num_contigs',
+        'largest_contig',
+        'assembly_N50',
+        'assembly_N75',
+        'assembly_L50',
+        'assembly_L75',
+        'num_contigs_gt_0_bp',
+        'num_contigs_gt_1000_bp',
+        'num_contigs_gt_5000_bp',
+        'num_contigs_gt_10000_bp',
+        'num_contigs_gt_25000_bp',
+        'num_contigs_gt_50000_bp',
+        'total_length_gt_0_bp',
+        'total_length_gt_1000_bp',
+        'total_length_gt_5000_bp',
+        'total_length_gt_10000_bp',
+        'total_length_gt_25000_bp',
+        'total_length_gt_50000_bp',
+        'num_N_per_100_kb',
+    ]
+
     report = parse_transposed_quast_report(args.transposed_quast_report)
-    print(json.dumps(report, indent=2))
+    writer = csv.DictWriter(sys.stdout, fieldnames=output_fieldnames)
+    writer.writeheader()
+    for record in report:
+        writer.writerow(record)
 
 
 if __name__ == '__main__':

diff --git a/modules/quast.nf b/modules/quast.nf
@@ -2,8 +2,6 @@ process quast {
 
     tag { sample_id }
 
-    publishDir "${params.outdir}/${sample_id}", pattern: "${sample_id}_${assembler}_quast.tsv", mode: 'copy'
-
     input:
       tuple val(sample_id), path(assembly), val(assembler)
 
@@ -13,7 +11,7 @@ process quast {
 
     script:
       """
-      printf -- "- tool_name: quast\\n  tool_version: \$(quast --version | cut -d ' ' -f 2)\\n" > ${sample_id}_${assembler}_quast_provenance.yml
+      printf -- "- tool_name: quast\\n  tool_version: \$(quast --version | cut -d ' ' -f 2 | tr -d 'v')\\n" > ${sample_id}_${assembler}_quast_provenance.yml
       quast --threads ${task.cpus} ${assembly} --space-efficient --fast --output-dir ${sample_id}
       mv ${sample_id}/transposed_report.tsv ${sample_id}_${assembler}_quast.tsv
       """
@@ -25,16 +23,16 @@ process parse_quast_report {
 
     executor 'local'
 
-    publishDir "${params.outdir}/${sample_id}", pattern: "${sample_id}_${assembler}_quast.json", mode: 'copy'
+    publishDir "${params.outdir}/${sample_id}", pattern: "${sample_id}_${assembler}_quast.csv", mode: 'copy'
 
     input:
       tuple val(sample_id), path(quast_report), val(assembler)
 
     output:
-      tuple val(sample_id), path("${sample_id}_${assembler}_quast.json")
+      tuple val(sample_id), path("${sample_id}_${assembler}_quast.csv")
 
     script:
       """
-      parse_quast_report.py ${quast_report} > ${sample_id}_${assembler}_quast.json
+      parse_quast_report.py ${quast_report} > ${sample_id}_${assembler}_quast.csv
       """
 }
diff --git a/modules/unicycler.nf b/modules/unicycler.nf
@@ -15,7 +15,7 @@ process unicycler {
 
     script:
       """
-      printf -- "- tool_name: unicycler\\n  tool_version: \$(unicycler --version | cut -d ' ' -f 2)\\n" > ${sample_id}_unicycler_provenance.yml
+      printf -- "- tool_name: unicycler\\n  tool_version: \$(unicycler --version | cut -d ' ' -f 2 | tr -d 'v')\\n" > ${sample_id}_unicycler_provenance.yml
       unicycler --threads ${task.cpus} -1 ${reads_1} -2 ${reads_2} -o ${sample_id}_assembly
       sed 's/^>/>${sample_id}_/' ${sample_id}_assembly/assembly.fasta > ${sample_id}_unicycler.fa
       cp ${sample_id}_assembly/assembly.gfa ${sample_id}_unicycler.gfa