fix reviewer suggestions

genomic-medicine-sweden · Oct 25, 2023 · 71a93cd · 71a93cd
1 parent c4b0983
commit 71a93cd
Show file tree

Hide file tree

Showing 5 changed files with 11 additions and 19 deletions.
diff --git a/bin/drop_sample_annot.py b/bin/drop_sample_annot.py
@@ -1,7 +1,6 @@
 #!/usr/bin/env python3
 
 import argparse
-from pathlib import Path
 import csv
 from pandas import read_csv, DataFrame, concat
 import os
@@ -59,8 +58,7 @@ def write_final_annot_to_tsv(ref_count_file: str, ref_annot: str, out_file: str)
     df_samples: DataFrame = read_csv("drop_annotation_given_samples.tsv", sep="\t")
     df_reference: DataFrame = read_csv(ref_annot, sep="\t")
     df_reference["GENE_COUNTS_FILE"] = ref_count_file
-    df_reference["SPLICE_COUNTS_DIR"] = df_reference["SPLICE_COUNTS_DIR"].str.rstrip("/")
-    df_reference["SPLICE_COUNTS_DIR"] = df_reference["SPLICE_COUNTS_DIR"].apply(os.path.basename)
+    df_reference["SPLICE_COUNTS_DIR"] = df_reference["SPLICE_COUNTS_DIR"].str.rstrip("/").apply(os.path.basename)
     df_reference["DROP_GROUP"] = df_reference["DROP_GROUP"].str.replace(" ", "")
     df_samples["COUNT_OVERLAPS"] = df_reference["COUNT_OVERLAPS"].iloc[0]
     df_samples["COUNT_MODE"] = df_reference["COUNT_MODE"].iloc[0]

diff --git a/conf/modules.config b/conf/modules.config
@@ -465,13 +465,11 @@ process {
 
 process {
     withName: '.*ANNOTATE_SNV:ENSEMBLVEP' {
-        ext.prefix = { "${vcf.simpleName}_rohann_vcfanno_filter_vep" }
+        ext.prefix = { "${vcf.simpleName}_vep" }
         ext.args   = [
             '--dir_plugins cache/Plugins',
             '--plugin LoFtool,cache/Plugins/LoFtool_scores.txt',
             '--plugin pLI,cache/Plugins/pLI_values_107.txt',
-            '--plugin SpliceAI,snv=cache/Plugins/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz,indel=cache/Plugins/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz',
-            '--plugin MaxEntScan,cache/Plugins/fordownload,SWA,NCSS',
             '--distance 5000',
             '--buffer_size 20000',
             '--format vcf --max_sv_size 248956422',

diff --git a/subworkflows/local/analyse_transcripts.nf b/subworkflows/local/analyse_transcripts.nf
@@ -34,7 +34,7 @@ workflow ANALYSE_TRANSCRIPTS {
         // Generates count files for samples and merges them with reference count file
 
         // Generates sample annotation
-        star_samples  = gene_counts.map{ meta, cnt_file -> meta }.collect()
+        star_samples = gene_counts.map{ meta, cnt_file -> meta }.collect()
         ch_bam_files = ch_bam_ds_bai.collect{it[1]}
         DROP_SAMPLE_ANNOT(
             ch_bam_files,
@@ -46,8 +46,8 @@ workflow ANALYSE_TRANSCRIPTS {
         )
 
         // Generates  config file and runs Aberrant expression module
-        ch_bai_files = ch_bam_ds_bai.collect{it[2]}.toList()
-        ch_bam_bai_files=ch_bam_files.toList().combine(ch_bai_files)
+        ch_bai_files = ch_bam_ds_bai.collect{ it[2] }.toList()
+        ch_bam_bai_files = ch_bam_files.toList().combine(ch_bai_files)
         DROP_CONFIG_RUN_AE(
             ch_fasta_fai_meta, 
             ch_gtf, 
@@ -90,7 +90,7 @@ workflow ANALYSE_TRANSCRIPTS {
         )
 
         // Stringtie
-        ch_bam = ch_bam_bai.map{ meta, bam, bai -> [meta, [bam]]}
+        ch_bam = ch_bam_bai.map{ meta, bam, bai -> [meta, [bam]] }
         STRINGTIE_STRINGTIE(
             ch_bam,
             ch_gtf
@@ -103,7 +103,6 @@ workflow ANALYSE_TRANSCRIPTS {
             ch_gtf.map{ gtf -> [ [id:gtf.simpleName], gtf ] }
         )
 
-        //ch_versions = ch_versions.mix(DROP_COUNTS.out.versions)
         ch_versions = ch_versions.mix(DROP_SAMPLE_ANNOT.out.versions)
         ch_versions = ch_versions.mix(DROP_CONFIG_RUN_AE.out.versions)
         ch_versions = ch_versions.mix(DROP_CONFIG_RUN_AS.out.versions)

diff --git a/subworkflows/local/prepare_references.nf b/subworkflows/local/prepare_references.nf
@@ -31,7 +31,7 @@ workflow PREPARE_REFERENCES {
     main:
         ch_versions = Channel.empty()
 
-        fasta_meta=Channel.fromPath(fasta).map { it -> [[id:it[0]], it]}.collect()
+        fasta_meta = Channel.fromPath(fasta).map { it -> [ [id:it[0] ], it] }.collect()
         GUNZIP_FASTA(fasta_meta)
         ch_fasta = fasta.endsWith(".gz") ? GUNZIP_FASTA.out.gunzip.collect() : fasta_meta
 
@@ -43,7 +43,7 @@ workflow PREPARE_REFERENCES {
         BUILD_DICT(ch_fasta)
         ch_dict = BUILD_DICT.out.dict.collect()
 
-        gtf_meta=Channel.fromPath(gtf).map{it -> [[id:it[0]], it]}.collect()
+        gtf_meta = Channel.fromPath(gtf).map{ it -> [ [id:it[0]], it ] }.collect()
         GUNZIP_GTF(gtf_meta)
         ch_gtf_no_meta = gtf.endsWith(".gz") ? GUNZIP_GTF.out.gunzip.map{ meta, gtf -> [gtf] }.collect() : Channel.fromPath(gtf)
 
@@ -57,21 +57,19 @@ workflow PREPARE_REFERENCES {
         UNTAR_STAR_INDEX( ch_star.map { it -> [[:], it] } )
         ch_star_index = (!star_index) ?  BUILD_STAR_GENOME.out.index.collect() : 
                                         (star_index.endsWith(".gz") ? UNTAR_STAR_INDEX.out.untar.map { it[1] } : star_index)
-
         // Convert gtf to refflat for picard
         GTF_TO_REFFLAT(ch_gtf_no_meta)
 
         // Get rRNA transcripts and convert to interval_list format
         GET_RRNA_TRANSCRIPTS(ch_gtf_no_meta)
 
-        BEDTOINTERVALLIST( GET_RRNA_TRANSCRIPTS.out.bed.map {it -> [ [id:it.name], it ]}, ch_dict )
+        BEDTOINTERVALLIST( GET_RRNA_TRANSCRIPTS.out.bed.map { it -> [ [id:it.name], it ] }, ch_dict )
 
         UNTAR_VEP_CACHE (ch_vep_cache)
 
         // Preparing transcript fasta
         ch_fasta_fai = ch_fasta.join(ch_fai).collect()
-        GFFREAD(ch_gtf_no_meta.map{it -> [[id:it[0].simpleName], it]},ch_fasta_fai)
-        tr=GFFREAD.out.tr_fasta.collect()
+        GFFREAD(ch_gtf_no_meta.map{ it -> [ [id:it[0].simpleName], it ] },ch_fasta_fai)
         transcript_fasta_no_meta = (!transcript_fasta) ? GFFREAD.out.tr_fasta.collect() :
                                     (transcript_fasta.endsWith(".gz") ? GUNZIP_TRFASTA.out.gunzip.collect().map{ meta, fasta -> [ fasta ] } : transcript_fasta)
 
@@ -109,6 +107,6 @@ workflow PREPARE_REFERENCES {
         refflat          = GTF_TO_REFFLAT.out.refflat.collect()
         rrna_bed         = GET_RRNA_TRANSCRIPTS.out.bed.collect()
         interval_list    = BEDTOINTERVALLIST.out.interval_list.map{ meta, interv -> [interv] }.collect()
-        vep_resources    = UNTAR_VEP_CACHE.out.untar.map{meta, files -> [files]}.collect()     // channel: [ path(cache) ]
+        vep_resources    = UNTAR_VEP_CACHE.out.untar.map{ meta, files -> [files] }.collect()     // channel: [ path(cache) ]
         versions         = ch_versions
 }
diff --git a/workflows/tomte.nf b/workflows/tomte.nf
@@ -111,7 +111,6 @@ workflow TOMTE {
         exit 1, 'Input samplesheet not specified!'
     }
 
-    //fasta                         = Channel.fromPath(params.fasta).map { it -> [[id:it[0].simpleName], it] }.collect()
     ch_vep_cache_unprocessed      = params.vep_cache                    ? Channel.fromPath(params.vep_cache).map { it -> [[id:'vep_cache'], it] }.collect()
                                                                         : Channel.value([[],[]])
     ch_vep_filters                = params.vep_filters                  ? Channel.fromPath(params.vep_filters).collect()