Merge pull request #74 from sanger-bentley-group/dev

Dev
sanger-bentley-group · Aug 17, 2022 · b30d7f3 · b30d7f3
2 parents 7248ad8 + a6aa4b6
commit b30d7f3
Show file tree

Hide file tree

Showing 7 changed files with 117 additions and 11 deletions.
diff --git a/modules/combine.nf b/modules/combine.nf
@@ -19,6 +19,15 @@ process combine_results {
         -x "${surface_protein_incidence}" \
         -n "${version}" \
         -o ${pair_id}
+
+    unlink ${sero_results}
+    unlink ${res_incidence}
+    unlink ${res_alleles}
+    unlink ${surface_protein_incidence}
+    unlink ${surface_protein_variants}
+    unlink ${mlst_allelic_frequency}
+    unlink ${version}
+    unlink ${config}
     """
 }
 

diff --git a/modules/mlst.nf b/modules/mlst.nf
@@ -15,10 +15,24 @@ process srst2_for_mlst {
     mlst_name="Streptococcus_agalactiae"
 
     """
-    set +e
+
     getmlst.py --species 'Streptococcus agalactiae'
     srst2 --samtools_args '\\-A' --input_pe ${reads[0]} ${reads[1]} --output ${pair_id} --save_scores --mlst_db ${mlst_db} --mlst_definitions profiles_csv --mlst_delimiter '_' --min_coverage ${min_coverage}
+
     touch ${pair_id}__mlst__${mlst_name}__results.txt
+
+    # Clean directory
+    mkdir output
+    mv ${pair_id}*.bam output
+    mv ${pair_id}__mlst__${mlst_name}__results.txt output
+    mv ${mlst_db} output
+    find . -maxdepth 1 -type f -delete
+    unlink ${reads[0]}
+    unlink ${reads[1]}
+    mv output/${pair_id}*.bam .
+    mv output/${pair_id}__mlst__${mlst_name}__results.txt .
+    mv output/${mlst_db} .
+    rm -d output
     """
 }
 
@@ -41,7 +55,7 @@ process get_mlst_allele_and_pileup {
     output_new_mlst_alleles_log="${pair_id}_new_mlst_alleles.log"
 
     """
-    set +e
+
     # Get alleles from mismatches in SRST2 MLST results file
     samtools index ${bam_file}
     get_alleles_from_srst2_mlst.py --mlst_results_file ${results_file} --min_read_depth ${min_read_depth} --output_prefix ${pair_id}
@@ -81,11 +95,22 @@ process get_mlst_allele_and_pileup {
         echo "${pair_id}: No new MLST alleles found." > tmp.log
     fi
 
+    if [ -f tmp.fasta ]
+    then
+        mv tmp.fasta ${output_new_mlst_alleles_fasta}
+    fi
+
+    if [ -f tmp_pileup.txt ]
+    then
+        mv tmp_pileup.txt ${output_new_mlst_pileup}
+    fi
 
-    touch ${pair_id}_new_mlst_alleles.log
-    mv tmp.fasta ${output_new_mlst_alleles_fasta}
-    mv tmp_pileup.txt ${output_new_mlst_pileup}
     mv tmp.log ${output_new_mlst_alleles_log}
+
+    # Clean
+    unlink ${bam_file}
+    unlink ${results_file}
+    unlink ${mlst_alleles}
     """
 
 }
diff --git a/modules/pbp_typer.nf b/modules/pbp_typer.nf
@@ -17,6 +17,16 @@ process get_pbp_genes {
 
     # Get BED file of PBP fragments
     get_pbp_genes_from_contigs.py --blast_out_file ${pair_id}_blast_blactam.out --query_fasta ${blactam_ref} --frac_align_len_threshold ${frac_align_len_threshold} --frac_identity_threshold ${frac_identity_len_threshold} --output_prefix ${pair_id}_
+
+    # Clean directory
+    mkdir output
+    mv ${pair_id}_*bed output
+    mv ${contigs} output
+    find . -maxdepth 1 -type f -delete
+    unlink ${blactam_ref}
+    mv output/${pair_id}_*bed .
+    mv output/${contigs} .
+    rm -d output
     """
 }
 
@@ -45,6 +55,11 @@ process get_pbp_alleles {
 
         # Get identical or imperfect hits
         get_pbp_alleles.py --blast_out_file ${pair_id}_blast_${pbp_type}.out --query_fasta ${pair_id}_${pbp_type}.faa --output_prefix ${pair_id}_${pbp_type}_PBP
+
+        unlink ${pair_id}_${pbp_type}.bed
     fi
+
+    unlink ${contigs}
+    unlink ${gbs_blactam_db}
     """
 }
diff --git a/modules/res_alignments.nf b/modules/res_alignments.nf
@@ -13,9 +13,22 @@ process srst2_for_res_typing {
     script:
     db_name=db.getSimpleName()
     """
-    set +e
+
     srst2 --samtools_args '\\-A' --input_pe ${reads[0]} ${reads[1]} --output ${pair_id} --log --save_scores --min_coverage ${min_coverage} --max_divergence ${max_divergence} --gene_db ${db}
+
     touch ${pair_id}__fullgenes__${db_name}__results.txt
+
+    # Clean directory
+    mkdir output
+    mv ${pair_id}*.bam output
+    mv ${pair_id}__fullgenes__${db_name}__results.txt output
+    find . -maxdepth 1 -type f -delete
+    unlink ${reads[0]}
+    unlink ${reads[1]}
+    unlink ${db}
+    mv output/${pair_id}*.bam .
+    mv output/${pair_id}__fullgenes__${db_name}__results.txt .
+    rm -d output
     """
 }
 
@@ -30,6 +43,10 @@ process split_target_RES_sequences {
 
     """
     get_targets_from_db.py -f ${fasta_file} -t ${targets_file} -o CHECK_
+
+    # Clean
+    unlink ${fasta_file}
+    unlink ${targets_file}
     """
 }
 
@@ -45,15 +62,20 @@ process split_target_RES_seq_from_sam_file {
     file("*_*_${pair_id}*.bai")
 
     """
-    set +e
+
     samtools view -h ${bam_file} > \$(basename ${bam_file} .bam).sam
     get_targets_from_samfile.py -s \$(basename ${bam_file} .bam).sam -t ${targets_file} -i ${pair_id} -o CHECK_
     for check_sam_file in CHECK_*_${pair_id}*.sam; do
         samtools view -bS \${check_sam_file} > \$(basename \${check_sam_file} .sam).bam
         samtools index \$(basename \${check_sam_file} .sam).bam \$(basename \${check_sam_file} .sam).bai
     done
+
     touch dummy_dummy_${pair_id}_dummy.bam
     touch dummy_dummy_${pair_id}_dummy.bai
+
+    # Clean directory
+    unlink ${bam_file}
+    unlink ${targets_file}
     """
 }
 
@@ -69,14 +91,31 @@ process freebayes {
     tuple val(pair_id), file("${pair_id}_consensus_seq.fna"), emit: consensus
 
     """
-    set +e
     for check_bam_file in CHECK_*_${pair_id}*.bam; do
         target=\$(echo \${check_bam_file} | sed 's/CHECK_//g' | sed 's/_${pair_id}.*//g')
         freebayes -q 20 -p 1 -f CHECK_\${target}_ref.fna \${check_bam_file} -v CHECK_\${target}_${pair_id}_seq.vcf
         bgzip CHECK_\${target}_${pair_id}_seq.vcf
         tabix -p vcf CHECK_\${target}_${pair_id}_seq.vcf.gz
         cat CHECK_\${target}_ref.fna | vcf-consensus CHECK_\${target}_${pair_id}_seq.vcf.gz >> ${pair_id}_consensus_seq.fna
+        rm CHECK_\${target}_${pair_id}_seq.vcf.gz
+        rm CHECK_\${target}_${pair_id}_seq.vcf.gz.tbi
+        rm CHECK_\${target}_ref.fna.fai
     done
+
     touch ${pair_id}_consensus_seq.fna
+
+    # Clean directory
+    for check_bam_file in CHECK_*_${pair_id}*.bam; do
+        target=\$(echo \${check_bam_file} | sed 's/CHECK_//g' | sed 's/_${pair_id}.*//g')
+        unlink \${check_bam_file}
+        unlink CHECK_\${target}_${pair_id}_seq.bai
+        unlink CHECK_\${target}_ref.fna
+    done
+
+    mkdir output
+    mv ${pair_id}_consensus_seq.fna output
+    find . -maxdepth 1 -type f -delete
+    mv output/${pair_id}_consensus_seq.fna .
+    rm -d output
     """
 }
diff --git a/modules/res_typer.nf b/modules/res_typer.nf
@@ -15,7 +15,7 @@ process res_typer {
     variants_output_file="${pair_id}_res_gbs_variants.txt"
     alleles_accessions_file="${pair_id}_res_alleles_accessions.txt"
     """
-    set +e
+
     process_res_typer_results.py \
         --srst2_gbs_fullgenes ${gbs_fullgenes} \
         --srst2_gbs_consensus ${gbs_consensus} \

diff --git a/modules/serotyping.nf b/modules/serotyping.nf
@@ -12,7 +12,6 @@ process serotyping {
     sero_gene_db="GBS-SBG.fasta"
 
     """
-    set +e
 
     # Get latest version of GBS Serotype Database
     git clone https://github.com/swainechen/GBS-SBG
@@ -22,5 +21,14 @@ process serotyping {
     process_serotyper_results.py --srst2_output SERO_${pair_id} --sero_db ${sero_gene_db} --output ${pair_id}_SeroType_Results.txt --min_read_depth ${min_read_depth}
 
     touch ${output_file}
+
+    # Clean directory
+    mkdir output
+    mv ${output_file} output
+    find . -maxdepth 1 -type f -delete
+    unlink ${reads[0]}
+    unlink ${reads[1]}
+    mv output/${output_file} .
+    rm -d output
     """
 }
diff --git a/modules/surface_typer.nf b/modules/surface_typer.nf
@@ -14,11 +14,21 @@ process surface_typer {
     inc_output_file="${pair_id}_surface_protein_incidence_sample.txt"
     variants_output_file="${pair_id}_surface_protein_variants_sample.txt"
     """
-    set +e
+
     srst2 --samtools_args '\\-A' --input_pe ${reads[0]} ${reads[1]} --output ${pair_id}_SURFACE --log --save_scores --min_coverage ${min_coverage} --max_divergence ${max_divergence} --gene_db ${surface_protein_db}
     process_surface_typer_results.py --srst2_gbs_fullgenes ${pair_id}_SURFACE --surface_db ${surface_protein_db} --output_prefix ${pair_id} --min_read_depth ${min_read_depth}
 
     touch ${inc_output_file}
     touch ${variants_output_file}
+
+    # Clean directory
+    mkdir output
+    mv ${inc_output_file} output
+    mv ${variants_output_file} output
+    find . -maxdepth 1 -type f -delete
+    unlink ${surface_protein_db}
+    mv output/${inc_output_file} .
+    mv output/${variants_output_file} .
+    rm -d output
     """
 }