recent changes

ylab-hi · May 20, 2024 · 8da4f95 · 8da4f95
1 parent 71bc0fe
commit 8da4f95
Show file tree

Hide file tree

Showing 17 changed files with 1,270 additions and 326 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -14,7 +14,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
     - pathogen similarity (BLAST against pathogen-derived epitopes from IEDB)
     - proteome similarity (BLAST against human proteome)
 - Prioritization of neoantigens is now done separately for each variant type (speeds up the process)
+- Prioritization of neoantigens is in chunks (rather than per allele and epitope length)
 - NMD information (e.g., escape rule,...) is now also calculated for all variants
+- Retention of introns is no longer ignored for the variant effects (INFO tag intret)
 
 ## [0.2.2] - 2024-03-01
 

diff --git a/workflow/envs/prioritization.yml b/workflow/envs/prioritization.yml
@@ -14,3 +14,4 @@ dependencies:
  - pip:
    - gffutils==0.12
    - blosum==2.0.2
+   - intervaltree==3.1.0
diff --git a/workflow/rules/align.smk b/workflow/rules/align.smk
@@ -158,7 +158,7 @@ rule rnaseq_postproc_markdup:
       samtools sort -@4 -m4G -O BAM -T tmp/ {input.bam} \
           -o tmp/rnaseq_fixmate_sorted_{wildcards.sample}_{wildcards.group}.bam > {log} 2>&1
       samtools markdup -r -@4 tmp/rnaseq_fixmate_sorted_{wildcards.sample}_{wildcards.group}.bam \
-          {output} > {log} 2>&1 
+          {output} >> {log} 2>&1 
       rm tmp/rnaseq_fixmate_sorted_{wildcards.sample}_{wildcards.group}.bam
     """
 
@@ -173,7 +173,7 @@ rule postproc_bam_index:
     "logs/{sample}/postproc/index/rnaseq_{group}.log"
   shell:
     """
-      samtools index {input} > {log} 2>&1
+      samtools index {input} >> {log} 2>&1
     """
 
 ## retrieve readgroups from bam file
@@ -189,7 +189,7 @@ rule get_readgroups:
   shell:
     """
           python workflow/scripts/get_readgroups.py '{input}' \
-          {output} > {log} 2>&1
+          {output} >> {log} 2>&1
       """
 
 # realign RNAseq and align DNAseq 
@@ -234,7 +234,7 @@ if config['data']['dnaseq_filetype'] in ['.fq','.fastq']:
         bwa mem -t{threads} -C resources/refs/bwa/genome {input.reads} \
         | samtools addreplacerg -r ID:{wildcards.group} -r SM:{wildcards.sample} \
         -r LB:{wildcards.sample} -r PL:ILLUMINA -r PU:{wildcards.group} - - \
-        | samtools sort -@ 6 -n -m1g - -o {output} > {log} 2>&1
+        | samtools sort -@ 6 -n -m1g - -o {output} >> {log} 2>&1
       """
 
   rule dnaseq_postproc:
@@ -254,7 +254,7 @@ if config['data']['dnaseq_filetype'] in ['.fq','.fastq']:
       """
         samtools fixmate -pcmu -O bam -@ 6 {input.aln} - \
             | samtools sort -m1g -O bam -T tmp/ - -o - \
-            | samtools markdup -r -@ 6 - {output.bam} > {log} 2>&1
+            | samtools markdup -r -@ 6 - {output.bam} >> {log} 2>&1
       """
 
 rule samtools_index_BWA_final:

diff --git a/workflow/rules/altsplicing.smk b/workflow/rules/altsplicing.smk
@@ -21,7 +21,7 @@ rule spladder:
               {params.confidence} \
               {params.iteration} \
               {params.edgelimit} \
-              --qmode all > {log} 2>&1
+              --qmode all >> {log} 2>&1
         """
 
 rule splicing_to_vcf:
@@ -39,7 +39,7 @@ rule splicing_to_vcf:
     """
       python workflow/scripts/altsplc2vcf.py \
           -i {input} -r resources/refs/genome.fasta \
-          -g {wildcards.group} -o {output} > {log} 2>&1
+          -g {wildcards.group} -o {output} >> {log} 2>&1
     """
 
 rule sort_altsplicing:
@@ -55,7 +55,7 @@ rule sort_altsplicing:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools sort {input} -o - | bcftools view -O z -o {output} > {log} 2>&1
+      bcftools sort {input} -o - | bcftools view -O z -o {output} >> {log} 2>&1
     """
 
 rule combine_altsplicing:
@@ -71,5 +71,5 @@ rule combine_altsplicing:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools concat --naive -O z {input} -o  - | bcftools sort -O z -o {output} > {log} 2>&1
+      bcftools concat --naive -O z {input} -o  - | bcftools sort -O z -o {output} >> {log} 2>&1
     """
diff --git a/workflow/rules/annotation.smk b/workflow/rules/annotation.smk
@@ -47,7 +47,7 @@ rule index_variants:
     "../envs/samtools.yml"
   shell:
     """
-      tabix {input}
+      tabix {input} >> {log} 2>&1
     """
 
 rule annotate_variants:

diff --git a/workflow/rules/custom.smk b/workflow/rules/custom.smk
@@ -15,7 +15,7 @@ rule augment_custom_variants:
           {input} \
           custom \
           custom \
-          {output} > {log} 2>&1
+          {output} >> {log} 2>&1
     """
 
 rule sort_custom_variants:
@@ -31,5 +31,5 @@ rule sort_custom_variants:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools sort {input} -o - | bcftools view -O z -o {output} > {log} 2>&1
+      bcftools sort {input} -o - | bcftools view -O z -o {output} >> {log} 2>&1
     """
diff --git a/workflow/rules/exitron.smk b/workflow/rules/exitron.smk
@@ -31,7 +31,7 @@ rule prepare_scanexitron_config:
           {input.genome} \
           {input.annotation} \
           {input.cds} \
-          {output} > {log}
+          {output} >> {log} 2>&1
     """
 
 rule scanexitron:
@@ -65,7 +65,7 @@ rule scanexitron:
           --pso {params.pso} \
           -c ../../../{input.config} \
           -i {input.bam} \
-          -r hg38
+          -r hg38 >> {log} 2>&1
         mv {wildcards.group}_final_STAR.exitron {output}
         mv {wildcards.group}_final_STAR* results/{wildcards.sample}/rnaseq/exitron/
       """
@@ -83,7 +83,7 @@ rule exitron_to_vcf:
     """
       python workflow/scripts/exitron2vcf.py \
         {input} {output} \
-        resources/refs/genome.fasta > {log}
+        resources/refs/genome.fasta >> {log} 2>&1
     """
 
 rule exitron_augment:
@@ -103,7 +103,7 @@ rule exitron_augment:
           {input} \
           exitron \
           {wildcards.group} \
-          {output} > {log} 2>&1
+          {output} >> {log} 2>&1
     """
 
 rule sort_exitron:
@@ -119,7 +119,7 @@ rule sort_exitron:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools sort {input} -o - | bcftools view -O z -o {output} > {log} 2>&1
+      bcftools sort {input} -o - | bcftools view -O z -o {output} >> {log} 2>&1
     """
 
 rule combine_exitrons:
@@ -135,6 +135,6 @@ rule combine_exitrons:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools concat --naive -O z {input} -o  - | bcftools sort -O z -o {output} > {log} 2>&1
+      bcftools concat --naive -O z {input} -o  - | bcftools sort -O z -o {output} >> {log} 2>&1
     """
 
diff --git a/workflow/rules/germline.smk b/workflow/rules/germline.smk
@@ -50,7 +50,7 @@ checkpoint split_bam_htc_first_round:
   shell:
     """
       python workflow/scripts/split_bam_by_chr.py \
-          {input.bam} {output}
+          {input.bam} {output} >> {log} 2>&1
     """
 
 rule index_split_bam_htc_first_round:
@@ -66,7 +66,7 @@ rule index_split_bam_htc_first_round:
     "../envs/samtools.yml"
   shell:
     """
-      samtools index {input.bam} > {log} 2>&1
+      samtools index {input.bam} >> {log} 2>&1
     """
 
 rule detect_variants_htc_first_round:
@@ -99,7 +99,7 @@ rule sort_variants_htc_first_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools sort {input} -o - | bcftools view -O z -o {output} > {log} 2>&1
+      bcftools sort {input} -o - | bcftools view -O z -o {output} >> {log} 2>&1
     """
 
 rule index_variants_htc_first_round:
@@ -115,7 +115,7 @@ rule index_variants_htc_first_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools index -t {input} > {log} 2>&1
+      bcftools index -t {input} >> {log} 2>&1
     """
 
 rule merge_variants_htc_first_round:
@@ -132,7 +132,7 @@ rule merge_variants_htc_first_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools concat -O z -a {input.vcf} -o {output} > {log} 2>&1
+      bcftools concat -O z -a {input.vcf} -o {output} >> {log} 2>&1
     """
 
 rule index_merged_variants_htc_first_round:
@@ -148,7 +148,7 @@ rule index_merged_variants_htc_first_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools index -t {input} > {log} 2>&1
+      bcftools index -t {input} >> {log} 2>&1
     """
 
 
@@ -299,7 +299,7 @@ checkpoint split_bam_htc_final_round:
   shell:
     """
       python workflow/scripts/split_bam_by_chr.py \
-          {input.bam} {output}
+          {input.bam} {output} >> {log} 2>&1
     """
 
 rule index_split_bam_htc_final_round:
@@ -315,7 +315,7 @@ rule index_split_bam_htc_final_round:
     "../envs/samtools.yml"
   shell:
     """
-      samtools index {input.bam} > {log} 2>&1
+      samtools index {input.bam} >> {log} 2>&1
     """
 
 rule detect_variants_htc_final_round:
@@ -348,7 +348,7 @@ rule sort_variants_htc_final_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools sort {input} -o - | bcftools view -O z -o {output} > {log} 2>&1
+      bcftools sort {input} -o - | bcftools view -O z -o {output} >> {log} 2>&1
     """
 
 rule index_variants_htc_final_round:
@@ -364,7 +364,7 @@ rule index_variants_htc_final_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools index -t {input} > {log} 2>&1
+      bcftools index -t {input} >> {log} 2>&1
     """
 
 rule merge_variants_htc_final_round:
@@ -381,7 +381,7 @@ rule merge_variants_htc_final_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools concat -O z -a {input.vcf} -o {output} > {log} 2>&1
+      bcftools concat -O z -a {input.vcf} -o {output} >> {log} 2>&1
     """
 
 rule index_merged_variants_htc_final_round:
@@ -397,7 +397,7 @@ rule index_merged_variants_htc_final_round:
     "../envs/samtools.yml"
   shell:
     """
-      bcftools index -t {input} > {log} 2>&1
+      bcftools index -t {input} >> {log} 2>&1
     """