From 0d34988df8228de94523c7ed0f8a5d0f5304fab2 Mon Sep 17 00:00:00 2001
From: riasc <richard.schaefer@zoho.com>
Date: Wed, 26 Jun 2024 22:08:50 -0500
Subject: [PATCH] changes to speedup process

---
 CHANGELOG.md                                    | 7 +++++++
 workflow/rules/align.smk                        | 6 ++++--
 workflow/rules/hlatyping.smk                    | 7 +++++--
 workflow/scripts/genotyping/optitype_wrapper.py | 2 +-
 4 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index f41306b..1ee574b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Prioritization of neoantigens is now done separately for each variant type (speeds up the process)
 - NMD information (e.g., escape rule,...) is now also calculated for all variants
 
+## [0.2.8] - 2024-06-26
+
+### Fix 
+
+- Added threads option to samtools sort calls to speed up the process
+- Fixed wrong call to optitype within the wrapper script
+
 ## [0.2.7] - 2024-06-23 
 
 ### Fix 
diff --git a/workflow/rules/align.smk b/workflow/rules/align.smk
index bf29421..9c030b1 100644
--- a/workflow/rules/align.smk
+++ b/workflow/rules/align.smk
@@ -248,11 +248,13 @@ if config['data']['dnaseq_filetype'] in ['.fq','.fastq']:
       "../envs/samtools.yml"
     params:
       extra=""
-    threads: config['threads']
+    threads: 6
+    resources:
+      mem_mb=20000
     shell:
       """
         samtools fixmate -pcmu -O bam -@ 6 {input.aln} - \
-            | samtools sort -m1g -O bam -T tmp/ - -o - \
+            | samtools sort -@ 4 -m1g -O bam -T tmp/ - -o - \
             | samtools markdup -r -@ 6 - {output.bam} > {log} 2>&1
       """
     
diff --git a/workflow/rules/hlatyping.smk b/workflow/rules/hlatyping.smk
index f3b3270..9f4717f 100644
--- a/workflow/rules/hlatyping.smk
+++ b/workflow/rules/hlatyping.smk
@@ -65,12 +65,15 @@ rule get_reads_hlatyping_PE:
     "Retrieve paired-end reads ({wildcards.nartype}) for HLA genotyping - sample:{wildcards.sample} group:{wildcards.group}"
   log:
     "logs/{sample}/hla/get_reads_hlatyping_PE_{group}_{nartype}.log"
+  threads: 4
+  resources: 
+    mem_mb=20000
   conda:
     "../envs/samtools.yml"
   shell:
     """
-      samtools sort -n {input.fwd} -T tmp/ | samtools fastq > {output.fwd} 
-      samtools sort -n {input.rev} -T tmp/ | samtools fastq > {output.rev}
+      samtools sort -@4 -m4g -n {input.fwd} -T tmp/ | samtools fastq -@4 > {output.fwd} 
+      samtools sort -@4 -m4g -n {input.rev} -T tmp/ | samtools fastq -@4 > {output.rev}
     """
 
 ######### single-end reads #########
diff --git a/workflow/scripts/genotyping/optitype_wrapper.py b/workflow/scripts/genotyping/optitype_wrapper.py
index f50b1b9..b26cf85 100644
--- a/workflow/scripts/genotyping/optitype_wrapper.py
+++ b/workflow/scripts/genotyping/optitype_wrapper.py
@@ -32,7 +32,7 @@ def main():
             tsv = subprocess.Popen("touch " + outpath + prefix + "_result.tsv", shell=True)
         else:
             # call optitype 
-            optitype = subprocess.Popen("optitype --input " + inbams + 
+            optitype = subprocess.Popen("OptiTypePipeline.py --input " + inbams + 
                                         " --prefix " + prefix + " --" + nartype + "-v", shell=True)