added support to include both HLA genotyping on DNA and RNA

workflow/envs/optitype.yml

@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - optitype =1.3.5
+  - pysam

workflow/envs/transindel.yml

@@ -0,0 +1,13 @@
+channels:
+  - bioconda
+  - conda-forge
+  - defaults
+  - r
+dependencies:
+  - samtools
+  - pysam
+  - htseq
+  - pyfaidx
+  - pip
+  - pip:
+    - vcfpy==0.13.6

workflow/envs/yara.yml

@@ -0,0 +1,5 @@
+channels:
+  - bioconda
+dependencies:
+  - yara
+  - samtools

workflow/rules/hlatyping.smk

@@ -102,7 +102,7 @@ if config['data']['rnaseq'] is not None:
       rule get_hla_filtering_input_single_RNA:
         input:
           get_hla_flt_rna_se,
-          dna=multiext("resources/hla/yara/idx/dna", 
+          dna=multiext("resources/hla/yara/idx/rna", 
             ".lf.drp", ".lf.drs", ".lf.drv", 
             ".lf.pst", ".rid.concat", ".rid.limits",
             ".sa.ind", ".sa.len", ".sa.val", 
@@ -131,7 +131,7 @@ if config['data']['rnaseq'] is not None:
       rule get_hla_filtering_input_paired_RNA:
         input:
           get_hla_flt_rna_pe,
-          dna=multiext("resources/hla/yara/idx/dna", 
+          dna=multiext("resources/hla/yara/idx/rna", 
             ".lf.drp", ".lf.drs", ".lf.drv", 
             ".lf.pst", ".rid.concat", ".rid.limits",
             ".sa.ind", ".sa.len", ".sa.val", 
@@ -187,9 +187,28 @@ rule hla_genotyping_RNA:
     """
       OptiTypePipeline.py --input {input} \
           --outdir results/{wildcards.sample}/hla/ \
-          --prefix {wildcards.group}_dna --dna > {log}
+          --prefix {wildcards.group}_rna --rna > {log}
     """
 
 
+rule merge_alleles:
+  input:
+    get_alleles,
+  output:
+    "results/{sample}/hla/alleles.tsv"
+  message:
+    "Merging the detected alleles in {wildcards.sample}"
+  log:
+    "logs/{sample}/hla/merge_alleles"
+  conda:
+    "../envs/basic.yml"
+  shell:
+    """
+      python3 workflow/scripts/merge_alleles.py '{input}' \
+          {output} 2> {log}
+    """
+
+
+
 
 

workflow/scripts/merge_alleles.py

@@ -0,0 +1,41 @@
+import sys
+
+def main():
+    alleles = {
+            'A1': [], 'A2': [],'B1': [],
+            'B2': [], 'C1': [],'C2': []
+    }
+
+    for alfile in sys.argv[1].split(' '):
+        with open(alfile, 'r') as f:
+            next(f)
+            for line in f:
+                line = line.rstrip().split('\t')
+
+                if line[1] not in alleles['A1']:
+                    alleles['A1'].append(line[1])
+
+                if line[2] not in alleles['A2']:
+                    alleles['A2'].append(line[2])
+
+                if line[3] not in alleles['B1']:
+                    alleles['B1'].append(line[3])
+
+                if line[4] not in alleles['B2']:
+                    alleles['B2'].append(line[4])
+
+                if line[5] not in alleles['C1']:
+                    alleles['C1'].append(line[5])
+
+                if line[6] not in alleles['C2']:
+                    alleles['C2'].append(line[6])
+
+
+    output = open(sys.argv[2], 'w')
+    for key in alleles.keys():
+        output.write(key + '\t' + '\t'.join(alleles[key]) + '\n')
+    output.close()
+
+
+
+main()