Add fusion filters for transgene (resolves #237)

Added all fusion parameters to the input config so users can control
what fusion filters are applied.

Author: arkal

MANUAL.md

@@ -414,6 +414,11 @@ be substituted with S3 links. Descriptions for creating all files can be found i
             gencode_transcript_fasta : /path/to/gencode_transcripts.faa     -> The transcript file for the gencode gtf.
             gencode_annotation_gtf : /path/to/gencode_annotation.gtf        -> The gencode genome annotation file.
             genome_fasta : /path/to/hg19.faa                                -> The gencode genome fasta file
+            filter_mt_fusions: True                                         -> Switch to filter mitochondrial gene pairs
+            filter_ig_pairs: True                                           -> Switch to filter immunoglobulin gene pairs
+            filter_rna_gene_fusions: True                                   -> Switch to filter rna-gene pairs
+            filter_readthroughs: True                                       -> Switch to filter readthroughs
+            readthrough_threshold: 500000                                   -> Threshold below which pairs will be called readthroughs
             version: 2.2.2
 
     haplotyping:

src/protect/mutation_translation.py

@@ -90,7 +90,8 @@ def run_transgene(job, snpeffed_file, rna_bam, univ_options, transgene_options,
                   '--pep_lens', '9,10,15',
                   '--cores', str(transgene_options['n']),
                   '--genome', input_files['genome.fa'],
-                  '--annotation', input_files['annotation.gtf']]
+                  '--annotation', input_files['annotation.gtf'],
+                  '--log_file', '/data/transgene.log']
 
     if snpeffed_file is not None:
         parameters.extend(['--snpeff', input_files['snpeffed_muts.vcf']])
@@ -110,6 +111,15 @@ def run_transgene(job, snpeffed_file, rna_bam, univ_options, transgene_options,
         fusion_files = {key: docker_path(path) for key, path in fusion_files.items()}
         parameters += ['--transcripts', fusion_files['transcripts.fa'],
                        '--fusions', fusion_files['fusion_calls']]
+        if transgene_options['filter_mt_fusions'] is True:
+            parameters.append('--filter_mt')
+        if transgene_options['filter_ig_pairs'] is True:
+            parameters.append('--filter_ig')
+        if transgene_options['filter_rg'] is True:
+            parameters.append('--filter_rna_gene_fusions')
+        if transgene_options['filter_readthroughs'] is True:
+            parameters.append('--filter_rt')
+            parameters.extend(['--rt_threshold', transgene_options['readthrough_threshold']])
 
     docker_call(tool='transgene',
                 tool_parameters=parameters,

src/protect/pipeline/defaults.yaml

@@ -88,6 +88,11 @@ mutation_annotation:
 
 mutation_translation:
     transgene:
+        filter_mt_fusions: True
+        filter_ig_pairs: True
+        filter_rna_gene_fusions: True
+        filter_readthroughs: True
+        readthrough_threshold: 500000
         version: 2.5.0
 
 haplotyping:

src/protect/pipeline/input_parameters.yaml

@@ -133,6 +133,11 @@ mutation_translation:
         gencode_peptide_fasta : S3://protect-data/hg38_references/gencode.v25.pc_translations_NOPARY.fa.tar.gz
         gencode_transcript_fasta : S3://protect-data/hg38_references/gencode.v25.pc_transcripts_NOPARY.fa.tar.gz
         gencode_annotation_gtf : S3://protect-data/hg38_references/gencode.v25.annotation_NOPARY.gtf.tar.gz
+        filter_mt_fusions: True
+        filter_ig_pairs: True
+        filter_rna_gene_fusions: True
+        filter_readthroughs: True
+        readthrough_threshold: 500000
         genome_fasta : S3://protect-data/hg38_references/hg38.fa.tar.gz
         # version: 2.2.2