refactor: Update the list of files to be stored and delivered (#915)

Clinical-Genomics · May 23, 2022 · 3c87fe3 · 3c87fe3
1 parent 523026d
commit 3c87fe3
Show file tree

Hide file tree

Showing 22 changed files with 275 additions and 124 deletions.
diff --git a/BALSAMIC/assets/scripts/collect_qc_metrics.py b/BALSAMIC/assets/scripts/collect_qc_metrics.py
@@ -51,8 +51,8 @@ def capture_kit_resolve_type(capture_kit: str):
 
     if capture_kit == "None":
         return None
-    else:
-        return capture_kit
+
+    return capture_kit
 
 
 def get_multiqc_data_source(multiqc_data: dict, sample: str, tool: str) -> str:

diff --git a/BALSAMIC/constants/workflow_rules.py b/BALSAMIC/constants/workflow_rules.py
@@ -113,31 +113,31 @@
 
 
 DELIVERY_RULES = [
-    "fastp",
     "multiqc",
     "collect_custom_qc_metrics",
-    "vep_somatic_snv",
-    "vep_somatic_sv",
-    "vep_germline",
-    "tmb_calculation",
-    "bcftools_filter_TNscope_umi_tumor_only",
-    "bcftools_filter_TNscope_umi_tumor_normal",
-    "bcftools_filter_vardict_tumor_only",
-    "bcftools_filter_vardict_tumor_normal",
-    "bcftools_filter_tnscope_tumor_only",
-    "bcftools_filter_tnscope_tumor_normal",
-    "bcftools_filter_tnhaplotyper_tumor_only",
-    "bcftools_filter_tnhaplotyper_tumor_normal",
-    "bcftools_filter_svdb",
-    "bcftools_intersect_tumor_only",
-    "bcftools_filter_TNscope_umi_tumor_only",
-    "genmod_score_vardict",
     "mergeBam_tumor",
     "mergeBam_normal",
     "mergeBam_tumor_umiconsensus",
     "mergeBam_normal_umiconsensus",
-    "cnvkit_paired",
+    "vep_germline",
+    "svdb_merge_tumor_only",
+    "svdb_merge_tumor_normal",
+    "sentieon_TNscope_tumor_only",
+    "sentieon_TNscope",
+    "vardict_merge",
+    "sentieon_tnscope_umi",
+    "sentieon_tnscope_umi_tn",
+    "ascat_tumor_normal",
+    "ascat_tumor_normal_merge_output",
+    "delly_cnv_tumor_only",
     "cnvkit_single",
+    "cnvkit_paired",
     "vcf2cytosure_convert",
-    "ascat_tumor_normal_merge_output",
+    "bcftools_filter_svdb",
+    "bcftools_intersect_tumor_only",
+    "bcftools_filter_tnscope_tumor_normal",
+    "bcftools_filter_vardict_tumor_only",
+    "bcftools_filter_vardict_tumor_normal",
+    "bcftools_filter_TNscope_umi_tumor_only",
+    "bcftools_filter_TNscope_umi_tumor_normal",
 ]
diff --git a/BALSAMIC/snakemake_rules/annotation/varcaller_filter_tumor_normal.rule b/BALSAMIC/snakemake_rules/annotation/varcaller_filter_tumor_normal.rule
@@ -63,7 +63,6 @@ rule bcftools_filter_tnhaplotyper_tumor_normal:
     Path(singularity_image, config["bioinfo_tools"].get("bcftools") + ".sif").as_posix()
   params:
     pop_freq = [COMMON_FILTERS.pop_freq.tag_value, COMMON_FILTERS.pop_freq.filter_name],
-    housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
     case_name =  '{case_name}'
   threads:
     get_threads(cluster_config, 'bcftools_filter_tnhaplotyper_tumor_normal')

diff --git a/BALSAMIC/snakemake_rules/annotation/varcaller_filter_tumor_only.rule b/BALSAMIC/snakemake_rules/annotation/varcaller_filter_tumor_only.rule
@@ -61,7 +61,6 @@ rule bcftools_filter_tnhaplotyper_tumor_only:
     Path(singularity_image, config["bioinfo_tools"].get("bcftools") + ".sif").as_posix()
   params:
     pop_freq = [COMMON_FILTERS.pop_freq.tag_value, COMMON_FILTERS.pop_freq.filter_name],
-    housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
     case_name =  '{case_name}'
   threads:
     get_threads(cluster_config, 'bcftools_filter_tnhaplotyper_tumor_only')

diff --git a/BALSAMIC/snakemake_rules/annotation/varcaller_wgs_filter_tumor_normal.rule b/BALSAMIC/snakemake_rules/annotation/varcaller_wgs_filter_tumor_normal.rule
@@ -60,7 +60,6 @@ rule bcftools_filter_tnhaplotyper_tumor_normal:
     Path(singularity_image, config["bioinfo_tools"].get("bcftools") + ".sif").as_posix()
   params:
     pop_freq = [SENTIEON_CALLER.pop_freq.tag_value, SENTIEON_CALLER.pop_freq.filter_name],
-    housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
     case_name = '{case_name}'
   threads: 
     get_threads(cluster_config, 'bcftools_filter_tnhaplotyper_tumor_normal')

diff --git a/BALSAMIC/snakemake_rules/annotation/varcaller_wgs_filter_tumor_only.rule b/BALSAMIC/snakemake_rules/annotation/varcaller_wgs_filter_tumor_only.rule
@@ -23,7 +23,6 @@ rule bcftools_filter_tnscope_tumor_only:
     strand_reads = [SENTIEON_CALLER.strand_reads.tag_value, SENTIEON_CALLER.strand_reads.filter_name],
     qss = [SENTIEON_CALLER.qss.tag_value, SENTIEON_CALLER.qss.filter_name],
     sor = [SENTIEON_CALLER.sor.tag_value, SENTIEON_CALLER.sor.filter_name],
-    housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
     case_name = '{case_name}'
   threads: 
     get_threads(cluster_config, 'bcftools_filter_tnscope_tumor_only')
@@ -67,7 +66,6 @@ rule bcftools_filter_tnhaplotyper_tumor_only:
     pop_freq = [SENTIEON_CALLER.pop_freq.tag_value, SENTIEON_CALLER.pop_freq.filter_name],
     strand_reads = [SENTIEON_CALLER.strand_reads.tag_value, SENTIEON_CALLER.strand_reads.filter_name],
     qss = [SENTIEON_CALLER.qss.tag_value, SENTIEON_CALLER.qss.filter_name],
-    housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
     case_name = '{case_name}'
   threads: 
     get_threads(cluster_config, 'bcftools_filter_tnhaplotyper_tumor_only')

diff --git a/BALSAMIC/snakemake_rules/annotation/vep.rule b/BALSAMIC/snakemake_rules/annotation/vep.rule
@@ -15,7 +15,6 @@ rule vep_somatic_snv:
   singularity:
     Path(singularity_image, config["bioinfo_tools"].get("ensembl-vep") + ".sif").as_posix()
   params:
-    housekeeper_id = {"id": "{case_name}", "tags": "annotated-somatic"},
     ref_path = Path(config["reference"]["gnomad_variant"]).parent.as_posix(),
     message_text = "SNV.somatic.{case_name}.{var_caller}.vcf.gz",
     tmpvcf = vep_dir + "SNV.somatic.{case_name}.{var_caller}.tmp.vcf.gz",
@@ -62,7 +61,6 @@ rule vep_somatic_sv:
   singularity:
     Path(singularity_image, config["bioinfo_tools"].get("ensembl-vep") + ".sif").as_posix()
   params:
-    housekeeper_id = {"id": "{case_name}", "tags": "annotated-somatic"},
     message_text = "SV.somatic.{case_name}.svdb.vcf.gz",
     vep_cache = config["reference"]["vep"],
     vep_defaults = params.vep.vep_filters
@@ -100,7 +98,6 @@ rule tmb_calculation:
   params:
     af_cutoff = "0.05",
     bed = config["panel"]["capture_kit"] if "panel" in config else "",
-    housekeeper_id = {"id": "{case_name}", "tags": "stat-somatic"},
     message_text = "{var_type}.somatic.{case_name}.{var_caller}.all",
     tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
   threads:
@@ -156,7 +153,7 @@ rule vep_germline:
   singularity:
     Path(singularity_image, config["bioinfo_tools"].get("ensembl-vep") + ".sif").as_posix() 
   params:
-    housekeeper_id = {"id": "{sample}", "tags": "annotated-germline"},
+    housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "annotated-germline"},
     sample = '{sample}',
     vep_cache = config["reference"]["vep"],
     vep_defaults = params.vep.vep_filters

diff --git a/BALSAMIC/snakemake_rules/quality_control/fastp.rule b/BALSAMIC/snakemake_rules/quality_control/fastp.rule
@@ -32,8 +32,8 @@ rule fastp_umi:
         read1=config["analysis"]["fastq_path"] + "{sample}" + "_1.fastq.gz",
         read2=config["analysis"]["fastq_path"] + "{sample}" + "_2.fastq.gz",
     output:
-        read1 = fastq_dir + "{sample}_1.umi_optimized.fastq.gz",
-        read2 = fastq_dir + "{sample}_2.umi_optimized.fastq.gz",
+        read1 = temp(fastq_dir + "{sample}_1.umi_optimized.fastq.gz"),
+        read2 = temp(fastq_dir + "{sample}_2.umi_optimized.fastq.gz"),
         json = qc_dir + "fastp/{sample}_fastp_umi.json",
         html = qc_dir + "fastp/{sample}_fastp_umi.html",
     benchmark:
@@ -73,16 +73,15 @@ rule fastp:
         read1 = fastq_dir + "{sample}_1.umi_optimized.fastq.gz",
         read2 = fastq_dir + "{sample}_2.umi_optimized.fastq.gz"
     output:
-        read1 = fastq_dir + "{sample}_1.fp.fastq.gz",
-        read2 = fastq_dir + "{sample}_2.fp.fastq.gz",
+        read1 = temp(fastq_dir + "{sample}_1.fp.fastq.gz"),
+        read2 = temp(fastq_dir + "{sample}_2.fp.fastq.gz"),
         json = qc_dir + "fastp/{sample}_fastp.json",
         html = qc_dir + "fastp/{sample}_fastp.html"
     benchmark:
         Path(benchmark_dir, "fastp_" + "{sample}.tsv").as_posix()
     singularity: 
         Path(singularity_image, config["bioinfo_tools"].get("fastp") + ".sif").as_posix() 
     params:
-        housekeeper_id = {"id": "{sample}", "tags": "quality-trimmed-fastq"},
         tmpdir = tmp_dir,
         umi = " ".join(fastp_param_umi),
         minimum_length = config["QC"]["min_seq_length"],

diff --git a/BALSAMIC/snakemake_rules/umi/sentieon_varcall_tnscope.rule b/BALSAMIC/snakemake_rules/umi/sentieon_varcall_tnscope.rule
@@ -12,11 +12,12 @@ rule sentieon_tnscope_umi:
         bed = config["panel"]["capture_kit"],
         dbsnp = config["reference"]["dbsnp"]
     output:
-        vcf = vcf_dir +  "SNV.somatic."+ config["analysis"]["case_id"] + ".TNscope_umi.vcf.gz",
+        vcf_tnscope_umi = vcf_dir +  "SNV.somatic."+ config["analysis"]["case_id"] + ".TNscope_umi.vcf.gz",
         namemap = vcf_dir + "SNV.somatic." + config["analysis"]["case_id"] + ".TNscope_umi.sample_name_map"
     benchmark:
         Path(benchmark_dir, "sentieon_tnscope_umi_" + config["analysis"]["case_id"] + ".tsv").as_posix()
     params:
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         sentieon_exec = config["SENTIEON_EXEC"],
         sentieon_lic = config["SENTIEON_LICENSE"],
@@ -58,7 +59,7 @@ export SENTIEON_LICENSE={params.sentieon_lic};
 --max_error_per_read {params.error_rate} \
 --pcr_indel_model {params.pcr_model} \
 --prune_factor {params.prune_factor} \
-{output.vcf};
+{output.vcf_tnscope_umi};
 
 echo -e \"{params.tumor}\\tTUMOR\" > {output.namemap}; 
         """
diff --git a/BALSAMIC/snakemake_rules/umi/sentieon_varcall_tnscope_tn.rule b/BALSAMIC/snakemake_rules/umi/sentieon_varcall_tnscope_tn.rule
@@ -12,11 +12,12 @@ rule sentieon_tnscope_umi_tn:
         bed = config["panel"]["capture_kit"],
         dbsnp = config["reference"]["dbsnp"]
     output:
-        vcf = vcf_dir +  "SNV.somatic."+ config["analysis"]["case_id"] + ".TNscope_umi.vcf.gz",
+        vcf_tnscope_umi = vcf_dir +  "SNV.somatic."+ config["analysis"]["case_id"] + ".TNscope_umi.vcf.gz",
         namemap = vcf_dir + "SNV.somatic." + config["analysis"]["case_id"] + ".TNscope_umi.sample_name_map"
     benchmark:
         Path(benchmark_dir, "sentieon_tnscope_umi_" + config["analysis"]["case_id"] + ".tsv").as_posix()
     params:
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         sentieon_exec = config["SENTIEON_EXEC"],
         sentieon_lic = config["SENTIEON_LICENSE"],
@@ -62,7 +63,7 @@ export SENTIEON_LICENSE={params.sentieon_lic};
 --max_error_per_read {params.error_rate} \
 --pcr_indel_model {params.pcr_model} \
 --prune_factor {params.prune_factor} \
-{output.vcf};
+{output.vcf_tnscope_umi};
 
 echo -e \"{params.tumor}\\tTUMOR\\n{params.normal}\\tNORMAL\" > {output.namemap};
         """
diff --git a/BALSAMIC/snakemake_rules/variant_calling/sentieon_t_varcall.rule b/BALSAMIC/snakemake_rules/variant_calling/sentieon_t_varcall.rule
@@ -127,12 +127,13 @@ rule sentieon_TNscope_tumor_only:
         bam = expand(bam_dir + "tumor.merged.bam"),
         recal = expand(bam_dir + "tumor.merged.recal_data.table")
     output:
-        vcf = vcf_dir + "sentieon_tnscope" + "/" + "ALL.somatic." + config["analysis"]["case_id"] + ".tnscope.vcf.gz",
+        vcf_tnscope = vcf_dir + "sentieon_tnscope" + "/" + "ALL.somatic." + config["analysis"]["case_id"] + ".tnscope.vcf.gz",
         namemap_snv = vcf_dir + "SNV.somatic." + config["analysis"]["case_id"] + ".tnscope.sample_name_map",
         namemap_sv = vcf_dir + "SV.somatic." + config["analysis"]["case_id"] + ".tnscope.sample_name_map",
     benchmark:
         Path(benchmark_dir, "sentieon_TNscope_tumor_only_" + config["analysis"]["case_id"] + ".tsv").as_posix()
     params:
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         tumor = "TUMOR", 
         tumor_options = VARCALL_PARAMS["tnscope"]["tumor"], 
@@ -162,7 +163,7 @@ export SENTIEON_LICENSE={params.sentieon_lic};
 --tumor_sample {params.tumor} {params.pon} \
 --dbsnp {input.dbsnp} \
 --pcr_indel_mode {params.pcr_model} \
-{params.tumor_options} {output.vcf};
+{params.tumor_options} {output.vcf_tnscope};
 
 echo -e \"{params.tumor}\\tTUMOR\" > {output.namemap_snv};
 

diff --git a/BALSAMIC/snakemake_rules/variant_calling/sentieon_tn_varcall.rule b/BALSAMIC/snakemake_rules/variant_calling/sentieon_tn_varcall.rule
@@ -162,12 +162,13 @@ rule sentieon_TNscope:
         recalT = expand(bam_dir + "tumor.merged.recal_data.table"),
         recalN = expand(bam_dir + "normal.merged.recal_data.table"),
     output:
-        vcf_all = vcf_dir + "sentieon_tnscope/ALL.somatic." + config["analysis"]["case_id"] + ".tnscope.vcf.gz",
+        vcf_tnscope = vcf_dir + "sentieon_tnscope/ALL.somatic." + config["analysis"]["case_id"] + ".tnscope.vcf.gz",
         namemap_snv = vcf_dir + "SNV.somatic." + config["analysis"]["case_id"] + ".tnscope.sample_name_map",
         namemap_sv = vcf_dir + "SV.somatic." + config["analysis"]["case_id"] + ".tnscope.sample_name_map",
     benchmark:
         Path(benchmark_dir, 'sentieon_TNscope_' + config[ "analysis" ][ "case_id" ] + ".tsv").as_posix()
     params:
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         tumor = "TUMOR",
         normal = "NORMAL",
@@ -211,7 +212,7 @@ intermediate_vcf={params.tmpdir}/tn_sentieon_varcall_file
 -r {input.ref} \
 --algo TNModelApply \
 -m {params.sentieon_ml_tnscope} \
--v $intermediate_vcf {output.vcf_all};
+-v $intermediate_vcf {output.vcf_tnscope};
 
 echo -e \"{params.tumor}\\tTUMOR\\n{params.normal}\\tNORMAL\" > {output.namemap_snv};
 cp {output.namemap_snv} {output.namemap_sv}

diff --git a/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_normal.rule b/BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_normal.rule
@@ -122,17 +122,20 @@ rule ascat_tumor_normal:
     output:
         final_vcf = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.vcf.gz",
         ascat_copynumber = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.copynumber.txt.gz",
-        sample_statistics = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.samplestatistics.txt",
-        ascat_plots= expand(
-            vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat." + "{output_suffix}" + ".png",
-            output_suffix=["ascatprofile", "rawprofile", "ASPCF", "tumor", "germline", "sunrise"]
-        ),
+        sample_statistics = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.samplestatistics.txt"),
+        plot_ascat_profile = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.ascatprofile.png"),
+        plot_raw_profile = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.rawprofile.png"),
+        plot_aspcf = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.ASPCF.png"),
+        plot_tumor = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.tumor.png"),
+        plot_germline = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.germline.png"),
+        plot_sunrise = temp(vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.sunrise.png"),
         namemap = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.sample_name_map",
     benchmark:
         benchmark_dir + 'ascat_tumor_normal_' + config["analysis"]["case_id"] + "_ascat.tsv"
     singularity:
         Path(singularity_image, config["bioinfo_tools"].get("ascatNgs") + ".sif").as_posix()
     params:
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "clinical"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         tumor = "TUMOR",
         normal = "NORMAL",
@@ -164,17 +167,17 @@ cp {params.tmpdir}/{params.tumor}.copynumber.txt.gz {output.ascat_copynumber}
 
 cp {params.tmpdir}/{params.tumor}.samplestatistics.txt {output.sample_statistics};
 
-cp {params.tmpdir}/{params.tumor}.ASCATprofile.png {output.ascat_plots[0]};
+cp {params.tmpdir}/{params.tumor}.ASCATprofile.png {output.plot_ascat_profile};
 
-cp {params.tmpdir}/{params.tumor}.rawprofile.png {output.ascat_plots[1]};
+cp {params.tmpdir}/{params.tumor}.rawprofile.png {output.plot_raw_profile};
 
-cp {params.tmpdir}/{params.tumor}.ASPCF.png {output.ascat_plots[2]};
+cp {params.tmpdir}/{params.tumor}.ASPCF.png {output.plot_aspcf};
 
-cp {params.tmpdir}/{params.tumor}.tumour.png {output.ascat_plots[3]};
+cp {params.tmpdir}/{params.tumor}.tumour.png {output.plot_tumor};
 
-cp {params.tmpdir}/{params.tumor}.germline.png {output.ascat_plots[4]};
+cp {params.tmpdir}/{params.tumor}.germline.png {output.plot_germline};
 
-cp {params.tmpdir}/{params.tumor}.sunrise.png {output.ascat_plots[5]};
+cp {params.tmpdir}/{params.tumor}.sunrise.png {output.plot_sunrise};
 
 tabix -p vcf -f {output.final_vcf};
 
@@ -191,9 +194,9 @@ rule ascat_tumor_normal_merge_output:
             output_suffix=["ascatprofile", "rawprofile", "ASPCF", "tumor", "germline", "sunrise"]
         ),
     output:
-        ascat_output_pdf = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.output.pdf"
+        ascat_pdf = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".ascat.output.pdf"
     params:
-        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "clinical"},
         merge_ascat_output_script= get_script_path("create_pdf.py"),
     singularity:
         Path(singularity_image, "balsamic.sif").as_posix()
@@ -203,7 +206,7 @@ rule ascat_tumor_normal_merge_output:
         "Merging the output plots and the sample statistics from ascatNGS into a single PDF"
     shell:
         """
-python {params.merge_ascat_output_script} {output.ascat_output_pdf} {input.sample_statistics} {input.ascat_plots}
+python {params.merge_ascat_output_script} {output.ascat_pdf} {input.sample_statistics} {input.ascat_plots}
         """
 
 rule svdb_merge_tumor_normal:
@@ -215,13 +218,14 @@ rule svdb_merge_tumor_normal:
                 vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".{caller}.vcf.gz",
                 caller=somatic_caller_cnv)
     output:
-        svdb_vcf = vcf_dir + "SV.somatic." + config["analysis"]["case_id"] + ".svdb.vcf.gz",
+        vcf_svdb = vcf_dir + "SV.somatic." + config["analysis"]["case_id"] + ".svdb.vcf.gz",
         namemap = vcf_dir + "SV.somatic." + config["analysis"]["case_id"] + ".svdb.sample_name_map",
     benchmark:
         Path(benchmark_dir, 'svdb_merge_tumor_normal_' + config["analysis"]["case_id"] + ".tsv")
     singularity:
         Path(singularity_image, config["bioinfo_tools"].get("svdb") + ".sif").as_posix()
     params:
+        housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tumor = get_sample_type(config["samples"], "tumor"),
         normal = get_sample_type(config["samples"], "normal"),
         case_name = config["analysis"]["case_id"],
@@ -236,7 +240,8 @@ rule svdb_merge_tumor_normal:
 svdb --merge --no_intra --bnd_distance 5000 --overlap 0.80 \
 --vcf {params.vcf} \
 --priority {params.svdb_priority} | \
-bgzip -l 9 -c  > {output.svdb_vcf};
+bgzip -l 9 -c  > {output.vcf_svdb};
+tabix -p vcf -f {output.vcf_svdb};
 
 echo -e \"{params.tumor}\\tTUMOR\\n{params.normal}\\tNORMAL\" > {output.namemap};
         """