Optional spikeins report

Only run if spikeins_db is set in config.
broadinstitute · Apr 11, 2016 · aba821b · aba821b
1 parent 2fcbc0f
commit aba821b
Show file tree

Hide file tree

Showing 2 changed files with 44 additions and 37 deletions.
diff --git a/pipes/Snakefile b/pipes/Snakefile
@@ -2,7 +2,7 @@
     This is a basic framework for processing of of viral genomes, currently
     tailored for EBOV. Some generalization work needed to expand this
     to generic viral genomes with an arbitrary number of segments/chromosomes.
-    
+
     Make copies of this Snakefile and config.yaml to your analysis directory and
     customize as needed.
 """
@@ -25,21 +25,26 @@ include: os.path.join(pipesDir, 'ncbi.rules')
 include: os.path.join(pipesDir, 'intrahost.rules')
 include: os.path.join(pipesDir, 'reports.rules')
 
+all_inputs = [
+    # create final assemblies for all samples
+    expand("{data_dir}/{subdir}/{sample}.fasta",
+           data_dir=config["data_dir"], subdir=config["subdirs"]["assembly"],
+           sample=read_samples_file(config["samples_assembly"])),
+    # create BAMs of aligned reads to own consensus and to common ref
+    expand("{data_dir}/{subdir}/{sample}.bam",
+           data_dir=config["data_dir"], subdir=config["subdirs"]["align_self"],
+           sample=read_samples_file(config["samples_assembly"])),
+    # intrahost variant calling
+    config["data_dir"]+'/'+config["subdirs"]["intrahost"] +'/isnvs.vcf.gz',
+    # create summary reports
+    config["reports_dir"]+'/summary.fastqc.txt',
+]
+
+if config.get('spikeins_db'):
+    all_inputs.append(config["reports_dir"]+'/summary.spike_count.txt')
+
 rule all:
-    input:
-        # create final assemblies for all samples
-        expand("{data_dir}/{subdir}/{sample}.fasta",
-            data_dir=config["data_dir"], subdir=config["subdirs"]["assembly"],
-            sample=read_samples_file(config["samples_assembly"])),
-        # create BAMs of aligned reads to own consensus and to common ref
-        expand("{data_dir}/{subdir}/{sample}.bam",
-            data_dir=config["data_dir"], subdir=config["subdirs"]["align_self"],
-            sample=read_samples_file(config["samples_assembly"])),
-        # intrahost variant calling
-        config["data_dir"]+'/'+config["subdirs"]["intrahost"] +'/isnvs.vcf.gz',
-        # create summary reports
-        config["reports_dir"]+'/summary.fastqc.txt',
-        config["reports_dir"]+'/summary.spike_count.txt'
+    input: all_inputs
     params: LSF="-N"
     run:
             if "job_profiler" in config:

diff --git a/pipes/rules/reports.rules b/pipes/rules/reports.rules
@@ -7,11 +7,13 @@ __author__ = 'Kristian Andersen <andersen@broadinstitute.org>, Daniel Park <dpar
 from snakemake.utils import makedirs
 import os, os.path, gzip, shutil
 
+all_reports = [config["reports_dir"]+'/summary.fastqc.txt']
+
+if config.get("spikeins_db"):
+    all_reports.append(config["reports_dir"]+'/summary.spike_count.txt')
 
 rule all_reports:
-    input:
-        config["reports_dir"]+'/summary.fastqc.txt',
-        config["reports_dir"]+'/summary.spike_count.txt'
+    input: all_reports
     params: LSF="-N"
 
 
@@ -42,23 +44,23 @@ rule consolidate_fastqc:
 
 #-----------SPIKE-INS------------------
 
-rule spikein_report:
-    input:  config["data_dir"]+'/'+config["subdirs"]["depletion"]+'/{sample}.cleaned.bam'
-    output: config["reports_dir"]+'/spike_count/{sample}.spike_count.txt'
-    resources: mem=3
-    params: LSF=config.get('LSF_queues', {}).get('short', '-W 4:00'),
-            UGER=config.get('UGER_queues', {}).get('short', '-q short'),
-            logid="{sample}",
-            spikeins_db=config["spikeins_db"]
-    run:
-            makedirs(os.path.join(config["reports_dir"], 'spike_count'))
-            makedirs(os.path.join(config["tmp_dir"], config["subdirs"]["depletion"]))
-            shell("{config[bin_dir]}/read_utils.py align_and_count_hits {input} {params.spikeins_db} {output}")
-
-rule consolidate_spike_count:
-    input:  expand("{{dir}}/spike_count/{sample}.spike_count.txt", \
-                sample=read_samples_file(config["samples_per_run"]))
-    output: '{dir}/summary.spike_count.txt'
-    params: logid="all"
-    shell:  "{config[bin_dir]}/reports.py consolidate_spike_count {wildcards.dir}/spike_count {output}"
+if config.get("spikeins_db"):
+    rule spikein_report:
+        input:  config["data_dir"]+'/'+config["subdirs"]["depletion"]+'/{sample}.cleaned.bam'
+        output: config["reports_dir"]+'/spike_count/{sample}.spike_count.txt'
+        resources: mem=3
+        params: LSF=config.get('LSF_queues', {}).get('short', '-W 4:00'),
+                UGER=config.get('UGER_queues', {}).get('short', '-q short'),
+                logid="{sample}",
+                spikeins_db=config["spikeins_db"]
+        run:
+                makedirs(os.path.join(config["reports_dir"], 'spike_count'))
+                makedirs(os.path.join(config["tmp_dir"], config["subdirs"]["depletion"]))
+                shell("{config[bin_dir]}/read_utils.py align_and_count_hits {input} {params.spikeins_db} {output}")
 
+    rule consolidate_spike_count:
+        input:  expand("{{dir}}/spike_count/{sample}.spike_count.txt", \
+                    sample=read_samples_file(config["samples_per_run"]))
+        output: '{dir}/summary.spike_count.txt'
+        params: logid="all"
+        shell:  "{config[bin_dir]}/reports.py consolidate_spike_count {wildcards.dir}/spike_count {output}"