Merge pull request #139 from /issues/138-hard-code-tool-dockers

Hardcode tool docker versions (related to #138)

required_docker_tools.txt

@@ -1,39 +1,40 @@
 # Alignment
-    cutadapt:latest
-    bwa:latest
-    star:latest
-    starlong:latest
+	cutadapt:1.9.1
+	bwa:0.7.9a
+	star:2.4.2a
+	starlong:2.4.2a
 
 # Alignment post
-    samtools:latest
-    picard:latest
+	samtools:1.2
+	picard:1.135
 
 # Expression Estimation
-    rsem:latest
+	rsem:1.2.20
 
 # Haplotyping
-    phlat:latest
+	phlat:1.0
 
 # Mutation Calling
-    mutect:1.1.7
-    radia:latest
-    filterradia:latest
-    muse:latest
-    somaticsniper:latest (proposed)
-    vardict:latest (proposed)
+	mutect:1.1.7
+	radia:398366ef07b5911d8082ed61cbf03d487a41f286
+	filterradia:398366ef07b5911d8082ed61cbf03d487a41f286
+	muse:1.0rc_submission_b391201
+	somaticsniper:1.0.4
+	somaticsniper-addons:1.0.4
+	samtools:0.1.8
+	strelka:1.0.15
+	bam-readcount:0.7.4
 
 # Mutation Annotation
-    snpeff:latest
-    transvar:latest
+	snpeff:3.6
 
 # Mutation Translation
-    transgene:latest
+	transgene:1.0.0
 
 # MHC:peptide binding prediction
-    mhci:latest
-    mhcii:latest
-    netmhciipan:final:latest
-
-# MHC post
-    rankboost:latest
+	mhci:2.13
+	mhcii:2.13
+	netmhciipan:3.1
 
+# Prediction Ranking
+	rankboost:1.0.0

src/protect/alignment/common.py

@@ -46,7 +46,7 @@ def index_bamfile(job, bamfile, sample_type, univ_options):
     input_files = get_files_from_filestore(job, input_files, work_dir, docker=True)
     parameters = ['index',
                   input_files[in_bamfile]]
-    docker_call(tool='samtools', tool_parameters=parameters,
+    docker_call(tool='samtools:1.2', tool_parameters=parameters,
                 work_dir=work_dir, dockerhub=univ_options['dockerhub'])
     out_bai = '/'.join([work_dir, in_bamfile + '.bai'])
     output_files = {in_bamfile: bamfile,

src/protect/alignment/dna.py

@@ -112,7 +112,7 @@ def run_bwa(job, fastqs, sample_type, univ_options, bwa_options):
                   input_files['dna_1.fastq' + gz],
                   input_files['dna_2.fastq' + gz]]
     with open(''.join([work_dir, '/', sample_type, '_aligned.sam']), 'w') as samfile:
-        docker_call(tool='bwa', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='bwa:0.7.9a', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=samfile)
     # samfile.name retains the path info
     output_file = job.fileStore.writeGlobalFile(samfile.name)
@@ -144,7 +144,7 @@ def bam_conversion(job, samfile, sample_type, univ_options):
                   '-o', docker_path(bamfile),
                   input_files[sample_type + '_aligned.sam']
                   ]
-    docker_call(tool='samtools', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='samtools:1.2', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     output_file = job.fileStore.writeGlobalFile(bamfile)
     # The samfile is no longer useful so delete it
@@ -174,7 +174,7 @@ def fix_bam_header(job, bamfile, sample_type, univ_options):
                   '-H',
                   input_files[sample_type + '_aligned.bam']]
     with open('/'.join([work_dir, sample_type + '_aligned_bam.header']), 'w') as headerfile:
-        docker_call(tool='samtools', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='samtools:1.2', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=headerfile)
     with open(headerfile.name, 'r') as headerfile, \
             open('/'.join([work_dir, sample_type + '_output_bam.header']), 'w') as outheaderfile:
@@ -186,7 +186,7 @@ def fix_bam_header(job, bamfile, sample_type, univ_options):
                   docker_path(outheaderfile.name),
                   input_files[sample_type + '_aligned.bam']]
     with open('/'.join([work_dir, sample_type + '_aligned_fixPG.bam']), 'w') as fixpg_bamfile:
-        docker_call(tool='samtools', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='samtools:1.2', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=fixpg_bamfile)
     output_file = job.fileStore.writeGlobalFile(fixpg_bamfile.name)
     # The old bam file is now useless.
@@ -223,7 +223,7 @@ def add_readgroups(job, bamfile, sample_type, univ_options):
                   'PL=ILLUMINA',
                   'PU=12345',
                   ''.join(['SM=', sample_type.rstrip('_dna')])]
-    docker_call(tool='picard', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='picard:1.135', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'], java_opts=univ_options['java_Xmx'])
     output_file = job.fileStore.writeGlobalFile(
         '/'.join([work_dir, sample_type + '_aligned_fixpg_sorted_reheader.bam']))

src/protect/alignment/rna.py

@@ -100,10 +100,10 @@ def run_star(job, fastqs, univ_options, star_options):
     if gz:
         parameters.extend(['--readFilesCommand', 'zcat'])
     if star_options['type'] == 'star':
-        docker_call(tool='star', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='star:2.4.2a', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'])
     else:
-        docker_call(tool='starlong', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='starlong:2.4.2a', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'])
     output_files = defaultdict()
     for bam_file in ['rnaAligned.toTranscriptome.out.bam',

src/protect/binding_prediction/mhci.py

@@ -37,7 +37,7 @@ def predict_mhci_binding(job, peptfile, allele, peplen, univ_options,
                   peplen,
                   input_files['peptfile.faa']]
     with open('/'.join([work_dir, 'predictions.tsv']), 'w') as predfile:
-        docker_call(tool='mhci', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='mhci:2.13', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=predfile, interactive=True)
     output_file = job.fileStore.writeGlobalFile(predfile.name)
     return output_file

src/protect/binding_prediction/mhcii.py

@@ -38,7 +38,7 @@ def predict_mhcii_binding(job, peptfile, allele, univ_options, mhcii_options):
                   allele,
                   input_files['peptfile.faa']]
     with open('/'.join([work_dir, 'predictions.tsv']), 'w') as predfile:
-        docker_call(tool='mhcii', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='mhcii:2.13', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=predfile, interactive=True)
     run_netmhciipan = True
     predictor = None
@@ -92,7 +92,7 @@ def predict_netmhcii_binding(job, peptfile, allele, univ_options):
                   '-f', input_files['peptfile.faa']]
     # netMHC writes a lot of useless stuff to sys.stdout so we open /dev/null and dump output there.
     with open(os.devnull, 'w') as output_catcher:
-        docker_call(tool='netmhciipan:final', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='netmhciipan:3.1', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=output_catcher)
     output_file = job.fileStore.writeGlobalFile('/'.join([work_dir, 'predictions.tsv']))
     return output_file, 'netMHCIIpan'

src/protect/common.py

@@ -354,7 +354,7 @@ def bam2fastq(bamfile, univ_options):
                   ''.join(['F=/data/', base_name, '_1.fastq']),
                   ''.join(['F2=/data/', base_name, '_2.fastq']),
                   ''.join(['FU=/data/', base_name, '_UP.fastq'])]
-    docker_call(tool='picard', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='picard:1.135', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'], java_opts=univ_options['java_Xmx'])
     first_fastq = ''.join([work_dir, '/', base_name, '_1.fastq'])
     assert os.path.exists(first_fastq)

src/protect/expression_profiling/rsem.py

@@ -80,7 +80,7 @@ def run_rsem(job, rna_bam, univ_options, rsem_options):
                   '--no-bam-output',
                   '/'.join([input_files['rsem_index'], 'hg19']),
                   'rsem']
-    docker_call(tool='rsem', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='rsem:1.2.20', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     output_files = {}
     for filename in ('rsem.genes.results', 'rsem.isoforms.results'):

src/protect/haplotyping/phlat.py

@@ -77,7 +77,7 @@ def run_phlat(job, fastqs, sample_type, univ_options, phlat_options):
                   '-e', '/home/phlat-1.0',  # Phlat directory home
                   '-o', '/data',  # Output directory
                   '-p', str(phlat_options['n'])]  # Number of threads
-    docker_call(tool='phlat', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='phlat:1.0', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     output_file = job.fileStore.writeGlobalFile(''.join([work_dir, '/', sample_type, '_HLA.sum']))
     return output_file

src/protect/mutation_annotation/snpeff.py

@@ -66,7 +66,7 @@ def run_snpeff(job, merged_mutation_file, univ_options, snpeff_options):
                   input_files['merged_mutations.vcf']]
     xmx = snpeff_options['java_Xmx'] if snpeff_options['java_Xmx'] else univ_options['java_Xmx']
     with open('/'.join([work_dir, 'mutations.vcf']), 'w') as snpeff_file:
-        docker_call(tool='snpeff', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='snpeff:3.6', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], java_opts=xmx, outfile=snpeff_file)
     export_results(job, snpeff_file.name, univ_options, subfolder='mutations/snpeffed')
     output_file = job.fileStore.writeGlobalFile(snpeff_file.name)

src/protect/mutation_calling/muse.py

@@ -145,7 +145,7 @@ def run_muse_perchrom(job, tumor_bam, normal_bam, univ_options, muse_options, ch
                   '-O', docker_path(output_prefix),
                   input_files['tumor.bam'],
                   input_files['normal.bam']]
-    docker_call(tool='muse', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='muse:1.0rc_submission_b391201', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     outfile = job.fileStore.writeGlobalFile(''.join([output_prefix, '.MuSE.txt']))
     return outfile
@@ -176,7 +176,7 @@ def run_muse_sump_perchrom(job, muse_output, univ_options, muse_options, chrom):
                   '-D', input_files['dbsnp_coding.vcf.gz'],
                   '-E']
 
-    docker_call(tool='muse', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='muse:1.0rc_submission_b391201', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     export_results(job, output_file, univ_options, subfolder='mutations/muse')
     outfile = job.fileStore.writeGlobalFile(output_file)

src/protect/mutation_calling/radia.py

@@ -174,8 +174,8 @@ def run_radia_perchrom(job, bams, univ_options, radia_options, chrom):
                   '--disease', 'CANCER',
                   '-l', 'INFO',
                   '-g', docker_path(radia_log)]
-    docker_call(tool='radia', tool_parameters=parameters, work_dir=work_dir,
-                dockerhub=univ_options['dockerhub'])
+    docker_call(tool='radia:398366ef07b5911d8082ed61cbf03d487a41f286', tool_parameters=parameters,
+                work_dir=work_dir, dockerhub=univ_options['dockerhub'])
     output_file = job.fileStore.writeGlobalFile(radia_output)
     return output_file
 
@@ -230,8 +230,8 @@ def run_filter_radia(job, bams, radia_file, univ_options, radia_options, chrom):
                   '-f', input_files['genome.fa'],
                   '--log=INFO',
                   '-g', docker_path(filterradia_log)]
-    docker_call(tool='filterradia', tool_parameters=parameters,
-                work_dir=work_dir, dockerhub=univ_options['dockerhub'])
+    docker_call(tool='filterradia:398366ef07b5911d8082ed61cbf03d487a41f286',
+                tool_parameters=parameters, work_dir=work_dir, dockerhub=univ_options['dockerhub'])
     output_file = ''.join([work_dir, '/', chrom, '.vcf'])
     os.rename(''.join([work_dir, '/', univ_options['patient'], '_', chrom, '.vcf']), output_file)
     export_results(job, output_file, univ_options, subfolder='mutations/radia')

src/protect/mutation_calling/somaticsniper.py

@@ -165,7 +165,7 @@ def run_somaticsniper_full(job, tumor_bam, normal_bam, univ_options, somaticsnip
                   input_files['tumor.bam'],
                   input_files['normal.bam'],
                   docker_path(output_file)]
-    docker_call(tool='somaticsniper', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='somaticsniper:1.0.4', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     outfile = job.fileStore.writeGlobalFile(output_file)
     return outfile
@@ -205,14 +205,14 @@ def filter_somaticsniper(job, tumor_bam, somaticsniper_output, tumor_pileup, uni
                   '--snp-file', input_files['input.vcf'],
                   '--indel-file', input_files['pileup.txt']]
     # Creates /data/input.vcf.SNPfilter
-    docker_call(tool='somaticsniper-addons', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='somaticsniper-addons:1.0.4', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
 
     # Run prepare_for_readcount.pl
     parameters = ['prepare_for_readcount.pl',
                   '--snp-file', input_files['input.vcf'] + '.SNPfilter']
     # Creates /data/input.vcf.SNPfilter.pos
-    docker_call(tool='somaticsniper-addons', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='somaticsniper-addons:1.0.4', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
 
     # Run  bam-readcount
@@ -223,7 +223,7 @@ def filter_somaticsniper(job, tumor_bam, somaticsniper_output, tumor_pileup, uni
                   input_files['tumor.bam']]
     # Creates the read counts file
     with open(os.path.join(work_dir, 'readcounts.txt'), 'w') as readcounts_file:
-        docker_call(tool='bam-readcount', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='bam-readcount:0.7.4', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'], outfile=readcounts_file)
 
     # Run fpfilter.pl
@@ -232,15 +232,15 @@ def filter_somaticsniper(job, tumor_bam, somaticsniper_output, tumor_pileup, uni
                   '--readcount-file', docker_path(readcounts_file.name)]
 
     # Creates input.vcf.SNPfilter.fp_pass and input.vcf.SNPfilter.fp_fail
-    docker_call(tool='somaticsniper-addons', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='somaticsniper-addons:1.0.4', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
 
     # Run highconfidence.pl
     parameters = ['highconfidence.pl',
                   '--snp-file', input_files['input.vcf'] + '.SNPfilter.fp_pass']
 
     # Creates input.vcf.SNPfilter.fp_pass.hc
-    docker_call(tool='somaticsniper-addons', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='somaticsniper-addons:1.0.4', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
 
     outfile = job.fileStore.writeGlobalFile(os.path.join(os.getcwd(),

src/protect/mutation_calling/strelka.py

@@ -139,7 +139,7 @@ def run_strelka_full(job, tumor_bam, normal_bam, univ_options, strelka_options):
                   input_files['genome.fa'],
                   str(job.cores)
                   ]
-    docker_call(tool='strelka', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='strelka:1.0.15', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     output_dict = {}
     for mutation_type in ['snvs', 'indels']:

src/protect/mutation_translation.py

@@ -60,7 +60,7 @@ def run_transgene(job, snpeffed_file, rna_bam, univ_options, transgene_options):
                   '--rna_file', input_files['rna.bam'],
                   '--prefix', 'transgened',
                   '--pep_lens', '9,10,15']
-    docker_call(tool='transgene', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='transgene:1.0.0', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     output_files = defaultdict()
     for peplen in ['9', '10', '15']:

src/protect/qc/rna.py

@@ -65,7 +65,7 @@ def run_cutadapt(job, fastqs, univ_options, cutadapt_options):
                   '-p', docker_path('rna_cutadapt_2.fastq.gz'),  # Output for R2
                   input_files['rna_1.fastq' + gz],
                   input_files['rna_2.fastq' + gz]]
-    docker_call(tool='cutadapt', tool_parameters=parameters, work_dir=work_dir,
+    docker_call(tool='cutadapt:1.9.1', tool_parameters=parameters, work_dir=work_dir,
                 dockerhub=univ_options['dockerhub'])
     output_files = []
     for fastq_file in ['rna_cutadapt_1.fastq.gz', 'rna_cutadapt_2.fastq.gz']:

src/protect/rankboost.py

@@ -62,7 +62,7 @@ def boost_ranks(job, isoform_expression, merged_mhc_calls, transgene_out, univ_o
                       input_files[''.join([mhc, '_peptides.faa'])],
                       rank_boost_options[''.join([mhc, '_combo'])]
                       ]
-        docker_call(tool='rankboost', tool_parameters=parameters, work_dir=work_dir,
+        docker_call(tool='rankboost:1.0.0', tool_parameters=parameters, work_dir=work_dir,
                     dockerhub=univ_options['dockerhub'])
         mhc_concise = ''.join([work_dir, '/', mhc, '_merged_files_concise_results.tsv'])
         mhc_detailed = ''.join([work_dir, '/', mhc, '_merged_files_detailed_results.tsv'])