def run(
self, network, antecedents, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
MAX_RAM = 64 # maximum amount of ram to use in Gb.
bam_node, ref_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
jobs = [] # list of (in_filename, log_filename, out_filename)
for in_filename in bam_filenames:
p, f = os.path.split(in_filename)
s, ext = os.path.splitext(f)
log_filename = os.path.join(out_path, "%s.log" % s)
out_filename = os.path.join(out_path, f)
x = in_filename, log_filename, out_filename
jobs.append(x)
# java -Xmx5g -jar /usr/local/bin/GATK/GenomeAnalysisTK.jar
# -T SplitNCigarReads -R ../hg19.fa -I $i -o $j
# -rf ReassignOneMappingQuality -RMQF 255 -RMQT 60
# -U ALLOW_N_CIGAR_READS
# Start with 5 Gb RAM.
commands = make_commands(jobs, ref.fasta_file_full, 5)
nc = mlib.calc_max_procs_from_ram(5, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["commands"] = commands
metadata["num_procs"] = nc
# If any of the analyses didn't finish, try again with more
# RAM.
jobs2 = []
for x in jobs:
in_filename, log_filename, out_filename = x
if filelib.exists_nz(out_filename):
continue
jobs2.append(x)
if jobs2:
commands = make_commands(jobs2, ref.fasta_file_full, MAX_RAM)
nc = mlib.calc_max_procs_from_ram(MAX_RAM, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["commands"] += commands
# Make sure the analysis completed successfully.
out_filenames = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(out_filenames)
return metadata
def run(
self, network, in_data, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import config
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
bam_path = in_data.identifier
assert os.path.exists(bam_path)
assert os.path.isdir(bam_path)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "samtools %s" % alignlib.get_samtools_version()
# Find all the BAM files.
bam_filenames = filelib.list_files_in_path(
bam_path, endswith=".bam", case_insensitive=True)
jobs = [] # list of in_filename, out_filename
for in_filename in bam_filenames:
p, f = os.path.split(in_filename)
out_filename = os.path.join(out_path, f)
assert not os.path.exists(out_filename)
x = in_filename, out_filename
jobs.append(x)
# Symlink the BAM files to the output path.
for x in jobs:
in_filename, out_filename = x
os.symlink(in_filename, out_filename)
# Index each of the files.
sq = parallel.quote
samtools = filelib.which_assert(config.samtools)
commands = []
for x in jobs:
in_filename, out_filename = x
cmd = [
sq(samtools),
"index",
sq(out_filename),
]
x = " ".join(cmd)
commands.append(x)
metadata["commands"] = commands
parallel.pshell(commands, max_procs=num_cores, path=out_path)
# TODO: Check for output files.
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils
bam_node, ref_node = antecedents
#in_filenames = filelib.list_files_in_path(
# bam_node.identifier, endswith=".bam", case_insensitive=True)
in_filenames = module_utils.find_bam_files(bam_node.identifier)
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
# java -Xmx5g -jar /usr/local/bin/picard/picard.jar ReorderSam \
# I=<input.bam> O=<output.bam> REFERENCE=ucsc.hg19.fasta
picard_jar = alignlib.find_picard_jar("picard")
jobs = [] # list of (in_filename, out_filename)
for in_filename in in_filenames:
p, f = os.path.split(in_filename)
out_filename = os.path.join(out_path, f)
x = in_filename, out_filename
jobs.append(x)
# Make a list of commands.
sq = parallel.quote
commands = []
for x in jobs:
in_filename, out_filename = x
x = [
"java",
"-Xmx5g",
"-jar",
sq(picard_jar),
"ReorderSam",
"I=%s" % sq(in_filename),
"O=%s" % sq(out_filename),
"REFERENCE=%s" % ref.fasta_file_full,
]
x = " ".join(x)
commands.append(x)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
for x in jobs:
in_filename, out_filename = x
filelib.assert_exists_nz(out_filename)
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import parallel
from genomicode import alignlib
from genomicode import filelib
from Betsy import module_utils as mlib
bam_node, ref_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "samtools %s" % alignlib.get_samtools_version()
# list of (in_filename, err_filename, out_filename)
jobs = []
for in_filename in bam_filenames:
p, f = os.path.split(in_filename)
sample, ext = os.path.splitext(f)
err_filename = os.path.join(out_path, "%s.log" % sample)
out_filename = os.path.join(out_path, "%s.pileup" % sample)
x = in_filename, err_filename, out_filename
jobs.append(x)
# samtools mpileup -f [reference sequence] [BAM file(s)]
# > myData.mpileup
samtools = mlib.findbin("samtools")
sq = mlib.sq
commands = []
for x in jobs:
in_filename, err_filename, out_filename = x
x = [
sq(samtools),
"mpileup",
"-f",
sq(ref.fasta_file_full),
]
x.append(sq(in_filename))
x = " ".join(map(str, x))
x = "%s 2> %s 1> %s" % (x, err_filename, out_filename)
commands.append(x)
parallel.pshell(commands, max_procs=num_cores)
metadata["num_cores"] = num_cores
metadata["commands"] = commands
x = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(x)
return metadata
def run(self, network, in_data, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from Betsy import module_utils as mlib
sam_filenames = mlib.find_sam_files(in_data.identifier)
assert sam_filenames, "No .sam files."
filelib.safe_mkdir(out_path)
metadata = {}
samtools = mlib.findbin("samtools")
jobs = [] # list of (sam_filename, bam_filename)
for sam_filename in sam_filenames:
p, f = os.path.split(sam_filename)
assert f.endswith(".sam")
f = f.replace(".sam", ".bam")
bam_filename = os.path.join(out_path, f)
x = sam_filename, bam_filename
jobs.append(x)
# Make a list of samtools commands.
sq = parallel.quote
commands = []
for x in jobs:
sam_filename, bam_filename = x
# samtools view -bS -o <bam_filename> <sam_filename>
x = [
sq(samtools),
"view",
"-bS",
"-o",
sq(bam_filename),
sq(sam_filename),
]
x = " ".join(x)
commands.append(x)
metadata["commands"] = commands
metadata["num_cores"] = num_cores
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
x = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(x)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import parallel
from genomicode import filelib
from genomicode import alignlib
from Betsy import module_utils as mlib
fastq_node, sample_node, reference_node = antecedents
fastq_files = mlib.find_merged_fastq_files(sample_node.identifier,
fastq_node.identifier)
ref = alignlib.create_reference_genome(reference_node.identifier)
assert os.path.exists(ref.fasta_file_full)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "bowtie2 %s" % alignlib.get_bowtie2_version()
# Make a list of the jobs to run.
jobs = []
for x in fastq_files:
sample, pair1, pair2 = x
sam_filename = os.path.join(out_path, "%s.sam" % sample)
log_filename = os.path.join(out_path, "%s.log" % sample)
x = sample, pair1, pair2, sam_filename, log_filename
jobs.append(x)
sq = mlib.sq
commands = []
for x in jobs:
sample, pair1, pair2, sam_filename, log_filename = x
nc = max(1, num_cores / len(jobs))
x = alignlib.make_bowtie2_command(ref.fasta_file_full,
pair1,
fastq_file2=pair2,
sam_file=sam_filename,
num_threads=nc)
x = "%s >& %s" % (x, sq(log_filename))
commands.append(x)
metadata["commands"] = commands
metadata["num_cores"] = num_cores
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
x = [x[-2] for x in jobs]
filelib.assert_exists_nz_many(x)
return metadata
def run(self, network, in_data, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils
vcf_node = in_data
vcf_filenames = filelib.list_files_in_path(vcf_node.identifier,
endswith=".vcf")
assert vcf_filenames, "No .vcf files."
filelib.safe_mkdir(out_path)
buildver = module_utils.get_user_option(user_options,
"buildver",
allowed_values=["hg19"],
not_empty=True)
jobs = [] # list of (in_filename, log_filename, out_filestem)
for in_filename in vcf_filenames:
# Annovar takes a filestem, without the ".vcf".
p, f = os.path.split(in_filename)
f, exp = os.path.splitext(f)
log_filename = os.path.join(out_path, "%s.log" % f)
out_filestem = os.path.join(out_path, f)
x = in_filename, log_filename, out_filestem
jobs.append(x)
# Make a list of commands.
commands = []
for x in jobs:
in_filename, log_filename, out_filestem = x
x = alignlib.make_annovar_command(in_filename, log_filename,
out_filestem, buildver)
commands.append(x)
#for x in commands:
# print x
#import sys; sys.exit(0)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
x = [x[-1] for x in jobs] # out_filestems
x = ["%s.%s_multianno.vcf" % (x, buildver) for x in x]
filelib.assert_exists_nz_many(x)
def run_many_pybinreg(jobs, num_procs):
# jobs should be a list of cmd, outpath, outfile.
from genomicode import parallel
commands = []
for x in jobs:
cmd, outpath, outfile = x
if not os.path.exists(outpath):
os.mkdir(outpath)
cmd = "%s >& %s" % (cmd, outfile)
commands.append(cmd)
parallel.pshell(commands, max_procs=num_procs)
for x in jobs:
cmd, outpath, outfile = x
check_pybinreg(outpath, outfile, cmd)
def _run_genomecov(jobs, reference_file, num_cores):
from genomicode import parallel
from genomicode import filelib
from genomicode import ngslib
# Set up the commands to run.
commands = []
for x in jobs:
x = ngslib.make_bedtools_genomecov_command(x.bam_filename,
reference_file,
x.genomecov_filename)
commands.append(x)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
x = [x.genomecov_filename for x in jobs]
filelib.assert_exists_nz_many(x)
return commands
def run(self, network, in_data, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from Betsy import module_utils as mlib
filenames = mlib.find_fastq_files(in_data.identifier)
assert filenames, "FASTQ files not found: %s" % in_data.identifier
filelib.safe_mkdir(out_path)
metadata = {}
fastqc = mlib.findbin("fastqc")
fastqc_q = parallel.quote(fastqc)
commands = [
"%s --outdir=%s --extract %s" % (fastqc_q, out_path, x)
for x in filenames
]
metadata["commands"] = commands
metadata["num_cores"] = num_cores
#commands = ["ls > %s" % x for x in filenames]
parallel.pshell(commands, max_procs=num_cores)
# Fastqc generates files:
# <file>_fastqc/
# <file>_fastqc.zip
# The contents of the .zip file are identical to the directories.
# If this happens, then delete the .zip files because they are
# redundant.
files = os.listdir(out_path)
filenames = [os.path.join(out_path, x) for x in files]
for filename in filenames:
zip_filename = "%s.zip" % filename
if os.path.exists(zip_filename):
os.unlink(zip_filename)
def run(
self, network, antecedents, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_node, nc_node, ref_node, interval_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
nc_match = mlib.read_normal_cancer_file(nc_node.identifier)
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.assert_exists_nz(interval_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# TODO: Figure out MuTect version.
# Make sure intervals file ends with:
# .bed, .list, .picard, .interval_list, or .intervals
x, x, ext = mlib.splitpath(interval_node.identifier)
assert ext in [
".bed", ".list", ".picard", ".interval_list", ".intervals"]
cosmic_file = mlib.get_user_option(
user_options, "mutect_cosmic_vcf", not_empty=True, check_file=True)
dbsnp_file = mlib.get_user_option(
user_options, "mutect_dbsnp_vcf", not_empty=True, check_file=True)
# sample -> bam filename
sample2bamfile = mlib.root2filename(bam_filenames)
# Make sure files exist for all the samples.
mlib.assert_normal_cancer_samples(nc_match, sample2bamfile)
# list of (cancer_sample, normal_bamfile, tumor_bamfile, call_outfile,
# coverage_outfile, vcf_outfile, logfile)
opj = os.path.join
jobs = []
for (normal_sample, cancer_sample) in nc_match:
normal_bamfile = sample2bamfile[normal_sample]
cancer_bamfile = sample2bamfile[cancer_sample]
path, sample, ext = mlib.splitpath(cancer_bamfile)
call_outfile = opj(out_path, "%s.call_stats.out" % sample)
cov_outfile = opj(out_path, "%s.coverage.wig.txt" % sample)
raw_vcf_outfile = opj(out_path, "%s.vcf.raw" % sample)
vcf_outfile = opj(out_path, "%s.vcf" % sample)
log_outfile = opj(out_path, "%s.log" % sample)
x = normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
call_outfile, cov_outfile, raw_vcf_outfile, vcf_outfile, \
log_outfile
jobs.append(x)
# java -Xmx2g -jar muTect.jar
# --analysis_type MuTect
# --reference_sequence <reference>
# --cosmic <cosmic.vcf>
# --dbsnp <dbsnp.vcf>
# --intervals <intervals_to_process>
# --input_file:normal <normal.bam>
# --input_file:tumor <tumor.bam>
# --out <call_stats.out>
# --coverage_file <coverage.wig.txt>
# Generate the commands.
sq = mlib.sq
commands = []
for x in jobs:
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
call_outfile, cov_outfile, raw_vcf_outfile, vcf_outfile, \
log_outfile = x
UNHASHABLE = [
("input_file:normal", sq(normal_bamfile)),
("input_file:tumor", sq(cancer_bamfile)),
]
x = alignlib.make_MuTect_command(
analysis_type="MuTect",
reference_sequence=sq(ref.fasta_file_full),
cosmic=sq(cosmic_file),
dbsnp=sq(dbsnp_file),
intervals=sq(interval_node.identifier),
out=sq(call_outfile),
coverage_file=sq(cov_outfile),
vcf=sq(raw_vcf_outfile),
_UNHASHABLE=UNHASHABLE,
)
x = "%s >& %s" % (x, log_outfile)
commands.append(x)
assert len(commands) == len(jobs)
nc = mlib.calc_max_procs_from_ram(15, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["num_cores"] = nc
metadata["commands"] = commands
# Make sure log files have no errors. Check the log files
# before the VCF files. If there's an error, the VCF files
# may not be created.
# ##### ERROR -------------------------------------------------------
# ##### ERROR A GATK RUNTIME ERROR has occurred (version 2.2-25-g2a68
# ##### ERROR
# ##### ERROR Please visit the wiki to see if this is a known problem
# ##### ERROR If not, please post the error, with stack trace, to the
# ##### ERROR Visit our website and forum for extensive documentation
# ##### ERROR commonly asked questions http://www.broadinstitute.org/
# ##### ERROR
# ##### ERROR MESSAGE: java.lang.IllegalArgumentException: Comparison
# ##### ERROR -------------------------------------------------------
for i, x in enumerate(jobs):
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
call_outfile, cov_outfile, raw_vcf_outfile, vcf_outfile, \
log_outfile = x
# Pull out the error lines.
x = [x for x in open(log_outfile)]
x = [x for x in x if x.startswith("##### ERROR")]
x = "".join(x)
msg = "MuTect error [%s]:\n%s\n%s" % (
cancer_sample, commands[i], x)
assert not x, msg
# Make sure output VCF files exist.
x = [x[6] for x in jobs]
filelib.assert_exists_many(x)
# Fix the files.
for x in jobs:
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
call_outfile, cov_outfile, raw_vcf_outfile, vcf_outfile, \
log_outfile = x
alignlib.clean_mutect_vcf(
normal_bamfile, cancer_bamfile, normal_sample, cancer_sample,
raw_vcf_outfile, vcf_outfile)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import parallel
from genomicode import filelib
from genomicode import alignlib
from Betsy import module_utils as mlib
fastq_node, group_node, reference_node = antecedents
fastq_files = mlib.find_merged_fastq_files(group_node.identifier,
fastq_node.identifier)
assert fastq_files, "No FASTQ files found."
ref = alignlib.create_reference_genome(reference_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "bwa %s" % alignlib.get_bwa_version()
# Make sure no duplicate samples.
x1 = [x[0] for x in fastq_files]
x2 = {}.fromkeys(x1).keys()
assert len(x1) == len(x2), "dup sample"
# Make a list of all FASTQ files to align.
fastq_filenames = []
for x in fastq_files:
sample, pair1, pair2 = x
assert pair1
fastq_filenames.append(pair1)
if pair2:
fastq_filenames.append(pair2)
# Make a list of all the jobs to do.
jobs = [] # list of (fastq_filename, sai_filename)
for in_filename in fastq_filenames:
in_path, in_file = os.path.split(in_filename)
x = in_file
if x.lower().endswith(".fq"):
x = x[:-3]
elif x.lower().endswith(".fastq"):
x = x[:-6]
sai_filename = os.path.join(out_path, "%s.sai" % x)
log_filename = os.path.join(out_path, "%s.log" % x)
x = in_filename, sai_filename, log_filename
jobs.append(x)
# Calculate the number of threads per job.
nc = max(1, num_cores / len(jobs))
# Make the bwa commands.
commands = []
for x in jobs:
fastq_filename, sai_filename, log_filename = x
x = alignlib.make_bwa_aln_command(ref.fasta_file_full,
fastq_filename,
sai_filename,
log_filename,
num_threads=nc)
commands.append(x)
metadata["commands"] = commands
metadata["num cores"] = num_cores
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
for x in jobs:
in_filename, sai_filename, log_filename = x
assert filelib.exists_nz(sai_filename), \
"Missing: %s" % sai_filename
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
# For debugging.
RUN_VARIANT_CALLING = True
FILTER_CALLS = True
MERGE_CALLS = True
FIX_VCF_FILES = True
dna_bam_node, rna_bam_node, nc_node, ref_node = antecedents
dna_bam_filenames = mlib.find_bam_files(dna_bam_node.identifier)
assert dna_bam_filenames, "No DNA .bam files."
rna_bam_filenames = mlib.find_bam_files(rna_bam_node.identifier)
assert rna_bam_filenames, "No RNA .bam files."
nc_match = mlib.read_normal_cancer_file(nc_node.identifier)
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "Radia %s" % alignlib.get_radia_version()
## Make sure the BAM files do not contain spaces in the
## filenames. Radia doesn't work well with spaces.
#filenames = dna_bam_filenames + rna_bam_filenames
#has_spaces = []
#for filename in filenames:
# if filename.find(" ") >= 0:
# has_spaces.append(filename)
#x = has_spaces
#if len(x) > 5:
# x = x[:5] + ["..."]
#x = ", ".join(x)
#msg = "Radia breaks if there are spaces in filenames: %s" % x
#assert not has_spaces, msg
# sample -> bam filename
dnasample2bamfile = mlib.root2filename(dna_bam_filenames)
rnasample2bamfile = mlib.root2filename(rna_bam_filenames)
# Make sure files exist for all the samples. The DNA-Seq
# should have both normal and cancer. RNA is not needed for
# normal sample.
mlib.assert_normal_cancer_samples(nc_match, dnasample2bamfile)
mlib.assert_normal_cancer_samples(nc_match,
rnasample2bamfile,
ignore_normal_sample=True)
# Make sure Radia and snpEff are configured.
radia_genome_assembly = mlib.get_user_option(user_options,
"radia_genome_assembly",
not_empty=True)
assert radia_genome_assembly == "hg19", "Only hg19 handled."
snp_eff_genome = mlib.get_user_option(user_options,
"snp_eff_genome",
not_empty=True)
radia_path = mlib.get_config("radia_path", assert_exists=True)
snp_eff_path = mlib.get_config("snp_eff_path", assert_exists=True)
radia_files = get_radia_files(radia_path, radia_genome_assembly)
# Make a list of the chromosomes to use. Pick an arbitrarily
# BAM file. Look at only the chromosomes that are present in
# all files.
all_bamfiles = dnasample2bamfile.values() + rnasample2bamfile.values()
chroms = list_common_chromosomes(all_bamfiles)
assert chroms, "No chromosomes found in all files."
# Only use the chromosomes that can be filtered by Radia.
chroms = filter_radia_chromosomes(chroms, radia_files)
# Make output directories.
radia_outpath = "radia1.tmp"
filter_outpath = "radia2.tmp"
merge_outpath = "radia3.tmp"
if not os.path.exists(radia_outpath):
os.mkdir(radia_outpath)
if not os.path.exists(filter_outpath):
os.mkdir(filter_outpath)
if not os.path.exists(merge_outpath):
os.mkdir(merge_outpath)
# Steps:
# 1. Call variants (radia.py)
# -o <file.vcf>
# 2. Filter variants (filterRadia.py)
# <outpath>
# Creates a file: <filter_outpath>/<patient_id>_chr<chrom>.vcf
# 3. Merge (mergeChroms.py)
# Takes as input: <filter_outpath>
# Produces: <merge_outpath>/<patient_id>.vcf
# list of (normal_sample, cancer_sample, chrom,
# normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile,
# radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile,
# final_vcf_outfile,
# radia_logfile, filter_logfile, merge_logfile)
opj = os.path.join
jobs = []
for i, (normal_sample, cancer_sample) in enumerate(nc_match):
normal_bamfile = dnasample2bamfile[normal_sample]
dna_tumor_bamfile = dnasample2bamfile[cancer_sample]
rna_tumor_bamfile = rnasample2bamfile[cancer_sample]
merge_vcf_outfile = opj(merge_outpath, "%s.vcf" % cancer_sample)
merge_logfile = opj(merge_outpath, "%s.log" % cancer_sample)
final_vcf_outfile = opj(out_path, "%s.vcf" % cancer_sample)
for chrom in chroms:
radia_vcf_outfile = opj(
radia_outpath, "%s_chr%s.vcf" % (cancer_sample, chrom))
filter_vcf_outfile = opj(
filter_outpath, "%s_chr%s.vcf" % (cancer_sample, chrom))
radia_logfile = opj(radia_outpath,
"%s_chr%s.log" % (cancer_sample, chrom))
filter_logfile = opj(filter_outpath,
"%s_chr%s.log" % (cancer_sample, chrom))
x = normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile
jobs.append(x)
# Since Radia doesn't work well if there are spaces in the
# filenames, symlink these files here to guarantee that there
# are no spaces.
normal_path = "normal.bam"
dna_path = "dna.bam"
rna_path = "rna.bam"
if not os.path.exists(normal_path):
os.mkdir(normal_path)
if not os.path.exists(dna_path):
os.mkdir(dna_path)
if not os.path.exists(rna_path):
os.mkdir(rna_path)
for i, x in enumerate(jobs):
normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile = x
x1 = hash_and_symlink_bamfile(normal_bamfile, normal_path)
x2 = hash_and_symlink_bamfile(dna_tumor_bamfile, dna_path)
x3 = hash_and_symlink_bamfile(rna_tumor_bamfile, rna_path)
clean_normal, clean_dna, clean_rna = x1, x2, x3
x = normal_sample, cancer_sample, chrom, \
clean_normal, clean_dna, clean_rna, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile
jobs[i] = x
# Generate the commands for doing variant calling.
python = mlib.get_config("python", which_assert_file=True)
# filterRadia.py calls the "blat" command, and there's no way
# to set the path. Make sure "blat" is executable.
if not filelib.which("blat"):
# Find "blat" in the configuration and add it to the path.
x = mlib.get_config("blat", which_assert_file=True)
path, x = os.path.split(x)
if os.environ["PATH"]:
path = "%s:%s" % (os.environ["PATH"], path)
os.environ["PATH"] = path
# Make sure it's findable now.
filelib.which_assert("blat")
# STEP 1. Call variants with radia.py.
# python radia.py test31 5 \
# -n bam04/PIM001_G.bam \
# -t bam04/196B-MG.bam \
# -r bam34/196B-MG.bam \
# -f genomes/Broad.hg19/Homo_sapiens_assembly19.fa \
# -o test32.vcf
# --dnaTumorMitochon MT \
# --rnaTumorMitochon MT \
sq = mlib.sq
commands = []
for x in jobs:
normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile = x
x = [
sq(python),
sq(radia_files.radia_py),
cancer_sample,
chrom,
"-n",
sq(normal_bamfile),
"-t",
sq(dna_tumor_bamfile),
"-r",
sq(rna_tumor_bamfile),
"-f",
sq(ref.fasta_file_full),
"-o",
radia_vcf_outfile,
]
if "MT" in chroms:
x += [
"--dnaNormalMitochon MT",
"--dnaTumorMitochon MT",
"--rnaTumorMitochon MT",
]
x = " ".join(x)
x = "%s >& %s" % (x, radia_logfile)
commands.append(x)
assert len(commands) == len(jobs)
# Only uses ~200 Mb of ram.
if RUN_VARIANT_CALLING:
parallel.pshell(commands, max_procs=num_cores)
metadata["num_cores"] = num_cores
metadata["commands"] = commands
# Make sure log files are empty.
logfiles = [x[10] for x in jobs]
filelib.assert_exists_z_many(logfiles)
# STEP 2. Filter variants with filterRadia.py.
commands = []
for x in jobs:
normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile = x
x = [
sq(python),
sq(radia_files.filterRadia_py),
cancer_sample,
chrom,
sq(radia_vcf_outfile),
sq(filter_outpath),
sq(radia_files.scripts_dir),
"-b",
sq(radia_files.blacklist_dir),
"-d",
sq(radia_files.snp_dir),
"-r",
sq(radia_files.retro_dir),
"-p",
sq(radia_files.pseudo_dir),
"-c",
sq(radia_files.cosmic_dir),
"-t",
sq(radia_files.target_dir),
"-s",
sq(snp_eff_path),
"-e",
snp_eff_genome,
"--rnaGeneBlckFile",
sq(radia_files.rnageneblck_file),
"--rnaGeneFamilyBlckFile",
sq(radia_files.rnagenefamilyblck_file),
]
x = " ".join(x)
x = "%s >& %s" % (x, filter_logfile)
commands.append(x)
assert len(commands) == len(jobs)
# Sometimes samtools crashes in the middle of a run. Detect
# this case, and re-run the analysis if needed.
assert len(commands) == len(jobs)
py_commands = []
for x, cmd in zip(jobs, commands):
normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile = x
args = cmd, cancer_sample, chrom, filter_logfile
x = _run_filterRadia_with_restart, args, {}
py_commands.append(x)
# Takes ~10 Gb each.
nc = mlib.calc_max_procs_from_ram(25, upper_max=num_cores)
if FILTER_CALLS:
parallel.pyfun(py_commands, num_procs=nc)
metadata["commands"] += commands
# Make sure log files are empty.
logfiles = [x[11] for x in jobs]
filelib.assert_exists_z_many(logfiles)
# Make sure filter_vcf_outfile exists.
outfiles = [x[7] for x in jobs]
filelib.assert_exists_nz_many(outfiles)
# STEP 3. Merge the results.
commands = []
for x in jobs:
normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile = x
# python /usr/local/radia/scripts/mergeChroms.py 196B-MG \
# radia2.tmp/ radia3.tmp
# The "/" after radia2.tmp is important. If not given,
# will generate some files with only newlines.
fo = filter_outpath
if not fo.endswith("/"):
fo = "%s/" % fo
x = [
sq(python),
sq(radia_files.mergeChroms_py),
cancer_sample,
fo,
merge_outpath,
]
x = " ".join(x)
x = "%s >& %s" % (x, merge_logfile)
commands.append(x)
assert len(commands) == len(jobs)
# Since the chromosomes were separated for the previous steps,
# this will generate one merge for each chromosome. This is
# unnecessary, since we only need to merge once per sample.
# Get rid of duplicates.
commands = sorted({}.fromkeys(commands))
if MERGE_CALLS:
parallel.pshell(commands, max_procs=num_cores)
metadata["commands"] += commands
# Make sure log files are empty.
logfiles = [x[12] for x in jobs]
logfiles = sorted({}.fromkeys(logfiles))
filelib.assert_exists_z_many(logfiles)
# Fix the VCF files.
commands = []
for x in jobs:
normal_sample, cancer_sample, chrom, \
normal_bamfile, dna_tumor_bamfile, rna_tumor_bamfile, \
radia_vcf_outfile, filter_vcf_outfile, merge_vcf_outfile, \
final_vcf_outfile, \
radia_logfile, filter_logfile, merge_logfile = x
args = normal_sample, cancer_sample, \
merge_vcf_outfile, final_vcf_outfile
x = alignlib.clean_radia_vcf, args, {}
commands.append(x)
if FIX_VCF_FILES:
parallel.pyfun(commands, num_procs=num_cores)
# Make sure output VCF files exist.
x = [x[9] for x in jobs]
filelib.assert_exists_nz_many(x)
return metadata
def run(
self, network, in_data, out_attributes, user_options, num_cores,
out_path):
import os
import shutil
from genomicode import parallel
from genomicode import filelib
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_filenames = mlib.find_bam_files(in_data.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "bam2fastx (unknown version)"
# Somehow bam2fastx doesn't work if there are spaces in the
# filename. Make a temporary filename with no spaces, and
# then rename it later.
# Actually, may not be bam2fastx's fault.
jobs = []
for i, bam_filename in enumerate(bam_filenames):
p, f, e = mlib.splitpath(bam_filename)
#bai_filename = alignlib.find_bai_file(bam_filename)
#assert bai_filename, "Missing index for: %s" % bam_filename
#temp_bam_filename = "%d.bam" % i
#temp_bai_filename = "%d.bam.bai" % i
#temp_fa_filename = "%d.fa" % i
fa_filename = os.path.join(out_path, "%s.fa" % f)
x = filelib.GenericObject(
bam_filename=bam_filename,
#bai_filename=bai_filename,
#temp_bam_filename=temp_bam_filename,
#temp_bai_filename=temp_bai_filename,
#temp_fa_filename=temp_fa_filename,
fa_filename=fa_filename)
jobs.append(x)
bam2fastx = mlib.findbin("bam2fastx")
# Link all the bam files.
#for j in jobs:
# assert not os.path.exists(j.temp_bam_filename)
# #assert not os.path.exists(j.temp_bai_filename)
# os.symlink(j.bam_filename, j.temp_bam_filename)
# #os.symlink(j.bai_filename, j.temp_bai_filename)
commands = []
for j in jobs:
# bam2fastx -A --fasta -o rqc14.fa rqc11.bam
x = [
mlib.sq(bam2fastx),
"-A",
"--fasta",
#"-o", mlib.sq(j.temp_fa_filename),
#mlib.sq(j.temp_bam_filename),
"-o", mlib.sq(j.fa_filename),
mlib.sq(j.bam_filename),
]
x = " ".join(x)
commands.append(x)
metadata["commands"] = commands
metadata["num_cores"] = num_cores
parallel.pshell(commands, max_procs=num_cores)
#for j in jobs:
# # Move the temporary files to the final location.
# shutil.move(j.temp_fa_filename, j.fa_filename)
# # Remove the link to the BAM file.
# os.unlink(j.temp_bam_filename)
x = [j.fa_filename for x in jobs]
filelib.assert_exists_nz_many(x)
return metadata
def run(self, network, in_data, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from genomicode import config
from Betsy import module_utils as mlib
mpileup_node = in_data
mpileup_filenames = filelib.list_files_in_path(mpileup_node.identifier,
endswith=".pileup")
assert mpileup_filenames, "No .pileup files."
#nc_match = mlib.read_normal_cancer_file(nc_node.identifier)
#ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
# Figure out whether the purpose is to get coverage. Change
# the parameters if it is.
assert "vartype" in out_attributes
vartype = out_attributes["vartype"]
assert vartype in ["snp", "indel"]
tool = "mpileup2snp"
if vartype == "indel":
tool = "mpileup2indel"
# list of (sample, in_filename, tmp1_filename, tmp2_filename,
# out_filename)
jobs = []
for in_filename in mpileup_filenames:
p, sample, ext = mlib.splitpath(in_filename)
tmp1_filename = os.path.join(out_path, "%s.tmp1" % sample)
tmp2_filename = os.path.join(out_path, "%s.tmp2" % sample)
out_filename = os.path.join(out_path, "%s.vcf" % sample)
x = sample, in_filename, tmp1_filename, tmp2_filename, out_filename
jobs.append(x)
# VarScan will generate a "Parsing Exception" if there are 0
# reads in a location. Filter those out.
sq = parallel.quote
commands = []
for x in jobs:
sample, in_filename, tmp1_filename, tmp2_filename, out_filename = x
x = "awk -F'\t' '$4 != 0 {print}' %s > %s" % (in_filename,
tmp1_filename)
commands.append(x)
parallel.pshell(commands, max_procs=num_cores)
x = [x[2] for x in jobs]
filelib.assert_exists_nz_many(x)
# java -jar /usr/local/bin/VarScan.jar <tool> $i --output_vcf 1 > $j
varscan = filelib.which_assert(config.varscan_jar)
# Make a list of commands.
commands = []
for x in jobs:
sample, in_filename, tmp1_filename, tmp2_filename, out_filename = x
x = [
"java",
"-jar",
sq(varscan),
tool,
tmp1_filename,
"--p-value",
0.05,
"--output-vcf",
1,
]
x = " ".join(map(str, x))
x = "%s >& %s" % (x, tmp2_filename)
commands.append(x)
#for x in commands:
# print x
#import sys; sys.exit(0)
parallel.pshell(commands, max_procs=num_cores)
x = [x[3] for x in jobs]
filelib.assert_exists_nz_many(x)
# Clean up the VCF files. VarScan leaves extraneous lines
# there.
for x in jobs:
sample, in_filename, tmp1_filename, tmp2_filename, out_filename = x
alignlib.clean_varscan_vcf(sample, tmp2_filename, out_filename)
x = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(x)
# The tmp files are really big. Don't save those.
for x in jobs:
sample, in_filename, tmp1_filename, tmp2_filename, out_filename = x
filelib.safe_unlink(tmp1_filename)
filelib.safe_unlink(tmp2_filename)
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_node, nc_node, ref_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
nc_match = mlib.read_normal_cancer_file(nc_node.identifier)
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "MuSE %s" % alignlib.get_muse_version()
wgs_or_wes = mlib.get_user_option(user_options,
"wgs_or_wes",
not_empty=True,
allowed_values=["wgs", "wes"])
dbsnp_file = mlib.get_user_option(user_options,
"muse_dbsnp_vcf",
not_empty=True,
check_file=True)
# Make sure dbsnp_file is compressed and indexed.
assert dbsnp_file.endswith(".vcf.gz"), \
"muse_dbsnp_vcf must be bgzip compressed."
x = "%s.tbi" % dbsnp_file
assert filelib.exists_nz(x), "muse_dbsnp_vcf must be tabix indexed."
# sample -> bam filename
sample2bamfile = mlib.root2filename(bam_filenames)
# Make sure files exist for all the samples.
mlib.assert_normal_cancer_samples(nc_match, sample2bamfile)
# list of (normal_sample, cancer_sample, normal_bamfile, tumor_bamfile,
# muse_call_stem, muse_call_file, raw_vcf_outfile, vcf_outfile,
# logfile1, logfile2)
opj = os.path.join
jobs = []
for (normal_sample, cancer_sample) in nc_match:
normal_bamfile = sample2bamfile[normal_sample]
cancer_bamfile = sample2bamfile[cancer_sample]
path, sample, ext = mlib.splitpath(cancer_bamfile)
muse_call_stem = opj(out_path, "%s.call" % cancer_sample)
muse_call_file = "%s.MuSE.txt" % muse_call_stem
raw_vcf_outfile = opj(out_path, "%s.vcf.raw" % cancer_sample)
vcf_outfile = opj(out_path, "%s.vcf" % cancer_sample)
log_outfile1 = opj(out_path, "%s.call.log" % cancer_sample)
log_outfile2 = opj(out_path, "%s.sump.log" % cancer_sample)
x = normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
muse_call_stem, muse_call_file, raw_vcf_outfile, vcf_outfile, \
log_outfile1, log_outfile2
jobs.append(x)
# Generate the commands.
# MuSE call -O test11 -f genomes/Broad.hg19/Homo_sapiens_assembly19.fa\
# bam04/196B-MG.bam bam04/PIM001_G.bam
# MuSE sump -I test11.MuSE.txt -E -O test12.vcf \
# -D MuSE/dbsnp_132_b37.leftAligned.vcf.gz
MuSE = mlib.findbin("muse")
sq = mlib.sq
commands = []
for x in jobs:
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
muse_call_stem, muse_call_file, raw_vcf_outfile, vcf_outfile, \
log_outfile1, log_outfile2 = x
x = [
sq(MuSE),
"call",
"-O",
muse_call_stem,
"-f",
sq(ref.fasta_file_full),
cancer_bamfile,
normal_bamfile,
]
x = " ".join(x)
x = "%s >& %s" % (x, log_outfile1)
commands.append(x)
assert len(commands) == len(jobs)
# Not sure about RAM.
nc = mlib.calc_max_procs_from_ram(10, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["num_cores"] = nc
metadata["commands"] = commands
# Make sure the log files have no errors. The files should be
# empty.
log_files = [x[8] for x in jobs]
filelib.assert_exists_z_many(log_files)
# Make sure the call files are created and not empty.
call_files = [x[5] for x in jobs]
filelib.assert_exists_nz_many(call_files)
# Run the "sump" step.
commands = []
for x in jobs:
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
muse_call_stem, muse_call_file, raw_vcf_outfile, vcf_outfile, \
log_outfile1, log_outfile2 = x
x = [
sq(MuSE),
"sump",
"-I",
sq(muse_call_file),
]
assert wgs_or_wes in ["wgs", "wes"]
if wgs_or_wes == "wgs":
x += ["-G"]
else:
x += ["-E"]
x += [
"-O",
sq(raw_vcf_outfile),
"-D",
sq(dbsnp_file),
]
x = " ".join(x)
x = "%s >& %s" % (x, log_outfile2)
commands.append(x)
assert len(commands) == len(jobs)
# Not sure about RAM.
nc = mlib.calc_max_procs_from_ram(10, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["commands"] = metadata["commands"] + commands
# Make sure the log files have no errors. The files should be
# empty.
log_files = [x[9] for x in jobs]
filelib.assert_exists_z_many(log_files)
# Make sure the raw files are created and not empty.
vcf_files = [x[6] for x in jobs]
filelib.assert_exists_nz_many(vcf_files)
# Fix the files.
commands = [] # Should be python commands.
for x in jobs:
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
muse_call_stem, muse_call_file, raw_vcf_outfile, vcf_outfile, \
log_outfile1, log_outfile2 = x
args = normal_sample, cancer_sample, raw_vcf_outfile, vcf_outfile
x = alignlib.clean_muse_vcf, args, {}
commands.append(x)
parallel.pyfun(commands, num_procs=num_cores)
# Delete the log_outfiles if empty.
for x in jobs:
normal_sample, cancer_sample, normal_bamfile, cancer_bamfile, \
muse_call_stem, muse_call_file, raw_vcf_outfile, vcf_outfile, \
log_outfile1, log_outfile2 = x
if os.path.exists(log_outfile1):
os.unlink(log_outfile1)
if os.path.exists(log_outfile2):
os.unlink(log_outfile2)
# Make sure output VCF files exist.
x = [x[7] for x in jobs]
filelib.assert_exists_many(x)
return metadata
def run(
self, network, antecedents, out_attributes, user_options, num_cores,
out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_node, ref_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# java -jar picard.jar CollectAlignmentSummaryMetrics \
# R=reference_sequence.fasta \
# I=input.bam \
# O=output.txt
opj = os.path.join
jobs = [] # list of filelib.GenericObject
for bam_filename in bam_filenames:
# <in_path>/<sample>.bam
in_path, sample, ext = mlib.splitpath(bam_filename)
assert ext == ".bam"
out_filename = opj(out_path, "%s.alignment_metrics.txt" % sample)
log_filename = opj(out_path, "%s.log" % sample)
x = filelib.GenericObject(
sample=sample,
bam_filename=bam_filename,
out_filename=out_filename,
log_filename=log_filename)
jobs.append(x)
# Make the commands to run picard.
picard_jar = alignlib.find_picard_jar("picard")
sq = parallel.quote
commands = []
for j in jobs:
# Should have better way of getting java path.
cmd = [
"java",
"-Xmx10g",
"-jar", sq(picard_jar), "CollectAlignmentSummaryMetrics",
"I=%s" % sq(j.bam_filename),
"R=%s" % sq(ref.fasta_file_full),
"O=%s" % sq(j.out_filename),
]
cmd = " ".join(cmd)
cmd = "%s >& %s" % (cmd, sq(j.log_filename))
commands.append(cmd)
metadata["commands"] = commands
parallel.pshell(commands, max_procs=num_cores)
x = [x.out_filename for x in jobs]
filelib.assert_exists_nz_many(x)
# Summarize the insert size files.
outfile = opj(out_path, "summary.txt")
_summarize_alignment_summary_metrics(jobs, outfile)
filelib.assert_exists_nz(outfile)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import alignlib
from genomicode import parallel
from genomicode import hashlib
from Betsy import module_utils as mlib
fastq_node, sample_node, strand_node, reference_node = antecedents
fastq_files = mlib.find_merged_fastq_files(sample_node.identifier,
fastq_node.identifier)
assert fastq_files, "I could not find any FASTQ files."
ref = alignlib.create_reference_genome(reference_node.identifier)
stranded = mlib.read_stranded(strand_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
metadata["tool"] = "RSEM %s" % alignlib.get_rsem_version()
# Figure out whether to align to genome or transcriptome.
x = out_attributes["align_to"]
assert x in ["genome", "transcriptome"]
align_to_genome = (x == "genome")
# RSEM makes files:
# <sample_name>.genome.bam
# <sample_name>.transcript.bam
# <sample_name>.genes.results
# <sample_name>.isoforms.results
# <sample_name>.stat
#
# Does not work right if there is a space in the sample name.
# Therefore, give a hashed sample name, and then re-name
# later.
# Make a list of the jobs to run.
jobs = []
for x in fastq_files:
sample, pair1, pair2 = x
sample_h = hashlib.hash_var(sample)
x1, x2, x3 = mlib.splitpath(pair1)
x = "%s%s" % (hashlib.hash_var(x2), x3)
pair1_h = os.path.join(out_path, x)
if pair2:
x1, x2, x3 = mlib.splitpath(pair2)
x = "%s%s" % (hashlib.hash_var(x2), x3)
pair2_h = os.path.join(out_path, x)
results_filename = os.path.join(out_path,
"%s.genes.results" % sample)
log_filename = os.path.join(out_path, "%s.log" % sample)
x = filelib.GenericObject(sample=sample,
sample_h=sample_h,
pair1=pair1,
pair2=pair2,
pair1_h=pair1_h,
pair2_h=pair2_h,
results_filename=results_filename,
log_filename=log_filename)
jobs.append(x)
# Make sure hashed samples are unique.
seen = {}
for j in jobs:
assert j.sample_h not in seen, \
"Dup (%d): %s" % (len(jobs), j.sample_h)
assert j.pair1_h not in seen
assert j.pair2_h not in seen
seen[j.sample_h] = 1
seen[j.pair1_h] = 1
seen[j.pair2_h] = 1
# Symlink the fastq files.
for j in jobs:
os.symlink(j.pair1, j.pair1_h)
if j.pair2:
os.symlink(j.pair2, j.pair2_h)
s2fprob = {
"unstranded": None,
"firststrand": 0.0,
"secondstrand": 1.0,
}
assert stranded.stranded in s2fprob, "Unknown stranded: %s" % \
stranded.stranded
forward_prob = s2fprob[stranded.stranded]
# How much memory for bowtie. May need to increase this if
# there are lots of memory warnings in the log files:
# Warning: Exhausted best-first chunk memory for read
# ST-J00106:110:H5NY5BBXX:6:1101:18203:44675 1:N:0:1/1
# (patid 2076693); skipping read
# Default is 64.
# Seems like too high a value can cause problems.
#chunkmbs = 4*1024 # Generates warnings.
chunkmbs = 512
# Get lots of warnings with bowtie:
# Warning: Detected a read pair whose two mates have different names
# Use STAR aligner instead.
use_STAR = True
sq = parallel.quote
commands = []
for j in jobs:
# Debug: If the results file exists, don't run it again.
if filelib.exists_nz(j.results_filename) and \
filelib.exists(j.log_filename):
continue
# If using the STAR aligner, then most memory efficient
# way is to let STAR take care of the multiprocessing.
nc = max(1, num_cores / len(jobs))
if use_STAR:
nc = num_cores
keywds = {}
if use_STAR:
keywds["align_with_star"] = True
else:
keywds["align_with_bowtie2"] = True
x = alignlib.make_rsem_command(ref.fasta_file_full,
j.sample_h,
j.pair1_h,
fastq_file2=j.pair2_h,
forward_prob=forward_prob,
output_genome_bam=align_to_genome,
bowtie_chunkmbs=chunkmbs,
num_threads=nc,
**keywds)
x = "%s >& %s" % (x, sq(j.log_filename))
commands.append(x)
metadata["commands"] = commands
metadata["num cores"] = num_cores
# Need to run in out_path. Otherwise, files will be everywhere.
nc = num_cores
if use_STAR:
nc = 1
parallel.pshell(commands, max_procs=nc, path=out_path)
# Rename the hashed sample names back to the original unhashed
# ones.
files = os.listdir(out_path)
rename_files = [] # list of (src, dst)
for j in jobs:
if j.sample == j.sample_h:
continue
for f in files:
if not f.startswith(j.sample_h):
continue
src = os.path.join(out_path, f)
x = j.sample + f[len(j.sample_h):]
dst = os.path.join(out_path, x)
rename_files.append((src, dst))
for src, dst in rename_files:
filelib.assert_exists(src)
os.rename(src, dst)
# Delete the symlinked fastq files.
for j in jobs:
filelib.safe_unlink(j.pair1_h)
filelib.safe_unlink(j.pair2_h)
# Make sure the analysis completed successfully.
x1 = [x.results_filename for x in jobs]
x2 = [x.log_filename for x in jobs]
filelib.assert_exists_nz_many(x1 + x2)
return metadata
def get_paired_orientation_bowtie2(
reference_genome, filename1, filename2, outpath=None):
# Return tuple of ("ff", "fr", or "rf"; reads_ns; reads_fr;
# reads_rf; reads_ff).
import os
import shutil
import tempfile
import multiprocessing
#from genomicode import genomelib
from genomicode import alignlib
from genomicode import parallel
# Strategy: run bowtie2 in all orientations. Return the one with
# most reads aligned. Do with a subset of the data, so this
# doesn't take a long time.
# 100 is too low. Gave is wrong result (fr instead of rf) on the
# Thunderbolts miSEQ data. Minimum number that gives right answer
# is 250.
# NUM_READS Time (s) 1 core
# 50 2.4
# 100 2.4
# 250 2.5
# 500 2.7
# 1000 2.9
# 2000 3.3
# 5000 4.6
# 10000 7.8
# 100000 52.6
NUM_READS = 1000
# If outpath is None, then put everything into a temporary
# directory.
path = outpath # where to write the results
tempdir = None # temporary directory to be deleted
try:
if path is None:
tempdir = tempfile.mkdtemp(dir=".")
path = tempdir # write into a temporary directory
#short_filename1 = os.path.join(path, "short_1.fq")
#short_filename2 = os.path.join(path, "short_2.fq")
#copy_fastq(filename1, short_filename1, NUM_READS)
#copy_fastq(filename2, short_filename2, NUM_READS)
sam_ff = os.path.join(path, "orient_ff.sam")
sam_fr = os.path.join(path, "orient_fr.sam")
sam_rf = os.path.join(path, "orient_rf.sam")
sam_ns = os.path.join(path, "orient_ns.sam")
log_ff = os.path.join(path, "orient_ff.log")
log_fr = os.path.join(path, "orient_fr.log")
log_rf = os.path.join(path, "orient_rf.log")
log_ns = os.path.join(path, "orient_ns.log")
nc = multiprocessing.cpu_count()
nc = int(max(nc/4.0, 1))
nc = 1
x1 = alignlib.make_bowtie2_command(
reference_genome, fastq_file1=filename1,
fastq_file2=filename2, sam_file=sam_ff, orientation="ff",
max_reads=NUM_READS, num_threads=nc)
x2 = alignlib.make_bowtie2_command(
reference_genome, fastq_file1=filename1,
fastq_file2=filename2, sam_file=sam_fr, orientation="fr",
max_reads=NUM_READS, num_threads=nc)
x3 = alignlib.make_bowtie2_command(
reference_genome, fastq_file1=filename1,
fastq_file2=filename2, sam_file=sam_rf, orientation="rf",
max_reads=NUM_READS, num_threads=nc)
x4 = alignlib.make_bowtie2_command(
reference_genome, fastq_file1=filename1,
fastq_file2=filename2, sam_file=sam_ns, orientation=None,
max_reads=NUM_READS, num_threads=nc)
x1 += " >& %s" % log_ff
x2 += " >& %s" % log_fr
x3 += " >& %s" % log_rf
x4 += " >& %s" % log_ns
commands = [x1, x2, x3, x4]
parallel.pshell(commands)
# Read the results.
output_ff = alignlib.parse_bowtie2_output(log_ff)
output_fr = alignlib.parse_bowtie2_output(log_fr)
output_rf = alignlib.parse_bowtie2_output(log_rf)
output_ns = alignlib.parse_bowtie2_output(log_ns)
finally:
if tempdir is not None and os.path.exists(tempdir):
shutil.rmtree(tempdir)
reads_ff = output_ff["concordant_reads"]
reads_fr = output_fr["concordant_reads"]
reads_rf = output_rf["concordant_reads"]
reads_ns = output_ns["concordant_reads"]
assert type(reads_ff) is type(0)
orient = [
(reads_ff, "ff"),
(reads_fr, "fr"),
(reads_rf, "rf"),
#(reads_ns, None),
]
orient.sort(reverse=True)
# Debug:
if False:
print orient
raise AssertionError
# If highest is within 10% of the un-stranded one, then it's
#cutoff = reads_ns * 0.10
#if reads_ns >= orient[3][0] - reads_ns*0.10:
# return None
return orient[0][-1], reads_ns, reads_fr, reads_rf, reads_ff
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils
bam_node, ref_node = antecedents
bam_filenames = module_utils.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# TODO: Figure out GATK version.
## Figure out whether the user wants SNPs or INDELs.
#assert "vartype" in out_attributes
#vartype = out_attributes["vartype"]
#assert vartype in ["all", "snp", "indel"]
jobs = []
for bam_filename in bam_filenames:
p, f = os.path.split(bam_filename)
sample, ext = os.path.splitext(f)
#raw_outfile = os.path.join(out_path, "%s.raw" % sample)
vcf_outfile = os.path.join(out_path, "%s.vcf" % sample)
log_filename = os.path.join(out_path, "%s.log" % sample)
x = filelib.GenericObject(bam_filename=bam_filename,
vcf_outfile=vcf_outfile,
log_filename=log_filename)
jobs.append(x)
# java -Xmx5g -jar /usr/local/bin/GATK/GenomeAnalysisTK.jar
# -T HaplotypeCaller -R ucsc.hg19.fasta
# -dontUseSoftClippedBases -stand_call_conf 20.0
# -stand_emit_conf 20.0 -I $i -o $j
# Make a list of commands.
commands = []
for j in jobs:
# For debugging. If exists, don't do it again.
#if filelib.exists_nz(j.raw_outfile):
if filelib.exists_nz(j.vcf_outfile):
continue
x = alignlib.make_GATK_command(T="HaplotypeCaller",
R=ref.fasta_file_full,
dontUseSoftClippedBases=None,
stand_call_conf=20.0,
stand_emit_conf=20.0,
I=j.bam_filename,
o=j.vcf_outfile)
x = "%s >& %s" % (x, j.log_filename)
commands.append(x)
parallel.pshell(commands, max_procs=num_cores)
# Filter each of the VCF files.
#for j in jobs:
# filter_by_vartype(vartype, j.raw_outfile, j.vcf_outfile)
#metadata["filter"] = vartype
# Make sure the analysis completed successfully.
x = [j.vcf_outfile for j in jobs]
filelib.assert_exists_nz_many(x)
return metadata
def main():
import os
import shutil
import argparse
from genomicode import filelib
from genomicode import parallel
p = filelib.tswrite
parser = argparse.ArgumentParser(description="")
parser.add_argument("mapability_file", help="PeakSeq mapability file.")
parser.add_argument("treatment_bam", help="BAM file of treated sample.")
parser.add_argument("control_bam", help="BAM file of background sample.")
parser.add_argument("outpath", help="Directory to store the results.")
parser.add_argument("--experiment_name", help="Name of experiment.")
parser.add_argument("--fragment_length", type=int, help="")
#group.add_argument(
# "--noclobber", action="store_true",
# help="Don't overwrite files if they already exist.")
args = parser.parse_args()
filelib.assert_exists_nz(args.mapability_file)
filelib.assert_exists_nz(args.treatment_bam)
filelib.assert_exists_nz(args.control_bam)
if args.fragment_length:
assert args.fragment_length > 0 and args.fragment_length < 10000
# Set up directories to run it on.
p("Setting up directories.\n")
if not os.path.exists(args.outpath):
os.mkdir(args.outpath)
# Copy the mapability file to the outpath.
shutil.copy2(args.mapability_file, args.outpath)
# Do preprocessing for PeakSeq.
p("Preprocessing.\n")
treatment_preproc_path = os.path.join(args.outpath, "preprocess.treatment")
control_preproc_path = os.path.join(args.outpath, "preprocess.control")
if not os.path.exists(treatment_preproc_path):
os.mkdir(treatment_preproc_path)
if not os.path.exists(control_preproc_path):
os.mkdir(control_preproc_path)
x1 = make_peakseq_preproc_command(args.treatment_bam,
treatment_preproc_path)
x2 = make_peakseq_preproc_command(args.control_bam, control_preproc_path)
x = parallel.pshell([x1, x2])
print x
# Make sure expected files exist.
x1 = os.path.join(treatment_preproc_path, "chr_ids.txt")
x2 = os.path.join(control_preproc_path, "chr_ids.txt")
filelib.assert_exists_nz(x1)
filelib.assert_exists_nz(x2)
# Make configuration file.
p("Making configuration file.\n")
config_file = os.path.join(args.outpath, "config.dat")
make_config_file(config_file,
treatment_preproc_path,
control_preproc_path,
args.mapability_file,
experiment_name=args.experiment_name,
fragment_length=args.fragment_length)
# Run PeakSeq.
p("Running PeakSeq in %s.\n" % args.outpath)
cmd = make_peakseq_run_command(config_file)
x = parallel.sshell(cmd, path=args.outpath)
print x
p("Done.\n")
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils
vcf_node, ref_node = antecedents
vcf_filenames = filelib.list_files_in_path(vcf_node.identifier,
endswith=".vcf")
assert vcf_filenames, "No .vcf files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
jobs = []
for in_filename in vcf_filenames:
p, f = os.path.split(in_filename)
f, exp = os.path.splitext(f)
out_filename = os.path.join(out_path, "%s.grp" % f)
log_filename = os.path.join(out_path, "%s.log" % f)
recal_filename = os.path.join(out_path,
"%s.recalibrate_SNP.recal" % f)
tranches_filename = os.path.join(out_path,
"%s.recalibrate_SNP.tranches" % f)
rscript_filename = os.path.join(out_path,
"%s.recalibrate_SNP_plots.R" % f)
assert in_filename != out_filename
x = (in_filename, log_filename, recal_filename, tranches_filename,
rscript_filename)
jobs.append(x)
# -resource:dbsnp,known=true,training=false,truth=false,prior=6.0
# dbsnp_135.b37.vcf
# -resource:hapmap,known=false,training=true,truth=true,prior=15.0
# hapmap_3.3.b37.sites.vcf
# -resource:1000G,known=false,training=true,truth=false,prior=10.0
# 1000G_phase1.snps.high_confidence.vcf
# -resource:omni,known=false,training=true,truth=false,prior=12.0
# 1000G_omni2.5.b37.sites.vcf
known_sites = []
x1 = module_utils.get_user_option(user_options,
"vcf_recal_dbsnp",
not_empty=True,
check_file=True)
x2 = module_utils.get_user_option(user_options,
"vcf_recal_mills_indels",
not_empty=True,
check_file=True)
x3 = module_utils.get_user_option(user_options,
"vcf_recal_1kg_indels",
not_empty=True,
check_file=True)
x4 = module_utils.get_user_option(user_options,
"vcf_recal_omni",
not_empty=True,
check_file=True)
y1 = "resource:dbsnp,known=true,training=false,truth=false,prior=6.0"
y2 = "resource:hapmap,known=false,training=true,truth=true,prior=15.0"
y3 = "resource:1000G,known=false,training=true,truth=false,prior=10.0"
y4 = "resource:omni,known=false,training=true,truth=false,prior=12.0"
known_sites = [(y1, x1), (y2, x2), (y3, x3), (y4, x4)]
# Names of annotations to be used for annotations.
AN = [
"DP", "QD", "FS", "SOR", "MQ", "MQRankSum", "ReadPosRankSum",
"InbreedingCoeff"
]
TRANCHE = ["100.0", "99.9", "99.0", "90.0"]
# Make a list of commands.
commands = []
for x in jobs:
(in_filename, log_filename, recal_filename, tranches_filename,
rscript_filename) = x
x1 = known_sites
x2 = [("an", x) for x in AN]
x3 = [("tranche", x) for x in TRANCHE]
unhash = x1 + x2 + x3
x = alignlib.make_GATK_command(T="VariantRecalibrator",
R=ref.fasta_file_full,
input=in_filename,
mode="SNP",
recalFile=recal_filename,
tranchesFile=tranches_filename,
rscriptFile=rscript_filename,
_UNHASHABLE=unhash)
x = "%s >& %s" % (x, log_filename)
commands.append(x)
#for x in commands:
# print x
#import sys; sys.exit(0)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
out_filenames = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(out_filenames)
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_node, ref_node, insert_size_node, alignment_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# ./pindel -f <reference.fa> -i <bam_configuration_file>
# -c <chromosome_name> -o <out_prefix>
# -T <num threads>
#
# Creates files:
# <out_prefix>_D Deletion
# <out_prefix>_SI Short insertion
# <out_prefix>_LI Long insertion
# <out_prefix>_INV Inversion
# <out_prefix>_TD Tandem deletion
# <out_prefix>_BP Breakpoint
# <out_prefix>_RP ??? read pair???
# <out_prefix>_CloseEndMapped Only on end could be mapped.
# Pindel cannot handle spaces in the BAM filenames (because of
# the config file). Symlink the file to a local directory to make
# sure there are no spaces.
bam_path = "bam"
opj = os.path.join
jobs = [] # list of filelib.GenericObject
for bam_filename in bam_filenames:
p, f = os.path.split(bam_filename)
sample, ext = os.path.splitext(f)
bai_filename = "%s.bai" % bam_filename
filelib.assert_exists_nz(bai_filename)
x = sample.replace(" ", "_")
local_bam = opj(bam_path, "%s.bam" % x)
local_bai = opj(bam_path, "%s.bam.bai" % x)
config_filename = opj(out_path, "%s.config.txt" % sample)
out_prefix = opj(out_path, sample)
log_filename = opj(out_path, "%s.log" % sample)
x = filelib.GenericObject(sample=sample,
bam_filename=bam_filename,
bai_filename=bai_filename,
local_bam=local_bam,
local_bai=local_bai,
config_filename=config_filename,
out_prefix=out_prefix,
log_filename=log_filename)
jobs.append(x)
filelib.safe_mkdir(bam_path)
for j in jobs:
assert " " not in j.local_bam
filelib.assert_exists_nz(j.bam_filename)
filelib.assert_exists_nz(j.bai_filename)
if not os.path.exists(j.local_bam):
os.symlink(j.bam_filename, j.local_bam)
if not os.path.exists(j.local_bai):
os.symlink(j.bai_filename, j.local_bai)
# Read the insert sizes.
summary_file = opj(insert_size_node.identifier, "summary.txt")
filelib.assert_exists_nz(summary_file)
sample2size = _read_insert_sizes(summary_file)
# Make sure all the samples have inserts.
for j in jobs:
assert j.sample in sample2size, \
"Missing in insert size file: %s" % j.sample
# Read the fragment sizes.
summary_file = opj(alignment_node.identifier, "summary.txt")
filelib.assert_exists_nz(summary_file)
sample2readlen = _read_fragment_sizes(summary_file)
# Make sure all the samples have read lengths.
for j in jobs:
assert j.sample in sample2readlen, \
"Missing in alignment summary file: %s" % j.sample
# Make the config file.
for j in jobs:
# <insert size> is the whole length to be sequenced, including
# the length of the pair of reads. Picard only counts the
# sequence between the reads.
size = sample2size[j.sample]
read_length = sample2readlen[j.sample]
insert_size = size + read_length * 2
handle = open(j.config_filename, 'w')
print >> handle, "%s %s %s" % (j.local_bam, insert_size, j.sample)
handle.close()
# Make a list of commands.
pindel = mlib.get_config("pindel", which_assert_file=True)
sq = parallel.quote
commands = []
for j in jobs:
cmd = [
sq(pindel),
"-f",
sq(ref.fasta_file_full),
"-i",
sq(j.config_filename),
"-c",
"ALL",
"-T",
1,
"-o",
sq(j.out_prefix),
]
cmd = " ".join(map(str, cmd))
cmd = "%s >& %s" % (cmd, j.log_filename)
commands.append(cmd)
parallel.pshell(commands, max_procs=num_cores)
metadata["num_cores"] = num_cores
metadata["commands"] = commands
# Make sure the analysis completed successfully. If not, try
# to diagnose.
x = [x.log_filename for x in jobs]
filelib.assert_exists_nz_many(x)
x1 = ["%s_D" % x.out_prefix for x in jobs]
x2 = ["%s_SI" % x.out_prefix for x in jobs]
x3 = ["%s_LI" % x.out_prefix for x in jobs]
x4 = ["%s_INV" % x.out_prefix for x in jobs]
x5 = ["%s_TD" % x.out_prefix for x in jobs]
x6 = ["%s_BP" % x.out_prefix for x in jobs]
x = x1 + x2 + x3 + x4 + x5 + x6
filelib.assert_exists_many(x)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_node, nc_node, ref_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
nc_match = mlib.read_normal_cancer_file(nc_node.identifier)
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# TODO: Figure out version.
# Figure out whether the user wants SNPs or INDELs.
#assert "vartype" in out_attributes
#vartype = out_attributes["vartype"]
#assert vartype in ["all", "snp", "indel"]
# sample -> bam filename
sample2bamfile = mlib.root2filename(bam_filenames)
# Make sure files exist for all the samples.
mlib.assert_normal_cancer_samples(nc_match, sample2bamfile)
# list of (cancer_sample, normal_bamfile, tumor_bamfile, orig_outfile,
# fixed_outfile, filtered_outfile)
opj = os.path.join
jobs = []
for (normal_sample, cancer_sample) in nc_match:
normal_bamfile = sample2bamfile[normal_sample]
cancer_bamfile = sample2bamfile[cancer_sample]
path, sample, ext = mlib.splitpath(cancer_bamfile)
orig_outfile = opj(out_path, "%s.raw" % sample)
fix_outfile = opj(out_path, "%s.vcf" % sample)
#filter_outfile = opj(out_path, "%s.vcf" % sample)
x = cancer_sample, normal_bamfile, cancer_bamfile, \
orig_outfile, fix_outfile
x = filelib.GenericObject(cancer_sample=cancer_sample,
normal_bamfile=normal_bamfile,
cancer_bamfile=cancer_bamfile,
orig_outfile=orig_outfile,
fix_outfile=fix_outfile)
jobs.append(x)
# python /usr/local/museq/classify.py \
# normal:test31/normal.bam tumour:test31/tumor.bam \
# reference:genomes/Broad.hg19/Homo_sapiens_assembly19.fa \
# model:/usr/local/museq/model_v4.1.2.npz \
# --config /usr/local/museq/metadata.config \
# -o test51.vcf
opj = os.path.join
museq = mlib.get_config("museq", assert_exists=True)
classify_py = opj(museq, "classify.py")
model_file = opj(museq, "model_v4.1.2.npz")
config_file = opj(museq, "metadata.config")
filelib.assert_exists_nz(classify_py)
filelib.assert_exists_nz(model_file)
filelib.assert_exists_nz(config_file)
# museq's config file generates a broken VCF file. Fix it.
fixed_config_file = "fixed.config"
fix_config_file(config_file, fixed_config_file)
# Generate the commands.
sq = mlib.sq
commands = []
for j in jobs:
#cancer_sample, normal_bamfile, cancer_bamfile, \
# raw_outfile, fix_outfile, vcf_outfile = x
x = [
"python", # should allow user to specify python
sq(classify_py),
sq("normal:%s" % j.normal_bamfile),
sq("tumour:%s" % j.cancer_bamfile),
sq("reference:%s" % ref.fasta_file_full),
sq("model:%s" % model_file),
"--config",
sq(fixed_config_file),
"-o",
sq(j.orig_outfile),
]
x = " ".join(map(str, x))
commands.append(x)
# Not sure how much RAM this takes. On Thunderbolts test,
# took < 1 Gb.
nc = mlib.calc_max_procs_from_ram(5, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["num_cores"] = nc
metadata["commands"] = commands
# JointSNVMix produces non-standard VCF files. Fix this so it
# will work with other programs downstream.
for j in jobs:
#cancer_sample, normal_bamfile, cancer_bamfile, \
# raw_outfile, fix_outfile, vcf_outfile = x
fix_vcf_file(j.cancer_sample, j.orig_outfile, j.fix_outfile)
# Filter each of the VCF files.
#for x in jobs:
# cancer_sample, normal_bamfile, cancer_bamfile, \
# raw_outfile, fix_outfile, vcf_outfile = x
# filter_by_vartype(vartype, fix_outfile, vcf_outfile)
#metadata["filter"] = vartype
#x = [x[-1] for x in jobs]
x = [j.fix_outfile for x in jobs]
filelib.assert_exists_many(x)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_node, ref_node = antecedents
in_filenames = mlib.find_bam_files(bam_node.identifier)
assert in_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
jobs = [] # list of (in_filename, log_filename, out_filename)
for in_filename in in_filenames:
p, f = os.path.split(in_filename)
f, ext = os.path.splitext(f)
log_filename = os.path.join(out_path, "%s.log" % f)
out_filename = os.path.join(out_path, "%s.intervals" % f)
x = in_filename, log_filename, out_filename
jobs.append(x)
filter_reads_with_N_cigar = mlib.get_user_option(
user_options,
"filter_reads_with_N_cigar",
allowed_values=["no", "yes"])
known_sites = []
x1 = mlib.get_user_option(user_options,
"realign_known_sites1",
check_file=True)
x2 = mlib.get_user_option(user_options,
"realign_known_sites2",
check_file=True)
x3 = mlib.get_user_option(user_options,
"realign_known_sites3",
check_file=True)
x = [x1, x2, x3]
x = [x for x in x if x]
known_sites = x
assert known_sites
# I/O bound, so not likely to get a big speedup with nt.
# java -Xmx5g -jar /usr/local/bin/GATK/GenomeAnalysisTK.jar -nt 4
# -T RealignerTargetCreator -R ../genome.idx/erdman.fa -I $i -o $j
# --known <known_vcf_file>
# RealignerTargetCreator takes ~10Gb per process. Each thread
# takes the full amount of memory.
nc = mlib.calc_max_procs_from_ram(12, upper_max=num_cores)
# Make a list of commands.
commands = []
for x in jobs:
in_filename, log_filename, out_filename = x
n = max(1, nc / len(jobs))
x = [("-known", x) for x in known_sites]
if filter_reads_with_N_cigar == "yes":
x.append(("-filter_reads_with_N_cigar", None))
x = alignlib.make_GATK_command(nt=n,
T="RealignerTargetCreator",
R=ref.fasta_file_full,
I=in_filename,
o=out_filename,
_UNHASHABLE=x)
x = "%s >& %s" % (x, log_filename)
commands.append(x)
parallel.pshell(commands, max_procs=nc)
metadata["num_procs"] = nc
metadata["commands"] = commands
# Make sure the analysis completed successfully.
out_filenames = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(out_filenames)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import config
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils
## Importing pysam is hard!
#import sys
#sys_path_old = sys.path[:]
#sys.path = [x for x in sys.path if x.find("RSeQC") < 0]
#import pysam
#sys.path = sys_path_old
bam_node, ref_node = antecedents
bam_filenames = module_utils.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
# list of (in_filename, err_filename, out_filename)
jobs = []
for in_filename in bam_filenames:
p, f = os.path.split(in_filename)
s, ext = os.path.splitext(f)
log_filename = os.path.join(out_path, "%s.log" % s)
out_filename = os.path.join(out_path, f)
assert in_filename != out_filename
x = in_filename, log_filename, out_filename
jobs.append(x)
# Don't do this. Need MD, NM, NH in
# summarize_alignment_cigar. To be sure, just redo it.
## If the files already have MD tags, then just symlink the
## files. Don't add again.
#i = 0
#while i < len(jobs):
# in_filename, out_filename = jobs[i]
#
# handle = pysam.AlignmentFile(in_filename, "rb")
# align = handle.next()
# tag_dict = dict(align.tags)
# if "MD" not in tag_dict:
# i += 1
# continue
# # Has MD tags. Just symlink and continue.
# os.symlink(in_filename, out_filename)
# del jobs[i]
# Make a list of samtools commands.
# Takes ~200 Mb per process, so should not be a big issue.
samtools = filelib.which_assert(config.samtools)
sq = parallel.quote
commands = []
for x in jobs:
in_filename, log_filename, out_filename = x
# samtools calmd -b <in.bam> <ref.fasta> > <out.bam>
# May generate error:
# [bam_fillmd1] different NM for read
# 'ST-J00106:118:H75L3BBXX:3:2128:21846:47014': 0 -> 19
# Pipe stderr to different file.
x = [
samtools,
"calmd",
"-b",
sq(in_filename),
sq(ref.fasta_file_full),
]
x = " ".join(x)
x = "%s 2> %s 1> %s" % (x, sq(log_filename), sq(out_filename))
commands.append(x)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
x = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(x)
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import parallel
from genomicode import filelib
from genomicode import alignlib
from Betsy import module_utils as mlib
bam_folder, sample_node, gene_node, strand_node = antecedents
bam_path = bam_folder.identifier
assert filelib.dir_exists(bam_path)
gtf_file = gene_node.identifier
filelib.assert_exists_nz(gtf_file)
stranded = mlib.read_stranded(strand_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
attr2order = {
"name": "name",
"coordinate": "pos",
}
x = bam_folder.data.attributes["sorted"]
sort_order = attr2order.get(x)
assert sort_order, "Cannot handle sorted: %s" % x
#attr2stranded = {
# "single" : "no",
# "paired" : "no",
# "paired_ff" : None,
# "paired_fr" : "yes",
# "paired_rf" : "reverse",
# }
#x = sample_node.data.attributes["orientation"]
#stranded = attr2stranded.get(x)
#assert stranded, "Cannot handle orientation: %s" % x
ht_stranded = None
if stranded.stranded == "unstranded":
ht_stranded = "no"
elif stranded.stranded == "firststrand":
ht_stranded = "reverse"
elif stranded.stranded == "secondstrand":
ht_stranded = "yes"
assert ht_stranded is not None
#gtf_file = mlib.get_user_option(
# user_options, "gtf_file", not_empty=True)
#assert os.path.exists(gtf_file), "File not found: %s" % gtf_file
mode = mlib.get_user_option(user_options,
"htseq_count_mode",
allowed_values=[
"union", "intersection-strict",
"intersection-nonempty"
])
# Make a list of the jobs to run.
jobs = []
for bam_filename in filelib.list_files_in_path(bam_path,
endswith=".bam",
case_insensitive=True):
x = os.path.split(bam_filename)[1]
x = os.path.splitext(x)[0]
x = "%s.count" % x
out_file = x
x = bam_filename, out_file
jobs.append(x)
# Generate commands for each of the files.
sq = parallel.quote
commands = []
for x in jobs:
bam_filename, out_file = x
x = alignlib.make_htseq_count_command(bam_filename,
gtf_file,
sort_order,
ht_stranded,
mode=mode)
x = "%s >& %s" % (x, sq(out_file))
commands.append(x)
metadata["commands"] = commands
metadata["num_cores"] = num_cores
parallel.pshell(commands, max_procs=num_cores, path=out_path)
# Make sure the analysis completed successfully.
x = [x[1] for x in jobs]
x = [os.path.join(out_path, x) for x in x]
output_filenames = x
filelib.assert_exists_nz_many(output_filenames)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
import call_somatic_varscan
bam_node, nc_node, ref_node, interval_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
nc_match = mlib.read_normal_cancer_file(nc_node.identifier)
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.assert_exists_nz(interval_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# TODO: Figure out GATK version.
# Make sure intervals file ends with:
# .bed, .list, .picard, .interval_list, or .intervals
x, x, ext = mlib.splitpath(interval_node.identifier)
assert ext in [
".bed", ".list", ".picard", ".interval_list", ".intervals"
]
cosmic_file = mlib.get_user_option(user_options,
"mutect_cosmic_vcf",
not_empty=True,
check_file=True)
dbsnp_file = mlib.get_user_option(user_options,
"mutect_dbsnp_vcf",
not_empty=True,
check_file=True)
# sample -> bam filename
sample2bamfile = mlib.root2filename(bam_filenames)
# Make sure files exist for all the samples.
mlib.assert_normal_cancer_samples(nc_match, sample2bamfile)
opj = os.path.join
jobs = []
for (normal_sample, cancer_sample) in nc_match:
normal_bamfile = sample2bamfile[normal_sample]
cancer_bamfile = sample2bamfile[cancer_sample]
path, sample, ext = mlib.splitpath(cancer_bamfile)
vcf_outfile = opj(out_path, "%s.vcf" % sample)
log_outfile = opj(out_path, "%s.log" % sample)
x = filelib.GenericObject(normal_sample=normal_sample,
cancer_sample=cancer_sample,
normal_bamfile=normal_bamfile,
cancer_bamfile=cancer_bamfile,
vcf_outfile=vcf_outfile,
log_outfile=log_outfile)
jobs.append(x)
# java -jar GenomeAnalysisTK.jar \
# -T MuTect2 \
# -R reference.fasta \
# -I:tumor tumor.bam \
# -I:normal normal.bam \
# [--dbsnp dbSNP.vcf] \
# [--cosmic COSMIC.vcf] \
# [-L targets.interval_list] \
# -o output.vcf
# Generate the commands.
sq = mlib.sq
commands = []
for j in jobs:
UNHASHABLE = [
("I:normal", sq(normal_bamfile)),
("I:tumor", sq(cancer_bamfile)),
# --dbsnp and --cosmic use two dashes, for some
# reason. Since make_GATK_command only uses one dash,
# add one manually.
("-dbsnp", sq(dbsnp_file)),
("-cosmic", sq(cosmic_file)),
]
x = alignlib.make_GATK_command(
T="MuTect2",
R=sq(ref.fasta_file_full),
L=sq(interval_node.identifier),
o=sq(j.vcf_outfile),
_UNHASHABLE=UNHASHABLE,
)
x = "%s >& %s" % (x, j.log_outfile)
commands.append(x)
assert len(commands) == len(jobs)
nc = mlib.calc_max_procs_from_ram(25, upper_max=num_cores)
parallel.pshell(commands, max_procs=nc)
metadata["num_cores"] = nc
metadata["commands"] = commands
# Make sure log files have no errors. Check the log files
# before the VCF files. If there's an error, the VCF files
# may not be created.
# ##### ERROR -------------------------------------------------------
# ##### ERROR A GATK RUNTIME ERROR has occurred (version 2.2-25-g2a68
# ##### ERROR
# ##### ERROR Please visit the wiki to see if this is a known problem
# ##### ERROR If not, please post the error, with stack trace, to the
# ##### ERROR Visit our website and forum for extensive documentation
# ##### ERROR commonly asked questions http://www.broadinstitute.org/
# ##### ERROR
# ##### ERROR MESSAGE: java.lang.IllegalArgumentException: Comparison
# ##### ERROR -------------------------------------------------------
for i, j in enumerate(jobs):
# Pull out the error lines.
x = [x for x in open(j.log_outfile)]
x = [x for x in x if x.startswith("##### ERROR")]
x = "".join(x)
msg = "MuTect2 error [%s]:\n%s\n%s" % (cancer_sample, commands[i],
x)
assert not x, msg
# Make sure output VCF files exist.
x = [x.vcf_outfile for x in jobs]
filelib.assert_exists_many(x)
# Mutect2 names the samples "NORMAL" and "TUMOR". Replace
# them with the actual names.
for j in jobs:
call_somatic_varscan._fix_normal_cancer_names(
j.vcf_outfile, j.normal_sample, j.cancer_sample)
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils as mlib
#import call_variants_GATK
bam_node, ref_node = antecedents
bam_filenames = mlib.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
metadata = {}
# Figure out whether the user wants SNPs or INDELs.
#assert "vartype" in out_attributes
#vartype = out_attributes["vartype"]
#assert vartype in ["all", "snp", "indel"]
# Platypus generates an error if there are spaces in the BAM
# filename. Symlink the file to a local directory to make
# sure there are no spaces.
bam_path = "bam"
jobs = [] # list of filelib.GenericObject
for bam_filename in bam_filenames:
p, f = os.path.split(bam_filename)
sample, ext = os.path.splitext(f)
bai_filename = "%s.bai" % bam_filename
filelib.assert_exists_nz(bai_filename)
x = sample.replace(" ", "_")
local_bam = os.path.join(bam_path, "%s.bam" % x)
local_bai = os.path.join(bam_path, "%s.bam.bai" % x)
log_filename = os.path.join(out_path, "%s.log" % sample)
err_filename = os.path.join(out_path, "%s.err" % sample)
# Unfiltered file.
#raw_filename = os.path.join(out_path, "%s.raw" % sample)
# Final VCF file.
out_filename = os.path.join(out_path, "%s.vcf" % sample)
x = filelib.GenericObject(bam_filename=bam_filename,
bai_filename=bai_filename,
local_bam=local_bam,
local_bai=local_bai,
log_filename=log_filename,
err_filename=err_filename,
out_filename=out_filename)
jobs.append(x)
filelib.safe_mkdir(bam_path)
for j in jobs:
assert " " not in j.local_bam
filelib.assert_exists_nz(j.bam_filename)
filelib.assert_exists_nz(j.bai_filename)
if not os.path.exists(j.local_bam):
os.symlink(j.bam_filename, j.local_bam)
if not os.path.exists(j.local_bai):
os.symlink(j.bai_filename, j.local_bai)
# TODO: Keep better track of the metadata.
buffer_size = 100000
max_reads = 5E6
# Running into errors sometimes, so increase these numbers.
# WARNING - Too many reads (5000000) in region
# 1:500000-600000. Quitting now. Either reduce --bufferSize or
# increase --maxReads.
buffer_size = buffer_size * 10
max_reads = max_reads * 10
# Make a list of commands.
commands = []
for j in jobs:
#nc = max(1, num_cores/len(jobs))
x = alignlib.make_platypus_command(bam_file=j.local_bam,
ref_file=ref.fasta_file_full,
log_file=j.log_filename,
out_file=j.out_filename,
buffer_size=buffer_size,
max_reads=max_reads)
x = "%s >& %s" % (x, j.err_filename)
commands.append(x)
#for x in commands:
# print x
#import sys; sys.exit(0)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully. If not, try
# to diagnose.
for j in jobs:
if filelib.exists_nz(j.out_filename):
continue
for line in open(j.err_filename):
if line.find("WARNING - Too many reads") >= 0:
print line,
x = [j.out_filename for j in jobs]
filelib.assert_exists_nz_many(x)
# Filter each of the VCF files.
#for j in jobs:
# call_variants_GATK.filter_by_vartype(
# vartype, j.raw_filename, j.out_filename)
#metadata["filter"] = vartype
return metadata
def run(self, network, antecedents, out_attributes, user_options,
num_cores, out_path):
import os
from genomicode import filelib
from genomicode import parallel
from genomicode import alignlib
from Betsy import module_utils
bam_node, ref_node, target_node = antecedents
bam_filenames = module_utils.find_bam_files(bam_node.identifier)
assert bam_filenames, "No .bam files."
target_filenames = filelib.list_files_in_path(target_node.identifier,
endswith=".intervals")
assert target_filenames, "No .intervals files."
ref = alignlib.create_reference_genome(ref_node.identifier)
filelib.safe_mkdir(out_path)
assert len(bam_filenames) == len(target_filenames), \
"Should have an .intervals file for each bam file."
sample2bamfilename = {}
for filename in bam_filenames:
p, f = os.path.split(filename)
sample, ext = os.path.splitext(f)
assert sample not in sample2bamfilename
sample2bamfilename[sample] = filename
sample2targetfilename = {}
for filename in target_filenames:
p, f = os.path.split(filename)
sample, ext = os.path.splitext(f)
assert sample not in sample2targetfilename
sample2targetfilename[sample] = filename
assert len(sample2bamfilename) == len(sample2targetfilename)
missing = [
x for x in sample2bamfilename if x not in sample2targetfilename
]
assert not missing, "Missing interval files for %d bam files." % \
len(missing)
# list of (bam_filename, target_filename, log_filename, out_filename)
jobs = []
for sample in sample2bamfilename:
bam_filename = sample2bamfilename[sample]
target_filename = sample2targetfilename[sample]
p, f = os.path.split(bam_filename)
sample, ext = os.path.splitext(f)
out_filename = os.path.join(out_path, "%s.bam" % sample)
log_filename = os.path.join(out_path, "%s.log" % sample)
x = bam_filename, target_filename, log_filename, out_filename
jobs.append(x)
known_sites = []
x1 = module_utils.get_user_option(user_options,
"realign_known_sites1",
check_file=True)
x2 = module_utils.get_user_option(user_options,
"realign_known_sites2",
check_file=True)
x3 = module_utils.get_user_option(user_options,
"realign_known_sites3",
check_file=True)
x = [x1, x2, x3]
x = [x for x in x if x]
known_sites = x
assert known_sites
# java -Xmx5g -jar /usr/local/bin/GATK/GenomeAnalysisTK.jar \
# -T IndelRealigner -R <ref.fa> \
# -I <bam_file> -targetIntervals <target_file> -o <bam_file>
# Make a list of commands.
commands = []
for x in jobs:
bam_filename, target_filename, log_filename, out_filename = x
x = [("known", x) for x in known_sites]
x = alignlib.make_GATK_command(T="IndelRealigner",
R=ref.fasta_file_full,
I=bam_filename,
targetIntervals=target_filename,
o=out_filename,
_UNHASHABLE=x)
x = "%s >& %s" % (x, log_filename)
commands.append(x)
#for x in commands:
# print x
#import sys; sys.exit(0)
parallel.pshell(commands, max_procs=num_cores)
# Make sure the analysis completed successfully.
out_filenames = [x[-1] for x in jobs]
filelib.assert_exists_nz_many(out_filenames)