def __init__(self, in_files, config):
self.in_files = in_files
self.config = config
setup_logging(self.config)
start_cluster(self.config)
from bipy.cluster import view
self.view = view
self.curr_files = [in_files]
self.to_run = Queue()
map(self.to_run.put, self.setup_stages(config["run"]))
def test_cluster():
with open(CONFIG_FILE) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
from bipy.log import logger
start_cluster(config)
from bipy.cluster import view
logger.info("Serial result")
serial_result = map(mappable_function, range(32))
logger.info("Parallel result")
parallel_result = view.map(mappable_function, range(32))
assert(serial_result == parallel_result)
def test_cluster():
with open(CONFIG_FILE) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
from bipy.log import logger
start_cluster(config)
from bipy.cluster import view
logger.info("Serial result")
serial_result = map(mappable_function, range(32))
logger.info("Parallel result")
parallel_result = view.map(mappable_function, range(32))
assert (serial_result == parallel_result)
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
start_cluster(config)
from bipy.cluster import view
input_files = config["input"]
for stage in config["run"]:
if config["stage"][stage]["program"] == "tagdust":
tagdust_config = config["stage"][stage]
view.map(tagdust.run, input_files,
[tagdust_config] * len(input_files),
[config] * len(input_files))
stop_cluster()
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
start_cluster(config)
from bipy.cluster import view
input_files = config["input"]
for stage in config["run"]:
if config["stage"][stage]["program"] == "tagdust":
tagdust_config = config["stage"][stage]
view.map(tagdust.run, input_files,
[tagdust_config] * len(input_files),
[config] * len(input_files))
stop_cluster()
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
from bipy.log import logger
start_cluster(config)
from bipy.cluster import view
input_dir = config["dir"]["input_dir"]
results_dir = config["dir"]["results"]
input_files = glob.glob(os.path.join(input_dir, "*.bam"))
""" example running with macs
macs.run_with_config(input_file, config, control_file=None, stage=None)
"""
curr_files = input_files
# first combine all the negative controls into one file
negative_control = _merge_condition(input_files,
config["groups"]["negative"])
test_files = [_merge_condition(input_files, condition) for
condition in config["groups"]["test"]]
test_files = [x for x in test_files if x]
curr_files = test_files
for stage in config["run"]:
# for now just run macs on all of these files without the control
# file
if stage == "macs":
nfiles = len(curr_files)
out_files = view.map(macs.run_with_config, curr_files,
[config] * nfiles,
[negative_control] * nfiles,
[stage] * nfiles)
# just use the peak files going forward
peak_files = [x[0] for x in out_files]
curr_files = peak_files
if stage == "piranha":
nfiles = len(curr_files)
piranha_runner = piranha.PiranhaStage(config)
out_files = view.map(piranha_runner, curr_files)
stop_cluster()
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
from bipy.log import logger
start_cluster(config)
from bipy.cluster import view
input_dir = config["dir"]["input_dir"]
results_dir = config["dir"]["results"]
input_files = glob.glob(os.path.join(input_dir, "*.bam"))
""" example running with macs
macs.run_with_config(input_file, config, control_file=None, stage=None)
"""
curr_files = input_files
# first combine all the negative controls into one file
negative_control = _merge_condition(input_files,
config["groups"]["negative"])
test_files = [
_merge_condition(input_files, condition)
for condition in config["groups"]["test"]
]
test_files = [x for x in test_files if x]
curr_files = test_files
for stage in config["run"]:
# for now just run macs on all of these files without the control
# file
if stage == "macs":
nfiles = len(curr_files)
out_files = view.map(macs.run_with_config, curr_files,
[config] * nfiles,
[negative_control] * nfiles, [stage] * nfiles)
# just use the peak files going forward
peak_files = [x[0] for x in out_files]
curr_files = peak_files
if stage == "piranha":
nfiles = len(curr_files)
piranha_runner = piranha.PiranhaStage(config)
out_files = view.map(piranha_runner, curr_files)
stop_cluster()
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
from bipy.log import logger
start_cluster(config)
from bipy.cluster import view
# view.push({'logger': logger})
input_files = [
os.path.join(config["dir"]["data"], x) for x in config["input"]
]
results_dir = config["dir"]["results"]
map(safe_makedir, config["dir"].values())
curr_files = input_files
for stage in config["run"]:
if stage == "fastqc":
nfiles = len(curr_files)
logger.info("Running %s on %s" % (stage, str(curr_files)))
fastqc_config = _get_stage_config(config, stage)
fastqc_outputs = view.map(fastqc.run, curr_files,
[fastqc_config] * nfiles,
[config] * nfiles)
if stage == "cutadapt":
nfiles = len(curr_files)
cutadapt_config = _get_stage_config(config, stage)
cutadapt_outputs = view.map(cutadapt_tool.run, curr_files,
[cutadapt_config] * nfiles,
[config] * nfiles)
curr_files = cutadapt_outputs
if stage == "novoalign":
nfiles = len(curr_files)
novoalign_config = _get_stage_config(config, stage)
#db = novoindex.run(config["ref"],
# _get_stage_config(config, "novoindex"),
# config)
db = config["genome"]["file"]
novoalign_outputs = view.map(novoalign.run, curr_files,
[db] * nfiles,
[novoalign_config] * nfiles,
[config] * nfiles)
picard = BroadRunner(config["program"]["picard"])
args = zip(*itertools.product([picard], novoalign_outputs))
# conver to bam
bamfiles = view.map(picardrun.picard_formatconverter, *args)
args = zip(*itertools.product([picard], bamfiles))
# sort bam
sorted_bf = view.map(picardrun.picard_sort, *args)
# index bam
args = zip(*itertools.product([picard], sorted_bf))
view.map(picardrun.picard_index, *args)
curr_files = novoalign_outputs
if stage == "htseq-count":
nfiles = len(curr_files)
htseq_config = _get_stage_config(config, stage)
htseq_outputs = view.map(htseq_count.run_with_config, curr_files,
[config] * nfiles, [stage] * nfiles)
column_names = _get_short_names(input_files)
logger.info("Column names: %s" % (column_names))
out_file = os.path.join(config["dir"]["results"], stage,
"combined.counts")
combined_out = htseq_count.combine_counts(htseq_outputs,
column_names, out_file)
rpkm = htseq_count.calculate_rpkm(combined_out,
config["annotation"]["file"])
rpkm_file = os.path.join(config["dir"]["results"], stage,
"rpkm.txt")
rpkm.to_csv(rpkm_file, sep="\t")
if stage == "coverage":
logger.info("Calculating RNASeq metrics on %s." % (curr_files))
nrun = len(curr_files)
ref = blastn.prepare_ref_file(config["stage"][stage]["ref"],
config)
ribo = config["stage"][stage]["ribo"]
picard = BroadRunner(config["program"]["picard"])
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
out_files = [
replace_suffix(os.path.basename(x), "metrics")
for x in curr_files
]
out_files = [os.path.join(out_dir, x) for x in out_files]
out_files = view.map(picardrun.picard_rnaseq_metrics,
[picard] * nrun, curr_files, [ref] * nrun,
[ribo] * nrun, out_files)
if stage == "deseq":
conditions = [
os.path.basename(x).split("_")[0] for x in input_files
]
deseq_config = _get_stage_config(config, stage)
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
for comparison in deseq_config["comparisons"]:
comparison_name = "_vs_".join(comparison)
out_dir = os.path.join(results_dir, stage, comparison_name)
safe_makedir(out_dir)
# get the of the conditons that match this comparison
indexes = [
x for x, y in enumerate(conditions) if y in comparison
]
# find the htseq_files to combine and combine them
htseq_files = [htseq_outputs[index] for index in indexes]
htseq_columns = [column_names[index] for index in indexes]
logger.info(htseq_files)
logger.info(htseq_columns)
out_file = os.path.join(out_dir,
comparison_name + ".counts.txt")
combined_out = htseq_count.combine_counts(
htseq_files, htseq_columns, out_file)
deseq_conds = [conditions[index] for index in indexes]
deseq_prefix = os.path.join(out_dir, comparison_name)
deseq_out = view.map(deseq.run, [combined_out], [deseq_conds],
[deseq_prefix])
logger.info("Annotating %s." % (deseq_out))
annotated_file = view.map(annotate.annotate_table_with_biomart,
deseq_out, ["id"],
["ensembl_gene_id"], ["human"])
stop_cluster()
def _args_valid_for_local(args):
return not args.scheduler and not args.queue
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='generic launcher')
parser.add_argument('--profile', required=True,
help="IPython profile name to use")
parser.add_argument('--cores', required=True,
help="Number of IPython engines to start.")
parser.add_argument('--queue',
help="Name of queue to use.")
parser.add_argument('--scheduler', default="",
help="Name of scheduler to use (LSF or SGE)")
args = parser.parse_args()
cluster_config = {"cluster":
{"profile": args.profile,
"cores": int(args.cores),
"queue": args.queue,
"scheduler": args.scheduler}}
setup_logging(cluster_config)
if _args_valid_for_scheduler(args) or _args_valid_for_local(args):
start_cluster(cluster_config)
from bipy.cluster import view
main()
stop_cluster()
else:
print parser.usage()
sys.exit(1)
def main(config_file):
# load yaml config file
with open(config_file) as in_handle:
config = yaml.load(in_handle)
# setup logging
setup_logging(config)
from bipy.log import logger
# start cluster
start_cluster(config)
from bipy.cluster import view
found = sh.find(config["dir"]["data"], "-name", "Variations")
var_dirs = [str(x).strip() for x in found]
logger.info("Var_dirs: %s" % (var_dirs))
in_dirs = map(os.path.dirname, var_dirs)
logger.info("in_dirs: %s" % (in_dirs))
# XXX for testing only load 3
#curr_files = in_dirs[0:5]
curr_files = in_dirs
# run the illumina fixer
logger.info("Running illumina fixer on %s." % (curr_files))
illf_class = STAGE_LOOKUP.get("illumina_fixer")
illf = illf_class(config)
curr_files = view.map(illf, curr_files)
# sort the vcf files
def sort_vcf(in_file):
from bipy.utils import append_stem
from bcbio.distributed.transaction import file_transaction
from bcbio.utils import file_exists
import sh
out_file = append_stem(in_file, "sorted")
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tmp_out_file:
sh.vcf_sort(in_file, _out=tmp_out_file)
return out_file
# combine
out_file = os.path.join(config["dir"].get("results", "results"),
"geminiloader", "all_combined.vcf")
logger.info("Combining files %s into %s." % (curr_files, out_file))
if file_exists(out_file):
curr_files = [out_file]
else:
curr_files = [
genotype.combine_variant_files(curr_files, out_file,
config["ref"]["fasta"], config)
]
# break the VCF files up by chromosome for speed
logger.info("Breaking up %s by chromosome." % (curr_files))
breakvcf_class = STAGE_LOOKUP.get("breakvcf")
breakvcf = breakvcf_class(config)
curr_files = view.map(breakvcf, curr_files)
# run VEP on the separate files in parallel
logger.info("Running VEP on %s." % (curr_files))
vep_class = STAGE_LOOKUP.get("vep")
vep = vep_class(config)
curr_files = view.map(vep, list(flatten(curr_files)))
curr_files = filter(file_exists, curr_files)
# load the files into gemini not in parallel
# don't run in parallel
# sort the vcf files
logger.info("Sorting %s." % (curr_files))
curr_files = view.map(sort_vcf, curr_files)
# don't run the rest of this in parallel, so take the cluster down
stop_cluster()
out_file = os.path.join(config["dir"].get("results", "results"),
"geminiloader", "all_combined.vep.vcf")
logger.info("Combining files %s into %s." % (curr_files, out_file))
if file_exists(out_file):
curr_files = [out_file]
else:
curr_files = [
genotype.combine_variant_files(curr_files, out_file,
config["ref"]["fasta"], config)
]
logger.info("Loading %s into gemini." % (curr_files))
gemini_class = STAGE_LOOKUP.get("geminiloader")
geminiloader = gemini_class(config)
curr_files = map(geminiloader, curr_files)
logger.info("Run complete.")
view.map(rseqc.junction_annotation, *rseq_args)
view.map(rseqc.junction_saturation, *rseq_args)
RPKM_args = zip(*product(final_bamfiles, [config]))
RPKM_count_out = view.map(rseqc.RPKM_count, *RPKM_args)
RPKM_count_fixed = view.map(rseqc.fix_RPKM_count_file,
RPKM_count_out)
"""
annotate_args = zip(*product(RPKM_count_fixed,
["gene_id"],
["ensembl_gene_id"],
["human"]))
view.map(annotate.annotate_table_with_biomart,
*annotate_args)
"""
view.map(rseqc.RPKM_saturation, *rseq_args)
curr_files = tophat_outputs
# end gracefully
stop_cluster()
if __name__ == "__main__":
# read in the config file and perform initial setup
main_config_file = sys.argv[1]
with open(main_config_file) as config_in_handle:
startup_config = yaml.load(config_in_handle)
setup_logging(startup_config)
start_cluster(startup_config)
from bipy.cluster import view
main(main_config_file)
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
from bipy.log import logger
start_cluster(config)
data_dir = config["dir"]["data"]
from bipy.cluster import view
input_files = [glob.glob(os.path.join(data_dir, x, "*_rep*")) for x in
config["input_dirs"]]
input_files = list(flatten(input_files))
logger.info("Input files to process: %s" % (input_files))
results_dir = config["dir"]["results"]
map(safe_makedir, config["dir"].values())
curr_files = input_files
for stage in config["run"]:
if stage == "fastqc":
nfiles = len(curr_files)
logger.info("Running %s on %s" % (stage, str(curr_files)))
fastqc_config = _get_stage_config(config, stage)
fastqc_outputs = view.map(fastqc.run, curr_files,
[fastqc_config] * nfiles,
[config] * nfiles)
if stage == "cutadapt":
nfiles = len(curr_files)
cutadapt_config = _get_stage_config(config, stage)
cutadapt_outputs = view.map(cutadapt_tool.run,
curr_files,
[cutadapt_config] * nfiles,
[config] * nfiles)
curr_files = cutadapt_outputs
if stage == "novoalign":
nfiles = len(curr_files)
novoalign_config = _get_stage_config(config, stage)
#db = novoindex.run(config["ref"],
# _get_stage_config(config, "novoindex"),
# config)
db = config["genome"]["file"]
novoalign_outputs = view.map(novoalign.run, curr_files,
[db] * nfiles,
[novoalign_config] * nfiles,
[config] * nfiles)
picard = BroadRunner(config["program"]["picard"])
args = zip(*itertools.product([picard], novoalign_outputs))
# conver to bam
bamfiles = view.map(picardrun.picard_formatconverter,
*args)
args = zip(*itertools.product([picard], bamfiles))
# sort bam
sorted_bf = view.map(picardrun.picard_sort, *args)
# index bam
args = zip(*itertools.product([picard], sorted_bf))
view.map(picardrun.picard_index, *args)
curr_files = novoalign_outputs
if stage == "htseq-count":
logger.info("Running htseq-count on %s" %(curr_files))
htseq_outputs = curr_files
column_names = _get_short_names(input_files)
logger.info("Column names: %s" % (column_names))
out_file = os.path.join(config["dir"]["results"], stage,
"combined.counts")
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
combined_out = htseq_count.combine_counts(htseq_outputs,
column_names,
out_file)
rpkm = htseq_count.calculate_rpkm(combined_out,
config["annotation"]["file"])
rpkm_file = os.path.join(config["dir"]["results"], stage,
"rpkm.txt")
rpkm.to_csv(rpkm_file, sep="\t")
if stage == "coverage":
logger.info("Calculating RNASeq metrics on %s." % (curr_files))
nrun = len(curr_files)
ref = blastn.prepare_ref_file(config["stage"][stage]["ref"],
config)
ribo = config["stage"][stage]["ribo"]
picard = BroadRunner(config["program"]["picard"])
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
out_files = [replace_suffix(os.path.basename(x),
"metrics") for x in curr_files]
out_files = [os.path.join(out_dir, x) for x in out_files]
out_files = view.map(picardrun.picard_rnaseq_metrics,
[picard] * nrun,
curr_files,
[ref] * nrun,
[ribo] * nrun,
out_files)
if stage == "deseq":
conditions = [os.path.basename(x).split("_")[0] for x in
input_files]
deseq_config = _get_stage_config(config, stage)
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
for comparison in deseq_config["comparisons"]:
comparison_name = "_vs_".join(comparison)
out_dir = os.path.join(results_dir, stage, comparison_name)
safe_makedir(out_dir)
# get the of the conditons that match this comparison
indexes = [x for x, y in enumerate(conditions) if
y in comparison]
# find the htseq_files to combine and combine them
htseq_files = [htseq_outputs[index] for index in indexes]
htseq_columns = [column_names[index] for index in indexes]
logger.info(htseq_files)
logger.info(htseq_columns)
out_file = os.path.join(out_dir,
comparison_name + ".counts.txt")
combined_out = htseq_count.combine_counts(htseq_files,
htseq_columns,
out_file)
deseq_conds = [conditions[index] for index in indexes]
deseq_prefix = os.path.join(out_dir, comparison_name)
deseq_out = view.map(deseq.run, [combined_out],
[deseq_conds], [deseq_prefix])
logger.info("Annotating %s." % (deseq_out))
annotated_file = view.map(annotate.annotate_table_with_biomart,
deseq_out,
["id"],
["ensembl_gene_id"],
["human"])
if stage == "dss":
conditions = [os.path.basename(x).split("_")[0] for x in
input_files]
dss_config = _get_stage_config(config, stage)
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
for comparison in dss_config["comparisons"]:
comparison_name = "_vs_".join(comparison)
out_dir = os.path.join(results_dir, stage, comparison_name)
safe_makedir(out_dir)
# get the of the conditons that match this comparison
indexes = [x for x, y in enumerate(conditions) if
y in comparison]
# find the htseq_files to combine and combine them
htseq_files = [htseq_outputs[index] for index in indexes]
htseq_columns = [column_names[index] for index in indexes]
out_file = os.path.join(out_dir,
comparison_name + ".counts.txt")
combined_out = htseq_count.combine_counts(htseq_files,
htseq_columns,
out_file)
dss_conds = [conditions[index] for index in indexes]
dss_prefix = os.path.join(out_dir, comparison_name)
logger.info("Running DSS on %s with conditions %s and comparison %s." % (combined_out, dss_conds, comparison))
dss_out = dss.run(combined_out, dss_conds, comparison,
dss_prefix)
stop_cluster()
parser = argparse.ArgumentParser(description='generic launcher')
parser.add_argument('--profile',
required=True,
help="IPython profile name to use")
parser.add_argument('--cores',
required=True,
help="Number of IPython engines to start.")
parser.add_argument('--queue', help="Name of queue to use.")
parser.add_argument('--scheduler',
default="",
help="Name of scheduler to use (LSF or SGE)")
args = parser.parse_args()
cluster_config = {
"cluster": {
"profile": args.profile,
"cores": int(args.cores),
"queue": args.queue,
"scheduler": args.scheduler
}
}
setup_logging(cluster_config)
if _args_valid_for_scheduler(args) or _args_valid_for_local(args):
start_cluster(cluster_config)
from bipy.cluster import view
main()
stop_cluster()
else:
print parser.usage()
sys.exit(1)
def main(config_file):
# load yaml config file
with open(config_file) as in_handle:
config = yaml.load(in_handle)
# setup logging
setup_logging(config)
from bipy.log import logger
# start cluster
start_cluster(config)
from bipy.cluster import view
found = sh.find(config["dir"]["data"], "-name", "Variations")
var_dirs = [str(x).strip() for x in found]
logger.info("Var_dirs: %s" % (var_dirs))
in_dirs = map(os.path.dirname, var_dirs)
logger.info("in_dirs: %s" % (in_dirs))
# XXX for testing only load 3
#curr_files = in_dirs[0:5]
curr_files = in_dirs
# run the illumina fixer
logger.info("Running illumina fixer on %s." % (curr_files))
illf_class = STAGE_LOOKUP.get("illumina_fixer")
illf = illf_class(config)
curr_files = view.map(illf, curr_files)
# sort the vcf files
def sort_vcf(in_file):
from bipy.utils import append_stem
from bcbio.distributed.transaction import file_transaction
from bcbio.utils import file_exists
import sh
out_file = append_stem(in_file, "sorted")
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tmp_out_file:
sh.vcf_sort(in_file, _out=tmp_out_file)
return out_file
# combine
out_file = os.path.join(config["dir"].get("results", "results"),
"geminiloader",
"all_combined.vcf")
logger.info("Combining files %s into %s." % (curr_files, out_file))
if file_exists(out_file):
curr_files = [out_file]
else:
curr_files = [genotype.combine_variant_files(curr_files, out_file,
config["ref"]["fasta"],
config)]
# break the VCF files up by chromosome for speed
logger.info("Breaking up %s by chromosome." % (curr_files))
breakvcf_class = STAGE_LOOKUP.get("breakvcf")
breakvcf = breakvcf_class(config)
curr_files = view.map(breakvcf, curr_files)
# run VEP on the separate files in parallel
logger.info("Running VEP on %s." % (curr_files))
vep_class = STAGE_LOOKUP.get("vep")
vep = vep_class(config)
curr_files = view.map(vep, list(flatten(curr_files)))
curr_files = filter(file_exists, curr_files)
# load the files into gemini not in parallel
# don't run in parallel
# sort the vcf files
logger.info("Sorting %s." % (curr_files))
curr_files = view.map(sort_vcf, curr_files)
# don't run the rest of this in parallel, so take the cluster down
stop_cluster()
out_file = os.path.join(config["dir"].get("results", "results"),
"geminiloader",
"all_combined.vep.vcf")
logger.info("Combining files %s into %s." % (curr_files, out_file))
if file_exists(out_file):
curr_files = [out_file]
else:
curr_files = [genotype.combine_variant_files(curr_files, out_file,
config["ref"]["fasta"],
config)]
logger.info("Loading %s into gemini." % (curr_files))
gemini_class = STAGE_LOOKUP.get("geminiloader")
geminiloader = gemini_class(config)
curr_files = map(geminiloader, curr_files)
logger.info("Run complete.")
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
start_cluster(config)
# after the cluster is up, import the view to i
from bipy.cluster import view
input_files = config["input"]
results_dir = config["dir"]["results"]
# make the needed directories
map(safe_makedir, config["dir"].values())
curr_files = input_files
## qc steps
for stage in config["run"]:
if stage == "fastqc":
# run the basic fastqc
logger.info("Running %s on %s" % (stage, str(curr_files)))
fastqc_config = config["stage"][stage]
fastqc_outputs = view.map(fastqc.run, curr_files,
[fastqc_config] * len(curr_files),
[config] * len(curr_files))
# this does nothing for now, not implemented yet
summary_file = _combine_fastqc(fastqc_outputs)
if stage == "trim":
logger.info("Trimming poor quality ends "
" from %s" % (str(curr_files)))
nlen = len(curr_files)
min_length = str(config["stage"][stage].get("min_length", 20))
# trim low quality ends of reads
# do this dirty for now
out_dir = os.path.join(results_dir, "trimmed")
safe_makedir(out_dir)
out_files = [append_stem(os.path.basename(x), "trim") for
x in curr_files]
out_files = [os.path.join(out_dir, x) for x in out_files]
# XXX remove the magic number of 10 the length of the
# minimum read to keep
out_files = view.map(sickle.run, curr_files,
["se"] * nlen,
["sanger"] * nlen,
[min_length] * nlen,
out_files)
curr_files = out_files
if stage == "tagdust":
input_files = curr_files
# remove tags matching the other miRNA tested
logger.info("Running %s on %s." % (stage, input_files))
tagdust_config = config["stage"][stage]
tagdust_outputs = view.map(tagdust.run, input_files,
[tagdust_config] * len(input_files),
[config] * len(input_files))
curr_files = [x[0] for x in tagdust_outputs]
if stage == "filter_length":
# filter out reads below or above a certain length
filter_config = config["stage"][stage]
min_length = filter_config.get("min_length", 0)
max_length = filter_config.get("max_length", MAX_READ_LENGTH)
# length predicate
def length_filter(x):
return min_length < len(x.seq) < max_length
# filter the input reads based on length
# parallelizing this doesn't seem to work
# ipython can't accept closures as an argument to view.map()
"""
filtered_fastq = view.map(filter_seqio, tagdust_outputs,
[lf] * len(tagdust_outputs),
["filt"] * len(tagdust_outputs),
["fastq"] * len(tagdust_outputs))"""
out_files = [append_stem(os.path.basename(input_file[0]),
"filt") for input_file in tagdust_outputs]
out_dir = os.path.join(config["dir"]["results"],
"length_filtered")
safe_makedir(out_dir)
out_files = [os.path.join(out_dir, x) for x in out_files]
filtered_fastq = [filter_seqio(x[0], length_filter, y, "fastq")
for x, y in zip(tagdust_outputs, out_files)]
curr_files = filtered_fastq
if stage == "count_ends":
logger.info("Compiling nucleotide counts at 3' and 5' ends.")
# count the nucleotide at the end of each read
def count_ends(x, y):
""" keeps a running count of an arbitrary set of keys
during the reduce step """
x[y] = x.get(y, 0) + 1
return x
def get_3prime_end(x):
return str(x.seq[-1])
def get_5prime_end(x):
return str(x.seq[0])
def output_counts(end_function, count_file):
# if the count_file already exists, skip
outdir = os.path.join(config["dir"]["results"], stage)
safe_makedir(outdir)
count_file = os.path.join(outdir, count_file)
if os.path.exists(count_file):
return count_file
# outputs a tab file of the counts at the end
# of the fastq files kj
counts = [reduce(count_ends,
apply_seqio(x, end_function, kind="fastq"),
{}) for x in curr_files]
df = pd.DataFrame(counts,
index=map(_short_name, curr_files))
df = df.astype(float)
total = df.sum(axis=1)
df = df.div(total, axis=0)
df["total"] = total
df.to_csv(count_file, sep="\t")
output_counts(get_3prime_end, "3prime_counts.tsv")
output_counts(get_5prime_end, "5prime_counts.tsv")
if stage == "tophat":
tophat_config = config["stage"][stage]
logger.info("Running tophat on %s" % (str(curr_files)))
nlen = len(curr_files)
pair_file = None
ref_file = tophat_config["annotation"]
out_base = os.path.join(results_dir, "mirna")
align_dir = os.path.join(results_dir, "tophat")
config = config
tophat_files = view.map(tophat.align,
curr_files,
[pair_file] * nlen,
[ref_file] * nlen,
[out_base] * nlen,
[align_dir] * nlen,
[config] * nlen)
curr_files = tophat_files
if stage == "novoalign":
logger.info("Running novoalign on %s" % (str(curr_files)))
# align
ref = config["genome"]["file"]
novoalign_config = config["stage"][stage]
aligned_outputs = view.map(novoalign.run, curr_files,
[ref] * len(curr_files),
[novoalign_config] * len(curr_files),
[config] * len(curr_files))
# convert sam to bam, sort and index
picard = BroadRunner(config["program"]["picard"], None, {})
bamfiles = view.map(picardrun.picard_formatconverter,
[picard] * len(aligned_outputs),
aligned_outputs)
sorted_bf = view.map(picardrun.picard_sort,
[picard] * len(bamfiles),
bamfiles)
view.map(picardrun.picard_index, [picard] * len(sorted_bf),
sorted_bf)
# these files are the new starting point for the downstream
# analyses, so copy them over into the data dir and setting
# them to read only
#data_dir = os.path.join(config["dir"]["data"], stage)
#safe_makedir(data_dir)
#view.map(shutil.copy, sorted_bf, [data_dir] * len(sorted_bf))
#new_files = [os.path.join(data_dir, x) for x in
# map(os.path.basename, sorted_bf)]
#[os.chmod(x, stat.S_IREAD | stat.S_IRGRP) for x in new_files]
# index the bam files for later use
#view.map(picardrun.picard_index, [picard] * len(new_files),
# new_files)
curr_files = sorted_bf
if stage == "new_coverage":
logger.info("Calculating RNASeq metrics on %s." % (curr_files))
nrun = len(curr_files)
ref = blastn.prepare_ref_file(config["stage"][stage]["ref"],
config)
ribo = config["stage"][stage]["ribo"]
picard = BroadRunner(config["program"]["picard"], None, {})
out_dir = os.path.join(results_dir, "new_coverage")
safe_makedir(out_dir)
out_files = [replace_suffix(os.path.basename(x),
"metrics") for x in curr_files]
out_files = [os.path.join(out_dir, x) for x in out_files]
out_files = view.map(picardrun.picard_rnaseq_metrics,
[picard] * nrun,
curr_files,
[ref] * nrun,
[ribo] * nrun,
out_files)
curr_files = out_files
if stage == "coverage":
gtf = blastn.prepare_ref_file(config["annotation"], config)
logger.info("Calculating coverage of features in %s for %s"
% (gtf, str(sorted_bf)))
out_files = [replace_suffix(x, "counts.bed") for
x in sorted_bf]
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
logger.info(out_files)
out_files = [os.path.join(out_dir,
os.path.basename(x)) for x in out_files]
logger.info(out_files)
view.map(bedtools.count_overlaps, sorted_bf,
[gtf] * len(sorted_bf),
out_files)
if stage == "htseq-count":
nfiles = len(curr_files)
htseq_config = _get_stage_config(config, stage)
htseq_outputs = view.map(htseq_count.run_with_config,
aligned_outputs,
[config] * nfiles,
[stage] * nfiles)
column_names = _get_short_names(input_files)
logger.info("Column names: %s" % (column_names))
out_file = os.path.join(config["dir"]["results"], stage,
"combined.counts")
combined_out = htseq_count.combine_counts(htseq_outputs,
column_names,
out_file)
if stage == "bedtools_intersect":
bedfiles = config["stage"]["bedtools_intersect"].get("bed", None)
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
for bedfile in bedfiles:
bedbase, bedext = os.path.splitext(bedfile)
out_files = [remove_suffix(x) for x in sorted_bf]
out_files = [os.path.join(out_dir, os.path.basename(x)) for x in
out_files]
out_files = ["_vs_".join([x, os.path.basename(bedbase)])
for x in out_files]
out_files = [".".join([x, "bam"]) for x in out_files]
test_out = map(bedtools.intersectbam2bed, sorted_bf,
[bedfile] * len(sorted_bf),
[False] * len(sorted_bf),
out_files)
count_files = [replace_suffix(x, "stats") for x in
out_files]
map(write_ratios, sorted_bf, out_files, count_files)
if stage == "piranha":
piranha_runner = piranha.PiranhaStage(config)
out_files = view.map(piranha_runner, curr_files)
stop_cluster()
view.map(rseqc.junction_annotation, *rseq_args)
view.map(rseqc.junction_saturation, *rseq_args)
RPKM_args = zip(*product(final_bamfiles, [config]))
RPKM_count_out = view.map(rseqc.RPKM_count, *RPKM_args)
RPKM_count_fixed = view.map(rseqc.fix_RPKM_count_file,
RPKM_count_out)
"""
annotate_args = zip(*product(RPKM_count_fixed,
["gene_id"],
["ensembl_gene_id"],
["human"]))
view.map(annotate.annotate_table_with_biomart,
*annotate_args)
"""
view.map(rseqc.RPKM_saturation, *rseq_args)
curr_files = tophat_outputs
# end gracefully
stop_cluster()
if __name__ == "__main__":
# read in the config file and perform initial setup
main_config_file = sys.argv[1]
with open(main_config_file) as config_in_handle:
startup_config = yaml.load(config_in_handle)
setup_logging(startup_config)
start_cluster(startup_config)
from bipy.cluster import view
main(main_config_file)
def main(config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
setup_logging(config)
start_cluster(config)
# after the cluster is up, import the view to i
from bipy.cluster import view
input_files = config["input"]
results_dir = config["dir"]["results"]
# make the needed directories
map(safe_makedir, config["dir"].values())
curr_files = input_files
## qc steps
for stage in config["run"]:
if stage == "fastqc":
# run the basic fastqc
logger.info("Running %s on %s" % (stage, str(curr_files)))
fastqc_config = config["stage"][stage]
fastqc_outputs = view.map(fastqc.run, curr_files,
[fastqc_config] * len(curr_files),
[config] * len(curr_files))
# this does nothing for now, not implemented yet
summary_file = _combine_fastqc(fastqc_outputs)
if stage == "trim":
logger.info("Trimming poor quality ends "
" from %s" % (str(curr_files)))
nlen = len(curr_files)
min_length = str(config["stage"][stage].get("min_length", 20))
# trim low quality ends of reads
# do this dirty for now
out_dir = os.path.join(results_dir, "trimmed")
safe_makedir(out_dir)
out_files = [
append_stem(os.path.basename(x), "trim") for x in curr_files
]
out_files = [os.path.join(out_dir, x) for x in out_files]
# XXX remove the magic number of 10 the length of the
# minimum read to keep
out_files = view.map(sickle.run, curr_files, ["se"] * nlen,
["sanger"] * nlen, [min_length] * nlen,
out_files)
curr_files = out_files
if stage == "tagdust":
input_files = curr_files
# remove tags matching the other miRNA tested
logger.info("Running %s on %s." % (stage, input_files))
tagdust_config = config["stage"][stage]
tagdust_outputs = view.map(tagdust.run, input_files,
[tagdust_config] * len(input_files),
[config] * len(input_files))
curr_files = [x[0] for x in tagdust_outputs]
if stage == "filter_length":
# filter out reads below or above a certain length
filter_config = config["stage"][stage]
min_length = filter_config.get("min_length", 0)
max_length = filter_config.get("max_length", MAX_READ_LENGTH)
# length predicate
def length_filter(x):
return min_length < len(x.seq) < max_length
# filter the input reads based on length
# parallelizing this doesn't seem to work
# ipython can't accept closures as an argument to view.map()
"""
filtered_fastq = view.map(filter_seqio, tagdust_outputs,
[lf] * len(tagdust_outputs),
["filt"] * len(tagdust_outputs),
["fastq"] * len(tagdust_outputs))"""
out_files = [
append_stem(os.path.basename(input_file[0]), "filt")
for input_file in tagdust_outputs
]
out_dir = os.path.join(config["dir"]["results"], "length_filtered")
safe_makedir(out_dir)
out_files = [os.path.join(out_dir, x) for x in out_files]
filtered_fastq = [
filter_seqio(x[0], length_filter, y, "fastq")
for x, y in zip(tagdust_outputs, out_files)
]
curr_files = filtered_fastq
if stage == "count_ends":
logger.info("Compiling nucleotide counts at 3' and 5' ends.")
# count the nucleotide at the end of each read
def count_ends(x, y):
""" keeps a running count of an arbitrary set of keys
during the reduce step """
x[y] = x.get(y, 0) + 1
return x
def get_3prime_end(x):
return str(x.seq[-1])
def get_5prime_end(x):
return str(x.seq[0])
def output_counts(end_function, count_file):
# if the count_file already exists, skip
outdir = os.path.join(config["dir"]["results"], stage)
safe_makedir(outdir)
count_file = os.path.join(outdir, count_file)
if os.path.exists(count_file):
return count_file
# outputs a tab file of the counts at the end
# of the fastq files kj
counts = [
reduce(count_ends,
apply_seqio(x, end_function, kind="fastq"), {})
for x in curr_files
]
df = pd.DataFrame(counts, index=map(_short_name, curr_files))
df = df.astype(float)
total = df.sum(axis=1)
df = df.div(total, axis=0)
df["total"] = total
df.to_csv(count_file, sep="\t")
output_counts(get_3prime_end, "3prime_counts.tsv")
output_counts(get_5prime_end, "5prime_counts.tsv")
if stage == "tophat":
tophat_config = config["stage"][stage]
logger.info("Running tophat on %s" % (str(curr_files)))
nlen = len(curr_files)
pair_file = None
ref_file = tophat_config["annotation"]
out_base = os.path.join(results_dir, "mirna")
align_dir = os.path.join(results_dir, "tophat")
config = config
tophat_files = view.map(tophat.align, curr_files,
[pair_file] * nlen, [ref_file] * nlen,
[out_base] * nlen, [align_dir] * nlen,
[config] * nlen)
curr_files = tophat_files
if stage == "novoalign":
logger.info("Running novoalign on %s" % (str(curr_files)))
# align
ref = config["genome"]["file"]
novoalign_config = config["stage"][stage]
aligned_outputs = view.map(novoalign.run, curr_files,
[ref] * len(curr_files),
[novoalign_config] * len(curr_files),
[config] * len(curr_files))
# convert sam to bam, sort and index
picard = BroadRunner(config["program"]["picard"], None, {})
bamfiles = view.map(picardrun.picard_formatconverter,
[picard] * len(aligned_outputs),
aligned_outputs)
sorted_bf = view.map(picardrun.picard_sort,
[picard] * len(bamfiles), bamfiles)
view.map(picardrun.picard_index, [picard] * len(sorted_bf),
sorted_bf)
# these files are the new starting point for the downstream
# analyses, so copy them over into the data dir and setting
# them to read only
#data_dir = os.path.join(config["dir"]["data"], stage)
#safe_makedir(data_dir)
#view.map(shutil.copy, sorted_bf, [data_dir] * len(sorted_bf))
#new_files = [os.path.join(data_dir, x) for x in
# map(os.path.basename, sorted_bf)]
#[os.chmod(x, stat.S_IREAD | stat.S_IRGRP) for x in new_files]
# index the bam files for later use
#view.map(picardrun.picard_index, [picard] * len(new_files),
# new_files)
curr_files = sorted_bf
if stage == "new_coverage":
logger.info("Calculating RNASeq metrics on %s." % (curr_files))
nrun = len(curr_files)
ref = blastn.prepare_ref_file(config["stage"][stage]["ref"],
config)
ribo = config["stage"][stage]["ribo"]
picard = BroadRunner(config["program"]["picard"], None, {})
out_dir = os.path.join(results_dir, "new_coverage")
safe_makedir(out_dir)
out_files = [
replace_suffix(os.path.basename(x), "metrics")
for x in curr_files
]
out_files = [os.path.join(out_dir, x) for x in out_files]
out_files = view.map(picardrun.picard_rnaseq_metrics,
[picard] * nrun, curr_files, [ref] * nrun,
[ribo] * nrun, out_files)
curr_files = out_files
if stage == "coverage":
gtf = blastn.prepare_ref_file(config["annotation"], config)
logger.info("Calculating coverage of features in %s for %s" %
(gtf, str(sorted_bf)))
out_files = [replace_suffix(x, "counts.bed") for x in sorted_bf]
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
logger.info(out_files)
out_files = [
os.path.join(out_dir, os.path.basename(x)) for x in out_files
]
logger.info(out_files)
view.map(bedtools.count_overlaps, sorted_bf,
[gtf] * len(sorted_bf), out_files)
if stage == "htseq-count":
nfiles = len(curr_files)
htseq_config = _get_stage_config(config, stage)
htseq_outputs = view.map(htseq_count.run_with_config,
aligned_outputs, [config] * nfiles,
[stage] * nfiles)
column_names = _get_short_names(input_files)
logger.info("Column names: %s" % (column_names))
out_file = os.path.join(config["dir"]["results"], stage,
"combined.counts")
combined_out = htseq_count.combine_counts(htseq_outputs,
column_names, out_file)
if stage == "bedtools_intersect":
bedfiles = config["stage"]["bedtools_intersect"].get("bed", None)
out_dir = os.path.join(results_dir, stage)
safe_makedir(out_dir)
for bedfile in bedfiles:
bedbase, bedext = os.path.splitext(bedfile)
out_files = [remove_suffix(x) for x in sorted_bf]
out_files = [
os.path.join(out_dir, os.path.basename(x))
for x in out_files
]
out_files = [
"_vs_".join([x, os.path.basename(bedbase)])
for x in out_files
]
out_files = [".".join([x, "bam"]) for x in out_files]
test_out = map(bedtools.intersectbam2bed, sorted_bf,
[bedfile] * len(sorted_bf),
[False] * len(sorted_bf), out_files)
count_files = [replace_suffix(x, "stats") for x in out_files]
map(write_ratios, sorted_bf, out_files, count_files)
if stage == "piranha":
piranha_runner = piranha.PiranhaStage(config)
out_files = view.map(piranha_runner, curr_files)
stop_cluster()