def parseGene(pickle_filename, event):
"""
Parse a pickled gene.
"""
if not os.path.isfile(pickle_filename):
raise Exception, "Error: no filename %s" %(pickle_filename)
gff_genes = gff_utils.load_indexed_gff_file(pickle_filename)
if gff_genes == None:
raise Exception, "Error: could not load genes from %s" \
%(pickle_filename)
exon_starts = []
exon_ends = []
mRNAs = []
chrom = None
mRNA_ids = []
for gene_id, gene_info in gff_genes.iteritems():
if event == gene_id:
gene_obj = gene_info['gene_object']
gene_hierarchy = gene_info['hierarchy']
tx_start, tx_end = gff_utils.get_inclusive_txn_bounds(\
gene_hierarchy[gene_id])
chrom = gene_obj.chrom
for mRNA_id, mRNA_info in gene_hierarchy[gene_id]['mRNAs'].iteritems():
mRNA = []
mRNA_ids.append(mRNA_id)
for exon_id, exon_info in gene_hierarchy[gene_id]['mRNAs']\
[mRNA_id]['exons'].\
iteritems():
exon_rec = gene_hierarchy[gene_id]['mRNAs']\
[mRNA_id]['exons'][exon_id]['record']
strand = exon_rec.strand
exon_starts.append(exon_rec.start)
exon_ends.append(exon_rec.end)
mRNA.append(sorted([exon_rec.start, exon_rec.end]))
mRNAs.append(mRNA)
break
mRNAs.sort(key=len)
return tx_start, tx_end, exon_starts, exon_ends, gene_obj, \
mRNAs, strand, chrom, mRNA_ids
def parseGene(pickle_filename, event):
"""
Parse a pickled gene.
"""
if not os.path.isfile(pickle_filename):
raise Exception, "Error: no filename %s" % (pickle_filename)
gff_genes = gff_utils.load_indexed_gff_file(pickle_filename)
if gff_genes == None:
raise Exception, "Error: could not load genes from %s" \
%(pickle_filename)
exon_starts = []
exon_ends = []
mRNAs = []
chrom = None
for gene_id, gene_info in gff_genes.iteritems():
if event == gene_id:
gene_obj = gene_info['gene_object']
gene_hierarchy = gene_info['hierarchy']
tx_start, tx_end = gff_utils.get_inclusive_txn_bounds(\
gene_hierarchy[gene_id])
chrom = gene_obj.chrom
for mRNA_id, mRNA_info in gene_hierarchy[gene_id][
'mRNAs'].iteritems():
mRNA = []
for exon_id, exon_info in gene_hierarchy[gene_id]['mRNAs']\
[mRNA_id]['exons'].\
iteritems():
exon_rec = gene_hierarchy[gene_id]['mRNAs']\
[mRNA_id]['exons'][exon_id]['record']
strand = exon_rec.strand
exon_starts.append(exon_rec.start)
exon_ends.append(exon_rec.end)
mRNA.append(sorted([exon_rec.start, exon_rec.end]))
mRNAs.append(mRNA)
break
mRNAs.sort(key=len)
return tx_start, tx_end, exon_starts, exon_ends, gene_obj, \
mRNAs, strand, chrom
def compute_gene_psi(gene_ids, gff_index_filename, bam_filename,
output_dir, read_len, overhang_len,
paired_end=None,
event_type=None,
verbose=True):
"""
Run Psi at the Gene-level (for multi-isoform inference.)
Arguments:
- Set of gene IDs corresponding to gene IDs from the GFF
- Indexed GFF filename describing the genes
- BAM filename with the reads (must be sorted and indexed)
- Output directory
- Optional: Run in paired-end mode. Gives mean and standard deviation
of fragment length distribution.
"""
misc_utils.make_dir(output_dir)
if not os.path.exists(gff_index_filename):
print "Error: No GFF %s" %(gff_index_filename)
return
num_genes = len(gene_ids)
print "Computing Psi for %d genes..." %(num_genes)
print " - " + ", ".join(gene_ids)
print " - GFF filename: %s" %(gff_index_filename)
print " - BAM: %s" %(bam_filename)
print " - Outputting to: %s" %(output_dir)
if paired_end:
print " - Paired-end mode: ", paired_end
settings = Settings.get()
settings_params = Settings.get_sampler_params()
burn_in = settings_params["burn_in"]
lag = settings_params["lag"]
num_iters = settings_params["num_iters"]
num_chains = settings_params["num_chains"]
min_event_reads = Settings.get_min_event_reads()
strand_rule = Settings.get_strand_param()
mean_frag_len = None
frag_variance = None
if paired_end:
mean_frag_len = int(paired_end[0])
frag_variance = power(int(paired_end[1]), 2)
# Load the genes from the GFF
gff_genes = gff_utils.load_indexed_gff_file(gff_index_filename)
# If given a template for the SAM file, use it
template = None
if settings and "sam_template" in settings:
template = settings["sam_template"]
if "filter_reads" not in settings:
filter_reads = True
else:
filter_reads = settings["filter_reads"]
# Load the BAM file upfront
bamfile = sam_utils.load_bam_reads(bam_filename,
template=template)
# Check if we're in compressed mode
compressed_mode = misc_utils.is_compressed_index(gff_index_filename)
for gene_id, gene_info in gff_genes.iteritems():
lookup_id = gene_id
# Skip genes that we were not asked to run on
if lookup_id not in gene_ids:
continue
gene_obj = gene_info['gene_object']
gene_hierarchy = gene_info['hierarchy']
# Sanity check: if the isoforms are all shorter than the read,
# skip the event
if all(map(lambda l: l < read_len, gene_obj.iso_lens)):
print "All isoforms of %s shorter than %d, so skipping" \
%(gene_id, read_len)
continue
# Find the most inclusive transcription start and end sites
# for each gene
tx_start, tx_end = \
gff_utils.get_inclusive_txn_bounds(gene_info['hierarchy'][gene_id])
# Fetch reads aligning to the gene boundaries
gene_reads = \
sam_utils.fetch_bam_reads_in_gene(bamfile,
gene_obj.chrom,
tx_start,
tx_end,
gene_obj)
# Parse reads: checking strandedness and pairing
# reads in case of paired-end data
reads, num_raw_reads = \
sam_utils.sam_parse_reads(gene_reads,
paired_end=paired_end,
strand_rule=strand_rule,
target_strand=gene_obj.strand,
given_read_len=read_len)
# Skip gene if none of the reads align to gene boundaries
if filter_reads:
if num_raw_reads < min_event_reads:
print "Only %d reads in gene, skipping (needed >= %d reads)" \
%(num_raw_reads,
min_event_reads)
continue
else:
print "%d raw reads in event" %(num_raw_reads)
num_isoforms = len(gene_obj.isoforms)
hyperparameters = ones(num_isoforms)
##
## Run the sampler
##
# Create the sampler with the right parameters depending on whether
# this is a paired-end or single-end data set.
if paired_end:
# Sampler parameters for paired-end mode
sampler_params = \
miso.get_paired_end_sampler_params(num_isoforms,
mean_frag_len,
frag_variance,
read_len,
overhang_len=overhang_len)
sampler = miso.MISOSampler(sampler_params,
paired_end=True,
log_dir=output_dir)
else:
# Sampler parameters for single-end mode
sampler_params = miso.get_single_end_sampler_params(num_isoforms,
read_len,
overhang_len)
sampler = miso.MISOSampler(sampler_params,
paired_end=False,
log_dir=output_dir)
# Make directory for chromosome -- if given an event type, put
# the gene in the event type directory
if event_type != None:
chrom_dir = os.path.join(output_dir, event_type, gene_obj.chrom)
else:
chrom_dir = os.path.join(output_dir, gene_obj.chrom)
try:
os.makedirs(chrom_dir)
except OSError:
pass
# Pick .miso output filename based on the pickle filename
miso_basename = os.path.basename(gff_index_filename)
if not miso_basename.endswith(".pickle"):
print "Error: Invalid index file %s" %(gff_index_filename)
sys.exit(1)
miso_basename = miso_basename.replace(".pickle", "")
output_filename = os.path.join(chrom_dir, "%s" %(miso_basename))
sampler.run_sampler(num_iters, reads, gene_obj, hyperparameters,
sampler_params, output_filename,
num_chains=num_chains,
burn_in=burn_in,
lag=lag)
def main():
from optparse import OptionParser
parser = OptionParser()
##
## Main options
##
parser.add_option("--compute-gene-psi", dest="compute_gene_psi",
nargs=4, default=None,
help="Compute Psi using for a given multi-isoform gene. "
"Expects four arguments: the first is a gene ID or set "
"of comma-separated (no spaces) gene IDs, "
"the second is a GFF indexed file with the gene "
"information, the third is a sorted and "
"indexed BAM file with reads aligned to the gene, "
"and the fourth is an output directory.")
parser.add_option("--paired-end", dest="paired_end",
nargs=2, default=None,
help="Run in paired-end mode. Takes a mean and standard "
"deviation for the fragment length distribution (assumed "
"to have discretized normal form.)")
parser.add_option("--compute-genes-from-file", dest="compute_genes_from_file",
nargs=3, default=None,
help="Runs on a set of genes from a file. Takes as input: "
"(1) a two-column tab-delimited file, where column 1 is the "
"event ID (ID field from GFF) and the second column is "
"the path to the indexed GFF file for that event. "
"MISO will run on all the events described in the file, "
"(2) a sorted, indexed BAM file to run on, and (3) a "
"directory to output results to.")
##
## Psi utilities
##
parser.add_option("--compare-samples", dest="samples_to_compare",
nargs=3, default=None,
help="Compute comparison statistics between the two "
"given samples. Expects three directories: the first is "
"sample1's MISO output, the second is sample2's MISO "
"output, and the third is the directory where "
"results of the sample comparison will be outputted.")
parser.add_option("--comparison-labels", dest="comparison_labels",
nargs=2, default=None,
help="Use these labels for the sample comparison "
"made by --compare-samples. "
"Takes two arguments: the label for sample 1 "
"and the label for sample 2, where sample 1 and "
"sample 2 correspond to the order of samples given "
"to --compare-samples.")
parser.add_option("--summarize-samples", dest="summarize_samples",
nargs=2, default=None,
help="Compute summary statistics of the given set "
"of samples. Expects a directory with MISO output "
"and a directory to output summary file to.")
parser.add_option("--summary-label", dest="summary_label",
nargs=1, default=None,
help="Label for MISO summary file. If not given, "
"uses basename of MISO output directory.")
parser.add_option("--use-cluster", action="store_true",
dest="use_cluster", default=False)
parser.add_option("--chunk-jobs", dest="chunk_jobs",
default=False, type="int",
help="Size (in number of events) of each job to "
"chunk events file into. Only applies when "
"running on cluster.")
parser.add_option("--settings-filename", dest="settings_filename",
default=os.path.join(miso_settings_path,
"settings",
"miso_settings.txt"),
help="Filename specifying MISO settings.")
parser.add_option("--read-len", dest="read_len", type="int",
default=None)
parser.add_option("--overhang-len", dest="overhang_len", type="int",
default=None)
parser.add_option("--event-type", dest="event_type", default=None,
help="Event type of two-isoform "
"events (e.g. 'SE', 'RI', 'A3SS', ...)")
parser.add_option("--use-compressed", dest="use_compressed",
nargs=1, default=None,
help="Use compressed event IDs. Takes as input a "
"genes_to_filenames.shelve file produced by the "
"index_gff script.")
##
## Gene utilities
##
parser.add_option("--view-gene", dest="view_gene",
nargs=1, default=None,
help="View the contents of a gene/event that has "
"been indexed. Takes as input an "
"indexed (.pickle) filename.")
(options, args) = parser.parse_args()
if options.compute_gene_psi is None:
greeting()
##
## Load the settings file
##
Settings.load(os.path.expanduser(options.settings_filename))
use_compressed = None
if options.use_compressed is not None:
use_compressed = \
os.path.abspath(os.path.expanduser(options.use_compressed))
if not os.path.exists(use_compressed):
print "Error: mapping filename from event IDs to compressed IDs %s " \
"is not found." %(use_compressed)
sys.exit(1)
else:
print "Compression being used."
if options.samples_to_compare is not None:
sample1_dirname = os.path.abspath(options.samples_to_compare[0])
sample2_dirname = os.path.abspath(options.samples_to_compare[1])
output_dirname = os.path.abspath(options.samples_to_compare[2])
if not os.path.isdir(output_dirname):
print "Making comparisons directory: %s" %(output_dirname)
misc_utils.make_dir(output_dirname)
ht.output_samples_comparison(sample1_dirname,
sample2_dirname,
output_dirname,
sample_labels=options.comparison_labels,
use_compressed=use_compressed)
##
## Main interface based on SAM files
##
if options.compute_genes_from_file != None:
# Run on events given by file
run_compute_genes_from_file(options)
if options.compute_gene_psi != None:
run_compute_gene_psi(options)
##
## Summarizing samples
##
if options.summarize_samples:
samples_dir = \
os.path.abspath(os.path.expanduser(options.summarize_samples[0]))
if options.summary_label != None:
samples_label = options.summary_label
print "Using summary label: %s" %(samples_label)
else:
samples_label = \
os.path.basename(os.path.expanduser(samples_dir))
assert(len(samples_label) >= 1)
summary_output_dir = \
os.path.abspath(os.path.join(os.path.expanduser(options.summarize_samples[1]),
'summary'))
if not os.path.isdir(summary_output_dir):
os.makedirs(summary_output_dir)
summary_filename = os.path.join(summary_output_dir,
'%s.miso_summary' %(samples_label))
summarize_sampler_results(samples_dir, summary_filename,
use_compressed=use_compressed)
if options.view_gene != None:
indexed_gene_filename = \
os.path.abspath(os.path.expanduser(options.view_gene))
print "Viewing genes in %s" %(indexed_gene_filename)
gff_genes = gff_utils.load_indexed_gff_file(indexed_gene_filename)
if gff_genes == None:
print "No genes."
sys.exit(1)
for gene_id, gene_info in gff_genes.iteritems():
print "Gene %s" %(gene_id)
gene_obj = gene_info['gene_object']
print " - Gene object: ", gene_obj
print "=="
print "Isoforms: "
for isoform in gene_obj.isoforms:
print " - ", isoform
print "=="
print "mRNA IDs: "
for mRNA_id in gene_info['hierarchy'][gene_id]['mRNAs']:
print "%s" %(mRNA_id)
print "=="
print "Exons: "
for exon in gene_obj.parts:
print " - ", exon
def main():
from optparse import OptionParser
parser = OptionParser()
parser.add_option("--run", dest="compute_genes_psi",
nargs=2, default=None,
help="Compute Psi values for a given GFF annotation "
"of either whole mRNA isoforms or isoforms produced by "
"single alternative splicing events. Expects two "
"arguments: an indexed GFF directory with genes to "
"process, and a sorted, indexed BAM file (with "
"headers) to run on.")
parser.add_option("--event-type", dest="event_type", nargs=1,
help="[OPTIONAL] Type of event (e.g. SE, RI, A3SS, ...)",
default=None)
parser.add_option("--use-cluster", dest="use_cluster",
action="store_true", default=False,
help="Run events on cluster.")
parser.add_option("--chunk-jobs", dest="chunk_jobs",
default=False, type="int",
help="Size (in number of events) of each job to chunk "
"events file into. Only applies when running on cluster.")
parser.add_option("--no-filter-events", dest="no_filter_events",
action="store_true", default=False,
help="Do not filter events for computing Psi. "
"By default, MISO computes Psi only for events that "
"have a sufficient number of junction reads. "
"The default filter varies by event type.")
parser.add_option("--settings-filename", dest="settings_filename",
default=os.path.join(miso_settings_path,
"settings",
"miso_settings.txt"),
help="Filename specifying MISO settings.")
parser.add_option("--read-len", dest="read_len", default=None, type="int",
help="Length of sequenced reads.")
parser.add_option("--paired-end", dest="paired_end", nargs=2, default=None,
help="Run in paired-end mode. Takes mean and "
"standard deviation of insert length distribution.")
parser.add_option("--overhang-len", dest="overhang_len",
default=None, type="int",
help="Length of overhang constraints "
"imposed on junctions.")
parser.add_option("--output-dir", dest="output_dir", default=None,
help="Directory for MISO output.")
parser.add_option("--job-name", dest="job_name", nargs=1,
help="Name for jobs submitted to queue for SGE jobs. " \
"Default is misojob", default="misojob")
parser.add_option("--SGEarray", dest="SGEarray",
action="store_true", default=False,
help="Use MISO on cluster with Sun Grid Engine. "
"To be used in conjunction with --use-cluster option.")
parser.add_option("--prefilter", dest="prefilter", default=False,
action="store_true",
help="Prefilter events based on coverage. If given as "
"argument, run will begin by mapping BAM reads to event "
"regions (using bedtools), and omit events that do not "
"meet coverage criteria from the run. By default, turned "
"off. Note that events that do not meet the coverage criteria "
"will not be processed regardless, but --prefilter simply "
"does this filtering step at the start of the run, potentially "
"saving computation time so that low coverage events will not "
"be processed or distributed to jobs if MISO is run on a "
"cluster. This options requires bedtools to be installed and "
"available on path.")
parser.add_option("-p", dest="num_proc", default=None, nargs=1,
help="Number of processors to use. Only applies when running " \
"MISO on a single machine with multiple cores; does not apply " \
"to runs submitted to cluster with --use-cluster.")
parser.add_option("--version", dest="version", default=False,
action="store_true",
help="Print MISO version.")
parser.add_option("--no-wait", dest="no_wait", default=False,
action="store_true",
help="If passed in, do not wait on cluster jobs after " \
"they are submitted. By default, wait.")
##
## Gene utilities
##
parser.add_option("--view-gene", dest="view_gene",
nargs=1, default=None,
help="View the contents of a gene/event that has "
"been indexed. Takes as input an "
"indexed (.pickle) filename.")
(options, args) = parser.parse_args()
greeting()
if options.version:
print "MISO version %s\n" %(misopy.__version__)
##
## Load the settings file
##
if not os.path.isdir(miso_settings_path):
print "Error: %s is not a directory containing a default MISO " \
"settings filename. Please specify a settings filename " \
"using --settings-filename."
return
settings_filename = \
os.path.abspath(os.path.expanduser(options.settings_filename))
Settings.load(settings_filename)
if (not options.use_cluster) and options.chunk_jobs:
print "Error: Chunking jobs only applies when using " \
"the --use-cluster option to run MISO on cluster."
sys.exit(1)
if (not options.use_cluster) and options.SGEarray:
print "Error: SGEarray implies that you are using an SGE cluster," \
"please run again with --use-cluster option enabled."
sys.exit(1)
##
## Quantitation using BAM for all genes
##
if options.compute_genes_psi != None:
# GFF filename with genes to process
gff_filename = \
os.path.abspath(os.path.expanduser(options.compute_genes_psi[0]))
# BAM filename with reads
bam_filename = \
os.path.abspath(os.path.expanduser(options.compute_genes_psi[1]))
if options.output_dir == None:
print "Error: need --output-dir to compute Psi values."
sys.exit(1)
# Output directory to use
output_dir = os.path.abspath(os.path.expanduser(options.output_dir))
##
## Load the main logging object
##
logs_output_dir = os.path.join(output_dir, "logs")
main_logger = get_main_logger(logs_output_dir)
if options.read_len == None:
main_logger.error("need --read-len to compute Psi values.")
sys.exit(1)
overhang_len = 1
if options.paired_end != None and options.overhang_len != None:
main_logger.warning("cannot use --overhang-len in paired-end mode.\n" \
"Using overhang = 1")
if options.overhang_len != None:
overhang_len = options.overhang_len
# Whether to wait on cluster jobs or not
wait_on_jobs = not options.no_wait
compute_all_genes_psi(gff_filename, bam_filename,
options.read_len, output_dir,
main_logger,
overhang_len=overhang_len,
use_cluster=options.use_cluster,
SGEarray=options.SGEarray,
job_name=options.job_name,
chunk_jobs=options.chunk_jobs,
paired_end=options.paired_end,
settings_fname=settings_filename,
prefilter=options.prefilter,
num_proc=options.num_proc,
wait_on_jobs=wait_on_jobs)
if options.view_gene != None:
indexed_gene_filename = \
os.path.abspath(os.path.expanduser(options.view_gene))
print "Viewing genes in %s" %(indexed_gene_filename)
gff_genes = gff_utils.load_indexed_gff_file(indexed_gene_filename)
if gff_genes == None:
print "No genes."
sys.exit(1)
for gene_id, gene_info in gff_genes.iteritems():
print "Gene %s" %(gene_id)
gene_obj = gene_info['gene_object']
print " - Gene object: ", gene_obj
print "=="
print "Isoforms: "
for isoform in gene_obj.isoforms:
print " - ", isoform
print "=="
print "mRNA IDs: "
for mRNA_id in gene_info['hierarchy'][gene_id]['mRNAs']:
print "%s" %(mRNA_id)
print "=="
print "Exons: "
for exon in gene_obj.parts:
print " - ", exon
def main():
from optparse import OptionParser
parser = OptionParser()
parser.add_option("--run", dest="compute_genes_psi",
nargs=2, default=None,
help="Compute Psi values for a given GFF annotation "
"of either whole mRNA isoforms or isoforms produced by "
"single alternative splicing events. Expects two "
"arguments: an indexed GFF directory with genes to "
"process, and a sorted, indexed BAM file (with "
"headers) to run on.")
parser.add_option("--event-type", dest="event_type", nargs=1,
help="[OPTIONAL] Type of event (e.g. SE, RI, A3SS, ...)",
default=None)
parser.add_option("--use-cluster", dest="use_cluster",
action="store_true", default=False,
help="Run events on cluster.")
parser.add_option("--chunk-jobs", dest="chunk_jobs",
default=False, type="int",
help="Size (in number of events) of each job to chunk "
"events file into. Only applies when running on cluster.")
parser.add_option("--no-filter-events", dest="no_filter_events",
action="store_true", default=False,
help="Do not filter events for computing Psi. "
"By default, MISO computes Psi only for events that "
"have a sufficient number of junction reads. "
"The default filter varies by event type.")
parser.add_option("--settings-filename", dest="settings_filename",
default=os.path.join(miso_settings_path,
"settings",
"miso_settings.txt"),
help="Filename specifying MISO settings.")
parser.add_option("--read-len", dest="read_len", default=None, type="int",
help="Length of sequenced reads.")
parser.add_option("--paired-end", dest="paired_end", nargs=2, default=None,
help="Run in paired-end mode. Takes mean and "
"standard deviation of insert length distribution.")
parser.add_option("--overhang-len", dest="overhang_len",
default=None, type="int",
help="Length of overhang constraints "
"imposed on junctions.")
parser.add_option("--output-dir", dest="output_dir", default=None,
help="Directory for MISO output.")
parser.add_option("--job-name", dest="job_name", nargs=1,
help="Name for jobs submitted to queue for SGE jobs. " \
"Default is misojob", default="misojob")
parser.add_option("--SGEarray", dest="SGEarray",
action="store_true", default=False,
help="Use MISO on cluster with Sun Grid Engine. "
"To be used in conjunction with --use-cluster option.")
parser.add_option("--prefilter", dest="prefilter", default=False,
action="store_true",
help="Prefilter events based on coverage. If given as "
"argument, run will begin by mapping BAM reads to event "
"regions (using bedtools), and omit events that do not "
"meet coverage criteria from the run. By default, turned "
"off. Note that events that do not meet the coverage criteria "
"will not be processed regardless, but --prefilter simply "
"does this filtering step at the start of the run, potentially "
"saving computation time so that low coverage events will not "
"be processed or distributed to jobs if MISO is run on a "
"cluster. This options requires bedtools to be installed and "
"available on path.")
parser.add_option("-p", dest="num_proc", default=None, nargs=1,
help="Number of processors to use. Only applies when running " \
"MISO on a single machine with multiple cores; does not apply " \
"to runs submitted to cluster with --use-cluster.")
parser.add_option("--version", dest="version", default=False,
action="store_true",
help="Print MISO version.")
parser.add_option("--no-wait", dest="no_wait", default=False,
action="store_true",
help="If passed in, do not wait on cluster jobs after " \
"they are submitted. By default, wait.")
##
## Gene utilities
##
parser.add_option("--view-gene", dest="view_gene",
nargs=1, default=None,
help="View the contents of a gene/event that has "
"been indexed. Takes as input an "
"indexed (.pickle) filename.")
(options, args) = parser.parse_args()
greeting()
if options.version:
print "MISO version %s\n" %(misopy.__version__)
##
## Load the settings file
##
if not os.path.isdir(miso_settings_path):
print "Error: %s is not a directory containing a default MISO " \
"settings filename. Please specify a settings filename " \
"using --settings-filename."
return
settings_filename = \
os.path.abspath(os.path.expanduser(options.settings_filename))
Settings.load(settings_filename)
if (not options.use_cluster) and options.chunk_jobs:
print "Error: Chunking jobs only applies when using " \
"the --use-cluster option to run MISO on cluster."
sys.exit(1)
if (not options.use_cluster) and options.SGEarray:
print "Error: SGEarray implies that you are using an SGE cluster," \
"please run again with --use-cluster option enabled."
sys.exit(1)
##
## Quantitation using BAM for all genes
##
if options.compute_genes_psi != None:
# GFF filename with genes to process
gff_filename = \
os.path.abspath(os.path.expanduser(options.compute_genes_psi[0]))
# BAM filename with reads
bam_filename = \
os.path.abspath(os.path.expanduser(options.compute_genes_psi[1]))
if options.output_dir == None:
print "Error: need --output-dir to compute Psi values."
sys.exit(1)
# Output directory to use
output_dir = os.path.abspath(os.path.expanduser(options.output_dir))
if options.read_len == None:
print "Error: need --read-len to compute Psi values."
sys.exit(1)
overhang_len = 1
if options.paired_end != None and options.overhang_len != None:
print "WARNING: cannot use --overhang-len in paired-end mode."
print "Using overhang = 1"
if options.overhang_len != None:
overhang_len = options.overhang_len
# Whether to wait on cluster jobs or not
wait_on_jobs = not options.no_wait
compute_all_genes_psi(gff_filename, bam_filename,
options.read_len, output_dir,
overhang_len=overhang_len,
use_cluster=options.use_cluster,
SGEarray=options.SGEarray,
job_name=options.job_name,
chunk_jobs=options.chunk_jobs,
paired_end=options.paired_end,
settings_fname=settings_filename,
prefilter=options.prefilter,
num_proc=options.num_proc,
wait_on_jobs=wait_on_jobs)
if options.view_gene != None:
indexed_gene_filename = \
os.path.abspath(os.path.expanduser(options.view_gene))
print "Viewing genes in %s" %(indexed_gene_filename)
gff_genes = gff_utils.load_indexed_gff_file(indexed_gene_filename)
if gff_genes == None:
print "No genes."
sys.exit(1)
for gene_id, gene_info in gff_genes.iteritems():
print "Gene %s" %(gene_id)
gene_obj = gene_info['gene_object']
print " - Gene object: ", gene_obj
print "=="
print "Isoforms: "
for isoform in gene_obj.isoforms:
print " - ", isoform
print "=="
print "mRNA IDs: "
for mRNA_id in gene_info['hierarchy'][gene_id]['mRNAs']:
print "%s" %(mRNA_id)
print "=="
print "Exons: "
for exon in gene_obj.parts:
print " - ", exon
def compute_gene_psi(gene_ids, gff_index_filename, bam_filename,
output_dir, read_len, overhang_len,
paired_end=None,
event_type=None,
verbose=True):
"""
Run Psi at the Gene-level (for multi-isoform inference.)
Arguments:
- Set of gene IDs corresponding to gene IDs from the GFF
- Indexed GFF filename describing the genes
- BAM filename with the reads (must be sorted and indexed)
- Output directory
- Optional: Run in paired-end mode. Gives mean and standard deviation
of fragment length distribution.
"""
misc_utils.make_dir(output_dir)
if not os.path.exists(gff_index_filename):
print "Error: No GFF %s" %(gff_index_filename)
return
num_genes = len(gene_ids)
print "Computing Psi for %d genes..." %(num_genes)
print " - " + ", ".join(gene_ids)
print " - GFF filename: %s" %(gff_index_filename)
print " - BAM: %s" %(bam_filename)
print " - Outputting to: %s" %(output_dir)
if paired_end:
print " - Paired-end mode: ", paired_end
settings = Settings.get()
settings_params = Settings.get_sampler_params()
burn_in = settings_params["burn_in"]
lag = settings_params["lag"]
num_iters = settings_params["num_iters"]
num_chains = settings_params["num_chains"]
min_event_reads = Settings.get_min_event_reads()
strand_rule = Settings.get_strand_param()
mean_frag_len = None
frag_variance = None
if paired_end:
mean_frag_len = int(paired_end[0])
frag_variance = power(int(paired_end[1]), 2)
# Load the genes from the GFF
gff_genes = gff_utils.load_indexed_gff_file(gff_index_filename)
# If given a template for the SAM file, use it
template = None
if settings and "sam_template" in settings:
template = settings["sam_template"]
if "filter_reads" not in settings:
filter_reads = True
else:
filter_reads = settings["filter_reads"]
# Load the BAM file upfront
bamfile = sam_utils.load_bam_reads(bam_filename,
template=template)
# Check if we're in compressed mode
compressed_mode = misc_utils.is_compressed_index(gff_index_filename)
for gene_id, gene_info in gff_genes.iteritems():
lookup_id = gene_id
# Skip genes that we were not asked to run on
if lookup_id not in gene_ids:
continue
gene_obj = gene_info['gene_object']
gene_hierarchy = gene_info['hierarchy']
# Sanity check: if the isoforms are all shorter than the read,
# skip the event
if all(map(lambda l: l < read_len, gene_obj.iso_lens)):
print "All isoforms of %s shorter than %d, so skipping" \
%(gene_id, read_len)
continue
# Find the most inclusive transcription start and end sites
# for each gene
tx_start, tx_end = \
gff_utils.get_inclusive_txn_bounds(gene_info['hierarchy'][gene_id])
# Fetch reads aligning to the gene boundaries
gene_reads = \
sam_utils.fetch_bam_reads_in_gene(bamfile,
gene_obj.chrom,
tx_start,
tx_end,
gene_obj)
# Parse reads: checking strandedness and pairing
# reads in case of paired-end data
reads, num_raw_reads = \
sam_utils.sam_parse_reads(gene_reads,
paired_end=paired_end,
strand_rule=strand_rule,
target_strand=gene_obj.strand)
# Skip gene if none of the reads align to gene boundaries
if filter_reads:
if num_raw_reads < min_event_reads:
print "Only %d reads in gene, skipping (needed >= %d reads)" \
%(num_raw_reads,
min_event_reads)
continue
else:
print "%d raw reads in event" %(num_raw_reads)
num_isoforms = len(gene_obj.isoforms)
hyperparameters = ones(num_isoforms)
##
## Run the sampler
##
# Create the sampler with the right parameters depending on whether
# this is a paired-end or single-end data set.
if paired_end:
# Sampler parameters for paired-end mode
sampler_params = \
miso.get_paired_end_sampler_params(num_isoforms,
mean_frag_len,
frag_variance,
read_len,
overhang_len=overhang_len)
sampler = miso.MISOSampler(sampler_params,
paired_end=True,
log_dir=output_dir)
else:
# Sampler parameters for single-end mode
sampler_params = miso.get_single_end_sampler_params(num_isoforms,
read_len,
overhang_len)
sampler = miso.MISOSampler(sampler_params,
paired_end=False,
log_dir=output_dir)
# Make directory for chromosome -- if given an event type, put
# the gene in the event type directory
if event_type != None:
chrom_dir = os.path.join(output_dir, event_type, gene_obj.chrom)
else:
chrom_dir = os.path.join(output_dir, gene_obj.chrom)
try:
os.makedirs(chrom_dir)
except OSError:
pass
# Pick .miso output filename based on the pickle filename
miso_basename = os.path.basename(gff_index_filename)
if not miso_basename.endswith(".pickle"):
print "Error: Invalid index file %s" %(gff_index_filename)
sys.exit(1)
miso_basename = miso_basename.replace(".pickle", "")
output_filename = os.path.join(chrom_dir, "%s" %(miso_basename))
sampler.run_sampler(num_iters, reads, gene_obj, hyperparameters,
sampler_params, output_filename,
num_chains=num_chains,
burn_in=burn_in,
lag=lag)
def main():
from optparse import OptionParser
parser = OptionParser()
##
## Main options
##
parser.add_option("--compute-gene-psi", dest="compute_gene_psi",
nargs=4, default=None,
help="Compute Psi using for a given multi-isoform gene. "
"Expects four arguments: the first is a gene ID or set "
"of comma-separated (no spaces) gene IDs, "
"the second is a GFF indexed file with the gene "
"information, the third is a sorted and "
"indexed BAM file with reads aligned to the gene, "
"and the fourth is an output directory.")
parser.add_option("--paired-end", dest="paired_end",
nargs=2, default=None,
help="Run in paired-end mode. Takes a mean and standard "
"deviation for the fragment length distribution (assumed "
"to have discretized normal form.)")
parser.add_option("--compute-genes-from-file", dest="compute_genes_from_file",
nargs=3, default=None,
help="Runs on a set of genes from a file. Takes as input: "
"(1) a two-column tab-delimited file, where column 1 is the "
"event ID (ID field from GFF) and the second column is "
"the path to the indexed GFF file for that event. "
"MISO will run on all the events described in the file, "
"(2) a sorted, indexed BAM file to run on, and (3) a "
"directory to output results to.")
##
## Psi utilities
##
parser.add_option("--compare-samples", dest="samples_to_compare",
nargs=3, default=None,
help="Compute comparison statistics between the two "
"given samples. Expects three directories: the first is "
"sample1's MISO output, the second is sample2's MISO "
"output, and the third is the directory where "
"results of the sample comparison will be outputted.")
parser.add_option("--comparison-labels", dest="comparison_labels",
nargs=2, default=None,
help="Use these labels for the sample comparison "
"made by --compare-samples. "
"Takes two arguments: the label for sample 1 "
"and the label for sample 2, where sample 1 and "
"sample 2 correspond to the order of samples given "
"to --compare-samples.")
parser.add_option("--summarize-samples", dest="summarize_samples",
nargs=2, default=None,
help="Compute summary statistics of the given set "
"of samples. Expects a directory with MISO output "
"and a directory to output summary file to.")
parser.add_option("--summary-label", dest="summary_label",
nargs=1, default=None,
help="Label for MISO summary file. If not given, "
"uses basename of MISO output directory.")
parser.add_option("--use-cluster", action="store_true",
dest="use_cluster", default=False)
parser.add_option("--chunk-jobs", dest="chunk_jobs",
default=False, type="int",
help="Size (in number of events) of each job to "
"chunk events file into. Only applies when "
"running on cluster.")
parser.add_option("--settings-filename", dest="settings_filename",
default=os.path.join(miso_settings_path,
"settings",
"miso_settings.txt"),
help="Filename specifying MISO settings.")
parser.add_option("--read-len", dest="read_len", type="int",
default=None)
parser.add_option("--overhang-len", dest="overhang_len", type="int",
default=None)
parser.add_option("--event-type", dest="event_type", default=None,
help="Event type of two-isoform "
"events (e.g. 'SE', 'RI', 'A3SS', ...)")
parser.add_option("--use-compressed", dest="use_compressed",
nargs=1, default=None,
help="Use compressed event IDs. Takes as input a "
"genes_to_filenames.shelve file produced by the "
"index_gff script.")
##
## Gene utilities
##
parser.add_option("--view-gene", dest="view_gene",
nargs=1, default=None,
help="View the contents of a gene/event that has "
"been indexed. Takes as input an "
"indexed (.pickle) filename.")
(options, args) = parser.parse_args()
if options.compute_gene_psi is None:
greeting()
##
## Load the settings file
##
Settings.load(os.path.expanduser(options.settings_filename))
use_compressed = None
if options.use_compressed is not None:
use_compressed = \
os.path.abspath(os.path.expanduser(options.use_compressed))
if not os.path.exists(use_compressed):
print "Error: mapping filename from event IDs to compressed IDs %s " \
"is not found." %(use_compressed)
sys.exit(1)
else:
print "Compression being used."
if options.samples_to_compare is not None:
sample1_dirname = os.path.abspath(options.samples_to_compare[0])
sample2_dirname = os.path.abspath(options.samples_to_compare[1])
output_dirname = os.path.abspath(options.samples_to_compare[2])
if not os.path.isdir(output_dirname):
print "Making comparisons directory: %s" %(output_dirname)
misc_utils.make_dir(output_dirname)
ht.output_samples_comparison(sample1_dirname,
sample2_dirname,
output_dirname,
sample_labels=options.comparison_labels,
use_compressed=use_compressed)
##
## Main interface based on SAM files
##
if options.compute_genes_from_file != None:
# Run on events given by file
run_compute_genes_from_file(options)
if options.compute_gene_psi != None:
run_compute_gene_psi(options)
##
## Summarizing samples
##
if options.summarize_samples:
samples_dir = \
os.path.abspath(os.path.expanduser(options.summarize_samples[0]))
if options.summary_label != None:
samples_label = options.summary_label
print "Using summary label: %s" %(samples_label)
else:
samples_label = \
os.path.basename(os.path.expanduser(samples_dir))
assert(len(samples_label) >= 1)
summary_output_dir = \
os.path.abspath(os.path.join(os.path.expanduser(options.summarize_samples[1]),
'summary'))
if not os.path.isdir(summary_output_dir):
os.makedirs(summary_output_dir)
summary_filename = os.path.join(summary_output_dir,
'%s.miso_summary' %(samples_label))
summarize_sampler_results(samples_dir, summary_filename,
use_compressed=use_compressed)
if options.view_gene != None:
indexed_gene_filename = \
os.path.abspath(os.path.expanduser(options.view_gene))
print "Viewing genes in %s" %(indexed_gene_filename)
gff_genes = gff_utils.load_indexed_gff_file(indexed_gene_filename)
if gff_genes == None:
print "No genes."
sys.exit(1)
for gene_id, gene_info in gff_genes.iteritems():
print "Gene %s" %(gene_id)
gene_obj = gene_info['gene_object']
print " - Gene object: ", gene_obj
print "=="
print "Isoforms: "
for isoform in gene_obj.isoforms:
print " - ", isoform
print "=="
print "mRNA IDs: "
for mRNA_id in gene_info['hierarchy'][gene_id]['mRNAs']:
print "%s" %(mRNA_id)
print "=="
print "Exons: "
for exon in gene_obj.parts:
print " - ", exon
