def main():
from optparse import OptionParser
parser = OptionParser()
##
## 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("--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.")
(options, args) = parser.parse_args()
if options.samples_to_compare is None:
greeting()
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)
def main():
from optparse import OptionParser
parser = OptionParser()
##
## 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("--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.")
(options, args) = parser.parse_args()
if options.samples_to_compare is None:
greeting()
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)
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()
##
## 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