def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
if not validate_path_args(args):
parser.error('Please set required parameters')
if not (validate_library_file_existance(args) and
validate_experiment_file_existance(args)):
parser.error('Fix path to files')
sep = get_seperator(args.sep)
library_filenames = args.libraries
library_filenames.extend(args.other_libraries)
libraries = models.load_library_tables(library_filenames, sep)
read1 = dict(find_fastqs(libraries, 'read_1'))
if 'read_2' in libraries.columns:
read2 = dict(find_fastqs(libraries, 'read_2'))
else:
read2 = {}
dags = generate_star_rsem_analysis(args, libraries, read1, read2)
generate_combined_analysis(args, dags)
return 0
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
sep = get_seperator(args.sep)
if not validate_library_file_existance(args):
parser.error('Fix incorrect library file names')
library_filenames = args.libraries
if len(library_filenames) == 0:
parser.error('Need library information table')
libraries = load_library_tables(library_filenames, sep)
custom_tracks = []
for library_id, library in libraries.iterrows():
if args.bigwig:
custom_tracks.extend(
make_bigwig_custom_tracks(library, args.web_root, args.root))
if args.bam:
custom_tracks.append(
make_bam_custom_track(library, args.web_root, args.root))
print(os.linesep.join(custom_tracks))
def main(cmdline=None):
parser = ArgumentParser()
parser.add_argument('-n',
'--experiment-name',
required=True,
help='Experiment name to select')
add_metadata_arguments(parser)
add_debug_arguments(parser)
args = parser.parse_args(cmdline)
configure_logging(args)
header_printed = False
libraries = load_library_tables(args.libraries)
experiments = load_experiments(args.experiments)
replicates = experiments.loc[args.experiment_name, 'replicates']
for i, (library_id,
library) in enumerate(libraries.loc[replicates].iterrows()):
filename = find_library_bam_file(library)
LOGGER.info(' Reading %s %d/%d', filename, i + 1, len(replicates))
mode = get_mode(filename, 'r')
with pysam.AlignmentFile(filename, mode) as alignment:
if not header_printed:
print(str(alignment.header))
header_printed = True
for read in alignment:
print(read.to_string())
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
sep = get_seperator(args.sep)
experiments = models.load_experiments(args.experiments, sep=sep)
libraries = models.load_library_tables(args.libraries, sep=sep)
output_sep = get_seperator(args.output_format)
output_extension = {"TAB": ".tsv", ",": ".csv"}[args.output_format]
if args.transcriptome:
# isoforms
load_quantifications = madqc.load_transcriptome_quantifications
quantification_extension = "_isoform_" + args.quantification + output_extension
else:
# genes
load_quantifications = madqc.load_genomic_quantifications
quantification_extension = "_gene_" + args.quantification + output_extension
for name in experiments:
filename = name + quantification_extension
replicates = experiments[name]
logger.info("%s %s: %s", name, args.quantification, ",".join(replicates))
quantifications = load_quantifications(replicates, libraries, args.quantification)
quantifications.to_csv(filename, sep=output_sep)
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
logger.debug("current directory {}".format(os.getcwd()))
logger.debug("env: {}".format(os.environ))
if args.prefix:
prefix = args.prefix
else:
bam_extension = '_genome.bam'
if args.bam.endswith(bam_extension):
base = make_basename(args.bam)
prefix = base[:-len('_genome')]
else:
parser.error(
'Target prefix must be provided for non-standard bam names')
if args.stranded:
targets = {
'Signal.UniqueMultiple.str1.out.bg': prefix + '_minusAll.bw',
'Signal.Unique.str1.out.bg': prefix + '_minusUniq.bw',
'Signal.UniqueMultiple.str2.out.bg': prefix + '_plusAll.bw',
'Signal.Unique.str2.out.bg': prefix + '_plusUniq.bw',
}
else:
targets = {
'Signal.UniqueMultiple.str1.out.bg': prefix + '_all.bw',
'Signal.Unique.str1.out.bg': prefix + '_uniq.bw',
}
star_dir = Path(args.star_dir) if args.star_dir is not None else None
ucsc_tools_dir = Path(
args.ucsc_tools_dir) if args.ucsc_tools_dir is not None else None
run_star_to_bedgraph(args.bam, args.stranded, args.reference_prefix,
star_dir)
chrom_info = make_chrom_info(args.bam)
for target in targets:
run_bedsort(target, ucsc_tools_dir)
run_bedgraph2bigwig(target, chrom_info, targets[target],
ucsc_tools_dir)
os.unlink(chrom_info)
return 0
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
sep = get_seperator(args.sep)
experiments = models.load_experiments(args.experiments, sep=sep)
libraries = models.load_library_tables(args.libraries, sep=sep)
output_sep = get_seperator(args.output_format)
output_extension = {
'TAB': '.tsv',
',': '.csv',
}[args.output_format]
if args.add_names:
if args.gtf_cache is None:
parser.error('GTF-cache is needed to add names to the quantification file')
else:
logger.info('Loading GTF Cache %s', args.gtf_cache)
annotation = models.load_gtf_cache(args.gtf_cache)
else:
annotation = None
if args.transcriptome:
# isoforms
load_quantifications = madqc.load_transcriptome_quantifications
lookup_ids = models.lookup_gene_name_by_transcript_id
quantification_extension = '_isoform_' + args.quantification + output_extension
else:
# genes
load_quantifications = madqc.load_genomic_quantifications
lookup_ids = models.lookup_gene_name_by_gene_id
quantification_extension = '_gene_' + args.quantification + output_extension
for name in experiments:
filename = name + quantification_extension
replicates = experiments[name]
logger.info("%s %s: %s",
name, args.quantification, ','.join(replicates))
quantifications = load_quantifications(
replicates, libraries, args.quantification)
if annotation is not None:
quantifications = lookup_ids(annotation, quantifications)
quantifications.to_csv(filename, sep=output_sep)
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
experiments = load_experiments(args.experiments)
libraries = load_library_tables(args.libraries)
if args.use_experiment:
try:
experiments = experiments.loc[[args.use_experiment]]
except KeyError:
logger.error('{} was not found in {}'.format(
args.use_experiment, ', '.join(list(experiments.index))))
return None
if len(args.gene_type_filter) > 0:
logger.info('Limiting to the following gene types {}'.format(','.join(
args.gene_type_filter)))
else:
logger.info('Using all gene types')
# ids will be None if args.gene_list_filter is None
ids = load_gene_id_list(args.gene_list_filter)
plot = GenesDetectedPlot(
experiments,
libraries,
args.genome_dir,
args.quantification,
gene_type_filter=args.gene_type_filter,
gene_list_filter=ids,
)
if __name__ == '__main__':
curdoc().add_root(plot.static_layout())
save(curdoc(), args.output, title=plot.title)
return plot
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
sep = get_seperator(args.sep)
experiments = models.load_experiments(args.experiments, sep=sep)
libraries = models.load_library_tables(args.libraries, sep=sep)
if args.add_names:
if args.gtf_cache is None:
parser.error('GTF-cache is needed to add names to the quantification file')
else:
logger.info('Loading GTF Cache %s', args.gtf_cache)
annotation = models.load_gtf_cache(args.gtf_cache)
else:
annotation = None
loader = StarLoader(args.strand, annotation)
for i, experiment in experiments.iterrows():
quantification = loader.load(experiment, libraries)
loader.save(quantification, args.output_format)
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
sep = get_seperator(args.sep)
experiments = models.load_experiments(args.experiments, sep=sep)
libraries = models.load_library_tables(args.libraries, sep=sep)
gtf_cache = None
if args.add_names:
if args.genome_dir is None:
parser.error(
'genome-dir is needed to add names to the quantification file')
else:
gtf_cache = GTFCache(libraries, args.genome_dir)
if len(args.quantification) > 0:
quantification_list = args.quantification
else:
quantification_list = ['FPKM']
if args.transcriptome:
# isoforms
RsemLoader = IsoformRsemLoader
else:
# genes
RsemLoader = GeneRsemLoader
for quantification in quantification_list:
logger.info('Building expression matrix for %s', quantification)
for i, experiment in experiments.iterrows():
loader = RsemLoader(quantification, gtf_cache)
matrix = loader.load(experiment, libraries)
loader.save(matrix, args.output_format)
def main(cmdline=None):
parser = make_parser()
args = parser.parse_args(cmdline)
configure_logging(args)
if args.version:
parser.exit(0, 'version: %s\n' % (get_git_version(),))
if not validate_args(args):
parser.error("Please set required parameters")
sep = get_seperator(args.sep)
libraries = models.load_library_tables(args.libraries, sep)
read1 = dict(find_fastqs(libraries, 'read_1'))
if 'read_2' in libraries.columns:
read2 = dict(find_fastqs(libraries, 'read_2'))
else:
read2 = {}
dag = generate_star_rsem_analysis(args, libraries, read1, read2)
print(dag)
return 0