def count_total_reads(bam_filename):
"""
Return total number of proper reads in BAM file.
"""
bamfile = sam_utils.load_bam_reads(bam_filename)
num_total_reads = 0
for r in bamfile:
num_total_reads += 1
return num_total_reads
def count_total_reads(bam_filename):
"""
Return total number of proper reads in BAM file.
"""
bamfile = sam_utils.load_bam_reads(bam_filename)
num_total_reads = 0
for r in bamfile:
num_total_reads += 1
return num_total_reads
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 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 compute_rpkm(gff_filename, bam_filename, read_len, output_dir):
"""
Compute RPKMs for genes listed in GFF based on BAM reads.
"""
print "Computing RPKMs..."
print " - GFF filename: %s" % (gff_filename)
print " - BAM filename: %s" % (bam_filename)
print " - Output dir: %s" % (output_dir)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
output_filename = os.path.join(
output_dir, "%s.rpkm" % (os.path.basename(bam_filename)))
print "Outputting RPKMs to: %s" % (output_filename)
rpkm_fieldnames = ['gene_id', 'rpkm', 'const_exon_lens', 'num_reads']
# Parse the GFF into genes
print "Parsing GFF into genes..."
t1 = time.time()
gff_genes = load_genes_from_gff(gff_filename)
t2 = time.time()
print "Parsing took %.2f seconds" % (t2 - t1)
# Load the BAM file
bamfile = sam_utils.load_bam_reads(bam_filename)
print "Counting all reads..."
t1 = time.time()
num_total_reads = count_total_reads(bam_filename)
t2 = time.time()
print "Took: %.2f seconds" % (t2 - t1)
print "Number of total reads in BAM file: %d" % (num_total_reads)
num_genes = 0
rpkms_dictlist = []
exons_too_small = {}
num_no_const = 0
for gene_id, gene_info in gff_genes.iteritems():
# Get the gene object
gene = gene_info['gene_object']
# Get constitutive exons
const_exons = gene.get_const_parts()
num_reads = []
exon_lens = []
regions_counted = {}
if not gene.chrom.startswith("chr"):
chrom = "chr%s" % (gene.chrom)
else:
chrom = gene.chrom
if "random" in chrom:
print "Skipping random chromosome gene: %s, %s" \
%(gene_id, chrom)
continue
if len(const_exons) == 0:
print "Gene %s has no constitutive regions!" % (gene_id)
num_no_const += 1
continue
total_num_reads = 0
for exon in const_exons:
exon_len = exon.end - exon.start + 1
counts = 0
try:
reads = bamfile.fetch(chrom, exon.start, exon.end)
except ValueError:
print "Error fetching region: %s:%d-%d" % (chrom, exon.start,
exon.end)
break
# Count reads landing in exon
for r in reads:
counts += 1
total_num_reads += counts
# Skip exons that we've seen already or exons that are shorter
# than the read length
if (exon.start, exon.end) in regions_counted or \
exon_len < read_len:
continue
exon_lens.append(exon_len)
num_reads.append(counts)
regions_counted[(exon.start, exon.end)] = True
if len(regions_counted) == 0:
# print "Gene %s exons are too small for %d-long reads" \
# %(gene_id, read_len)
exons_too_small[gene_id] = total_num_reads
continue
# print "Used total of %d regions" %(len(regions_counted))
# print "Total of %d regions are too small" %(num_too_small)
rpkm = rpkm_per_region(exon_lens, num_reads, read_len, num_total_reads)
# print rpkm, exon_lens, num_reads, read_len
# Convert region lengths and number of reads to strings
exon_lens_str = ",".join([str(e) for e in exon_lens])
num_reads_str = ",".join([str(n) for n in num_reads])
rpkm_entry = {
'gene_id': gene_id,
'rpkm': "%.2f" % (rpkm),
'const_exon_lens': exon_lens_str,
'num_reads': num_reads_str
}
rpkms_dictlist.append(rpkm_entry)
# print "RPKM: %.2f" %(rpkm)
# Compute how many reads land in each constitutive exon
num_genes += 1
num_too_small = len(exons_too_small.keys())
print "Computed RPKMs for %d genes." % (num_genes)
print " - Total of %d genes cannot be used because they lack const. regions." \
%(num_no_const)
print " - Total of %d genes cannot be used since their exons are too small." \
%(num_too_small)
for gene, total_counts in exons_too_small.iteritems():
print " gene_id\ttotal_counts"
print " * %s\t%d" % (gene, total_counts)
# Output RPKMs to file
dictlist2file(rpkms_dictlist, output_filename, rpkm_fieldnames)
return rpkms_dictlist
def compute_rpkm(gff_filename, bam_filename, read_len,
output_dir):
"""
Compute RPKMs for genes listed in GFF based on BAM reads.
"""
print "Computing RPKMs..."
print " - GFF filename: %s" %(gff_filename)
print " - BAM filename: %s" %(bam_filename)
print " - Output dir: %s" %(output_dir)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
output_filename = os.path.join(output_dir,
"%s.rpkm" %(os.path.basename(bam_filename)))
print "Outputting RPKMs to: %s" %(output_filename)
rpkm_fieldnames = ['gene_id', 'rpkm', 'const_exon_lens',
'num_reads']
# Parse the GFF into genes
print "Parsing GFF into genes..."
t1 = time.time()
gff_genes = load_genes_from_gff(gff_filename)
t2 = time.time()
print "Parsing took %.2f seconds" %(t2 - t1)
# Load the BAM file
bamfile = sam_utils.load_bam_reads(bam_filename)
print "Counting all reads..."
t1 = time.time()
num_total_reads = count_total_reads(bam_filename)
t2 = time.time()
print "Took: %.2f seconds" %(t2 - t1)
print "Number of total reads in BAM file: %d" %(num_total_reads)
num_genes = 0
rpkms_dictlist = []
exons_too_small = {}
num_no_const = 0
for gene_id, gene_info in gff_genes.iteritems():
# Get the gene object
gene = gene_info['gene_object']
# Get constitutive exons
const_exons = gene.get_const_parts()
num_reads = []
exon_lens = []
regions_counted = {}
if not gene.chrom.startswith("chr"):
chrom = "chr%s" %(gene.chrom)
else:
chrom = gene.chrom
if "random" in chrom:
print "Skipping random chromosome gene: %s, %s" \
%(gene_id, chrom)
continue
if len(const_exons) == 0:
print "Gene %s has no constitutive regions!" %(gene_id)
num_no_const += 1
continue
total_num_reads = 0
for exon in const_exons:
exon_len = exon.end - exon.start + 1
counts = 0
try:
reads = bamfile.fetch(chrom, exon.start, exon.end)
except ValueError:
print "Error fetching region: %s:%d-%d" %(chrom,
exon.start,
exon.end)
break
# Count reads landing in exon
for r in reads: counts += 1
total_num_reads += counts
# Skip exons that we've seen already or exons that are shorter
# than the read length
if (exon.start, exon.end) in regions_counted or \
exon_len < read_len:
continue
exon_lens.append(exon_len)
num_reads.append(counts)
regions_counted[(exon.start, exon.end)] = True
if len(regions_counted) == 0:
# print "Gene %s exons are too small for %d-long reads" \
# %(gene_id, read_len)
exons_too_small[gene_id] = total_num_reads
continue
# print "Used total of %d regions" %(len(regions_counted))
# print "Total of %d regions are too small" %(num_too_small)
rpkm = rpkm_per_region(exon_lens, num_reads, read_len,
num_total_reads)
# print rpkm, exon_lens, num_reads, read_len
# Convert region lengths and number of reads to strings
exon_lens_str = ",".join([str(e) for e in exon_lens])
num_reads_str = ",".join([str(n) for n in num_reads])
rpkm_entry = {'gene_id': gene_id,
'rpkm': "%.2f" %(rpkm),
'const_exon_lens': exon_lens_str,
'num_reads': num_reads_str}
rpkms_dictlist.append(rpkm_entry)
# print "RPKM: %.2f" %(rpkm)
# Compute how many reads land in each constitutive exon
num_genes += 1
num_too_small = len(exons_too_small.keys())
print "Computed RPKMs for %d genes." %(num_genes)
print " - Total of %d genes cannot be used because they lack const. regions." \
%(num_no_const)
print " - Total of %d genes cannot be used since their exons are too small." \
%(num_too_small)
for gene, total_counts in exons_too_small.iteritems():
print " gene_id\ttotal_counts"
print " * %s\t%d" %(gene, total_counts)
# Output RPKMs to file
dictlist2file(rpkms_dictlist, output_filename,
rpkm_fieldnames)
return rpkms_dictlist