def main():
usage = 'usage: %prog [options] <gtf> <diff>'
parser = OptionParser(usage)
parser.add_option('-o', dest='out_dir', default='te_diff', help='Output directory [Default: %default]')
parser.add_option('-t', dest='te_gff', default='%s/hg19.fa.out.tpf.gff'%os.environ['MASK'])
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide .gtf and .diff files')
else:
gtf_file = args[0]
diff_file = args[1]
# hash genes -> TEs
gene_tes = te.hash_genes_repeats(gtf_file, options.te_gff, gene_key='transcript_id', add_star=True, stranded=True)
# create a fake family for unrepetitive genes
for line in open(gtf_file):
a = line.split('\t')
gene_id = gff.gtf_kv(a[8])['transcript_id']
if not gene_id in gene_tes:
gene_tes[gene_id] = set([('-','-','*')])
# get diffs stats
gene_diffs, te_diffs = get_diff_stats(diff_file, gene_tes)
# clean plot directory
if os.path.isdir(options.out_dir):
shutil.rmtree(options.out_dir)
os.mkdir(options.out_dir)
# stats
table_lines, pvals = compute_stats(te_diffs, gene_diffs, options.out_dir)
# perform multiple hypothesis correction
qvals = fdr.ben_hoch(pvals)
table_out = open('%s/table.txt' % options.out_dir, 'w')
for i in range(len(table_lines)):
print >> table_out, '%s %10.2e' % (table_lines[i],qvals[i])
table_out.close()
def main():
usage = 'usage: %prog [options] <gtf> <diff>'
parser = OptionParser(usage)
parser.add_option('-m', dest='max_stat', default=None, type='float', help='Maximum stat for plotting [Default: %default]')
parser.add_option('-o', dest='out_dir', default='te_diff', help='Output directory [Default: %default]')
parser.add_option('-c', dest='scale', default=1, type='float', help='CDF plot scale [Default: %default]')
parser.add_option('-t', dest='te_gff', default='%s/hg19.fa.out.tp.gff'%os.environ['MASK'])
parser.add_option('-s', dest='spread_factor', default=None, type='float', help='Allow multiplicative factor between the shortest and longest transcripts, used to filter [Default: %default]')
parser.add_option('-l', dest='spread_lower', default=None, type='float', help='Allow multiplicative factor between median and shortest transcripts [Defafult: %default]')
parser.add_option('-u', dest='spread_upper', default=None, type='float', help='Allow multiplicative factor between median and longest transcripts [Defafult: %default]')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide .gtf and .diff files')
else:
ref_gtf = args[0]
diff_file = args[1]
# clean plot directory
if os.path.isdir(options.out_dir):
shutil.rmtree(options.out_dir)
os.mkdir(options.out_dir)
if options.spread_factor or options.spread_lower or options.spread_upper:
# filter for similar length
if options.spread_factor:
options.spread_lower = math.sqrt(options.spread_factor)
options.spread_upper = math.sqrt(options.spread_factor)
spread_gtf = '%s/spread_factor.gtf' % options.out_dir
gff.length_filter(ref_gtf, spread_gtf, options.spread_lower, options.spread_lower)
ref_gtf = spread_gtf
##################################################
# hash TEs -> genes
##################################################
te_genes = te.hash_repeats_genes(ref_gtf, options.te_gff, gene_key='transcript_id', add_star=True, stranded=True)
##################################################
# hash genes -> RIP diff
##################################################
gene_diff = cuffdiff.hash_diff(diff_file, stat='fold', max_stat=options.max_stat, sample_first='input')
##################################################
# compute stats and make plots
##################################################
table_lines, pvals = compute_stats(te_genes, gene_diff, ref_gtf, options.out_dir, options.scale)
# perform multiple hypothesis correction
qvals = fdr.ben_hoch(pvals)
table_out = open('%s/table.txt' % options.out_dir, 'w')
for i in range(len(table_lines)):
print >> table_out, '%s %10.2e' % (table_lines[i],qvals[i])
table_out.close()
if options.spread_factor or options.spread_lower or options.spread_upper:
os.remove(spread_gtf)
def main():
usage = 'usage: %prog [options] <feature gff>'
parser = OptionParser(usage)
parser.add_option('-g', dest='filter_gff', help='Filter the TEs by overlap with genes in the given gff file [Default: %default]')
parser.add_option('-r', dest='repeats_gff', default='%s/research/common/data/genomes/hg19/annotation/repeatmasker/hg19.fa.out.tp.gff' % os.environ['HOME'])
parser.add_option('-s', dest='strand_split', default=False, action='store_true', help='Split statistics by strand [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide a gff file for the feature of interest.')
else:
feature_gff = args[0]
############################################
# GFF filter
############################################
# filter TEs and features by gff file
if options.filter_gff:
filter_merged_bed_fd, filter_merged_bed_file = tempfile.mkstemp()
subprocess.call('sortBed -i %s | mergeBed -i - > %s' % (options.filter_gff, filter_merged_bed_file), shell=True)
# filter TE GFF
te_gff_fd, te_gff_file = tempfile.mkstemp()
subprocess.call('intersectBed -a %s -b %s > %s' % (options.repeats_gff, filter_merged_bed_file, te_gff_file), shell=True)
options.repeats_gff = te_gff_file
# filter feature GFF
feature_gff_gff_fd, feature_gff_gff_file = tempfile.mkstemp()
subprocess.call('intersectBed -u -f 0.5 -a %s -b %s > %s' % (feature_gff, filter_merged_bed_file, feature_gff_gff_file), shell=True)
feature_gff = feature_gff_gff_file
############################################
# lengths
############################################
# compute feature length
feature_len, feature_num = feature_stats(feature_gff)
if feature_num == 0:
print >> sys.stderr, 'Zero features'
exit()
# compute size of search space
if options.filter_gff:
genome_length = count_bed(filter_merged_bed_file, feature_len)
else:
genome_length = count_hg19()
# hash counted repeat genomic bp
te_lengths = te_target_size(options.repeats_gff, feature_len)
############################################
# hash TE/feature overlaps
############################################
# initialize
te_features = {}
for rep, fam in te_lengths:
if options.strand_split:
te_features[(rep+'+',fam)] = set()
te_features[('*+',fam)] = set()
te_features[('*+','*')] = set()
te_features[(rep+'-',fam)] = set()
te_features[('*-',fam)] = set()
te_features[('*-','*')] = set()
else:
te_features[(rep,fam)] = set()
te_features[('*',fam)] = set()
te_features[('*','*')] = set()
p = subprocess.Popen('intersectBed -wo -a %s -b %s' % (options.repeats_gff,feature_gff), shell=True, stdout=subprocess.PIPE)
for line in p.stdout:
a = line.split('\t')
kv = gff.gtf_kv(a[8])
rep = kv['repeat']
fam = kv['family']
fchrom = a[9]
fstart = int(a[12])
fend = int(a[13])
rep_star = '*'
if options.strand_split:
tstrand = a[6]
fstrand = a[15]
if tstrand == fstrand:
rep += '+'
rep_star += '+'
else:
rep += '-'
rep_star += '-'
te_features[(rep,fam)].add((fchrom,fstart,fend))
te_features[(rep_star,fam)].add((fchrom,fstart,fend))
te_features[(rep_star,'*')].add((fchrom,fstart,fend))
p.communicate()
############################################SW
# compute stats and print
############################################
lines = []
p_vals = []
for te in te_features:
rep, fam = te
if options.strand_split:
te_len = te_lengths[(rep[:-1],fam)]
te_p = float(te_len) / (2*genome_length)
else:
te_len = te_lengths[(rep,fam)]
te_p = float(te_len) / genome_length
te_count = len(te_features.get(te,[]))
exp_count = te_p * feature_num
fold_change = te_count / exp_count
if fold_change > 1:
p_val = binom.sf(te_count-1, feature_num, te_p)
else:
p_val = binom.cdf(te_count, feature_num, te_p)
p_vals.append(p_val)
cols = (rep, fam, te_len, te_count, exp_count, fold_change, p_val)
lines.append('%-18s %-18s %9d %8d %8.1f %8.2f %10.2e' % cols)
# correct for multiple hypotheses correction
q_vals = fdr.ben_hoch(p_vals)
for i in range(len(lines)):
qline = lines[i] + ' %10.2e' % q_vals[i]
print qline
############################################
# clean
############################################
if options.filter_gff:
os.close(filter_merged_bed_fd)
os.remove(filter_merged_bed_file)
os.close(te_gff_fd)
os.remove(te_gff_file)
os.close(feature_gff_gff_fd)
os.remove(feature_gff_gff_file)
def main():
usage = 'usage: %prog [options] <feature gff/bed>'
parser = OptionParser(usage)
parser.add_option('-g', dest='gff_file', help='Filter the TEs by overlap with genes in the given gff file [Default: %default]')
parser.add_option('-r', dest='repeats_gff', default='%s/research/common/data/genomes/hg19/annotation/repeatmasker/hg19.fa.out.tp.gff' % home_dir)
parser.add_option('-n', dest='null_iterations', type=int, default=50, help='Number of shuffles to perform to estimate null distribution [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide a gff file for the feature of interest.')
else:
feature_gff = args[0]
############################################
# GFF filter
############################################
# filter TEs and features by gff file
if options.gff_file:
# filter TE GFF
te_gff_fd, te_gff_file = tempfile.mkstemp()
subprocess.call('intersectBed -a %s -b %s > %s' % (options.repeats_gff, options.gff_file, te_gff_file), shell=True)
options.repeats_gff = te_gff_file
# filter feature GFF
feature_gff_gff_fd, feature_gff_gff_file = tempfile.mkstemp()
subprocess.call('intersectBed -s -u -f 0.5 -a %s -b %s > %s' % (feature_gff, options.gff_file, feature_gff_gff_file), shell=True)
feature_gff = feature_gff_gff_file
############################################
# lengths
############################################
# compute size of search space
if options.gff_file:
genome_length = count_gff(options.gff_file)
else:
genome_length = count_hg19()
# compute feature length
feature_len, feature_num = feature_stats(feature_gff)
if feature_num == 0:
print >> sys.stderr, 'Zero features'
exit()
# hash counted repeat genomic bp
te_in = open(options.repeats_gff)
genome_te_bp = hash_te(te_in)
te_in.close()
############################################
# convert feature gff to bed
############################################
if feature_gff[-3:] == 'gtf':
feature_bed_fd, feature_bed_file = tempfile.mkstemp()
subprocess.call('gtf2bed.py %s > %s' % (feature_gff,feature_bed_file), shell=True)
elif feature_gff[-3:] == 'gff':
feature_bed_fd, feature_bed_file = tempfile.mkstemp()
subprocess.call('gff2bed.py %s > %s' % (feature_gff,feature_bed_file), shell=True)
elif feature_gff[-3:] == 'bed':
feature_bed_file = feature_gff
else:
parser.error('Cannot recognize gff format suffix')
############################################
# null distribution
############################################
shuffle_bed_fd, shuffle_bed_file = tempfile.mkstemp()
te_null_bp = {}
for ni in range(options.null_iterations):
print >> sys.stderr, ni
# shuffle feature bed
subprocess.call('shuffleBed -i %s -g %s/research/common/data/genomes/hg19/assembly/human.hg19.genome -excl %s/research/common/data/genomes/hg19/assembly/hg19_gaps.bed > %s' % (feature_bed_file, home_dir, home_dir, shuffle_bed_file), shell=True)
# intersect w/ TEs and hash overlaps
te_tmp_bp = intersect_hash(options.repeats_gff, shuffle_bed_file)
for te in genome_te_bp:
te_null_bp.setdefault(te,[]).append(te_tmp_bp.get(te,0))
############################################
# actual
############################################
te_bp = intersect_hash(options.repeats_gff, feature_gff)
############################################
# compute stats and print
############################################
lines = []
p_vals = []
for te in genome_te_bp:
feature_freq = float(te_bp.get(te,0))/feature_len
genome_freq = float(genome_te_bp[te])/genome_length
fold_change = feature_freq / genome_freq
#print te, stats.mean(te_null_bp[te]), stats.sd(te_null_bp[te])
null_u, null_sd = stats.mean_sd(te_null_bp[te])
if null_sd == 0:
null_sd = 1.0
if fold_change > 1:
p = norm.sf(te_bp[te]-1, loc=null_u, scale=null_sd)
else:
p = norm.cdf(te_bp.get(te,0), loc=null_u, scale=null_sd)
p_vals.append(p)
cols = (te[0], te[1], te_bp.get(te,0), feature_freq, genome_freq, fold_change, p)
lines.append('%-18s %-18s %8d %11.2e %11.2e %9.2f %10.2e' % cols)
# correct for multiple hypotheses correction
q_vals = fdr.ben_hoch(p_vals)
for i in range(len(lines)):
qline = lines[i] + ' %10.2e' % q_vals[i]
print qline
############################################
# clean
############################################
os.close(shuffle_bed_fd)
os.remove(shuffle_bed_file)
if feature_gff[-3:] != 'bed':
os.close(feature_bed_fd)
os.remove(feature_bed_file)
if options.gff_file:
os.close(te_gff_fd)
os.remove(te_gff_file)
os.close(feature_gff_gff_fd)
os.remove(feature_gff_gff_file)
def main():
usage = 'usage: %prog [options] <gtf> <diff>'
parser = OptionParser(usage)
parser.add_option('-o', dest='out_dir', default='te_diff_regress', help='Output directory to print regression summaries [Default: %default]')
parser.add_option('-t', dest='te_gff', default='%s/hg19.fa.out.tp.gff'%os.environ['MASK'])
parser.add_option('-m', dest='max_stat', default=None, type='float', help='Maximum stat for plotting [Default: %default]')
parser.add_option('-s', dest='spread_factor', default=None, type='float', help='Allow multiplicative factor between the shortest and longest transcripts, used to filter [Default: %default]')
parser.add_option('-l', dest='spread_lower', default=None, type='float', help='Allow multiplicative factor between median and shortest transcripts [Defafult: %default]')
parser.add_option('-u', dest='spread_upper', default=None, type='float', help='Allow multiplicative factor between median and longest transcripts [Defafult: %default]')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide .gtf and .diff files')
else:
ref_gtf = args[0]
diff_file = args[1]
# clean output directory
if os.path.isdir(options.out_dir):
shutil.rmtree(options.out_dir)
os.mkdir(options.out_dir)
if options.spread_factor or options.spread_lower or options.spread_upper:
# filter for similar length
if options.spread_factor:
options.spread_lower = math.sqrt(options.spread_factor)
options.spread_upper = math.sqrt(options.spread_factor)
spread_gtf = '%s/spread_factor.gtf' % options.out_dir
gff.length_filter(ref_gtf, spread_gtf, options.spread_lower, options.spread_lower, verbose=True)
ref_gtf = spread_gtf
# hash genes -> TEs
gene_tes = te.hash_genes_repeats(ref_gtf, options.te_gff, gene_key='transcript_id', add_star=True, stranded=True)
# hash diffs stats
gene_diffs = cuffdiff.hash_diff(diff_file, stat='fold', max_stat=options.max_stat, sample_first='input')
table_lines = []
pvals = []
for spair in gene_diffs:
sample1, sample2 = spair
# construct data frame
gene_list = list(set(gene_tes.keys()) & set(gene_diffs[spair].keys()))
df = pd.DataFrame({'diff': [gene_diffs[spair][gene_id] for gene_id in gene_list]})
covariate_str = ''
for fam in regression_tes:
te_key = '%s_fwd' % fam.replace('/','_').replace('-','')
df[te_key] = [1.0*(('*',fam,'+') in gene_tes.get(gene_id,[])) for gene_id in gene_list]
if len(covariate_str) == 0:
covariate_str = te_key
else:
covariate_str += ' + %s' % te_key
te_key = '%s_rev' % fam.replace('/','_').replace('-','')
df[te_key] = [1.0*(('*',fam,'-') in gene_tes.get(gene_id,[])) for gene_id in gene_list]
covariate_str += ' + %s' % te_key
# regress
mod = smf.ols(formula='diff ~ %s' % covariate_str, data=df).fit()
# output model
mod_out = open('%s/%s-%s.txt' % (options.out_dir, sample1, sample2), 'w')
print >> mod_out, mod.summary()
mod_out.close()
# save table lines
for fam in regression_tes:
te_key = '%s_fwd' % fam.replace('/','_').replace('-','')
cols = (fam, '+', sample1, sample2, sum(df[te_key]), mod.params[te_key], mod.tvalues[te_key], mod.pvalues[te_key]/0.5)
table_lines.append('%-17s %1s %-10s %-10s %6d %8.3f %8.3f %10.2e' % cols)
pvals.append(cols[-1])
te_key = '%s_rev' % fam.replace('/','_').replace('-','')
cols = (fam, '-', sample1, sample2, sum(df[te_key]), mod.params[te_key], mod.tvalues[te_key], mod.pvalues[te_key]/0.5)
table_lines.append('%-17s %1s %-10s %-10s %6d %8.3f %8.3f %10.2e' % cols)
pvals.append(cols[-1])
# perform multiple hypothesis correction
qvals = fdr.ben_hoch(pvals)
table_out = open('%s/table.txt' % options.out_dir, 'w')
for i in range(len(table_lines)):
print >> table_out, '%s %10.2e' % (table_lines[i],qvals[i])
table_out.close()
if options.spread_factor or options.spread_lower or options.spread_upper:
os.remove(spread_gtf)
def main():
usage = 'usage: %prog [options] <feature gff>'
parser = OptionParser(usage)
parser.add_option(
'-g',
dest='filter_gff',
help=
'Filter the TEs by overlap with genes in the given gff file [Default: %default]'
)
parser.add_option(
'-r',
dest='repeats_gff',
default=
'%s/research/common/data/genomes/hg19/annotation/repeatmasker/hg19.fa.out.tp.gff'
% os.environ['HOME'])
parser.add_option('-s',
dest='strand_split',
default=False,
action='store_true',
help='Split statistics by strand [Default: %default]')
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide a gff file for the feature of interest.')
else:
feature_gff = args[0]
############################################
# GFF filter
############################################
# filter TEs and features by gff file
if options.filter_gff:
filter_merged_bed_fd, filter_merged_bed_file = tempfile.mkstemp()
subprocess.call('sortBed -i %s | mergeBed -i - > %s' %
(options.filter_gff, filter_merged_bed_file),
shell=True)
# filter TE GFF
te_gff_fd, te_gff_file = tempfile.mkstemp()
subprocess.call(
'intersectBed -a %s -b %s > %s' %
(options.repeats_gff, filter_merged_bed_file, te_gff_file),
shell=True)
options.repeats_gff = te_gff_file
# filter feature GFF
feature_gff_gff_fd, feature_gff_gff_file = tempfile.mkstemp()
subprocess.call(
'intersectBed -u -f 0.5 -a %s -b %s > %s' %
(feature_gff, filter_merged_bed_file, feature_gff_gff_file),
shell=True)
feature_gff = feature_gff_gff_file
############################################
# lengths
############################################
# compute feature length
feature_len, feature_num = feature_stats(feature_gff)
if feature_num == 0:
print >> sys.stderr, 'Zero features'
exit()
# compute size of search space
if options.filter_gff:
genome_length = count_bed(filter_merged_bed_file, feature_len)
else:
genome_length = count_hg19()
# hash counted repeat genomic bp
te_lengths = te_target_size(options.repeats_gff, feature_len)
############################################
# hash TE/feature overlaps
############################################
# initialize
te_features = {}
for rep, fam in te_lengths:
if options.strand_split:
te_features[(rep + '+', fam)] = set()
te_features[('*+', fam)] = set()
te_features[('*+', '*')] = set()
te_features[(rep + '-', fam)] = set()
te_features[('*-', fam)] = set()
te_features[('*-', '*')] = set()
else:
te_features[(rep, fam)] = set()
te_features[('*', fam)] = set()
te_features[('*', '*')] = set()
p = subprocess.Popen('intersectBed -wo -a %s -b %s' %
(options.repeats_gff, feature_gff),
shell=True,
stdout=subprocess.PIPE)
for line in p.stdout:
a = line.split('\t')
kv = gff.gtf_kv(a[8])
rep = kv['repeat']
fam = kv['family']
fchrom = a[9]
fstart = int(a[12])
fend = int(a[13])
rep_star = '*'
if options.strand_split:
tstrand = a[6]
fstrand = a[15]
if tstrand == fstrand:
rep += '+'
rep_star += '+'
else:
rep += '-'
rep_star += '-'
te_features[(rep, fam)].add((fchrom, fstart, fend))
te_features[(rep_star, fam)].add((fchrom, fstart, fend))
te_features[(rep_star, '*')].add((fchrom, fstart, fend))
p.communicate()
############################################SW
# compute stats and print
############################################
lines = []
p_vals = []
for te in te_features:
rep, fam = te
if options.strand_split:
te_len = te_lengths[(rep[:-1], fam)]
te_p = float(te_len) / (2 * genome_length)
else:
te_len = te_lengths[(rep, fam)]
te_p = float(te_len) / genome_length
te_count = len(te_features.get(te, []))
exp_count = te_p * feature_num
fold_change = te_count / exp_count
if fold_change > 1:
p_val = binom.sf(te_count - 1, feature_num, te_p)
else:
p_val = binom.cdf(te_count, feature_num, te_p)
p_vals.append(p_val)
cols = (rep, fam, te_len, te_count, exp_count, fold_change, p_val)
lines.append('%-18s %-18s %9d %8d %8.1f %8.2f %10.2e' % cols)
# correct for multiple hypotheses correction
q_vals = fdr.ben_hoch(p_vals)
for i in range(len(lines)):
qline = lines[i] + ' %10.2e' % q_vals[i]
print qline
############################################
# clean
############################################
if options.filter_gff:
os.close(filter_merged_bed_fd)
os.remove(filter_merged_bed_file)
os.close(te_gff_fd)
os.remove(te_gff_file)
os.close(feature_gff_gff_fd)
os.remove(feature_gff_gff_file)
def main():
usage = 'usage: %prog [options] <gtf> <diff>'
parser = OptionParser(usage)
parser.add_option('-m',
dest='max_stat',
default=None,
type='float',
help='Maximum stat for plotting [Default: %default]')
parser.add_option('-o',
dest='out_dir',
default='te_diff',
help='Output directory [Default: %default]')
parser.add_option('-c',
dest='scale',
default=1,
type='float',
help='CDF plot scale [Default: %default]')
parser.add_option('-t',
dest='te_gff',
default='%s/hg19.fa.out.tp.gff' % os.environ['MASK'])
parser.add_option(
'-s',
dest='spread_factor',
default=None,
type='float',
help=
'Allow multiplicative factor between the shortest and longest transcripts, used to filter [Default: %default]'
)
parser.add_option(
'-l',
dest='spread_lower',
default=None,
type='float',
help=
'Allow multiplicative factor between median and shortest transcripts [Defafult: %default]'
)
parser.add_option(
'-u',
dest='spread_upper',
default=None,
type='float',
help=
'Allow multiplicative factor between median and longest transcripts [Defafult: %default]'
)
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide .gtf and .diff files')
else:
ref_gtf = args[0]
diff_file = args[1]
# clean plot directory
if os.path.isdir(options.out_dir):
shutil.rmtree(options.out_dir)
os.mkdir(options.out_dir)
if options.spread_factor or options.spread_lower or options.spread_upper:
# filter for similar length
if options.spread_factor:
options.spread_lower = math.sqrt(options.spread_factor)
options.spread_upper = math.sqrt(options.spread_factor)
spread_gtf = '%s/spread_factor.gtf' % options.out_dir
gff.length_filter(ref_gtf, spread_gtf, options.spread_lower,
options.spread_lower)
ref_gtf = spread_gtf
##################################################
# hash TEs -> genes
##################################################
te_genes = te.hash_repeats_genes(ref_gtf,
options.te_gff,
gene_key='transcript_id',
add_star=True,
stranded=True)
##################################################
# hash genes -> RIP diff
##################################################
gene_diff = cuffdiff.hash_diff(diff_file,
stat='fold',
max_stat=options.max_stat,
sample_first='input')
##################################################
# compute stats and make plots
##################################################
table_lines, pvals = compute_stats(te_genes, gene_diff, ref_gtf,
options.out_dir, options.scale)
# perform multiple hypothesis correction
qvals = fdr.ben_hoch(pvals)
table_out = open('%s/table.txt' % options.out_dir, 'w')
for i in range(len(table_lines)):
print >> table_out, '%s %10.2e' % (table_lines[i], qvals[i])
table_out.close()
if options.spread_factor or options.spread_lower or options.spread_upper:
os.remove(spread_gtf)
def main():
usage = 'usage: %prog [options] <gtf> <diff>'
parser = OptionParser(usage)
parser.add_option('-o', dest='out_dir', default='te_diff_regress', help='Output directory to print regression summaries [Default: %default]')
parser.add_option('-t', dest='te_gff', default='%s/hg19.fa.out.tpf.gff'%os.environ['MASK'])
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide .gtf and .diff files')
else:
gtf_file = args[0]
diff_file = args[1]
# hash genes -> TEs
gene_tes = te.hash_genes_repeats(gtf_file, options.te_gff, gene_key='transcript_id', add_star=True, stranded=True)
# hash diffs stats
gene_diffs = hash_diff(diff_file)
# clean output directory
if os.path.isdir(options.out_dir):
shutil.rmtree(options.out_dir)
os.mkdir(options.out_dir)
table_lines = []
pvals = []
for spair in gene_diffs:
sample1, sample2 = spair
# construct data frame
gene_list = list(set(gene_tes.keys()) & set(gene_diffs[spair].keys()))
df = pd.DataFrame({'diff': [gene_diffs[spair][gene_id] for gene_id in gene_list]})
covariate_str = ''
for fam in regression_tes:
te_key = '%s_fwd' % fam.replace('/','_').replace('-','')
df[te_key] = [1.0*(('*',fam,'+') in gene_tes.get(gene_id,[])) for gene_id in gene_list]
if len(covariate_str) == 0:
covariate_str = te_key
else:
covariate_str += ' + %s' % te_key
te_key = '%s_rev' % fam.replace('/','_').replace('-','')
df[te_key] = [1.0*(('*',fam,'-') in gene_tes.get(gene_id,[])) for gene_id in gene_list]
covariate_str += ' + %s' % te_key
# regress
mod = smf.ols(formula='diff ~ %s' % covariate_str, data=df).fit()
# output model
mod_out = open('%s/%s-%s.txt' % (options.out_dir, sample1, sample2), 'w')
print >> mod_out, mod.summary()
mod_out.close()
# save table lines
for fam in regression_tes:
te_key = '%s_fwd' % fam.replace('/','_').replace('-','')
cols = (fam, '+', sample1, sample2, sum(df[te_key]), mod.params[te_key], mod.tvalues[te_key], mod.pvalues[te_key]/0.5)
table_lines.append('%-17s %1s %-10s %-10s %6d %8.3f %8.3f %10.2e' % cols)
pvals.append(cols[-1])
te_key = '%s_rev' % fam.replace('/','_').replace('-','')
cols = (fam, '-', sample1, sample2, sum(df[te_key]), mod.params[te_key], mod.tvalues[te_key], mod.pvalues[te_key]/0.5)
table_lines.append('%-17s %1s %-10s %-10s %6d %8.3f %8.3f %10.2e' % cols)
pvals.append(cols[-1])
# perform multiple hypothesis correction
qvals = fdr.ben_hoch(pvals)
table_out = open('%s/table.txt' % options.out_dir, 'w')
for i in range(len(table_lines)):
print >> table_out, '%s %10.2e' % (table_lines[i],qvals[i])
table_out.close()
