def transcriptome_filter(poisson_cutoff, transcriptome_size, transcriptome_reads, cluster):
"""
filters each cluster by if it passes a transciptome wide cutoff or not, returns true if it passes
transcriptome cutoff, false if not
poisson_cutoff - float,user set cutoff
transcriptome_size - int number of genes in transcriptome
transcritpmoe_reads - int total number of reads analized
cluster - named tuple , namedtuple('Peak', ['chrom',
'genomic_start',
'genomic_stop',
'gene_name',
'super_local_poisson_p',
'strand',
'thick_start',
'thick_stop',
'peak_number',
'number_reads_in_peak',
'gene_poisson_p',
'size'
'p'
])
"""
transcriptome_p = poissonP(transcriptome_reads,
cluster.number_reads_in_peak,
transcriptome_size,
cluster.size)
if math.isnan(transcriptome_p):
logging.info("""Transcriptome P is NaN, transcriptome_reads = %d, cluster reads = %d, transcriptome_size = %d, cluster_size = %d""" % (transcriptome_reads, cluster.number_reads_in_peak, transcriptome_size, cluster.size))
return np.Inf
return transcriptome_p
def transcriptome_filter(poisson_cutoff, transcriptome_size, transcriptome_reads, cluster):
"""
filters each cluster by if it passes a transciptome wide cutoff or not, returns true if it passes
transcriptome cutoff, false if not
poisson_cutoff - float,user set cutoff
transcriptome_size - int number of genes in transcriptome
transcritpmoe_reads - int total number of reads analized
cluster - dict, stats about the cluster we are analizing {'Nreads' : int, 'size' : int}
"""
transcriptome_p = poissonP(transcriptome_reads,
cluster['Nreads'],
transcriptome_size,
cluster['size'])
if math.isnan(transcriptome_p):
verboseprint("""Transcriptome P is NaN, transcriptome_reads = %d,
cluster reads = %d, transcriptome_size = %d,
cluster_size = %d""" % (transcriptome_reads, cluster['Nreads'], transcriptome_size, cluster['size']))
return False
if transcriptome_p > poisson_cutoff:
print """%s\n Failed Transcriptome cutoff with %s reads,
pval: %s""" % (cluster,
cluster['Nreads'],
transcriptome_p)
return False
return True
def transcriptome_filter(poisson_cutoff, transcriptome_size,
transcriptome_reads, cluster):
"""
filters each cluster by if it passes a transciptome wide cutoff or not, returns true if it passes
transcriptome cutoff, false if not
poisson_cutoff - float,user set cutoff
transcriptome_size - int number of genes in transcriptome
transcritpmoe_reads - int total number of reads analized
cluster - dict, stats about the cluster we are analizing {'Nreads' : int, 'size' : int}
"""
transcriptome_p = poissonP(transcriptome_reads, cluster['Nreads'],
transcriptome_size, cluster['size'])
if math.isnan(transcriptome_p):
verboseprint("""Transcriptome P is NaN, transcriptome_reads = %d,
cluster reads = %d, transcriptome_size = %d,
cluster_size = %d""" % (transcriptome_reads, cluster['Nreads'],
transcriptome_size, cluster['size']))
return False
if transcriptome_p > poisson_cutoff:
print """%s\n Failed Transcriptome cutoff with %s reads,
pval: %s""" % (cluster, cluster['Nreads'], transcriptome_p)
return False
return True
def superlocal_poissonP(cluster):
return poissonP(cluster.area_reads, cluster.number_reads_in_peak,
cluster.area_size, cluster['size'])
def transcript_poissonP(cluster):
return poissonP(cluster.nreads_in_gene, cluster.number_reads_in_peak,
cluster.effective_length, cluster['size'])
def transcriptome_poissonP(cluster):
return poissonP(cluster.transcriptome_reads, cluster.number_reads_in_peak,
cluster.transcriptome_size, cluster['size'])
def superlocal_poissonP(cluster):
return poissonP(cluster.area_reads,
cluster.number_reads_in_peak,
cluster.area_size,
cluster['size'])
def transcript_poissonP(cluster):
return poissonP(cluster.nreads_in_gene,
cluster.number_reads_in_peak,
cluster.effective_length,
cluster['size'])
def transcriptome_poissonP(cluster):
return poissonP(cluster.transcriptome_reads,
cluster.number_reads_in_peak,
cluster.transcriptome_size,
cluster['size'])
def main(options):
if options.np == 'autodetect':
options.np = multiprocessing.cpu_count()
pool = multiprocessing.Pool(int(options.np))
#job_server = pp.Server(ncpus=options.np) #old pp stuff
bamfile = options.bam
if os.path.exists(bamfile):
#re-set to include the full path to bamfile
bamfile = os.path.abspath(bamfile)
verboseprint("bam file is set to %s\n" % (bamfile))
else:
sys.stderr.write("Bam file not defined")
raise IOError
genes, lengths = build_transcript_data(options.species,
options.geneBEDfile,
options.geneMRNAfile,
options.genePREMRNAfile,
options.premRNA)
margin = int(options.margin)
#this should be fixed, args should initally be ints if passed
if options.maxgenes is not None:
maxgenes = int(options.maxgenes)
minreads = int(options.minreads)
poisson_cutoff = options.poisson_cutoff
#gets all the genes to call peaks on
if options.gene is not None and len(options.gene ) > 0:
gene_list = options.gene
else: #selects all genes
gene_list = genes.keys()
results = []
#Set up peak calling by gene
running_list = [genes[gene] for gene in gene_list]
length_list = [lengths[gene] for gene in gene_list]
#truncates for max genes
if options.maxgenes is not None:
running_list = running_list[:maxgenes]
length_list = length_list[:maxgenes]
transcriptome_size = sum(length_list)
#do the parralization
tasks = [(gene, length, None, bamfile, margin, options.FDR_alpha,
options.threshold, minreads, poisson_cutoff,
options.plotit, 10, 1000, options.SloP, False)
for gene, length in zip(running_list, length_list)]
#jobs = []
#for job in tasks:
#func_star(job)
#growth = objgraph.show_growth(limit=10)
#if growth is not None:
# print job
# print objgraph.show_growth(limit=10)
#jobs.append(func_star(job))
#sets chunk size to be a fair bit smaller, than total input, but not
#to small
chunk_size = len(tasks) // int(options.np) * 10
if chunk_size < 1:
chunk_size = 1
jobs = pool.map(func_star, tasks, chunksize=chunk_size)
for job in jobs:
results.append(job)
verboseprint("finished with calling peaks")
#if we are going to save and output as a pickle file we should
#output as a pickle file we should factor instead create a method
#or object to handle all file output
if options.save_pickle is True:
pickle_file = open(options.outfile + ".pickle", 'w')
pickle.dump(results, file=pickle_file)
#combine results
allpeaks = set([])
#count total number of reads in transcriptiome
transcriptome_reads = 0
for gene_result in results:
if gene_result is not None:
verboseprint("nreads", gene_result['nreads'])
transcriptome_reads += gene_result['nreads']
print """Transcriptome size is %d, transcriptome
reads are %d""" % (transcriptome_size, transcriptome_reads)
#is this a missed indent?
for gener in results:
if gener['clusters'] is None:
print >> sys.stderr, gener, "no clusters"
continue
for cluster in gener['clusters'].keys():
try:
transcriptome_p = poissonP(transcriptome_reads,
gener['clusters'][cluster]['Nreads'],
transcriptome_size,
gener['clusters'][cluster]['size'])
if math.isnan(transcriptome_p):
print """Transcriptome P is NaN, transcriptome_reads = %d,
cluster reads = %d, transcriptome_size = %d,
cluster_size = %d""" % (transcriptome_reads,
gener['clusters'][cluster]['Nreads'],
transcriptome_size,
gener['clusters'][cluster]['size'])
continue
if transcriptome_p > poisson_cutoff:
print """%s\n Failed Transcriptome cutoff with %s reads,
pval: %s""" % (cluster,
gener['clusters'][cluster]['Nreads'],
transcriptome_p)
continue
min_pval = 1
corrected_SloP_pval = gener['clusters'][cluster]['SloP']
corrected_gene_pval = gener['clusters'][cluster]['GeneP']
if (corrected_SloP_pval < poisson_cutoff or
corrected_gene_pval < poisson_cutoff):
min_pval = min([corrected_SloP_pval, corrected_gene_pval])
else:
verboseprint("Failed Gene Pvalue: %s and failed SloP Pvalue: %s for cluster %s" % (corrected_gene_pval, corrected_SloP_pval, cluster))
continue
(chrom, g_start, g_stop, peak_name, geneP, signstrand, thick_start, thick_stop) = cluster.split("\t")
#print >> sys.stderr, cluster
bedline = "%s\t%d\t%d\t%s\t%s\t%s\t%d\t%d" % (chrom, int(g_start), int(g_stop), peak_name, min_pval, signstrand, int(thick_start), int(thick_stop))
allpeaks.add(bedline)
except NameError as error:
print >> sys.stderr, error
print >> sys.stderr, "parsing failed"
raise error
#again redundant code
outbed = options.outfile + ".BED"
color = options.color
pybedtools.BedTool("\n".join(allpeaks), from_string=True).sort(stream=True).saveas(outbed, trackline="track name=\"%s\" visibility=2 colorByStrand=\"%s %s\"" % (outbed, color, color))
print "wrote peaks to %s" % (options.outfile)
"\n".join(allpeaks)
return 1