def __init__(self,
load_refseq=True,
load_canonical=True,
load_transcript=False):
self.ensembl_id_patt = re.compile('(ENST\d+)')
if load_refseq:
gene_file = "%s/%s" % (snapconf.TABIX_DB_PATH,
snapconf.REFSEQ_ANNOTATION)
gene_pickle_file = "%s.pkl" % (gene_file)
self.gene_map = snaputil.load_cpickle_file(gene_pickle_file)
if not self.gene_map:
self.load_gene_coords(gene_file)
snaputil.store_cpickle_file(gene_pickle_file, self.gene_map)
if load_canonical:
canonical_gene_file = "%s/%s" % (snapconf.TABIX_DB_PATH,
snapconf.CANONICAL_ANNOTATION)
canonical_gene_pickle_file = "%s.pkl" % (canonical_gene_file)
self.canonical_gene_map = snaputil.load_cpickle_file(
canonical_gene_pickle_file)
if not self.canonical_gene_map:
self.load_canonical_gene_coords(canonical_gene_file)
snaputil.store_cpickle_file(canonical_gene_pickle_file,
self.canonical_gene_map)
#per transcript exons
if load_transcript:
transcript_file = "%s/%s" % (snapconf.TABIX_DB_PATH,
snapconf.TABIX_GENE_INTERVAL_DB)
transcript_pickle_file = "%s.pkl" % (transcript_file)
self.transcript_map = snaputil.load_cpickle_file(
transcript_pickle_file)
if not self.transcript_map:
self.load_transcripts(transcript_file)
snaputil.store_cpickle_file(transcript_pickle_file,
self.transcript_map)
def __init__(self,load_refseq=True,load_canonical=True,load_transcript=False):
self.ensembl_id_patt = re.compile('(ENST\d+)')
if load_refseq:
gene_file = "%s/%s" % (snapconf.TABIX_DB_PATH,snapconf.REFSEQ_ANNOTATION)
gene_pickle_file = "%s.pkl" % (gene_file)
self.gene_map = snaputil.load_cpickle_file(gene_pickle_file)
if not self.gene_map:
self.load_gene_coords(gene_file)
snaputil.store_cpickle_file(gene_pickle_file,self.gene_map)
if load_canonical:
canonical_gene_file = "%s/%s" % (snapconf.TABIX_DB_PATH,snapconf.CANONICAL_ANNOTATION)
canonical_gene_pickle_file = "%s.pkl" % (canonical_gene_file)
self.canonical_gene_map = snaputil.load_cpickle_file(canonical_gene_pickle_file)
if not self.canonical_gene_map:
self.load_canonical_gene_coords(canonical_gene_file)
snaputil.store_cpickle_file(canonical_gene_pickle_file,self.canonical_gene_map)
#per transcript exons
if load_transcript:
transcript_file = "%s/%s" % (snapconf.TABIX_DB_PATH,snapconf.TABIX_GENE_INTERVAL_DB)
transcript_pickle_file = "%s.pkl" % (transcript_file)
self.transcript_map = snaputil.load_cpickle_file(transcript_pickle_file)
if not self.transcript_map:
self.load_transcripts(transcript_file)
snaputil.store_cpickle_file(transcript_pickle_file,self.transcript_map)
def sample_ids2intron_ids_from_bit_vector(sample_ids):
snaptron_ids_final = None
for sample_id in sample_ids:
snaptron_ids = snaputil.load_cpickle_file("%s/%s.pkl" % (snapconf.PACKED_SAMPLE_IDS_PATH, str(sample_id)), compressed=False)
#in a few cases we may not have a mapping for a specific sample_id
if snaptron_ids is None:
continue
if snaptron_ids_final is None:
snaptron_ids_final = snaptron_ids
else:
snaptron_ids_final = snaptron_ids_final | snaptron_ids
snaptron_ids_final_set = set()
[snaptron_ids_final_set.add(str(i)) for (i,x) in enumerate(snaptron_ids_final) if x]
return snaptron_ids_final_set
def sample_ids2intron_ids_from_bit_vector(sample_ids):
snaptron_ids_final = None
for sample_id in sample_ids:
snaptron_ids = snaputil.load_cpickle_file("%s/%s.pkl" % (snapconf.PACKED_SAMPLE_IDS_PATH, str(sample_id)), compressed=False)
#in a few cases we may not have a mapping for a specific sample_id
if snaptron_ids is None:
continue
if snaptron_ids_final is None:
snaptron_ids_final = snaptron_ids
else:
snaptron_ids_final = snaptron_ids_final | snaptron_ids
snaptron_ids_final_set = set()
[snaptron_ids_final_set.add(str(i)) for (i,x) in enumerate(snaptron_ids_final) if x]
return snaptron_ids_final_set
def load_sample_metadata(file_):
start = time.time()
fmd=snaputil.load_cpickle_file("%s.pkl" % (file_))
if fmd:
end = time.time()
taken = end-start
return fmd
start = time.time()
fmd={}
#dont need the hash-on-column headers just yet
with open(file_,"r") as f:
for line in f:
line = line.rstrip()
fields=line.split("\t")
fmd[fields[0]]=line
end = time.time()
taken = end-start
#sys.stderr.write("time taken to load samples from normal: %d\n" % taken)
snaputil.store_cpickle_file("%s.pkl" % (file_),fmd)
return fmd
def load_sample_metadata(file_):
start = time.time()
fmd=snaputil.load_cpickle_file("%s.pkl" % (file_))
if fmd:
end = time.time()
taken = end-start
return fmd
start = time.time()
fmd={}
#dont need the hash-on-column headers just yet
with open(file_,"r") as f:
for line in f:
line = line.rstrip()
fields=line.split("\t")
fmd[fields[0]]=line
end = time.time()
taken = end-start
#sys.stderr.write("time taken to load samples from normal: %d\n" % taken)
snaputil.store_cpickle_file("%s.pkl" % (file_),fmd)
return fmd
COMPRESSED=False
path='/data3/snaptron/sample_ids_full'
#path='/data3/snaptron/sample_ids'
#suffix='.gz'
suffix=''
def orthem(ba1,ba2):
ba_final = ba1 | ba2
return ba_final
def setthem(ba_final):
i = 0
s1=set()
[s1.add(i) for (i,x) in enumerate(ba_final) if x]
#for bit in ba_final:
# if bit:
# s1.add(i)
# i+=1
return s1
ba_final = su.load_cpickle_file("%s/0.pkl%s" % (path,suffix), compressed=COMPRESSED)
for i in xrange(1,5000):
ba2 = su.load_cpickle_file("%s/%s.pkl%s" % (path,str(i),suffix), compressed=COMPRESSED)
if ba2 != None:
ba_final = orthem(ba2,ba_final)
s1 = setthem(ba_final)
print len(s1)
#sys.stdout.write(",".join([str(x) for x in s1]))
