def read_rep():
dn = 'rep.dict.pkl'
if cmn.filexist(dn):
print('loading repeats using precomputed data...')
return cmn.pickle_read(dn)
freps = cmn.cmd2lines('ls annotation_repeats/*.gff3')
repdict = {}
for frep in freps:
for line in cmn.file2lines(fn):
items = line.strip().split()
scaf = items[0]
if scaf not in repdict:
repdict[scaf] = set([])
i, j = list(map(int, items[3:5]))
repdict[scaf] = repdict[scaf] | set(range(i, j))
cmn.pickle_write(repdict, dn)
return repdict
#6188_3842_assembly_v2_snp_step2.vcf
#vcf_dict = {cmn.lastName(fn).replace('_snp_step2.vcf', ''): fn for fn in fns}
sps = list(vcf_dict.keys())
#ref_genomes, refmapping = detect_ref_genomes(sps, bwa_dirs)
ref_genomes, refmapping = set([]), {}
for fn in fns:
#../../step3_gatk/5729_3614_assembly_v1/5729_3614_assembly_v1_snp_step2.vcf
fnlabel = cmn.lastName(fn).replace('_snp_step2.vcf', '')
items = fnlabel.split('_')
sp = items[0]
ref = '_'.join(items[1:])
ref_genomes.add(ref)
refmapping[fnlabel] = ref
cmn.pickle_write(refmapping, 'ref_mapping.dict.pkl')
info = ['%s\t%s\n' % (sp, refmapping[sp]) for sp in refmapping]
cmn.write_file(''.join(info), 'ref_mapping.txt')
#3. make the length check
ref_dir = '/work/biophysics/mtang/SNP_calling/indexed_references'
unChecks = [
ref for ref in ref_genomes
if not os.path.exists('%s/%s_scafLength.txt' % (ref_dir, ref)) or (
not os.path.exists('%s/%s_scaf.header' % (ref_dir, ref)))
]
#unChecks = ref_genomes
print('#######################################################')
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py", file=sys.stderr)
sys.exit()
seqDict, length = read_fa(fn)
nameDict = {}
count = 0
new = ['%s\t%s' % (len(seqDict), length)]
for name in seqDict:
count += 1
newName = 'ID%s' % (count)
nameDict[newName] = name
newName = '{:<10}'.format(newName)
new.append('%s%s' % (newName, seqDict[name]))
dn = cmn.lastName(fn) + '.phylip'
cmn.write_lines(new, dn)
dn = cmn.lastName(fn) + '.phylipNames.dict.pkl'
cmn.pickle_write(nameDict, dn)
if __name__=='__main__':
#options=parse_options()
try:
fn=sys.argv[1]
except:
print("Usage: *.py coding.gff", file=sys.stderr)
sys.exit()
coding_indexes = []
with open(fn) as fp:
for line in fp:
#scaffold1_cov14552_reverse mitfi trnM(cat) 23 89 1.809e-09 + .
items = line.strip().split()
Range = list(map(int, items[3:5]))
if items[6] == '-':
j, i = Range
else:
i, j = Range
indexes = list(range(i, j+1))
coding_indexes += indexes
dn = 'coding.indexes.pkl'
cmn.pickle_write(set(coding_indexes), dn)
best_hits = find_bestE_reads(fn, label)
#then separate it by exomes
for line in best_hits:
exon = line.strip().split()[1]#??
try:
exome_dict[exon].append(line)
except:
exome_dict[exon] = [line]
try:
sp_dict[label] += best_hits
except:
sp_dict[label] = best_hits
print('writting outputs... ')
cmn.pickle_write(exome_dict, 'blastByExon.dict.pkl')
cmn.pickle_write(sp_dict, 'blastBySp.dict.pkl')
#output the exome blasts
#for exon in exome_dict:
# lines = exome_dict[exon]
# dn = '%s/%s.br' % (outdir, exon)
# cmn.write_file(''.join(lines), dn)
#get the reads and split them into exons
#fns = cmn.getid(fn)
rdict = {}
for fn in fns:
print('parsing ' + fn)
with open(fn) as fp:
for i, line in enumerate(fp):
if i % 4 == 0:
#record = []
ID = line.strip().replace(' ', '_')
#print 'checkID', ID
try:
sp = good_IDs[ID]
isGood = True
except KeyError:
isGood = False
#record.append(line)
if i % 4 == 1:
#record = ''.join(record)
seq = line.strip()
if isGood:
if sp not in rdict:
rdict[sp] = {}
rdict[sp][ID] = seq
dn = 'readsBySp.dict.pkl'
cmn.pickle_write(rdict, dn)
for fastq in fastqs:
if not os.path.exists(fastq):
print('fastq file %s doesn\'t exist! please email to ask!' % fastq)
sp = cmn.lastName(fastq).split('_')[0]
try:
qdict[sp].append(fastq)
except KeyError:
qdict[sp] = [fastq]
#3. check sp to see if refs are specified
goodSPs = []
for sp in qdict:
if sp in refdict:
goodSPs.append(sp)
else:
print('no reference genome found for sample %s, please email to ask' %
sp,
file=sys.stderr)
#4. output the mapping relationship
new = []
for sp in goodSPs:
for ref in refdict[sp]:
new.append('%s\t%s\t%s\n' % (sp, ','.join(qdict[sp]), ref))
dn = 'mapping_info.txt'
cmn.write_file(''.join(new), dn)
dn = 'require_SNPs.dict.pkl'
cmn.pickle_write(requires, dn)