bfa = '>%s\n%s\n' % (subjct, seq)
difference = compare_itself(fasta, bfa)
paired_fa.append(bfa)
keys = list(difference.keys())
keys.sort()
for pos in keys:
info.append('%s\t%s\t%s\t%s\n' %
(name, subjct, pos, difference[pos]))
if isInBlast:
#itself is found by blast
pass
else:
#this is very special
#the barcode is not in the blast result
difference, subjct = compare_top_hit(br_result)
bfa = '>%s(addBack_closest_barcode)\n%s\n' % (
subjct, barCodeDict[subjct])
paired_fa.append(bfa)
keys = list(difference.keys())
keys.sort()
for pos in keys:
info.append('%s\t%s\t%s\t%s\n' %
(name, subjct, pos, difference[pos]))
info.append('#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#\n')
dn = cmn.lastName(fn) + '.report'
cmn.write_file(''.join(info), dn)
dn = cmn.lastName(fn) + '_paired.fa'
cmn.write_file(''.join(paired_fa), dn)
if __name__=='__main__':
#options=parse_options()
try:
fn=sys.argv[1]
except:
print("Usage: *.py", file=sys.stderr)
sys.exit()
fall = '/project/biophysics/Nick_lab/wli/sequencing/scripts/data/barcodes/species_barcodes_4mapping.fa'
#fall = '/project/biophysics/Nick_lab/wli/sequencing/scripts/data/barcodes/all_barcodes.fasta'
seqDict = read_fa(fall)
info = []
for line in cmn.file2lines(fn):
#5077 Autochton zarex
items = line.strip().split()
sample, genus, sp = items[:3]
query_sequence, qlen = get_query_sequence(seqDict, genus, sp)
br_result = do_barcode_blast(query_sequence)
print(br_result)
#print '\n'.join(br_result)
baits = pick_barcode_baits(br_result, qlen, seqDict)
info += format_baits(sample, baits)
dn = cmn.lastName(fn) + '.baits'
cmn.write_file(''.join(info), dn)
fn, fadd = sys.argv[1:3]
except:
print("Usage: *.py aln repID.file", file=sys.stderr)
sys.exit()
#fID = '/work/biophysics/wli/introgression2/4_filterIntro/rep_sps'
#fID = '/project/biophysics/Nick_lab/wli/sequencing/myAnalysis/clean_ref_bias/4_build_tree/pureIDs'
#goodIDs = set([i.split()[0] for i in cmn.file2lines(fID)
# if i.strip() != ''])
#fadd = 'added_sps'
#if cmn.filexist(fadd):
# print 'found local list, add them in'
goodIDs = set(cmn.getid(fadd))
dn = cmn.lastName(fn).replace('.fasta', '').replace('.fa',
'') + '_taken.fa'
dp = open(dn, 'w')
new = []
leftIDs = set(goodIDs)
with open(fn) as fp:
for line in fp:
if line[0] == '>':
name = line[1:].strip().split('_')[0].split('-')[0]
if name in goodIDs:
isGood = True
if name in leftIDs:
leftIDs.remove(name)
else:
isGood = False
for each in contig:
scaf, position1, char1, char2, phase = each
phase += '[swap]'
newlist.append((scaf, position1, char2, char1, phase))
return newlist
if __name__ == '__main__':
#options=parse_options()
try:
fsam, fletter = sys.argv[1:]
except:
print("Usage: *.py *.sam *.letters", file=sys.stderr)
sys.exit()
outlabel = cmn.lastName(fletter)[:-8]
print(outlabel)
#{read_query_name: [record1, record2]}
paired_samDict = read_samfile(fsam)
#covDict[scaf][index][char]
covDict = compute_coverage_from_sam(paired_samDict)
cons_seq = make_cons_from_covDict(covDict)
#adict = {'scaf': position1: [A, T, phase]}
letter_dict, inconsistent_positions = read_letter_file(fletter)
#still save inconsistent letter in letter_dict because we need to break contigs by them
letter_dict, corrected_dict = correct_false_snp_call(
letter_dict, covDict, inconsistent_positions)
new = []
for scaf in corrected_dict:
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__=='__main__':
#options=parse_options()
try:
fR1, fR2 = sys.argv[1:3]
except:
print("Usage: *.py R1 R2", file=sys.stderr)
sys.exit()
sample = cmn.lastName(fR1).split('_')[0]
spacing_list = [2, 3, 5, 10]
count = 0
for spacing in spacing_list:
fpR1 = open(fR1)
fpR2 = open(fR2)
dnlabel = '%s.spacing%s' % (sample, spacing)
print('making %s' % dnlabel)
dnR1 = open('%s_R1.fastq' % dnlabel, 'w')
dnR2 = open('%s_R2.fastq' % dnlabel, 'w')
for i, line1 in enumerate(fpR1):
line2 = fpR2.readline()
adict[sp] = ref
rset.add(ref)
if isbad:
sys.exit()
return rset, adict
#1. read in data
fns = cmn.getid(sys.argv[1])
bwa_dirs = [line.strip().rstrip('/') for line in cmn.getid(sys.argv[2])]
#2. check which reference they used
#sp is unique
vcf_dict = {cmn.lastName(fn).replace('_snp_step2.vcf', ''): fn for fn in fns}
#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
import sys
python_lib = '/work/00412/mtang/sequencing/scripts'
if python_lib not in sys.path:
sys.path.append(python_lib)
import cmn
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py *.clw", file=sys.stderr)
sys.exit()
new = []
with open(fn) as fp:
for line in fp:
exon, sp, seq = line.strip().split()
sp = sp.split('.')[0]
new.append('>%s_%s\n%s\n' % (sp, exon, seq))
dn = cmn.lastName(fn).replace('.sum', '') + '.fa'
cmn.write_file(''.join(new), dn)
adict = {}
fastas = cmn.txt_read(fa).split('>')[1:]
print(fastas)
for each in fastas:
lines = each.strip().split('\n')
defline = lines[0]
seq = ''.join([line.strip() for line in lines[1:]])
#seq = seq.replace('N', '-')
adict[defline] = seq
return adict
if __name__ == '__main__':
#options=parse_options()
try:
fn, Range = sys.argv[1:3]
i, j = list(map(int, Range.split('-')))
except:
print("Usage: *.py aln 0-10000", file=sys.stderr)
sys.exit()
new = []
seqDict = read_fa(fn)
for name in seqDict:
seq = seqDict[name]
fasta = '>%s\n%s\n' % (name, seq[i:j])
new.append(fasta)
dn = '%s_%s.fa' % (cmn.lastName(fn).replace('.fa', ''), Range)
cmn.write_file(''.join(new), dn)
import cmn
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
ref_scaf = sys.argv[2]
except:
print("Usage: *.py samfile scaf", file=sys.stderr)
sys.exit()
dn = 'filtered' + cmn.lastName(fn)
dp = open(dn, 'w')
with open(fn) as fp:
for line in fp:
if line[0] == '@':
if ref_scaf in line:
dp.write(line)
else:
if line.strip().split()[2] == ref_scaf:
dp.write(line)
dp.close()
if __name__ == '__main__':
#options=parse_options()
try:
fqlist, fmitolist = sys.argv[1:]
except:
print("Usage: *.py fqlist refMitoList", file=sys.stderr)
sys.exit()
#ftemplate = '/work/biophysics/wli/Eudamine/wholeMito_run2/mito_denovo.template'
ftemplate = '/project/biophysics/Nick_lab/wli/sequencing/scripts/mito_scripts/mito_refDenovo.template'
template = cmn.txt_read(ftemplate)
fqlist = cmn.file2lines(fqlist)
groupDict = {}
for fq in fqlist:
fq = os.path.abspath(fq)
ID = cmn.lastName(fq).split('_')[0]
try:
groupDict[ID].append(fq)
except KeyError:
groupDict[ID] = [fq]
fmitolist = os.path.abspath(fmitolist)
for sample in groupDict:
fqlist = groupDict[sample]
wdir = 'mitoRef_%s' % sample
cmn.mkdir(wdir)
os.chdir(wdir)
cwd = os.getcwd()
info = template.replace('[cwd]', cwd)
cmn.write_lines(fqlist, 'fqlist')
cmd = 'cat %s|xargs cat > ref_mito.fa; module add bwa; bwa index ref_mito.fa' % fmitolist
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py *.fq", file=sys.stderr)
sys.exit()
taken = set([])
dn = cmn.lastName(fn).split('.')[0] + '_unified.fastq'
isGood = True
#new = []
dp = open(dn, 'w')
with open(fn) as fp:
for i, line in enumerate(fp):
if i % 4 == 0:
ID = line.strip()
if ID not in taken:
isGood = True
taken.add(ID)
else:
isGood = False
print('duplcated ID: %s' % ID)
if isGood:
import sys
python_lib = '/home2/wli/my_programs/python_lib'
if python_lib not in sys.path:
sys.path.append(python_lib)
import cmn
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py *.clw", file=sys.stderr)
sys.exit()
new = []
with open(fn) as fp:
for line in fp:
name, seq = line.strip().split()
new.append('>%s\n%s\n' % (name, seq))
dn = cmn.lastName(fn).replace('.clw', '') + '.fa'
cmn.write_file(''.join(new), dn)
]
fmis = cmn.cmd2lines('ls rescued_read_assembled_mis1*.txt')[0]
fns.append(fmis)
for fn in fns:
cmd = 'chmod a+w %s' % fn
cmn.run(cmd)
cmd = "ssh [email protected] 'rm /data/www/wenlin/html/transfer/barcode_lineup_files/%s_rescued_read_assembled_mis1*.txt'" % sp
cmn.run(cmd)
cmd = 'rm /project/biophysics/Nick_lab/wli/archive/BWA_barcodes/lineup_files/%s_rescued_read_assembled_mis1*.txt' % sp
cmn.run(cmd)
ddirs = [
'/project/biophysics/Nick_lab/wli/archive/BWA_barcodes/lineup_files',
'[email protected]:/data/www/wenlin/html/transfer/barcode_lineup_files/other_data'
]
cmd = 'rsync -av %s [email protected]:/data/www/wenlin/html/transfer/barcode_lineup_files/%s_%s' % (
fmis, sp, fmis)
cmn.run(cmd)
for ddir in ddirs:
for fn in fns:
if 'rescued_read_assembled_mis1' in fn and '/other_data' in ddir:
continue
cmd = 'rsync -av %s %s/%s_%s' % (fn, ddir, sp, cmn.lastName(fn))
cmn.run(cmd)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py assembly", file=sys.stderr)
sys.exit()
seqDict, order_scafs = read_fa(fn)
#write in the same dict as assembly
olabel = cmn.lastName(fn)
dnlabel = '.'.join(olabel.split('.')[:-1]) + '_scaf.header'
dn = fn.replace(olabel, dnlabel)
fdn = open(dn, 'w')
for name in order_scafs:
shortname = name.split()[0]
length = len(seqDict[name])
for i in range(length):
line = '%s\t%s\n' % (shortname, (i + 1))
fdn.write(line)
fdn.close()
with open(fn) as fp:
for line in fp:
if line[0] == '>':
defline = line.strip()
if sampleID in defline:
isTaken = True
else:
isTaken = False
else:
if isTaken:
takenSeq = line.strip()
print('take the base seq as %s for %s' %
(defline, sampleID))
break
goodP = [i for i in range(len(takenSeq)) if takenSeq[i] not in gapChars]
f_label = cmn.lastName(fn).replace('.fasta', '').replace('.fa', '')
dn = f_label + '_base%s.fa' % sampleID
dp = open(dn, 'w')
with open(fn) as fp:
for line in fp:
if line[0] == '>':
defline = line.strip()
else:
goodSeq = ''.join([line[i] for i in goodP])
dp.write('%s\n%s\n' % (defline, goodSeq))
dp.close()
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py sam", file=sys.stderr)
sys.exit()
dnH = cmn.lastName(fn).replace('.sam', '') + '.HighQmapStat'
dnL = cmn.lastName(fn).replace('.sam', '') + '.mapStat'
rdict = {}
hdict = {}
samfile = pysam.AlignmentFile(fn)
for record in samfile:
if record.is_unmapped:
continue
scaf = record.reference_name
aligns = record.get_aligned_pairs()
N = len([each for each in aligns if None not in each])
if scaf not in rdict:
rdict[scaf] = [0, 0]
adict[defline] = seq.upper()
return adict
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__=='__main__':
#options=parse_options()
try:
fn=sys.argv[1]
except:
print("Usage: *.py aln.fa", file=sys.stderr)
sys.exit()
seqDict = read_fa(fn)
newDict = {key: ''.join([rdict[char] for char in seqDict[key][::-1]])
for key in seqDict}
dn = cmn.lastName(fn) + '.reverse'
fastas = ['>%s_reverse\n%s\n' % (name, newDict[name])
for name in newDict]
cmn.write_file(''.join(fastas), dn)
adict[defline] = seq.upper()
return adict
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__=='__main__':
#options=parse_options()
try:
fn=sys.argv[1]
except:
print("Usage: *.py aln.fa", file=sys.stderr)
sys.exit()
seqDict = read_fa(fn)
newDict = {key: ''.join([rdict[char] for char in seqDict[key]])
for key in seqDict}
dn = cmn.lastName(fn) + '.cmpl'
fastas = ['>%s_reverse\n%s\n' % (name, newDict[name])
for name in newDict]
cmn.write_file(''.join(fastas), dn)
if copy_counts[0] > copy_counts[1]:
char2 = char1
else:
char1 = char2
else:
print('unrecognized line: %s' % line, file=sys.stderr)
sys.exit()
seq1.append(char1)
seq2.append(char2)
#output the last
phased_blocks.append('%s\t%s\t%s\t%s\t%s\t%s\n' % (lastPhase, lastScaf, lastPosition[1], right[1], lastPosition[2], right[2]))
dnlabel = cmn.lastName(fn).replace('.vcf', '')
sp = dnlabel.split('_')[1]
dn = dnlabel + '_phased.fa'
with open(dn, 'w') as dp:
dp.write('>%s_ref_or_phase1\n' % sp)
dp.write(''.join(seq1))
dp.write('\n')
dp.write('>%s_called_or_phase2\n' % sp)
dp.write(''.join(seq2))
dp.write('\n')
dn = dnlabel + 'phased.blocks'
cmn.write_file(''.join(phased_blocks), dn)
sys.exit()
fhead = '/work/biophysics/mtang/SNP_calling/indexed_references/Junonia_v2_scaf.header'
#fhead = 'Calycopis_cecrops_assembly_V1.1_scaf.header'
print('loading header info...')
headDict = {}
with open(fhead) as fp:
for i, line in enumerate(fp):
scaf, index = line.strip().split()
try:
headDict[scaf].append(i)
except KeyError:
headDict[scaf] = [i]
print('finish loading header, begin parsing fasta...')
outdir = '%s_scafs' % cmn.lastName(fn)
cmn.mkdir(outdir)
seqDict = read_fa(fn)
for scaf in headDict:
indexes = headDict[scaf]
new = []
for name in seqDict:
seq = seqDict[name]
newSeq = ''.join([seq[i] for i in indexes])
fasta = '>%s\n%s\n' % (name, newSeq)
new.append(fasta)
dn = '%s/%s.fa' % (outdir, scaf)
cmn.write_file(''.join(new), dn)
if python_lib not in sys.path:
sys.path.append(python_lib)
import cmn
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py vcf", file=sys.stderr)
sys.exit()
total = cmn.cmd2info('wc -l %s' % fn).split()[0]
SNPs = cmn.cmd2info('grep HaplotypeScore %s > %s.tmp; wc -l %s.tmp' %
(fn, fn, fn)).split()[0]
lowqual = cmn.cmd2info('grep LowQual %s.tmp|wc -l ; rm %s.tmp' %
(fn, fn)).split()[0]
print(cmn.lastName(fn), total, SNPs, lowqual,
int(SNPs) / float(total),
int(lowqual) / float(SNPs))
seq = []
else:
seq.append(line.strip())
#last seq
seqDict[sp].append(''.join(seq))
new = []
for sp in seqDict:
seq1, seq2 = seqDict[sp]
diffN = sum([seq1[i] != seq2[i]
for i in range(len(seq1))])
if diffN < cutoff:
if diffN == 0:
seq = seq1
defline = '%s_unique' % sp
else:
seq = collapse_seqs(seq1, seq2)
defline = '%s_diff%s' % (sp, diffN)
fasta = '>%s\n%s\n' % (defline, seq)
else:
#need to keep both copy
label = '%s_diff%s' % (sp, diffN)
fasta = '>%s_cp1\n%s\n>%s_cp2\n%s\n' % (label, seq1, label, seq2)
new.append(fasta)
dn = '%s_collapse_cut%s.fa' % (cmn.lastName(fn).replace('.fa', '') , cutoff)
cmn.write_file(''.join(new), dn)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__=='__main__':
#options=parse_options()
try:
fnlist, outdir = sys.argv[1:]
except:
print("Usage: *.py falist outdirName", file=sys.stderr)
sys.exit()
outlabel = cmn.lastName(fnlist)
#scan through to see the total IDlist
IDs = set([])
fns = cmn.file2lines(fnlist)
for fn in fns:
with open(fn) as fp:
for line in fp:
if line[0] == '>':
ID = name2ID(line[1:].strip())
IDs.add(ID)
#read in sequence and partition
shift = 0
final = {}
setList = []
for fn in fns:
adict = {}
alist = []
fastas = cmn.txt_read(fa).split('>')[1:]
for each in fastas:
lines = each.strip().split('\n')
defline = lines[0]
alist.append(defline)
seq = ''.join(lines[1:])
adict[defline] = seq
return adict, alist
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py", file=sys.stderr)
sys.exit()
seqDict, orderlist = read_fa(fn)
new = ['>%s\n%s\n' % (name, seqDict[name].upper()) for name in orderlist]
dn = cmn.lastName(fn).replace('.fa', '') + '_4tree.fa'
cmn.write_file(''.join(new), dn)
continue
if N == 0 or N == 1:
#skip the all gapped positions
#also skip same character lines
continue
else:
for i, char in enumerate(chars):
if char in missing_data:
result[i].append(-9)
continue
try:
code = char_label[char]
except KeyError:
code = current_count
char_label[char] = current_count
current_count += 1
result[i].append(code)
dn = cmn.lastName(fn) + 'STRUCTUREinput.txt'
new = ['\t'.join(map(str, line)) for line in result]
new.append('')
cmn.write_lines(new, dn)
print('number of loci: %s' % (len(line) - 1))
if __name__=='__main__':
#options=parse_options()
try:
#fn, f_table = sys.argv[1:3]
fn = sys.argv[1]
except:
print("Usage: *.py fqlist", file=sys.stderr)
sys.exit()
cmn.mkdir('tmpStat')
IDlist = set([])
fq_groups = {}
for line in cmn.file2lines(fn):
Id = cmn.lastName(line).split('_')[0]
Id = Id.replace('NVG-', '').replace('11-BOA-','').replace('LEP-', 'LEP')
IDlist.add(Id)
fq = os.path.abspath(line)
try:
fq_groups[Id].append(fq)
except KeyError:
fq_groups[Id] = [fq]
nameDict = get_names_4barcode()
fall = '/project/biophysics/Nick_lab/wli/sequencing/scripts/data/barcodes/species_barcodes_4mapping.fa'
#fall = '/project/biophysics/Nick_lab/wli/sequencing/scripts/data/barcodes/all_barcodes.fasta'
seqDict = read_fa(fall)
fadd = '/project/biophysics/Nick_lab/wli/sequencing/scripts/data/barcodes/addedBaits_fromPipeline.fa'
if cmn.filexist(fadd):
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#fns = cmn.cmd2lines('ls ../0_libs/*/*.fq')
#fns += cmn.cmd2lines('ls ../0_libs/*/*.fastq')
#fns = cmn.file2lines('../fqlist')
#fns = cmn.cmd2lines('ls /project/biophysics/Nick_lab/wli/sequencing/Eudamine/BEAST_timing/tmp_link_fastq/*q')
fns = cmn.file2lines(sys.argv[1])
#skip_list = set(['5316', '5721'])
gdict = {}
for fn in fns:
#items = fn.split('/')
#sp = items[-2]
sp = cmn.lastName(fn).split('_')[0]
try:
gdict[sp].append(fn)
except:
gdict[sp] = [fn]
formatcmds = '\n\n'
for sp in gdict:
#if sp in skip_list:
# continue
cmd = ''
fns = gdict[sp]
for fn in fns:
cmd += 'fq2fa %s >> %s.fa; ' % (fn, sp)
seq = ''.join(lines[1:])
adict[defline] = seq
return adict, len(seq)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#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)
new = ['%s\t%s' % (len(seqDict), length)]
for name in seqDict:
new.append('%s %s' % (name, seqDict[name]))
dn = cmn.lastName(fn) + '.phylip'
cmn.write_lines(new, dn)
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#main
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
if __name__ == '__main__':
#options=parse_options()
try:
fn = sys.argv[1]
except:
print("Usage: *.py", file=sys.stderr)
sys.exit()
adict = {}
with open(fn) as fp:
for line in fp:
if line[0] == '>':
label = line.strip()
else:
seq = line.strip()
adict[label] = '%s\n%s\n' % (label, seq)
times = 10
keys = list(adict.keys())
cmn.mkdir('shuffle_genome')
for each in range(times):
random.shuffle(keys)
new = [adict[key] for key in keys]
dn = 'shuffle_genome/%s_shuffle%s' % (cmn.lastName(fn), each)
cmn.write_file(''.join(new), dn)
if __name__ == '__main__':
#options=parse_options()
try:
fn, frange = sys.argv[1:]
except:
print("Usage: *.py", file=sys.stderr)
sys.exit()
geneRange = read_gene_range(frange)
seqDict, order_list = read_fa(fn)
stat = []
outdir = '%s_gene_fasta' % cmn.lastName(fn)
cmn.mkdir(outdir)
for gene in geneRange:
i, j = geneRange[gene]
print(gene, i, j)
stat.append('%s\t%s\n' % (gene, j - i))
dn = '%s/%s.fa' % (outdir, gene)
with open(dn, 'w') as dp:
for name in order_list:
seq = seqDict[name][i:j]
if seq.strip('-').strip('N') == '':
continue
fasta = '>%s\n%s\n' % (name, seq)
dp.write(fasta)
