def RefFa(file_in):
dict_fa = {}
for item in FastaReader(file_in):
list_lb = re.split('_', item.name)
lb = '_'.join(list_lb[:2])
dict_fa[lb] = str(item.seq)
return dict_fa
def RefFa(file_in):
dict_fa = {}
list_all = []
for item in FastaReader(file_in):
list_lb = re.split('__', item.name)
lb = list_lb[0]
list_all.append(list_lb[1])
dict_fa[lb] = str(item.seq)
return sorted(set(list_all)), dict_fa
def get_variants(chr, pos, vartype, fasta_chr_file):
variant_list = []
#fasta_chr_file="/NGENEBIO/workflow-dependencies/seqseek/homo_sapiens_GRCh37/chr%s.fa"%(chr)
ref_seq = FastaReader(fasta_chr_file).__iter__().next()
ref = ref_seq[pos - 1:pos + 3].seq.upper()
if vartype == 'SNV':
variant_list.extend(get_snps(chr, pos, ref))
if vartype == 'DEL':
variant_list.extend(get_insertions(chr, pos, ref))
if vartype == 'INS':
variant_list.extend(get_deletions(chr, pos, ref))
return variant_list
def HandleData(file_in, list_all, outfile):
dict_fa = {}
Cluster = os.path.basename(file_in).strip('.fa')
for item in FastaReader(file_in):
seq = str(item.seq)
if seq not in dict_fa:
dict_fa[seq] = [item.name,]
else:
dict_fa[seq] += [item.name,]
n = 1
for seq in dict_fa:
pd_out = MakeAllSample(dict_fa[seq], list_all, Cluster)
for index in pd_out.index:
outfile.write(index+'\t'+'\t'.join([str(i) for i in pd_out.loc[index,:]])+'\n')
def HandleData(file_in, pd_in):
list_all = [i for i in pd_in.columns]
dict_fa = {}
Cluster = os.path.basename(file_in).strip('.fa')
for item in FastaReader(file_in):
seq = str(item.seq)
if seq not in dict_fa:
dict_fa[seq] = [
item.name,
]
else:
dict_fa[seq] += [
item.name,
]
n = 1
for seq in dict_fa:
pd_out = MakeAllSample(dict_fa[seq], list_all, Cluster)
pd_in = pd_in.append(pd_out)
return pd_in
def HandleData(dir_in):
Input = os.path.join(dir_in, 'input.fa')
Output = os.path.join(dir_in, 'output.fa')
with open(Input, 'r') as f:
for line in f:
Consus = line.strip().lstrip('>')
break
dict_fa = {}
for item in FastaReader(Output):
dict_fa[item.name] = str(item.seq)
total = len(dict_fa[Consus])
dict_burdon = {}
for key in dict_fa:
m = 0
for i in range(total):
if dict_fa[key][i] != dict_fa[Consus][i]:
m += 1
lb = re.findall('(\w+_\w+)GM', key)[0]
dict_burdon[lb] = str(round(float(m*1000/total), 4))
return dict_burdon, Consus
def ReadFasta(file_in):
dict_out = {}
for s in FastaReader(file_in):
dict_out[s.name] = str(s.seq)
return dict_out