def calculateSkew(fullPath):
'''
reads file specified by function argument, records is parsed by using SeqIO
, gc skew is calculated with SeqUtils.GC_skew. for every 10000 nucleotides
the sequence ID, nucleotide index, cumulative average GC-skew,
and average nucleotide score is added to a pandas dataframe and returned.
The average gc-skew av nucleotide score is used as a compromise between
computational load and accuracy.
'''
df = pd.DataFrame(columns=["id", "x", "y", "z"])
df_index = 0
with open(fullPath, "r") as handle:
for record in SeqIO.parse(handle, "fasta"):
gc = SeqUtils.GC_skew(record.seq, 10000)
count = 0
skew = 0
for nc in gc:
count += 1
skew = skew + nc
df.loc[df_index] = [record.id, count, skew, nc]
df.index += 1
return df
from Bio import SeqIO
from Bio import SeqUtils
if __name__ == "__main__":
for fna in SeqIO.parse("../sample_genome/sample1.fasta", "fasta"):
print(fna.id)
print(fna.seq)
print(fna.seq.reverse_complement())
print(SeqUtils.GC(fna.seq))
print(SeqUtils.GC_skew(fna.seq)[0])
from Bio import SeqIO
from Bio import SeqUtils
if __name__ == "__main__":
size = 10000
for fna in SeqIO.parse("../sample_genome/sample2.fasta", "fasta"):
results = []
seq = fna.seq
results = SeqUtils.GC_skew(seq, size)
with open("{}_GCskew.txt".format(fna.id), "w") as o:
o.write(fna.id + "," + str(size) + "\n")
for i in range(len(results)):
o.write(str(i * size + 1) + "," + str(results[i]) + "\n")
import sys
import pyBigWig
from Bio import SeqIO
from Bio import SeqUtils
span = int(sys.argv[2])
bw = pyBigWig.open(sys.argv[3], "w")
# Prepare header separately because ugh
data = []
for rec in SeqIO.parse(sys.argv[1], "fasta"):
data.append((rec.id, len(rec)))
bw.addHeader(data)
for rec in SeqIO.parse(sys.argv[1], "fasta"):
gc = SeqUtils.GC_skew(rec.seq, span)
bw.addEntries(rec.id, 0, values=list(gc), span=span, step=span)
bw.close()
#!/usr/bin/python
# coding=utf-8
'''
gc_skew.py [input-fasta][output-txt]
'''
import sys,re
input_file_name = sys.argv[1]#"polish_assembly.fasta"
output_file = open(sys.argv[2],"w")#"GC_skew.txt"
from Bio import SeqIO, SeqUtils
rec = SeqIO.read(input_file_name, 'fasta')
gc = SeqUtils.GC_skew(rec.seq, 1000)
start = 1
for gc_value in gc:
end = start + 1000
if end > len(rec):
end = len(rec)
output_file.write(str(start)+"\t"+str(end)+"\t"+str(gc_value) + "\n")
start = start + 1000
output_file.close()
def get_lstm_xx(j, seq_dict, kmer=2, dim=128, mode='train'):
loc1, scf1, std1, st1, ed1, loc2, scf2, std2, st2, ed2 = j[:10]
if scf1 != scf2 or std1 != std2:
#X0 = np.ones((4 ** kmer, dim))
X0 = [127] * dim
#X0 = None
X1 = [10**4] * 11
return X0, X1
# get the sequence
st1, ed1, st2, ed2 = list(map(int, [st1, ed1, st2, ed2]))
st1 -= 1
st2 -= 1
if st1 > st2:
loc1, scf1, std1, st1, ed1, loc2, scf2, std2, st2, ed2 = loc2, scf2, std2, st2, ed2, loc1, scf1, std1, st1, ed1
seq1 = seq_dict[scf1][st1:ed1]
seq1 = std1 == '+' and seq1 or seq1.reverse_complement()
seq2 = seq_dict[scf2][st2:ed2]
seq2 = std1 == '+' and seq2 or seq2.reverse_complement()
start, end = ed1, st2
seq12 = seq_dict[scf1][start:end]
# if len(seq12) > dim:
# seq12 = seq12[: dim // 2] + seq12[-dim // 2: ]
seq12 = std1 == '+' and seq12 or seq12.reverse_complement()
seq1, seq2, seq12 = list(map(str, [seq1.seq, seq2.seq, seq12.seq]))
seq1, seq2, seq12 = seq1.upper(), seq2.upper(), seq12.upper()
# 1D features such as gc, dist
cai1, cai2, cai12 = list(map(cai, [seq1, seq2, seq12]))
dist = st2 - ed1
distn = (st2 - ed1) * 1. / (ed2 - st1)
ratio = math.log((ed1 - st1) * 1. / (ed2 - st2))
ratio = std1 == '+' and ratio or -ratio
idx = -100
bgs = Counter(seq12[idx:])
up10, up35 = find_motif(seq12[idx:], box_up10,
bgs), find_motif(seq12[idx:], box_up35, bgs)
if seq12[idx:]:
gc = SeqUtils.GC(seq12[idx:])
try:
skew = SeqUtils.GC_skew(seq12[idx:])[0]
except:
skew = 0.
else:
gc = skew = 0.
bias = sharekmer(seq1, seq2)
if st1 == st2 == '+':
X1 = [cai1, cai2, bias, distn, ratio, gc, skew] + up10[1:] + up35[1:]
else:
X1 = [cai2, cai1, bias, distn, ratio, gc, skew] + up10[1:] + up35[1:]
#X1 = [cai1, cai2, bias, distn, ratio, gc, skew] + up10[1: ] + up35[1: ]
# 1D features of lstm
n12 = len(seq12)
'''
L = dim // 2
R = dim - L
if n12 > dim:
seq12 = seq12[: L] + seq12[-R: ]
else:
seq12 = seq12[: L] +'N' * (dim - n12) + seq12[-R: ]
'''
lstm_seq = [
s2n(seq12[elem:elem + kmer], code5) for elem in range(n12 - kmer + 1)
]
#X0 = lstm_seq[::kmer]
#for i in xrange(kmer):
# X0.extend(lstm_seq[i::kmer])
#X0 = lstm_seq
X0 = [-1] * dim
ndim = len(lstm_seq)
if ndim == dim:
X0 = lstm_seq
#print 'X0 0', len(X0)
elif 2 <= ndim < dim:
ndim = ndim // 2
X0[:ndim] = lstm_seq[:ndim]
X0[-ndim:] = lstm_seq[-ndim:]
#print 'X0 1', len(X0)
elif ndim > dim:
ndim = dim // 2
X0[:ndim] = lstm_seq[:ndim]
X0[-ndim:] = lstm_seq[-ndim:]
#print 'X0 2', len(X0)
else:
pass
return X0, X1
def get_xx0(j, seq_dict, kmer=2, dim=128, mode='train', context=False):
loc1, scf1, std1, st1, ed1, loc2, scf2, std2, st2, ed2 = j[:10]
if scf1 != scf2 or std1 != std2:
if context:
X0 = np.ones((4**kmer * 3, dim // 3 * 3))
else:
X0 = np.ones((4**kmer * 3, dim // 3))
X1 = [10**4] * 11
X2 = [127] * dim
return [X0], X1, X2
# get the sequence
st1, ed1, st2, ed2 = list(map(int, [st1, ed1, st2, ed2]))
st1 -= 1
st2 -= 1
if st1 > st2:
loc1, scf1, std1, st1, ed1, loc2, scf2, std2, st2, ed2 = loc2, scf2, std2, st2, ed2, loc1, scf1, std1, st1, ed1
seq1 = seq_dict[scf1][st1:ed1]
seq1 = std1 == '+' and seq1 or seq1.reverse_complement()
seq2 = seq_dict[scf2][st2:ed2]
seq2 = std1 == '+' and seq2 or seq2.reverse_complement()
start, end = ed1, st2
seq12 = seq_dict[scf1][start:end]
seq12 = std1 == '+' and seq12 or seq12.reverse_complement()
seq1, seq2, seq12 = list(map(str, [seq1.seq, seq2.seq, seq12.seq]))
seq1, seq2, seq12 = seq1.upper(), seq2.upper(), seq12.upper()
# 1D features such as gc, dist
cai1, cai2, cai12 = list(map(cai, [seq1, seq2, seq12]))
dist = st2 - ed1
distn = (st2 - ed1) * 1. / (ed2 - st1)
ratio = math.log((ed1 - st1) * 1. / (ed2 - st2))
ratio = std1 == '+' and ratio or -ratio
idx = -100
bgs = Counter(seq12[idx:])
up10, up35 = find_motif(seq12[idx:], box_up10,
bgs), find_motif(seq12[idx:], box_up35, bgs)
if seq12[idx:]:
gc = SeqUtils.GC(seq12[idx:])
try:
skew = SeqUtils.GC_skew(seq12[idx:])[0]
except:
skew = 0.
else:
gc = skew = 0.
bias = sharekmer(seq1, seq2)
if st1 == st2 == '+':
X1 = [cai1, cai2, bias, distn, ratio, gc, skew] + up10[1:] + up35[1:]
else:
X1 = [cai2, cai1, bias, distn, ratio, gc, skew] + up10[1:] + up35[1:]
# 2D features of kmer matrix
if context:
seqmat12 = kpm(seq12, d=dim, k=kmer, scale=4)
seqmat1 = kpm(seq1, d=dim, k=kmer, scale=4)
seqmat2 = kpm(seq2, d=dim, k=kmer, scale=4)
seqmat = np.concatenate((seqmat1, seqmat12, seqmat2), 1)
else:
seqmat = kpm(seq12, d=dim, k=kmer, scale=4)
if ed1 > st2:
seqmat[:] = 0
X0 = [seqmat]
n12 = len(seq12)
X2 = [
s2n(seq12[elem:elem + kmer], code5) for elem in range(n12 - kmer + 1)
]
return X0, X1, X2
gdt2 = GenomeDiagram.Track('GC content', greytrack=1, greytrack_labels=4)
gdt2.add_set(gdgs)
track_list.append(gdt2)
def gcSkewData(lst):
ret_list = []
i = 50
for x in lst:
ret_list.append((i, x))
i = i + 100
return ret_list
graphdata2 = gcSkewData(SeqUtils.GC_skew(seq_string))
gdgs2 = GenomeDiagram.GraphSet('GC Skew')
gdgs2.new_graph(graphdata, 'GC Skew', style='line', linewidth=2)
gdt3 = GenomeDiagram.Track('GC Skew', greytrack=1, greytrack_labels=4)
gdt3.add_set(gdgs2)
track_list.append(gdt3)
gd_diagram = GenomeDiagram.Diagram("Tomato Curly Stunt Virus, complete genome",
track_size=0.7)
i = 1
for track in track_list:
