def auto_file(self):
pairs = []
p = pd.read_csv(self.pairs_file, sep='\n', header=None, nrows=30)
p = '\n'.join(p[0])
if 'path length' in p or 'MAXIMUM GAP' in p:
collinearity = base.read_colinearscan(self.pairs_file)
pairs = [[v[0], v[2]] for k in collinearity for v in k[1]]
elif 'MATCH_SIZE' in p or '## Alignment' in p:
collinearity = base.read_mcscanx(self.pairs_file)
pairs = [[v[0], v[2]] for k in collinearity for v in k[1]]
elif '# Alignment' in p:
collinearity = base.read_coliearity(self.pairs_file)
pairs = [[v[0], v[2]] for k in collinearity for v in k[1]]
elif '###' in p:
collinearity = base.read_jcvi(self.pairs_file)
pairs = [[v[0], v[2]] for k in collinearity for v in k[1]]
elif ',' in p:
collinearity = pd.read_csv(self.pairs_file, header=None)
pairs = collinearity.values.tolist()
else:
collinearity = pd.read_csv(self.pairs_file, header=None, sep='\t')
pairs = collinearity.values.tolist()
df = pd.DataFrame(pairs)
df = df.drop_duplicates()
df[0] = df[0].astype(str)
df[1] = df[1].astype(str)
df.index = df[0]+','+df[1]
return df
def auto_file(self, gff1, gff2):
f=open(self.collinearity)
p=' '.join(f.readlines()[0:30])
if 'path length' in p or 'MAXIMUM GAP' in p:
collinearity = base.read_colinearscan(self.collinearity)
elif 'MATCH_SIZE' in p or '## Alignment' in p:
col = base.read_mcscanx(self.collinearity)
collinearity = []
for block in col:
newblock = []
for k in block[1]:
if k[0] not in gff1.index or k[2] not in gff2.index:
continue
k[1], k[3] = gff1.loc[k[0], 'order'], gff2.loc[k[2], 'order']
newblock.append(k)
if len(newblock) == 0:
continue
collinearity.append([block[0], newblock, block[2]])
elif '# Alignment' in p:
collinearity = base.read_collinearity(self.collinearity)
elif '###' in p:
col = base.read_jcvi(self.collinearity)
collinearity = []
for block in col:
newblock = []
for k in block[1]:
if k[0] not in gff1.index or k[2] not in gff2.index:
continue
k[1], k[3] = gff1.loc[k[0], 'order'], gff2.loc[k[2], 'order']
newblock.append(k)
if len(newblock) == 0:
continue
collinearity.append([block[0], newblock, block[2]])
return collinearity
def run(self):
lens1 = base.newlens(self.lens1, self.position)
lens2 = base.newlens(self.lens2, self.position)
gff1 = base.newgff(self.gff1)
gff2 = base.newgff(self.gff2)
gff1 = gff1[gff1['chr'].isin(lens1.index)]
gff2 = gff2[gff2['chr'].isin(lens2.index)]
blast = base.newblast(self.blast, int(self.score), float(self.evalue),
gff1, gff2)
blast = self.blast_homo(blast, gff1, gff2, int(self.repnum))
blast.index = blast[0] + ',' + blast[1]
colinearity = base.read_colinearscan(self.colinearity)
ks = base.read_ks(self.ks, self.ks_col)
data = self.block_position(colinearity, blast, gff1, gff2, ks)
def rewriteblock(self, blast, file, fout):
num = 0
fout = open(fout, 'w')
collinearity = base.read_colinearscan(file)
for block in collinearity:
num += 1
if block[1][-1][0] + ',' + block[1][-1][2] not in blast.index:
block[1] = block[1][:-1]
fout.write('the ' + str(num) + 'th path length ' +
str(len(block[1])) + '\n')
for k in block[1]:
s = ' '.join([str(i) for i in k])
fout.write(s + '\n')
fout.write('>LOCALE p-value :' + block[2] + '\n\n')
def auto_file(self, gff1, gff2):
p = pd.read_csv(self.collinearity, sep='\n', header=None, nrows=30)
p = '\n'.join(p[0])
if 'path length' in p or 'MAXIMUM GAP' in p:
collinearity = base.read_colinearscan(self.collinearity)
elif 'MATCH_SIZE' in p or '## Alignment' in p:
col = base.read_mcscanx(self.collinearity)
collinearity = []
for block in col:
newblock = []
for k in block[1]:
if k[0] not in gff1.index or k[2] not in gff2.index:
continue
k[1], k[3] = gff1.loc[k[0], 'order'], gff2.loc[k[2],
'order']
newblock.append(k)
if len(newblock) == 0:
continue
collinearity.append([block[0], newblock, block[2]])
elif '# Alignment' in p:
collinearity = base.read_coliearity(self.collinearity)
return collinearity