def test_generate_traindata():
prots = ['env', 'gag', 'nef', 'pol',
'rev', 'tat', 'vif', 'vpr',
'vpu']
for prot in prots:
X, y = HIVAlignTools.generate_traindata(prot, train_type='pro')
yield ok_, y.shape[0] > 100, 'Had issue with %s' % prot
yield eq_, y.shape[0], X.shape[0], 'Had issue with %s' % prot
X, y = HIVAlignTools.generate_traindata('ltr', train_type='dna')
yield ok_, y.shape[0] > 100, 'Had issue with %s' % 'LTR'
yield eq_, y.shape[0], X.shape[0], 'Had issue with %s' % 'LTR'
def test_score_seq():
seqs = [('atgtag', 'atgtag', 30.0),
('atgtag', 'atg', 15),
('GTIJ', 'GTIJ', 15),
('GTIJAGATS', 'GTIJAGATS', 38)]
for s1, s2, score in seqs:
oscore = HIVAlignTools.score_seq(s1, s2)
yield eq_, score, oscore
def test_get_seq():
prots = ['env', 'gag', 'nef', 'pol',
'rev', 'tat', 'vif', 'vpr',
'vpu']
typs = ['PRO', 'DNA']
wanted = list(product(prots, typs))+[('genome', 'DNA'),
('ltr', 'DNA')]
for gene, typ in wanted:
names, seqs = HIVAlignTools.get_seq(gene, typ)
yield ok_, len(names) > 1, 'Had issue with %s, %s' % (gene, typ)
yield eq_, len(names), seqs.shape[0], 'Had issue with %s, %s' % (gene, typ)
def test_score_seqs():
seqs = [('atgtag', 'atgtag', 30.0),
('atgtag', 'atg', 15),
('GTIJ', 'GTIJ', 15),
('GTIJAGATS', 'GTIJAGATS', 38)]
former = HIVAlignTools.SeqTransformer()
known = former.transform(np.array([s for s, _, _ in seqs]))
guess = former.transform(np.array([s for _, s, _ in seqs]))
score = sum(v for _, _, v in seqs)
oscore = HIVAlignTools.score_seqs(known, guess)
eq_(score, oscore)
from Bio import SeqIO
import pandas as pd
import numpy as np
import sys
import os
sys.path.append('/home/will/PySeqUtils/')
from GeneralSeqTools import fasta_reader, fasta_writer
from HIVAlignTools import SeqTransformer, build_aligners
# <codecell>
import HIVAlignTools
# <codecell>
HIVAlignTools.build_aligners()
# <codecell>
import shlex
from subprocess import check_call
def score_seq(known, guess, gapopen=10, gapextend=1):
cmd = 'needle -asequence %(cb)s -bsequence %(seq)s -aformat score -gapopen %(go)f -gapextend %(ge)s -outfile %(out)s'
with NamedTemporaryFile() as conb_handle:
fasta_writer(conb_handle, [('SeqA', known)])
conb_handle.flush()
os.fsync(conb_handle.fileno())
with NamedTemporaryFile() as seq_handle:
fasta_writer(seq_handle, [('Seq1', guess)])