def s2s_blast_batch(self, queries, subjects, subject_locs=None, evalue=0.001, command='blastn', **kwargs):
results = self._s2s_blast_batch(queries, subjects, subject_locs, evalue, command, **kwargs)
if not results: return None
with ProgressCounter('Parsing results...', len(results)) as prg:
for qi in xrange(len(results)):
for si in xrange(len(results[qi])):
results_name = results[qi][si]
if not results_name: continue
with roDict(results_name) as db:
results[qi][si] = db['result']
prg.count()
return results
def s2s_blast_batch(self, queries, subjects, subject_locs=None, evalue=0.001, command='blastn', **kwargs):
results = self._s2s_blast_batch(queries, subjects, subject_locs, evalue, command, **kwargs)
if not results: return None
with ProgressCounter('Parsing results...', len(results)) as prg:
for qi in xrange(len(results)):
for si in xrange(len(results[qi])):
results_name = results[qi][si]
if not results_name: continue
with roDict(results_name) as db:
results[qi][si] = db['result']
prg.count()
return results
def _find_features_by_hsps(qs, translations, blast_results):
results_name = blast_results[qs[0]][qs[1]]
if not results_name: return None
with roDict(results_name) as db:
hsps = BlastCLI.all_hsps(db['result'])
if not hsps:
print 'no blast results in %s: %s' % (results_name, hsps)
return None
hsp = min(hsps, key=lambda h: h.expect)
for f in translations[qs[1]].features:
if hsp.sbjct_start-1 in f and hsp.sbjct_end-1 in f:
aln_len = abs(hsp.sbjct_start-hsp.sbjct_end)+1
return f, aln_len, float(hsp.identities)/hsp.align_length, hsp.expect
return None
def _find_features_by_hsps(qs, translations, blast_results):
results_name = blast_results[qs[0]][qs[1]]
if not results_name: return None
with roDict(results_name) as db:
hsps = BlastCLI.all_hsps(db['result'])
if not hsps:
print 'no blast results in %s: %s' % (results_name, hsps)
return None
hsp = min(hsps, key=lambda h: h.expect)
for f in translations[qs[1]].features:
if hsp.sbjct_start-1 in f and hsp.sbjct_end-1 in f:
aln_len = abs(hsp.sbjct_start-hsp.sbjct_end)+1
return f, aln_len, float(hsp.identities)/hsp.align_length, hsp.expect
return None
def __init__(self, fpath):
self._d = roDict(fpath)
self.reaction_id = self._d['reaction_id']
self.templates = [[],[]]
self.templates[1] = self._d['fwd_templates']
self.templates[0] = self._d['rev_templates']
self.products = dict()
annealing_keys = []
for k in self._d.iterkeys():
if k.startswith('p'):
self.products[int(k.strip('p'))] = self._d[k]
elif k.startswith('a'):
annealing_keys.append(k)
self.annealings = tupleView(annealing_keys, self._d)
def __init__(self, fpath):
self._d = roDict(fpath)
self.reaction_id = self._d['reaction_id']
self.templates = [[], []]
self.templates[1] = self._d['fwd_templates']
self.templates[0] = self._d['rev_templates']
self.products = dict()
annealing_keys = []
for k in self._d.iterkeys():
if k.startswith('p'):
self.products[int(k.strip('p'))] = self._d[k]
elif k.startswith('a'):
annealing_keys.append(k)
self.annealings = tupleView(annealing_keys, self._d)
def g2g2shelf():
return lb.g2g_blastp(ref,
subj,
11,
features_of_interest=[{
'ugene_name': 'FC-full'
}, {
'ugene_name': 'COC-full'
}])
g2g_res = '/tmp/DP-PCR-N_KAEs'
if not os.path.isfile(g2g_res):
g2g_res = g2g2shelf()
print g2g_res
if g2g_res:
with roDict(g2g_res) as db:
results = db['result']
if results:
lb.g2g_to_csv('g2g_test.csv', ref, subj, results)
print 'Done.'
import numpy as np
import pandas
import matplotlib.pyplot as plt
from matplotlib import cm, rc
df = pandas.read_csv('g2g_test.csv')
df = df.dropna(subset=('Thermococcus_onnurineus_NA1_percent',
'Thermococcus_sp._ES1_percent'))
ratio = 15 / 18.0
rc('text', usetex=True)
'Thermococcus-DS1-preliminary.gb']
genomes = load_files(abort_event, [os.path.join(genomes_dir, f) for f in genome_names], 'gb')
ref = genomes[0]
subj = genomes[1:]
@shelf_result
def g2g2shelf():
return lb.g2g_blastp(ref, subj, 11, features_of_interest=[{'ugene_name': 'FC-full'}, {'ugene_name': 'COC-full'}])
g2g_res = '/tmp/DP-PCR-N_KAEs'
if not os.path.isfile(g2g_res):
g2g_res = g2g2shelf()
print g2g_res
if g2g_res:
with roDict(g2g_res) as db:
results = db['result']
if results:
lb.g2g_to_csv('g2g_test.csv', ref, subj, results)
print 'Done.'
import numpy as np
import pandas
import matplotlib.pyplot as plt
from matplotlib import cm, rc
df = pandas.read_csv('g2g_test.csv')
df = df.dropna(subset=('Thermococcus_onnurineus_NA1_percent', 'Thermococcus_sp._ES1_percent'))
ratio = 15/18.0
rc('text', usetex=True)
rc('font', size=14)
