def test_predictor(self):
"""
to see if it can correctly predict SNPs in feature-vector format
"""
self.individual_debug = True
self.init_test("test_predictor")
self.init_predictor_instance()
predictor = Predictor()
test_dataset = DataSet(os.path.join(combivep_settings.COMBIVEP_CENTRAL_TEST_DATASET_DIR, "test_dataset"))
params_file = os.path.join(self.data_dir, "params.npz")
predictor.import_parameters(params_file=params_file)
out = predictor.predict(test_dataset)
self.assertEqual(round(out[0][0], 4), 0.2729, msg="Predictor does not functional properly")
def predict_deleterious_probability(SNPs_file,
params_file=combivep_settings.USER_PARAMETERS_FILE,
file_type=combivep_settings.FILE_TYPE_VCF,
output_file=None,
config_file=combivep_settings.COMBIVEP_CONFIGURATION_FILE,
):
"""
CBV (CombiVEP format) is a parsed format intended to be used by CombiVEP.
CBV has 5 fields, CHROM, POS, REF, ALT, EFFECT (1=deleterious, 0=neutral). All are tab separated
Required arguments
- SNPs_file : list of SNPs to be predicted, can be either VCF or CBV (default is VCF)
"""
#pre-processing test dataset
print >> sys.stderr, 'pre-processing dataset, this may take a while (around 750 SNPs/mins). . . . '
dm = DataSetManager(config_file=config_file)
dm.load_data(SNPs_file, file_type=file_type)
dm.validate_data()
dm.calculate_scores()
#predict
predictor = Predictor()
predictor.import_parameters(params_file=params_file)
out = (np.array(predictor.predict(dm.dataset)).reshape(-1,))
#print output
if output_file is not None:
sys.stdout = open(output_file, 'w')
print >> sys.stdout, "#%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s" % ("CHROM", "POS", "REF", "ALT", "ACTUAL_DELETERIOUS_EFFECT", "PREDICTED_DELETERIOUS_PROBABILITY", "PHYLOP_SCORE", "SIFT_SCORE", "PP2_SCORE", "LRT_SCORT", "MT_SCORE", "GERP_SCORE")
for i in xrange(len(dm.dataset)):
print >> sys.stdout, "%s\t%s\t%s\t%s\t%s\t%6.4f\t%s\t%s\t%s\t%s\t%s\t%s" % (dm.dataset[i][combivep_settings.KEY_SNP_INFO_SECTION][combivep_settings.KEY_CHROM],
dm.dataset[i][combivep_settings.KEY_SNP_INFO_SECTION][combivep_settings.KEY_POS],
dm.dataset[i][combivep_settings.KEY_SNP_INFO_SECTION][combivep_settings.KEY_REF],
dm.dataset[i][combivep_settings.KEY_SNP_INFO_SECTION][combivep_settings.KEY_ALT],
dm.dataset[i][combivep_settings.KEY_PREDICTION_SECTION][combivep_settings.KEY_TARGETS],
out[i],
dm.dataset[i][combivep_settings.KEY_SCORES_SECTION][combivep_settings.KEY_PHYLOP_SCORE],
dm.dataset[i][combivep_settings.KEY_SCORES_SECTION][combivep_settings.KEY_SIFT_SCORE],
dm.dataset[i][combivep_settings.KEY_SCORES_SECTION][combivep_settings.KEY_PP2_SCORE],
dm.dataset[i][combivep_settings.KEY_SCORES_SECTION][combivep_settings.KEY_LRT_SCORE],
dm.dataset[i][combivep_settings.KEY_SCORES_SECTION][combivep_settings.KEY_MT_SCORE],
dm.dataset[i][combivep_settings.KEY_SCORES_SECTION][combivep_settings.KEY_GERP_SCORE],
)
sys.stdout = sys.__stdout__
def test_predictor(self):
"""
to see if it can correctly predict SNPs in feature-vector format
"""
self.individual_debug = True
self.init_test('test_predictor')
self.init_predictor_instance()
predictor = Predictor()
test_data = DataSet(os.path.join(cbv_const.CBV_SAMPLE_DATASET_DIR,
'test_dataset'))
params_file = os.path.join(self.data_dir,
'params.npz')
predictor.import_parameters(params_file=params_file)
out = predictor.predict(test_data)
self.assertEqual(round(out[0][0], 4),
0.2729,
msg='Predictor does not functional properly')
def fast_predict(SNPs_file,
params_file=cbv_const.USER_PARAMS_FILE,
file_type=cbv_const.FILE_TYPE_VCF,
output_file=None,
cfg_file=cbv_const.CBV_CFG_FILE,
):
"""
CBV (CombiVEP format) is a parsed format intended to be used by CombiVEP.
CBV has 5 fields, CHROM, POS, REF, ALT, EFFECT (1=deleterious, 0=neutr).
All are tab separated
Required arguments
- SNPs_file : list of SNPs to be predicted, can be either VCF or CBV
(default is VCF)
"""
#pre-processing test dataset
info('pre-processing dataset, this may take a while (around 750 SNPs/mins). . .')
dm = FastDataSetManager(cfg_file=cfg_file)
dm.load_data(SNPs_file, file_type=dev_const.FILE_TYPE_SCORES)
#predict
predictor = Predictor()
predictor.import_parameters(params_file=params_file)
out = (np.array(predictor.predict(dm.dataset)).reshape(-1,))
#print output
if output_file is not None:
sys.stdout = open(output_file, 'w')
tmp_rec = []
tmp_rec.append("CHROM")
tmp_rec.append("POS")
tmp_rec.append("REF")
tmp_rec.append("ALT")
tmp_rec.append("ACTUAL_DELETERIOUS_EFFECT")
tmp_rec.append("PREDICTED_DELETERIOUS_PROBABILITY")
tmp_rec.append("PHYLOP_SCORE")
tmp_rec.append("SIFT_SCORE")
tmp_rec.append("PP2_SCORE")
tmp_rec.append("LRT_SCORT")
tmp_rec.append("MT_SCORE")
tmp_rec.append("GERP_SCORE")
print "#" + "\t".join(tmp_rec)
for i in xrange(len(dm.dataset)):
del tmp_rec[:]
snp_data = dm.dataset[i][cbv_const.KW_SNP_DATA]
scores = dm.dataset[i][cbv_const.KW_SCORES]
tmp_rec.append(snp_data.chrom)
tmp_rec.append(snp_data.pos)
tmp_rec.append(snp_data.ref)
tmp_rec.append(snp_data.alt)
tmp_rec.append(snp_data.target)
tmp_rec.append("%6.4f" % out[i])
tmp_rec.append(scores.phylop_score)
tmp_rec.append(scores.sift_score)
tmp_rec.append(scores.pp2_score)
tmp_rec.append(scores.lrt_score)
tmp_rec.append(scores.mt_score)
tmp_rec.append(scores.gerp_score)
print "\t".join(tmp_rec)
sys.stdout = sys.__stdout__
