continue
else:
param_count += 1
param_str = \
"%d: Assay = '%s', ngram %s, alphabet %s, mhc_class %s" % \
(param_count, assay, max_ngram, alphabet, mhc_class)
print param_str
d['assay'].append(assay)
d['alphabet'].append(alphabet)
d['ngram'].append(max_ngram)
d['mhc'].append(mhc_class)
X, Y, vectorizer = iedb.load_tcell_ngrams(
assay_group = assay,
human = True,
mhc_class = 1,
max_ngram = max_ngram,
reduced_alphabet = alphabet_dict,
min_count = None,
return_transformer = True)
print "Data shape", X.shape, "n_true", np.sum(Y)
ensemble = BalancedEnsembleClassifier()
accs = sklearn.cross_validation.cross_val_score(
ensemble, X, Y, cv = 3)
acc = np.mean(accs)
print "CV accuracy %0.4f (std %0.4f)" % \
(acc, np.std(accs))
d['cv_acc'].append(acc)
aucs = sklearn.cross_validation.cross_val_score(
ensemble, X, Y, cv = 5, scoring='roc_auc')
x_test_true = f.transform(cancer_peptides)
x_test_false = f.transform(self_peptides)
x_test = np.vstack([x_test_true, x_test_false])
y_test = np.ones(x_test.shape[0], dtype='bool')
y_test[len(x_test_true):] = 0
eval_dataset.eval_split(x,y,x_test,y_test)
ASSAY = 'cytotoxicity'
print
print "---"
print "aromatic unigram"
X, Y, f = iedb.load_tcell_ngrams(
noisy_labels = 'majority', assay_group = ASSAY, subsample_bigger_class = True,
human = True,
mhc_class = 1,
max_ngram = 1,
reduced_alphabet= reduced_alphabet.aromatic2,
return_transformer = True)
eval_dataset.eval_cv(X, Y)
print "Tumor-specific antigens"
run(X,Y,f)
print
print "---"
print "aromatic bigram"
X, Y, f = iedb.load_tcell_ngrams(
noisy_labels = 'majority', assay_group = ASSAY, subsample_bigger_class = True,
human = True,
mhc_class = 1,
import sklearn.linear_model
from epitopes import iedb
import eval_dataset
"""
Instead of dropping or keeping the noisy labels, started
trying to just the majority vote. This is saner and became the default
"""
print
print "---"
print "Human MHC1"
X_human_mhc1_filter, Y_human_mhc1_filter = iedb.load_tcell_ngrams(
noisy_labels = 'majority',
human = True,
mhc_class = 1)
eval_dataset.eval_cv(X_human_mhc1_filter, Y_human_mhc1_filter)
print
print "---"
print "No HLA-A2"
X_no_hla_a2, Y_no_hla_a2 = iedb.load_tcell_ngrams(
noisy_labels = 'majority',
human = True,
mhc_class = 1,
exclude_hla_type = 'HLA-A2$|A-\*02')
eval_dataset.eval_cv(X_no_hla_a2, Y_no_hla_a2)
from epitopes import iedb, amino_acid, features, reduced_alphabet
import eval_dataset
"""
Do results from a restrict HLA sample (only A2) generalize to all the other HLA types?
(repeated for AA bigrams)
"""
A2 = "A2$|A\*02"
print
print "---"
print "Human MHC1 (keep)"
X_human_mhc1, Y_human_mhc1 = iedb.load_tcell_ngrams(noisy_labels="keep", human=True, max_ngram=2, mhc_class=1)
eval_dataset.eval_cv(X_human_mhc1, Y_human_mhc1)
print
print "---"
print "Human MHC1 (drop)"
X_human_mhc1_filter, Y_human_mhc1_filter = iedb.load_tcell_ngrams(
noisy_labels="drop", human=True, max_ngram=2, mhc_class=1
)
eval_dataset.eval_cv(X_human_mhc1_filter, Y_human_mhc1_filter)
print
print "---"
print "Human MHC1 noisy = positive"
lr.fit(X,Y) print "LR coefs", lr.coef_ n_classifiers = 200 rf = sklearn.ensemble.RandomForestClassifier(n_classifiers) print "RF Accuracy", np.mean(sklearn.cross_validation.cross_val_score(rf, X, Y, cv = 10)) rf.fit(X,Y) print "RF Features", rf.feature_importances_ print "4 letter alphabet:" X4,Y4 = iedb.load_tcell_ngrams( assay_group = 'cytotoxicity', reduced_alphabet = reduced_alphabet.gbmr4, ) run_classifiers(X4, Y4) print "---" print print "12 letter alphabet:" X12,Y12 = iedb.load_tcell_ngrams( assay_group = 'cytotoxicity', reduced_alphabet = reduced_alphabet.sdm12, ) run_classifiers(X12, Y12) print "---" print
import sklearn.linear_model
from epitopes import iedb, amino_acid, features, reduced_alphabet
import eval_dataset
"""
Do results from a restrict HLA sample (only A2) generalize to all the other HLA types?
"""
A2 = 'A2$|A\*02'
print
print "---"
print "Human MHC1 (keep)"
X_human_mhc1, Y_human_mhc1 = iedb.load_tcell_ngrams(
noisy_labels = 'keep',
human = True,
mhc_class = 1)
eval_dataset.eval_cv(X_human_mhc1, Y_human_mhc1)
print
print "---"
print "Human MHC1 (drop)"
X_human_mhc1_filter, Y_human_mhc1_filter = iedb.load_tcell_ngrams(
noisy_labels = 'drop',
human = True,
mhc_class = 1)
eval_dataset.eval_cv(X_human_mhc1_filter, Y_human_mhc1_filter)
print
