def test_tcell_reduced_alphabet():
"""
IEBD T-cell:
Changing to a binary amino acid alphabet should reduce the number of
samples since some distinct 20-letter strings collide as 2-letter strings
"""
imm, non = iedb.load_tcell_classes(nrows = 100)
imm2, non2 = \
iedb.load_tcell_classes(
nrows = 100,
reduced_alphabet = reduced_alphabet.hp2)
assert len(imm) + len(non) > len(imm2) + len(non2)
import sklearn import sklearn.cross_validation import sklearn.ensemble import sklearn.linear_model from epitopes import iedb, amino_acid, features """ Compare IEDB classification AUC on: Logistic Regression vs. Random Forest 9mer vs. n-gram and: LR weights vs. RF feature importances """ imm, non = iedb.load_tcell_classes(peptide_length = 9) X, Y = features.make_kmer_dataset(imm, non) X_1gram, Y_1gram = features.make_ngram_dataset(imm, non, max_ngram = 1) X_2gram, Y_2gram = features.make_ngram_dataset(imm, non, max_ngram = 2) lr = sklearn.linear_model.LogisticRegression() print "Amino acid 9mers w/ Logistic Regression" print "LR Accuracy", np.mean(sklearn.cross_validation.cross_val_score(lr, X, Y, cv = 10)) lr.fit(X, Y) print "LR coefs", lr.coef_ print "Amino acid unigrams w/ Logistic Regression" print "LR Accuracy", np.mean(sklearn.cross_validation.cross_val_score(lr, X_1gram, Y_1gram, cv = 10)) lr.fit(X_1gram,Y_1gram) print "LR coefs", lr.coef_
import scipy.sparse
import numpy as np
import sklearn.metrics
import sklearn.metrics.pairwise
import sklearn.utils
import sklearn.utils.graph_shortest_path
from epitopes import iedb, amino_acid
from epitopes.amino_acid import peptide_to_indices
CUTOFF = 3
SPARSE = False
ASSAY = None #'cytotoxicity'
LENGTH = 9
imm, non = iedb.load_tcell_classes(peptide_length = LENGTH, assay_group = ASSAY)
imm = list(imm)
non = list(non)
peptides = imm + non
labels = [True] * len(imm) + [False] * len(non)
X = np.array([peptide_to_indices(p) for p in peptides])
Y = np.array(labels)
n = len(labels)
D = sklearn.metrics.pairwise.pairwise_distances(X, metric='hamming')
D = np.round(D*LENGTH).astype('int')
print "Distances"
n_features = 0
for i in xrange(max_ngram):
n_features += n_letters ** (i+1)
if n_features > 500:
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
imm_pos, imm_neg = iedb.load_tcell_classes(
assay_group = assay,
human = True,
min_count = None,
mhc_class = mhc_class)
mhc_pos, _ = iedb.load_mhc_classes(
human = True,
min_count = None,
mhc_class = mhc_class)
imm = list(mhc_pos.intersection(imm_pos))
non = list(mhc_pos.intersection(imm_neg))
vectorizer = PeptideVectorizer(
max_ngram = max_ngram,
reduced_alphabet = alphabet_dict)
X = vectorizer.fit_transform(imm + non)
'acc' : [],
}
best_model = None
best_vectorizer = None
best_params = None
param_count = 0
for assay in ('cytotoxicity', None, ):
for mhc_class in (1, None):
for min_count in (3, 5, None):
imm, non = iedb.load_tcell_classes(
assay_group = assay,
human = True,
mhc_class = mhc_class,
min_count = min_count)
for alphabet in \
('hp2', 'gbmr4', 'hp_vs_aromatic', 'sdm12', 'hsdm17'):
transformer = reduced_alphabet.make_alphabet_transformer(alphabet)
param_str = \
"%d: Assay = '%s', min_count %s, alphabet %s, mhc_class %s" % \
(param_count, assay, min_count, alphabet, mhc_class)
print param_str
d['assay'].append(assay)
d['alphabet'].append(alphabet)
d['mhc'].append(mhc_class)
import numpy as np import sklearn import sklearn.cross_validation import sklearn.ensemble import sklearn.linear_model from epitopes import iedb, amino_acid, features """ Better performance when filtering the assay group? cytotoxicity looks cleanest """ imm, non = iedb.load_tcell_classes(assay_group = 'cytotoxicity') X_1gram, Y_1gram = features.make_ngram_dataset(imm, non, max_ngram = 1) X_2gram, Y_2gram = features.make_ngram_dataset(imm, non, max_ngram = 2) lr = sklearn.linear_model.LogisticRegression() print "Amino acid unigrams w/ Logistic Regression" print "LR Accuracy", np.mean(sklearn.cross_validation.cross_val_score(lr, X_1gram, Y_1gram, cv = 10)) lr.fit(X_1gram,Y_1gram) #print "LR coefs", lr.coef_ print "Amino acid bigrams w/ Logistic Regression" print "LR Accuracy", np.mean(sklearn.cross_validation.cross_val_score(lr, X_2gram, Y_2gram, cv = 10)) lr.fit(X_2gram,Y_2gram) #print "LR coefs", lr.coef_ n_classifiers = 200