def GetRevcKmer(
k,
samples_file,
):
rev_kmer = RevcKmer(k=k, normalize=True)
vec = rev_kmer.make_revckmer_vec(open(samples_file))
np.savetxt('DHSs_reckmer_' + str(k) + '.txt', vec)
def whole_revc_kmer_psednc(pos_file, neg_file, k):
"""Generate revc_kmer and psednc feature into a file combined positive and negative file."""
revc_kmer = RevcKmer(k=k, normalize=True, upto=True)
with open(pos_file) as fp:
revc_kmer_pos_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
with open(neg_file) as fp:
revc_kmer_neg_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
lamada = 6
w = 0.8
psednc = PseDNC(lamada, w)
with open(pos_file) as fp:
psednc_pos_vecs = np.array(psednc.make_psednc_vec(fp))
with open(neg_file) as fp:
psednc_neg_vecs = np.array(psednc.make_psednc_vec(fp))
pos_vecs = np.column_stack((revc_kmer_pos_vecs, psednc_pos_vecs[:, -lamada:]))
neg_vecs = np.column_stack((revc_kmer_neg_vecs, psednc_neg_vecs[:, -lamada:]))
vecs = pos_vecs.tolist() + neg_vecs.tolist()
labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
# Write file.
write_file = "data/whole_revc_kmer_psednc.txt"
write_libsvm(vecs, labels, write_file)
def whole_revc_kmer_psednc_choose_args(pos_file, neg_file, k):
"""Generate revc_kmer and psednc feature into a file combined positive and negative file."""
revc_kmer = RevcKmer(k=k, normalize=True, upto=True)
with open(pos_file) as fp:
revc_kmer_pos_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
with open(neg_file) as fp:
revc_kmer_neg_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
for lamada in range(1, 2):
w = 0.1
while w < 1:
psednc = PseDNC(lamada, w)
with open(pos_file) as fp:
psednc_pos_vecs = np.array(psednc.make_psednc_vec(fp))
with open(neg_file) as fp:
psednc_neg_vecs = np.array(psednc.make_psednc_vec(fp))
pos_vecs = np.column_stack((revc_kmer_pos_vecs, psednc_pos_vecs[:, -lamada:]))
neg_vecs = np.column_stack((revc_kmer_neg_vecs, psednc_neg_vecs[:, -lamada:]))
vecs = pos_vecs.tolist() + neg_vecs.tolist()
labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
# Write file.
lamada_w = str(lamada) + '_' + str(w)
write_file = "data/whole_revc_kmer_psednc_" + lamada_w + ".txt"
print(write_file)
write_libsvm(vecs, labels, write_file)
w += 0.1
def borderline_smote_revc_psednc(fold_path):
revc_kmer = RevcKmer(k=2, normalize=True, upto=True)
with open("data/hs.fasta") as f:
pos_revc_kmer_vecs = np.array(revc_kmer.make_revckmer_vec(f))
with open("data/non-hs.fasta") as f:
neg_revc_kmer_vecs = np.array(revc_kmer.make_revckmer_vec(f))
lamada = 6
w = 0.8
psednc = PseDNC(lamada, w)
with open("data/hs.fasta") as f:
pos_psednc_vecs = np.array(psednc.make_psednc_vec(f))
with open("data/non-hs.fasta") as f:
neg_psednc_vecs = np.array(psednc.make_psednc_vec(f))
pos_vecs = np.column_stack((pos_revc_kmer_vecs, pos_psednc_vecs[:, -lamada:]))
neg_vecs = np.column_stack((neg_revc_kmer_vecs, neg_psednc_vecs[:, -lamada:]))
vecs = np.row_stack((pos_vecs, neg_vecs))
vecs_labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
_1, synthetic, _2 = (smote.borderline_smote(vecs, vecs_labels, 1, N=300, k=5))
pos_vecs = pos_vecs.tolist() + synthetic.tolist()
vecs = pos_vecs + neg_vecs.tolist()
labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
lamada_n = "_".join([str(lamada), str(w)])
write_file = "/".join([fold_path, lamada_n])
print(write_file)
write_libsvm(vecs, labels, write_file)
def cv5_loop_borderline_smote_revc_kmer(fold_path, filename, k):
revc_kmer = RevcKmer(k=k, normalize=True, upto=True)
for i in range(5):
# Generate RevcKmer vecs.
with open(fold_path + "test_neg_" + str(i)) as fp:
test_neg_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
with open(fold_path + "test_pos_" + str(i)) as fp:
test_pos_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
with open(fold_path + "train_neg_" + str(i)) as fp:
train_neg_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
with open(fold_path + "train_pos_" + str(i)) as fp:
train_pos_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
# Generate borderline SMOTE synthetic vecs from train_vecs.
train_vecs = np.row_stack((train_pos_revc_kmer_vecs, train_neg_revc_kmer_vecs))
train_vecs_labels = [1] * len(train_pos_revc_kmer_vecs) + [-1] * len(train_neg_revc_kmer_vecs)
synthetic = smote.loop_borderline_smote(train_vecs, train_vecs_labels, 1, -1, N=200, k=5)
# Write test file.
write_file = fold_path + filename + "_test_" + str(i) + ".txt"
test_vecs = test_pos_revc_kmer_vecs + test_neg_revc_kmer_vecs
test_vecs_labels = [1] * len(test_pos_revc_kmer_vecs) + [-1] * len(test_neg_revc_kmer_vecs)
write_libsvm(test_vecs, test_vecs_labels, write_file)
# Write train file.
write_file = fold_path + filename + "_train_" + str(i) + ".txt"
train_pos_revc_kmer_vecs = train_pos_revc_kmer_vecs + synthetic
train_vecs = train_pos_revc_kmer_vecs + train_neg_revc_kmer_vecs
train_vecs_labels = [1] * len(train_pos_revc_kmer_vecs) + [-1] * len(train_neg_revc_kmer_vecs)
write_libsvm(train_vecs, train_vecs_labels, write_file)
def revc_kmer_tool(k, pos_file, neg_file, write_file):
revc_kmer = RevcKmer(k=k, upto=True, normalize=True)
with open(pos_file) as fp:
pos_vecs = revc_kmer.make_revckmer_vec(fp)
with open(neg_file) as fp:
neg_vecs = revc_kmer.make_revckmer_vec(fp)
vecs = pos_vecs + neg_vecs
labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
write_libsvm(vecs, labels, write_file)
def whole_revc_kmer(pos_file, neg_file, k):
"""Generate revc_kmer into a file combined positive and negative file."""
revc_kmer = RevcKmer(k=k, normalize=True, upto=True)
with open(pos_file) as fp:
pos_vecs = revc_kmer.make_revckmer_vec(fp)
with open(neg_file) as fp:
neg_vecs = revc_kmer.make_revckmer_vec(fp)
vecs = pos_vecs + neg_vecs
labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
# Write file.
write_file = "data/whole_revc_kmer.txt"
write_libsvm(vecs, labels, write_file)
def cv5_smote_revc_psednc(fold_path, filename, k):
# Generate pos and neg vecs and SMOTE synthetic vecs.
lamada = 6
w = 0.8
revc_kmer = RevcKmer(k=k, normalize=True, upto=True)
psednc = PseDNC(lamada, w)
for i in range(5):
# Generate RevcKmer_PseDNC vecs.
with open(fold_path + "test_neg_" + str(i)) as fp:
test_neg_revc_kmer_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
with open(fold_path + "test_neg_" + str(i)) as fp:
test_neg_psednc_vecs = np.array(psednc.make_psednc_vec(fp))
test_neg_revc_psednc_vecs = np.column_stack((test_neg_revc_kmer_vecs, test_neg_psednc_vecs[:, -lamada:]))
with open(fold_path + "test_pos_" + str(i)) as fp:
test_pos_revc_kmer_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
with open(fold_path + "test_pos_" + str(i)) as fp:
test_pos_psednc_vecs = np.array(psednc.make_psednc_vec(fp))
test_pos_revc_psednc_vecs = np.column_stack((test_pos_revc_kmer_vecs, test_pos_psednc_vecs[:, -lamada:]))
with open(fold_path + "train_neg_" + str(i)) as fp:
train_neg_revc_kmer_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
with open(fold_path + "train_neg_" + str(i)) as fp:
train_neg_psednc_vecs = np.array(psednc.make_psednc_vec(fp))
train_neg_revc_psednc_vecs = np.column_stack((train_neg_revc_kmer_vecs, train_neg_psednc_vecs[:, -lamada:]))
with open(fold_path + "train_pos_" + str(i)) as fp:
train_pos_revc_kmer_vecs = np.array(revc_kmer.make_revckmer_vec(fp))
with open(fold_path + "train_pos_" + str(i)) as fp:
train_pos_psednc_vecs = np.array(psednc.make_psednc_vec(fp))
train_pos_revc_psednc_vecs = np.column_stack((train_pos_revc_kmer_vecs, train_pos_psednc_vecs[:, -lamada:]))
# Generate synthetic vecs from pos_vecs.
synthetic1 = (smote.smote(train_pos_revc_psednc_vecs, N=100, k=5)).tolist()
synthetic2 = (smote.smote(train_pos_revc_psednc_vecs, N=50, k=5)).tolist()
synthetic = np.row_stack((synthetic1, synthetic2))
n_lamada = "_".join([str(lamada), str(w)])
# Write test file.
write_file = fold_path + filename + '_' + n_lamada + "_test_" + str(i) + ".txt"
test_vecs = test_pos_revc_psednc_vecs.tolist() + test_neg_revc_psednc_vecs.tolist()
test_vecs_labels = [1] * len(test_pos_revc_psednc_vecs) + [-1] * len(test_neg_revc_psednc_vecs)
write_libsvm(test_vecs, test_vecs_labels, write_file)
# Write train file.
write_file = fold_path + filename + '_' + n_lamada + "_train_" + str(i) + ".txt"
train_pos_vecs = train_pos_revc_psednc_vecs.tolist() + synthetic.tolist()
train_vecs = train_pos_vecs + train_neg_revc_psednc_vecs.tolist()
train_vecs_labels = [1] * len(train_pos_vecs) + [-1] * len(train_neg_revc_psednc_vecs)
write_libsvm(train_vecs, train_vecs_labels, write_file)
def borderline_smote_revc_kmer():
revc_kmer = RevcKmer(k=6, normalize=True, upto=True)
with open("data/hs.fasta") as f:
pos_vecs = np.array(revc_kmer.make_revckmer_vec(f))
with open("data/non-hs.fasta") as f:
neg_vecs = np.array(revc_kmer.make_revckmer_vec(f))
vecs = np.row_stack((pos_vecs, neg_vecs))
vecs_labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
_1, synthetic1, _2 = smote.borderline_smote(vecs, vecs_labels, 1, N=300, k=5)
pos_vecs = pos_vecs.tolist() + synthetic1.tolist()
vecs = pos_vecs + neg_vecs.tolist()
labels = [1] * len(pos_vecs) + [-1] * len(neg_vecs)
write_libsvm(vecs, labels, "borderline_smote_revc_kmer.txt")
def ReverseComplimentKmer(gene2seq, k):
X = dict()
succeed_cnt = 0
rev_kmer = RevcKmer(k, normalize=True, upto=True)
for gene, seq in gene2seq.items():
seq = [seq]
try:
pos_vec = rev_kmer.make_revckmer_vec(seq)
X[gene] = pos_vec
succeed_cnt += 1
if succeed_cnt % 100 == 0:
print(succeed_cnt)
except Exception as e:
continue
print('Reverse Compliment Kmer, succeed for %d gene' % (succeed_cnt))
with open('%d-revcKmer-features.json' % (k), 'w') as output_f:
output_f.write(json.dumps(X))
return X
def cv5_upto_revckmer_tool(k, test_neg_file, test_pos_file, train_neg_file, train_pos_file, test_write_file,
train_write_file):
kmer = RevcKmer(k=k, upto=True, normalize=True)
with open(test_neg_file) as fp:
test_neg_vecs = kmer.make_revckmer_vec(fp)
with open(test_pos_file) as fp:
test_pos_vecs = kmer.make_revckmer_vec(fp)
with open(train_pos_file) as fp:
train_pos_vecs = kmer.make_revckmer_vec(fp)
with open(train_neg_file) as fp:
train_neg_vecs = kmer.make_revckmer_vec(fp)
train_vecs = train_pos_vecs + train_neg_vecs
test_vecs = test_pos_vecs + test_neg_vecs
train_labels = [1] * len(train_pos_vecs) + [-1] * len(train_neg_vecs)
test_labels = [1] * len(test_pos_vecs) + [-1] * len(test_neg_vecs)
# Write file.
write_libsvm(train_vecs, train_labels, train_write_file)
write_libsvm(test_vecs, test_labels, test_write_file)
def convert(name):
print("Now converting " + name)
#COnvert from fastq to fasta
fastq2fasta()
#4mers representation
revckmer = RevcKmer(k=6)
#Open file to write to
f = open("vectored_data/" + name + ".txt", "w")
temp = revckmer.make_kmer_vec(open("vectored_data/temp.fasta"))
for val in temp:
string = ""
for i, num in enumerate(val):
string += str(num) + ","
#end
f.write(string[0:-1 - 1] + "\n")
#end
#Close file correctly
f.close()
def cv5_revc_kmer(fold_path, filename, k):
revc_kmer = RevcKmer(k=k, normalize=True, upto=True)
for i in range(5):
# Generate RevcKmer vecs.
with open(fold_path + "test_neg_" + str(i)) as fp:
test_neg_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
with open(fold_path + "test_pos_" + str(i)) as fp:
test_pos_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
with open(fold_path + "train_neg_" + str(i)) as fp:
train_neg_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
with open(fold_path + "train_pos_" + str(i)) as fp:
train_pos_revc_kmer_vecs = revc_kmer.make_revckmer_vec(fp)
# Write test file.
write_file = fold_path + filename + "_test_" + str(i) + ".txt"
test_vecs = test_pos_revc_kmer_vecs + test_neg_revc_kmer_vecs
test_vecs_labels = [1] * len(test_pos_revc_kmer_vecs) + [-1] * len(test_neg_revc_kmer_vecs)
write_libsvm(test_vecs, test_vecs_labels, write_file)
# Write train file.
write_file = fold_path + filename + "_train_" + str(i) + ".txt"
train_vecs = train_pos_revc_kmer_vecs + train_neg_revc_kmer_vecs
train_vecs_labels = [1] * len(train_pos_revc_kmer_vecs) + [-1] * len(train_neg_revc_kmer_vecs)
write_libsvm(train_vecs, train_vecs_labels, write_file)
def GetRevcKmer(k):
rev_kmer = RevcKmer(k=k)
pos_vec = rev_kmer.make_revckmer_vec(open(posi_samples_file))
neg_vec = rev_kmer.make_revckmer_vec(open(nega_samples_file))
X = array(pos_vec + neg_vec)
return X
from sklearn.cross_validation import StratifiedKFold
from sklearn.metrics import roc_curve, auc
from scipy import interp
import matplotlib.pyplot as plt
if __name__ == '__main__':
begin_time = time.time()
print(
'Example1 Start.(This process may use several minutes, please do not close the program.)'
)
# ##############################################################################
# Data IO and generation.
# Generate the feature vectors based on reverse compliment kmer.
rev_kmer = RevcKmer(k=6, normalize=True, upto=True)
pos_vec = rev_kmer.make_revckmer_vec(open('hs.fasta'))
neg_vec = rev_kmer.make_revckmer_vec(open('non-hs.fasta'))
print(len(pos_vec))
print(len(neg_vec))
# Merge positive and negative feature vectors and generate their corresponding labels.
vec = np.array(pos_vec + neg_vec)
vec_label = np.array([1] * len(pos_vec) + [0] * len(neg_vec))
# ##############################################################################
# Classification and accurate analysis.
# Using 10-fold cross-validation to evaluate the performance of the predictor.
clf = svm.LinearSVC()
from sklearn import cross_validation
from sklearn.cross_validation import StratifiedKFold
from sklearn.metrics import roc_curve, auc
from scipy import interp
import matplotlib.pyplot as plt
if __name__ == '__main__':
begin_time = time.time()
print('Example1 Start.(This process may use several minutes, please do not close the program.)')
# ##############################################################################
# Data IO and generation.
# Generate the feature vectors based on reverse compliment kmer.
rev_kmer = RevcKmer(k=6, normalize=True, upto=True)
pos_vec = rev_kmer.make_revckmer_vec(open('hs.fasta'))
neg_vec = rev_kmer.make_revckmer_vec(open('non-hs.fasta'))
print(len(pos_vec))
print(len(neg_vec))
# Merge positive and negative feature vectors and generate their corresponding labels.
vec = np.array(pos_vec + neg_vec)
vec_label = np.array([1] * len(pos_vec) + [0] * len(neg_vec))
# ##############################################################################
# Classification and accurate analysis.
# Using 10-fold cross-validation to evaluate the performance of the predictor.
clf = svm.LinearSVC()