CNN和LSTM实现DNA结合蛋白二分类（python+keras实现）

CNN和LSTM实现DNA结合蛋白二分类（python+keras实现）

主要内容

* word to vector
* 结合蛋白序列修正
* word embedding
* CNN1D实现
* LSTM实现 from __future__ import print_function import numpy as np import h5py
from keras.models import model_from_json np.random.seed(1337) # for
reproducibility from keras.preprocessing import sequence from keras.models
import Sequential from keras.layers.core import Dense, Dropout, Activation from
keras.layers.embeddingsimport Embedding from keras.layers.recurrent import
LSTM, GRU, SimpleRNNfrom keras.layers.convolutional import Convolution1D,
MaxPooling1Dfrom keras.datasets import imdb import cPickle def trans(str1): a =
[] dic = {'A':1,'B':22,'U':23,'J':24,'Z':25,'O':26,'C':2,'D':3,'E':4,'F':5,'G':6
,'H':7,'I':8,'K':9,'L':10,'M':11,'N':12,'P':13,'Q':14,'R':15,'S':16,'T':17,'V':
18,'W':19,'Y':20,'X':21} for i in range(len(str1)): a.append(dic.get(str1[i]))
return a def createTrainData(str1): sequence_num = [] label_num = [] for line in
open(str1): proteinId, sequence, label = line.split(",") proteinId =
proteinId.strip(' \t\r\n'); sequence = sequence.strip(' \t\r\n');
sequence_num.append(trans(sequence)) label = label.strip(' \t\r\n');
label_num.append(int(label))return sequence_num,label_num a,b=createTrainData(
"positive_and_negative.csv") t = (a, b) cPickle.dump(t,open("data.pkl","wb"))
def createTrainTestData(str_path, nb_words=None, skip_top=0, maxlen=None,
test_split=0.25, seed=113, start_char=1, oov_char=2, index_from=3): X,labels =
cPickle.load(open(str_path,"rb")) np.random.seed(seed) np.random.shuffle(X)
np.random.seed(seed) np.random.shuffle(labels)if start_char is not None: X =
[[start_char] + [w + index_fromfor w in x] for x in X] elif index_from: X = [[w
+ index_fromfor w in x] for x in X] if maxlen: new_X = [] new_labels = [] for
x, yin zip(X, labels): if len(x) < maxlen: new_X.append(x) new_labels.append(y)
X = new_X labels = new_labelsif not X: raise Exception('After filtering for
sequences shorter than maxlen=' + str(maxlen) + ', no sequence was kept. '
'Increase maxlen.') if not nb_words: nb_words = max([max(x) for x in X]) if
oov_charis not None: X = [[oov_char if (w >= nb_words or w < skip_top) else w
for w in x] for x in X] else: nX = [] for x in X: nx = [] for w in x: if (w >=
nb_wordsor w < skip_top): nx.append(w) nX.append(nx) X = nX X_train =
np.array(X[:int(len(X) * (1 - test_split))]) y_train =
np.array(labels[:int(len(X) * (1 - test_split))]) X_test =
np.array(X[int(len(X) * (1 - test_split)):]) y_test =
np.array(labels[int(len(X) * (1 - test_split)):]) return (X_train, y_train),
(X_test, y_test)# Embedding max_features = 23 maxlen = 1000 embedding_size = 128
# Convolution #filter_length = 3 nb_filter = 64 pool_length = 2 # LSTM
lstm_output_size =70 # Training batch_size = 128 nb_epoch = 100 print('Loading
data...') (X_train, y_train), (X_test, y_test) = createTrainTestData("data.pkl"
,nb_words=max_features, test_split=0.2) print(len(X_train), 'train sequences')
print(len(X_test),'test sequences') print('Pad sequences (samples x time)')
X_train = sequence.pad_sequences(X_train, maxlen=maxlen) X_test =
sequence.pad_sequences(X_test, maxlen=maxlen) print('X_train shape:',
X_train.shape) print('X_test shape:', X_test.shape) print('Build model...')
model = Sequential() model.add(Embedding(max_features, embedding_size,
input_length=maxlen)) model.add(Dropout(0.5))
model.add(Convolution1D(nb_filter=nb_filter, filter_length=10, border_mode=
'valid', activation='relu', subsample_length=1))
model.add(MaxPooling1D(pool_length=pool_length))
model.add(Convolution1D(nb_filter=nb_filter, filter_length=5, border_mode=
'valid', activation='relu', subsample_length=1))
model.add(MaxPooling1D(pool_length=pool_length))
model.add(LSTM(lstm_output_size)) model.add(Dense(1)) model.add(Activation(
'relu')) model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[
'accuracy']) print('Train...') model.fit(X_train, y_train,
batch_size=batch_size, nb_epoch=nb_epoch, validation_data=(X_test, y_test))
#json_string = model.to_json() #open('my_model_rat.json',
'w').write(json_string) #model.save_weights('my_model_rat_weights.h5') score,
acc = model.evaluate(X_test, y_test, batch_size=batch_size) print('Test score:'
, score) print('Test accuracy:', acc) print(
'***********************************************************************')
github链接：代码实现
<https://github.com/chr2117216003/Keras_learninng/blob/master/Two_layers_CNNLSTM.py>

• « 上一篇：多迪前端面试题
• » 下一篇：题目摘录-编程语言(C++)（一）