np.random.seed(123) # for reproducibility
# In[5]:
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras.datasets import mnist
#############################################
# In[6]:
# 1. Load data into train and test sets
X, y = load_data("../data/promoters.data.txt") # sequences, labels
X = get_rep_mats(X) # convert to array of representation matrices
############
# In[ ]:
for i in X:
for idx, j in enumerate(i):
i[idx] = j[0]
############
# In[ ]:
y = conv_labels(y, "promoter") # convert to integer labels
X = np.asarray(X) # work with np arrays
y = np.asarray(y)
X_train = X[0:90]
seq = seq.upper() # b/c rep matrix built on uppercase
seq = seq.replace("\t","") # present in promoter
seq = seq.replace("N","A") # undetermined nucleotides in splice
seq = seq.replace("D","G")
seq = seq.replace("S","C")
seq = seq.replace("R","G")
#####
labels.append(label)
seqs.append(seq)
f.close()
return seqs, labels
# In[11]:
if __name__ == "__main__":
# reading in splice junction input data and converting to required format
seqs, labels = load_data("../data/splice.data.txt")
lbls_mod = conv_labels(labels)
seqs_mod = get_rep_mats(seqs)
print (len(seqs_mod))
print (len(lbls_mod))
# In[ ]: