def main_interpret(sequences=None,
arch_file=None,
weights_file=None,
pos_threshold=None,
peak_width=10,
prefix=None):
# encode fasta
print("loading sequence data...")
X = encode_fasta_sequences(sequences)
# load model
print("loading model...")
model = SequenceDNN.load(arch_file, weights_file)
# predict
print("getting predictions...")
predictions = model.predict(X)
# deeplift
print("getting deeplift scores...")
deeplift_scores = model.deeplift(X)
# get important sequences and write to file
print("extracting important sequences and writing to file...")
for task_index, task_scores in enumerate(deeplift_scores):
peak_positions = []
peak_sequences = []
for sequence_index, sequence_scores in enumerate(task_scores):
if predictions[sequence_index, task_index] > pos_threshold:
#print(sequence_scores.shape)
basewise_sequence_scores = sequence_scores.max(axis=(0,1))
peak_position = basewise_sequence_scores.argmax()
peak_positions.append(peak_position)
peak_sequences.append(X[sequence_index : sequence_index + 1,
:,
:,
peak_position - peak_width :
peak_position + peak_width])
else:
peak_positions.append(-1)
peak_sequences.append(np.zeros((1, 1, 4, 2 * peak_width)))
peak_sequences = np.concatenate(peak_sequences)
peak_sequence_strings = get_sequence_strings(peak_sequences)
# write important sequences to file
ofname = "%s.task_%i.important_sequences.txt" % (prefix, task_index)
with open(ofname, "w") as wf:
for i, peak_position in enumerate(peak_positions):
wf.write("> sequence_%i\n" % (i))
wf.write("%i: %s\n" %(peak_position, peak_sequence_strings[i]))
print("Done!")
def main_interpret(sequences=None,
arch_file=None,
weights_file=None,
pos_threshold=None,
peak_width=10,
prefix=None):
# encode fasta
print("loading sequence data...")
X = encode_fasta_sequences(sequences)
# load model
print("loading model...")
model = SequenceDNN.load(arch_file, weights_file)
# predict
print("getting predictions...")
predictions = model.predict(X)
# deeplift
print("getting deeplift scores...")
deeplift_scores = model.deeplift(X)
# get important sequences and write to file
print("extracting important sequences and writing to file...")
for task_index, task_scores in enumerate(deeplift_scores):
peak_positions = []
peak_sequences = []
for sequence_index, sequence_scores in enumerate(task_scores):
if predictions[sequence_index, task_index] > pos_threshold:
#print(sequence_scores.shape)
basewise_sequence_scores = sequence_scores.max(axis=(0, 1))
peak_position = basewise_sequence_scores.argmax()
peak_positions.append(peak_position)
peak_sequences.append(
X[sequence_index:sequence_index + 1, :, :,
peak_position - peak_width:peak_position + peak_width])
else:
peak_positions.append(-1)
peak_sequences.append(np.zeros((1, 1, 4, 2 * peak_width)))
peak_sequences = np.concatenate(peak_sequences)
peak_sequence_strings = get_sequence_strings(peak_sequences)
# write important sequences to file
ofname = "%s.task_%i.important_sequences.txt" % (prefix, task_index)
with open(ofname, "w") as wf:
for i, peak_position in enumerate(peak_positions):
wf.write("> sequence_%i\n" % (i))
wf.write("%i: %s\n" %
(peak_position, peak_sequence_strings[i]))
print("Done!")
from deeplift.dinuc_shuffle import dinuc_shuffle
from dragonn.utils import get_sequence_strings
import random
import numpy as np
import wget
url = "http://mitra.stanford.edu/kundaje/projects/dragonn/deep_lift_input_classification_spi1.npy"
wget.download(url)
deep_lift_input_classification_spi1 = np.load(
"deep_lift_input_classification_spi1.npy")
print(deep_lift_input_classification_spi1.shape)
deep_lift_input_classification_spi1_strings = get_sequence_strings(
deep_lift_input_classification_spi1)
for i in range(len(deep_lift_input_classification_spi1)):
random.seed(1234)
shuffled_strings = dinuc_shuffle(
deep_lift_input_classification_spi1_strings[i])
random.seed(1234)
shuffled_array = dinuc_shuffle(
deep_lift_input_classification_spi1[i].squeeze())
#decode the array
shuffled_array = ''.join(
get_sequence_strings(
np.expand_dims(np.expand_dims(shuffled_array, axis=1), axis=1)))
#make sure shuffling the string and numpy array gave same shuffle output
if (shuffled_strings != shuffled_array):
print("FAILED!")
print("TEST PASSED!")
from keras.models import load_model
from dragonn.tutorial_utils import deeplift
from dragonn.utils import get_sequence_strings, one_hot_encode
from deeplift import dinuc_shuffle
import numpy as np
import wget
url_data = "http://mitra.stanford.edu/kundaje/projects/dragonn/deep_lift_input_classification_spi1.npy"
url_model = "http://mitra.stanford.edu/kundaje/projects/dragonn/SPI1.classification.model.hdf5"
wget.download(url_data)
wget.download(url_model)
deep_lift_input_classification_spi1 = np.load(
"deep_lift_input_classification_spi1.npy")
deep_lift_input_classification_spi1_strings = get_sequence_strings(
deep_lift_input_classification_spi1)
#get scores with GC reference
deep_lift_scores_spi1_gc_ref = deeplift("SPI1.classification.model.hdf5",
deep_lift_input_classification_spi1,
reference="gc_ref")
print(deep_lift_scores_spi1_gc_ref.shape)
print(np.max(deep_lift_scores_spi1_gc_ref))
print(np.min(deep_lift_scores_spi1_gc_ref))
#Get scores with shuffled reference (starting with strings )
deep_lift_scores_spi1_shuffled_ref_strings = deeplift(
"SPI1.classification.model.hdf5",
deep_lift_input_classification_spi1_strings,
one_hot_func=one_hot_encode)
print(deep_lift_scores_spi1_shuffled_ref_strings.shape)