def predict(path, weightPath1, weightPath2, method):
predictionPath = "predictions.txt"
predictions = []
limit = 500
# load
weight1 = np.load(weightPath1)
weight2 = np.load(weightPath2)
method = method.lower()
if(method == 'fasta'):
proteins = fileUtils.readFasta(path)
for proteinId in range(len(proteins)):
sequences = sequenceUtils.openReadingFrames(proteins[proteinId])
for pos in range(len(sequences)):
# lav sekvens om til binær
inputLayer = sequenceUtils.createInputLayer(sequences[pos])
# forward
outputLayer = forward(inputLayer, weight1, weight2)[1]
outputLayer = logTransform.invTransform(outputLayer)
if(outputLayer <= limit):
# plus one, since both are zero indexed
predictions.append([proteinId + 1, pos + 1])
np.savetxt(predictionPath, np.array(predictions), fmt = '%d', delimiter = '\t')
print("There is {} predicted epitopes.".format(len(predictions)))
from forward import forward
# set seed to be able to reproduce results
np.random.seed(1234)
limit = 500
syfLimit = 21
names = np.array(["gag", "pol", "vif", "vpr", "tat", "rev", "vpu", "env", "nef"])
# mhc epitopes
mhcSequences, mhcAffinities = fileUtils.readHLA("data/mhcSequences.txt")
mhcEpitopes = mhcSequences[mhcAffinities <= limit]
# complete hiv
hivProteins = fileUtils.readFasta("data/hivCodingSequences.txt")
# SMMPMBEC
smm0 = fileUtils.readColumn("data/smmpmbec.csv", 0, True)
smm1 = fileUtils.readColumn("data/smmpmbec.csv", 1, True)
smm2 = fileUtils.readColumn("data/smmpmbec.csv", 2, True)
smm3 = fileUtils.readColumn("data/smmpmbec.csv", 3, True)
index = smm3 <= limit
smm = [smm2[index], np.repeat(0, sum(index)), smm1[index]]
# replace names wih numbers
for name in names:
# plus one to make it one indexed
smm[1][smm0[index] == name] = np.where(name == names)[0] +1
