def main(libsize=1000):
# load training sequences
data = load_AMPvsUniProt()
# describe sequences with PEPCATS descriptor
X = PeptideDescriptor(data.sequences, 'pepcats')
X.calculate_crosscorr(7)
# initialize Random Forest classifier
clf = RandomForestClassifier(n_estimators=500, oob_score=True, n_jobs=-1)
# fit the classifier on the PEPCATS data
clf.fit(X.descriptor, data.target)
# evaluate classifier performance as RF out of bag score
print("RandomForest OOB classifcation score: %.3f" % clf.oob_score_)
# generate a virtual peptide library of `size` sequences to screen
Lib = MixedLibrary(libsize)
Lib.generate_sequences()
print("Actual lirutal library size (without duplicates): %i" %
len(Lib.sequences))
# describe library with PEPCATS descriptor
X_lib = PeptideDescriptor(Lib.sequences, 'pepcats')
X_lib.calculate_crosscorr(7)
# predict class probabilities for sequences in Library
proba = clf.predict_proba(X_lib.descriptor)
# create ordered dictionary with sequences and prediction values and order it according to AMP predictions
d = dict(zip(Lib.sequences, proba[:, 1]))
d50 = OrderedDict(
sorted(d.items(), key=lambda t: t[1],
reverse=True)[:50]) # 50 top AMP predictions
# print the 50 top ranked predictions with their predicted probabilities
print("Sequence,Predicted_AMP_Probability")
for k in d50.keys():
print(k + "," + str(d50[k]))
def main():
# generate some virtual peptide sequences
libnum = 1000 # 1000 sequences per sublibrary
h = Helices(seqnum=libnum)
r = Random(seqnum=libnum)
n = AMPngrams(seqnum=libnum, n_min=4)
h.generate_sequences()
r.generate_sequences(proba='AMP')
n.generate_sequences()
# calculate molecular descirptors for the peptides
d = PeptideDescriptor(seqs=np.hstack(
(h.sequences, r.sequences, n.sequences)),
scalename='pepcats')
d.calculate_crosscorr(window=7)
# train a som on the descriptors and print / plot the training error
som = SOM(x=12, y=12)
som.fit(data=d.descriptor, epochs=100000, decay='hill')
print("Fit error: %.4f" % som.error)
som.plot_error_history(filename="som_error.png")
# load known antimicrobial peptides (AMPs) and transmembrane sequences
dataset = load_AMPvsTM()
d2 = PeptideDescriptor(dataset.sequences, 'pepcats')
d2.calculate_crosscorr(7)
targets = np.array(libnum * [0] + libnum * [1] + libnum * [2] + 206 * [3])
names = ['Helices', 'Random', 'nGrams', 'AMP']
# plot som maps with location of AMPs
som.plot_point_map(np.vstack((d.descriptor, d2.descriptor[206:])),
targets,
names,
filename="peptidesom.png")
som.plot_density_map(np.vstack((d.descriptor, d2.descriptor)),
filename="density.png")
som.plot_distance_map(colormap='Reds', filename="distances.png")
colormaps = ['Oranges', 'Purples', 'Greens', 'Reds']
for i, c in enumerate(set(targets)):
som.plot_class_density(np.vstack((d.descriptor, d2.descriptor)),
targets,
c,
names,
colormap=colormaps[i],
filename='class%i.png' % c)
# get neighboring peptides (AMPs / TMs) for a sequence of interest
my_d = PeptideDescriptor(seqs='GLFDIVKKVVGALLAG', scalename='pepcats')
my_d.calculate_crosscorr(window=7)
som.get_neighbors(datapoint=my_d.descriptor,
data=d2.descriptor,
labels=dataset.sequences,
d=0)
if y == '1':
class_in = 1
elif y == '-1':
class_in = 0
out.write(x + ', ' + str(class_in))
out.write('\n')
out.close()
# load the reformatted data
data = load_custom(os.getcwd() + '/formatted.csv')
# create descriptors for peptide sequences
descr_temp = PeptideDescriptor(data.sequences, scalename='pepArc')
descr_temp.calculate_crosscorr(window=4)
# develop best model and print out score with cross validation
best_RF = train_best_model('RF', descr_temp.descriptor, data.target)
score_cv(best_RF, descr_temp.descriptor, data.target, cv=10)
y_pred = []
# get predictions for values
for i in range(0, 392):
try:
pep_descr = PeptideDescriptor(samples_test[i], scalename='pepArc')
pep_descr.calculate_crosscorr(window=4)
proba = best_RF.predict_proba(pep_descr.descriptor)
y_pred.append(proba)
from modlamp.descriptors import PeptideDescriptor
from modlamp.datasets import load_AMPvsTM
from som import SOM
# generate some virtual peptide sequences
libnum = 1000 # 1000 sequences per sublibrary
h = Helices(seqnum=libnum)
r = Random(seqnum=libnum)
n = AMPngrams(seqnum=libnum, n_min=4)
h.generate_sequences()
r.generate_sequences(proba='AMP')
n.generate_sequences()
# calculate molecular descirptors for the peptides
d = PeptideDescriptor(seqs=np.hstack((h.sequences, r.sequences, n.sequences)), scalename='pepcats')
d.calculate_crosscorr(window=7)
# train a som on the descriptors and print / plot the training error
som = SOM(x=12, y=12)
som.fit(data=d.descriptor, epochs=100000, decay='hill')
print("Fit error: %.4f" % som.error)
som.plot_error_history(filename="som_error.png")
# load known antimicrobial peptides (AMPs) and transmembrane sequences
dataset = load_AMPvsTM()
d2 = PeptideDescriptor(dataset.sequences, 'pepcats')
d2.calculate_crosscorr(7)
targets = np.array(libnum*[0] + libnum*[1] + libnum*[2] + 206*[3])
names = ['Helices', 'Random', 'nGrams', 'AMP']
# plot som maps with location of AMPs
