def main():
# generate some random data with 36 features
data1 = np.random.normal(loc=-.25, scale=0.5, size=(500, 36))
data2 = np.random.normal(loc=.25, scale=0.5, size=(500, 36))
data = np.vstack((data1, data2))
som = SOM(10, 10) # initialize the SOM
som.fit(data, 10000, save_e=True, interval=100
) # fit the SOM for 10000 epochs, save the error every 100 steps
som.plot_error_history(
filename='images/som_error.png') # plot the training error history
targets = np.array(500 * [0] +
500 * [1]) # create some dummy target values
# now visualize the learned representation with the class labels
som.plot_point_map(data,
targets, ['Class 0', 'Class 1'],
filename='images/som.png')
som.plot_class_density(data,
targets,
t=0,
name='Class 0',
filename='images/class_0.png')
som.plot_distance_map(filename='images/distance_map.png'
) # plot the distance map after training
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 __name__ == "__main__":
# generate some random data with 36 features
data1 = np.random.normal(loc=-.25, scale=0.5, size=(500, 36))
data2 = np.random.normal(loc=.25, scale=0.5, size=(500, 36))
data = np.vstack((data1, data2))
som = SOM(10, 10) # initialize the SOM
som.fit(data, 1000, save_e=True, interval=100
) # fit the SOM for 10000 epochs, save the error every 100 steps
som.plot_error_history(
filename='E:\_Python\SelfOrganizingMap\images\som_error.png'
) # plot the training error history
targets = np.array(500 * [0] +
500 * [1]) # create some dummy target values
# now visualize the learned representation with the class labels
som.plot_point_map(
data,
targets, ['Class 0', 'Class 1'],
filename=r'E:\_Python\SelfOrganizingMap\images\som.t.png')
som.plot_class_density(
data,
targets,
t=0,
name='Class 0',
filename=r'E:\_Python\SelfOrganizingMap\images\class_0.t.png')
som.plot_distance_map(
filename='E:\_Python\SelfOrganizingMap\images\distance_map.t.png'
) # plot the distance map after training
import numpy as np from som import SOM # generate some random data with 36 features data1 = np.random.normal(loc=-.25, scale=0.5, size=(500, 36)) data2 = np.random.normal(loc=.25, scale=0.5, size=(500, 36)) data = np.vstack((data1, data2)) som = SOM(10, 10) # initialize the SOM som.fit(data, 10000, save_e=True, interval=100) # fit the SOM for 10000 epochs, save the error every 100 steps som.plot_error_history(filename='../images/som_error.png') # plot the training error history targets = np.array(500 * [0] + 500 * [1]) # create some dummy target values # now visualize the learned representation with the class labels som.plot_point_map(data, targets, ['Class 0', 'Class 1'], filename='../images/som.png') som.plot_class_density(data, targets, t=0, name='Class 0', filename='../images/class_0.png') som.plot_distance_map(filename='../images/distance_map.png') # plot the distance map after training
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)
