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)
def run(data, musics):
som = SOM(30, 30) # initialize the SOM
som.fit(data, 20000) # fit the SOM for 2000 epochs
#targets = len(data) * [0] # create some dummy target values
# vizualizando as paradas, ver se pego o que eu precido
# som.plot_point_map(data, targets, ['class 1', 'class 2'], filename='./results/som.png')
# som.plot_class_density(data, targets, 0, filename='./results/class_0.png', names=['a', 'b', 'c'], mode)
# som.plot_density_map(data, filename='som1.png')
#preparando para clusterizar, denovo
winners = som.winner_map(data)
#plt.imshow(winners, interpolation='nearest', extent=(0.5,10.5,0.5,10.5))
#plt.colorbar()
#plt.show()
points = []
for i in range(0, len(winners)):
for j in range(0, len(winners[0])):
points.append([i, j, winners[i][j]])
# create dendrogram para imprimir
#dendrogram = sch.dendrogram(sch.linkage(points, method='ward'))
# create clusters
hc = AgglomerativeClustering(n_clusters=6,
affinity='euclidean',
linkage='ward')
# save clusters for chart
y_hc = hc.fit_predict(points)
for j in range(0, len(y_hc)):
point = points[j]
winners[point[0], point[1]] = y_hc[j]
#vizualizando a qualidade da clusterizacao
#plt.matshow(winners)
#plt.show()
for music in musics:
winner = som.winner(music.toObject()['valor'])
music.setGroupKon(winners[winner[0]][winner[1]])
def main(in_file, out_file, x, y, epochs, ref=None, test=False, verbose=0):
if test:
df = pd.DataFrame(in_file, columns=range(in_file.shape[1]))
else:
df = pd.read_table(in_file, sep='\t', low_memory=True, index_col=0)
s = df.shape[0]
df.dropna(axis=0, how='any', inplace=True)
sn = df.shape[0]
if s != sn:
logger.warning('%d rows dropped due to missing values' % (s - sn))
s = df.shape[1]
df = df.select_dtypes(include=[np.number])
sn = df.shape[1]
if s != sn:
logger.warning('%d columns dropped due to non-numeric data type' % (s - sn))
basedir = os.path.dirname(os.path.abspath(__file__))
som = SOM(x, y)
if ref == 'IRCI':
som = som.load('/SOM.pkl')
embedding = som.winner_neurons(df.values)
else:
som.fit(df.values, epochs, verbose=verbose)
embedding = som.winner_neurons(df.values)
if ref == 'Create':
som.save(basedir + '/SOM.pkl')
emb_df = pd.DataFrame({'ID': df.index})
emb_df['X'] = embedding[:, 1]
emb_df['Y'] = embedding[:, 0]
if test:
return emb_df
else:
emb_df.to_csv(out_file, index=False, sep='\t')
from data import gen_kura_data
from som import SOM
import params
from visualizer import visualize_history
if __name__ == '__main__':
X = gen_kura_data(params)
som = SOM(resolution=params.resolution,
latent_dim=params.latent_dim,
sigma_max=params.sigma_max,
sigma_min=params.sigma_min,
tau=params.tau,
seed=params.seed)
history = som.fit(X, num_epoch=params.num_epoch)
visualize_history(X, history, params)
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, 2000) # fit the SOM for 2000 epochs
targets = 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 1', 'class 2'], filename='som.png')
som.plot_class_density(data,
targets,
1, ['class 1', 'class 2'],
filename='class_0.png')
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 print(targets.shape) print(data.shape) # # 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
for col in range(1, num_cols):
col_values.append(input_sheet.col_values(col)[1:])
x = np.array(col_values, dtype='|S4')
y = x.astype(np.float)
maxs = [max(y[col]) for col in range(0, num_cols - 1)]
mins = [min(y[col]) for col in range(0, num_cols - 1)]
data_points = []
for row in range(1, num_rows):
values = []
for col in range(1, num_cols):
values.append(
(float(input_sheet.cell(row, col).value) - mins[col - 1]) /
(maxs[col - 1] - mins[col - 1]))
d = DataPoint(values, int(output_sheet.cell(row, 0).value))
data_points.append(d)
print(num_rows - 1, " points with dimesion=", num_cols - 1, " are added")
return data_points
data_points = load_data("722.xlsx")
s = SOM(2, 8, 27)
s.load_input_data(data_points)
s.fit(2, 0.1)
v = LVQ(2, 6, 5)
v.load_data(data_points)
v.train(5, 0.01, 2)
s.predict(data_points)
v.predict(data_points)
# 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")
# 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=10, y=10)
som.fit(data=d.descriptor, epochs=10000)
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")
colormaps = ['Oranges', 'Purples', 'Greens', 'Reds']
