def run_BUMHMM_for_icSHAPE(control_files, treatment_files, sequence_file):
control_data = []
for filename in control_files:
control_data.append(GenomicData.load(filename))
treatment_data = []
for filename in treatment_files:
treatment_data.append(GenomicData.load(filename))
sequences = dict(read_fasta(sequence_file))
names, counts = np.unique(np.concatenate(
map(lambda x: x.names, control_data) +
map(lambda x: x.names, treatment_data)),
return_counts=True)
common_names = names[counts >= (len(control_data) + len(treatment_data))]
for name in common_names:
run_BUMHMM(
rt_stop_control=map(lambda x: x.feature(name, 'rt_stop'),
control_data),
coverage_control=map(lambda x: x.feature(name, 'base_density'),
control_data),
rt_stop_treatment=map(lambda x: x.feature(name, 'rt_stop'),
treatment_data),
coverage_treatment=map(lambda x: x.feature(name, 'base_density'),
treatment_data),
seq=sequences[name])
def create_dataset(args):
import numpy as np
import h5py
import pandas as pd
from tqdm import tqdm
from formats import read_fasta
logger.info('read peak file: ' + args.peak_file)
peaks = pd.read_table(args.peak_file,
names=['chrom', 'start', 'end', 'peak_id', 'label', 'strand'])
peaks['peak_id'] = peaks['peak_id'].astype('U')
peaks.index = peaks['peak_id']
logger.info('read sequence file: ' + args.sequence_file)
sequences = {name:seq for name, seq in read_fasta(args.sequence_file)}
if args.reactivity_file is not None:
logger.info('read reactivity file: ' + args.reactivity_file)
reactivities = {}
with h5py.File(args.reactivity_file, 'r') as f:
for peak_id in f.keys():
reactivities[peak_id.split(',')[0]] = f[peak_id][:]
peak_ids = []
for peak_id in sequences.keys():
if peak_id in reactivities:
coverage = np.sum(~np.isnan(reactivities[peak_id]))
else:
coverage = 0
if coverage >= args.min_coverage:
peak_ids.append(peak_id)
if coverage == 0:
reactivities[peak_id] = np.full(len(sequences[peak_id]), np.nan, dtype=np.float32)
else:
peak_ids = list(sorted(sequences.keys()))
def onehot_encode(x, alphabet='ATCG'):
alphabet = np.frombuffer(bytearray(alphabet, encoding='ascii'), dtype='S1')
x_shape = list(x.shape)
encoded = (x.reshape(x_shape + [1]) == alphabet.reshape([1]*len(x_shape) + [-1])).astype(np.int32)
return encoded
X_seq = np.concatenate([np.frombuffer(bytearray(sequences[peak_id], encoding='ascii'), dtype='S1')[np.newaxis, :] for peak_id in peak_ids], axis=0)
X_seq = onehot_encode(X_seq)
if args.reactivity_file is not None:
X_r = np.concatenate([reactivities[peak_id][np.newaxis, :, np.newaxis] for peak_id in peak_ids], axis=0)
# imputate reactivities with median values
X_r[np.isnan(X_r)] = np.nanmedian(X_r.flatten())
X = np.concatenate([X_seq, X_r], axis=2)
else:
X = X_seq
y = peaks['label'][peak_ids]
logger.info('create output file: ' + args.output_file)
with h5py.File(args.output_file, 'w') as fout:
fout.create_dataset('X', data=X)
fout.create_dataset('y', data=y)
def predict(args):
import numpy as np
import keras
import h5py
import models
from tqdm import tqdm
import six.moves.cPickle as pickle
from ioutils import prepare_output_file, make_dir
from formats import read_fasta
if args.n_threads >= 1:
logger.info('set number of threads to {} for TensorFlow'.format(
args.n_threads))
set_keras_num_threads(args.n_threads)
logger.info('load model: {}'.format(args.model_file))
model_format = detect_model_format(args.model_file)
logger.info('detected model format: ' + model_format)
if model_format == 'keras':
model = keras.models.load_model(args.model_file)
window_size = model.input.shape[1].value
elif model_format == 'sklearn':
with open(args.model_file, 'r') as f:
model = pickle.load(f)
# default offset
if args.offset is None:
offset = int(window_size) // 2
logger.info('load data: {}'.format(args.input_file))
if args.format == 'fasta':
names = []
logger.info('create output file: ' + args.output_file)
fout = h5py.File(args.output_file, 'w')
for name, sequence in tqdm(read_fasta(args.input_file),
unit='transcript'):
names.append(name)
sequence = np.frombuffer(bytearray(sequence, encoding='ascii'),
dtype='S1')
windows = split_windows_same(sequence,
window_size,
1,
offset=offset)
X = onehot_encode(windows)
y_pred = model.predict(X, batch_size=args.batch_size)
y_pred = np.squeeze(y_pred)
if args.swap_labels:
logger.info('swap labels')
y_pred = 1 - y_pred
fout.create_dataset(name, data=y_pred)
fout.close()
else:
raise ValueError('unknown input format: ' + args.format)
def __call__(self):
import numpy as np
from sklearn.model_selection import train_test_split
import h5py
from common import sequence_to_array
from scipy import signal
self.logger.info('read input file: ' + self.infile)
_, base_density, length, _ = read_background_rt(self.infile)
names = base_density.keys()
self.logger.info('read sequence file: ' + self.sequence_file)
sequences = dict(read_fasta(self.sequence_file))
if self.offset is None:
self.offset = (self.window_size + 1) / 2
X = []
y = []
if self.smooth:
self.logger.info(
'smooth the values using Gaussian window of width %.1f' %
self.smooth_width)
window = signal.gaussian(100, std=self.smooth_width)
for name in names:
seq = sequences[name]
values = base_density[name] / base_density[name].mean()
if self.smooth:
# smooth the signal
values = signal.convolve(values, window, mode='same')
for i in range(0, len(seq) - self.window_size, self.stride):
X.append(sequence_to_array(seq[i:(i + self.window_size)]))
y.append(values[i + self.offset])
if len(X) >= self.max_samples:
break
n_samples = len(X)
self.logger.info('created {} samples'.format(n_samples))
X = np.concatenate(X)
X = X.reshape((n_samples, self.window_size, 4))
y = np.asarray(y, dtype='float32')
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=self.test_ratio)
self.logger.info('save file: ' + self.outfile)
prepare_output_file(self.outfile)
f = h5py.File(self.outfile, 'w')
f.create_dataset('offset', data=int(self.offset))
f.create_dataset('window_size', data=int(self.window_size))
f.create_dataset('X_train', data=X_train)
f.create_dataset('y_train', data=y_train)
f.create_dataset('X_test', data=X_test)
f.create_dataset('y_test', data=y_test)
f.close()
def analyze_periodicity(args):
import h5py
import pandas as pd
import matplotlib
matplotlib.use('Agg')
import seaborn as sns
sns.set()
from genomic_data import GenomicData
logger.info('read input file: ' + args.input_file)
reactivities = {}
sequences = {}
if args.assay_type == 'shapemap':
with h5py.File(args.input_file, 'r') as f:
for tx_id in f['rep1'].keys():
reactivities[tx_id] = f['rep1/' + tx_id][:]
for tx_id in f['seq'].keys():
sequences[tx_id] = f['seq/' + tx_id][()]
elif args.assay_type == 'icshape':
icshape = GenomicData(args.input_file)
for name in icshape.names:
reactivities[name] = icshape.feature('icshape', name)
for name, seq in read_fasta(args.sequence_file):
if name in icshape.names:
sequences[name] = np.frombuffer(seq, dtype='S1')
seq_names = sequences.keys()
reactivities_concat = np.concatenate(
[reactivities[name] for name in seq_names])
sequences_concat = np.concatenate([sequences[name] for name in seq_names])
notnan_mask = ~np.isnan(reactivities_concat)
# plot overall distribution of SHAPE reactivity
fig, ax = plt.subplots(figsize=(8, 5))
ax.hist(reactivities_concat[notnan_mask], bins=50)
ax.set_xlabel('Reactivity')
ax.set_ylabel('Counts')
plt.savefig()
def __call__(self):
from formats import read_fasta
from tqdm import tqdm
import numpy as np
import pandas as pd
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
self.logger.info('read sequence file: ' + self.sequence_file)
sequences = dict(read_fasta(self.sequence_file))
self.logger.info('read input file: ' + self.infile)
data = GenomicData(self.infile)
if self.feature is None:
if len(data.features.keys()) == 1:
self.feature = data.features.keys()[0]
else:
raise ValueError('multiple features found in the input file and the feature is not specified')
# freqs[i]['A']: frequency of A in bin i
freqs = []
scores_all = data.features[self.feature]
scores_avail = scores_all[np.logical_not(np.isnan(scores_all))]
self.logger.info('use bin method: %s'%self.bin_method)
if self.bin_method == 'percentile':
qs = np.arange(1, self.bins + 1, dtype='float')*100.0/self.bins
percentiles = np.zeros(self.bins + 1, dtype='float')
percentiles[0] = scores_avail.min() - 1e-6
for i in range(1, self.bins):
percentiles[i] = np.percentile(scores_avail, qs[i - 1])
percentiles[self.bins] = scores_avail.max() + 1e-6
elif self.bin_method == 'value':
density, percentiles = np.histogram(scores_avail, bins=self.bins, density=True)
qs = np.cumsum(density)*100.0
percentiles[0] -= 1e-6
percentiles[-1] += 1e-6
else:
raise ValueError('unknown bin method: %s'%self.bin_method)
for i in range(self.bins):
d = {a:0 for a in self.alphabet}
freqs.append(d)
self.logger.info('count base frequencies with offset %d'%self.offset)
for name in tqdm(data.names):
scores_ts = data.feature(self.feature, name)
avail_ind = np.nonzero(np.logical_not(np.isnan(scores_ts)))[0]
seq_ts = np.frombuffer(sequences[name], dtype='S1')
avail_ind += self.offset
if self.offset > 0:
avail_ind = avail_ind[avail_ind < len(seq_ts)]
elif self.offset < 0:
avail_ind = avail_ind[avail_ind >= 0]
scores_avail_ts = scores_ts[avail_ind - self.offset]
seq_avail_ts = seq_ts[avail_ind]
for i in range(self.bins):
seq_bin = seq_avail_ts[np.logical_and(scores_avail_ts <= percentiles[i + 1],
scores_avail_ts > percentiles[i])]
for a in self.alphabet:
freqs[i][a] += np.count_nonzero(seq_bin == a)
# normalize base frequencies for each percentile
freq_total = []
for i in range(self.bins):
total = sum(freqs[i].values())
freq_total.append(total)
for a in self.alphabet:
if total == 0:
freqs[i][a] = 1.0/len(self.alphabet)
else:
freqs[i][a] = float(freqs[i][a])/total
table_file = self.prefix + '.txt'
self.logger.info('save results to file: ' + table_file)
prepare_output_file(table_file)
df = []
for i in range(self.bins):
for a in self.alphabet:
df.append((i, qs[i], percentiles[i], a, freq_total[i], freqs[i][a]))
df = pd.DataFrame.from_records(df,
columns=['bin', 'q', 'percentile', 'base', 'total_freq', 'fraction'])
df.to_csv(table_file, sep='\t', index=False)
# plot the distribution
self.logger.info('create plot')
plt.rcParams['font.family'] = 'Arial'
plt.rcParams['axes.labelsize'] = 'medium'
plt.rcParams['xtick.labelsize'] = 'x-small'
plt.rcParams['ytick.labelsize'] = 'x-small'
plt.rcParams['axes.titlesize'] = 'medium'
fig, ax = plt.subplots(figsize=(7, 5))
x = np.arange(self.bins)
xticklabels = ['%.2f'%a for a in percentiles[1:]]
for base in self.alphabet:
sub_df = df[df['base'] == base]
ax.plot(x, sub_df['fraction'], label=base)
ax.set_xticks(x)
ax.set_xticklabels(xticklabels)
ax.set_ylim(0, 1)
ax.set_xlabel('Values')
ax.set_ylabel('Base fraction')
ax.legend()
plt.tight_layout()
plot_file = self.prefix + '.pdf'
self.logger.info('save plot to file: ' + plot_file)
plt.savefig(plot_file)
def __call__(self):
import numpy as np
import pandas as pd
import h5py
from formats import read_rnafold, structure_to_pairs
self.logger.info('load model: {}'.format(self.model_file))
model = keras.models.load_model(self.model_file)
window_size = K.int_shape(model.input)[1]
self.logger.info('load input data (in %s format): %s'%(self.format, self.infile))
have_structure = False
if self.format == 'fasta':
# list of tuples: (name, seq)
input_data = list(read_fasta(self.infile))
elif self.format == 'ct_dir':
# read all .ct files from the directory
# list of tuples: (name, seq, pairs)
input_data = []
for filename in os.listdir(self.infile):
title, seq, pairs = read_ct(os.path.join(self.infile, filename))
title = os.path.splitext(filename)[0]
input_data.append((title, seq, pairs))
have_structure = True
elif self.format == 'ct':
title, seq, pairs = read_ct(self.infile)
title = os.path.splitext(os.path.basename(self.infile))[0]
input_data = [(title, seq, pairs)]
have_structure = True
elif self.format == 'rnafold':
input_data = []
for name, seq, structure, energy in read_rnafold(self.infile, parse_energy=False):
pairs = structure_to_pairs(structure)
input_data.append((name, seq, pairs))
have_structure = True
elif self.format == 'genomic_data':
from genomic_data import GenomicData
input_data = []
data = GenomicData(self.infile)
for name in data.names:
input_data.append((name,
data.feature('sequence', name).tostring(),
data.feature('reactivity', name)))
del data
have_structure = True
# combine all structures (base-pairs) into one array in the ct file
if have_structure:
structure = []
for i in range(len(input_data)):
structure.append(np.asarray(input_data[i][2], dtype='int32'))
structure = np.concatenate(structure)
else:
structure = None
X = []
names = []
# offset default to the center of the window
if self.offset is None:
self.offset = (window_size + 1)/2
offset = self.offset
# convert sequences to windows
windows = []
length = []
sequence = []
for item in input_data:
name = item[0]
seq = item[1]
windows += self.sequence_to_windows(seq, window_size, offset)
names.append(name)
length.append(len(seq))
sequence.append(seq)
# combine all sequences into one dataset
sequence = np.frombuffer(''.join(sequence), dtype='S1')
length = np.asarray(length, dtype='int64')
n_samples = len(windows)
windows = np.frombuffer(''.join(windows), dtype='S1').reshape((n_samples, window_size))
X = onehot_encode(windows, self.alphabet)
# set one-hot coding of padded sequence to [0.25, 0.25, 0.25, 0.25]
X[X.sum(axis=2) == 0] = 1.0/len(self.alphabet)
self.logger.info('run the model')
y_pred = model.predict(X, batch_size=self.batch_size)
y_pred = np.squeeze(y_pred)
if self.swap_labels:
self.logger.info('swap labels')
y_pred = 1 - y_pred
# start/end position of each transcript in the y_pred
end = np.cumsum(length)
start = end - length
if len(y_pred.shape) > 1:
# average the predictions
self.logger.info('average windows for dense prediction')
y_pred_dense = []
for i in range(len(input_data)):
y_pred_dense.append(self.predict_dense(y_pred[start[i]:end[i]], offset))
if self.dense_pred_file:
self.logger.info('save dense predictions: ' + self.dense_pred_file)
f = h5py.File(self.dense_pred_file, 'w')
for i in range(len(names)):
g = f.create_group(names[i])
g.create_dataset('predicted_values_dense', data=y_pred[start[i]:end[i]])
g.create_dataset('predicted_values_average', data=y_pred_dense[i])
# 0-based start/end position of each transcript in the array (y_pred, sequence, structure)
g.create_dataset('sequence', data=sequence[start[i]:end[i]])
if structure is not None:
g.create_dataset('structure', data=structure[start[i]:end[i]])
f.close()
y_pred = np.concatenate(y_pred_dense)
y_pred_labels = np.round(y_pred).astype('int32')
else:
y_pred_labels = np.round(y_pred).astype('int32')
if self.restraint_file:
header = ['name', 'position', 'pred', 'base']
table = pd.DataFrame()
table['name'] = np.repeat(np.asarray(names, dtype='S'), length)
# start position of each transcript relative to the y_pred
start = np.repeat(cum_length - length, length)
# position (1-based) relative to the transcript
position = np.arange(1, length.sum() + 1) - start
table['position'] = position
table['pred'] = y_pred_labels
table['base'] = sequence
table['true'] = structure
self.logger.info('write restraint file: ' + self.restraint_file)
prepare_output_file(self.restraint_file)
table.to_csv(self.restraint_file, sep='\t', index=False)
if self.metric_file:
self.logger.info('save metric file: ' + self.metric_file)
prepare_output_file(self.metric_file)
f = h5py.File(self.metric_file, 'w')
from sklearn.metrics import accuracy_score
f.create_dataset('y_pred', data=y_pred)
f.create_dataset('y_pred_labels', data=y_pred_labels)
if have_structure:
#print structure
y_true = (structure > 0).astype('int32')
f.create_dataset('y_true', data=y_true)
g = f.create_group('metrics')
for metric in self.metrics:
scorer = get_scorer(metric)
if get_scorer_type(metric) == 'continous':
score = scorer(y_true, y_pred)
else:
score = scorer(y_true, y_pred_labels)
self.logger.info('%s: %f'%(metric, score))
g.create_dataset(metric, data=score)
f.close()
if self.metric_by_sequence_file:
self.logger.info('calculate metrics by sequence')
records = []
for i in range(len(names)):
y_true_ = (structure[start[i]:end[i]] > 0).astype('int32')
y_pred_ = y_pred[start[i]:end[i]]
y_pred_labels_ = y_pred_labels[start[i]:end[i]]
scores = []
for metric in self.metrics:
scorer = get_scorer(metric)
if get_scorer_type(metric) == 'continuous':
try:
score = scorer(y_true_, y_pred_)
except ValueError:
score = np.nan
else:
score = scorer(y_true_, y_pred_labels_)
scores.append(score)
records.append([names[i], length[i]] + scores)
records = pd.DataFrame.from_records(records, columns=['name', 'length'] + self.metrics)
self.logger.info('save metric by sequence file: ' + self.metric_by_sequence_file)
prepare_output_file(self.metric_by_sequence_file)
records.to_csv(self.metric_by_sequence_file, sep='\t', index=False, na_rep='nan')
if self.pred_file:
self.logger.info('save predictions to file: ' + self.pred_file)
prepare_output_file(self.pred_file)
f = h5py.File(self.pred_file, 'w')
for i in range(len(names)):
y_true_ = (structure[start[i]:end[i]] > 0).astype('int32')
g = f.create_group(names[i])
g.create_dataset('sequence', data=sequence[start[i]:end[i]])
g.create_dataset('predicted_values', data=y_pred[start[i]:end[i]])
g.create_dataset('predicted_labels', data=y_pred[start[i]:end[i]])
g.create_dataset('true_labels', data=y_true_)
f.close()
def __call__(self):
import numpy as np
import h5py
control_data = []
for filename in self.control_file:
control_data.append(
icshape_raw_rt_to_genomic_data(filename, self.logger))
treatment_data = []
for filename in self.treatment_file:
treatment_data.append(
icshape_raw_rt_to_genomic_data(filename, self.logger))
combined_data = control_data + treatment_data
self.logger.info('read sequence file: ' + self.sequence_file)
sequences = dict(read_fasta(self.sequence_file))
names, counts = np.unique(np.concatenate(
map(lambda x: x.names, combined_data)),
return_counts=True)
common_names = names[counts >= len(combined_data)]
self.logger.info('create output file: ' + self.outfile)
prepare_output_file(self.outfile)
fout = h5py.File(self.outfile, 'w')
ncol = len(control_data) + len(treatment_data)
sample_name = np.asarray(
['C%d' % i for i in range(len(control_data))] +
['T%d' % i for i in range(len(treatment_data))],
dtype='S')
replicate = np.asarray(['control'] * len(control_data) +
['treatment'] * len(treatment_data),
dtype='S')
"""
for i, name in enumerate(common_names):
self.logger.info('create group: ' + str(name))
g = fout.create_group(name)
coverage = np.vstack(map(lambda x: x.feature('base_density', name)[1:], combined_data))
dropoff_count = np.vstack(map(lambda x: x.feature('rt_stop', name)[:-1], combined_data))
rpkm = np.mean(map(lambda x: x.feature('rpkm', name), combined_data))
g.create_dataset('coverage', data=coverage)
g.create_dataset('dropoff_count', data=dropoff_count)
g.create_dataset('sequence', data=np.asarray(sequences[name], dtype='S'))
g.create_dataset('sample_name', data=sample_name)
g.create_dataset('replicate', data=replicates)
g.create_dataset('rpkm', data=rpkm)
"""
coverage = [[]] * len(combined_data)
dropoff_count = [[]] * len(combined_data)
for i in range(len(combined_data)):
coverage[i] = [None] * len(common_names)
dropoff_count[i] = [None] * len(common_names)
for j in range(len(common_names)):
coverage[i][j] = combined_data[i].feature(
'base_density', common_names[j])[1:]
coverage[i][j][:20] = 0
dropoff_count[i][j] = combined_data[i].feature(
'rt_stop', common_names[j])[:-1]
dropoff_count[i][j][:20] = 0
if i == 0:
length = np.asarray(map(len, coverage[i]), dtype='int64')
end = np.cumsum(length)
start = end - length
coverage[i] = np.concatenate(coverage[i])
dropoff_count[i] = np.concatenate(dropoff_count[i])
coverage = np.vstack(coverage)
dropoff_count = np.vstack(dropoff_count)
sequence = np.asarray(''.join(
map(lambda name: sequences[name], common_names)),
dtype='S')
fout.create_dataset('name', data=common_names)
fout.create_dataset('start', data=start)
fout.create_dataset('end', data=end)
fout.create_dataset('coverage', data=coverage)
fout.create_dataset('dropoff_count', data=dropoff_count)
fout.create_dataset('sequence', data=sequence)
fout.create_dataset('replicate', data=replicate)
fout.create_dataset('sample_name', data=sample_name)
fout.close()
def create_dataset(args):
from tqdm import tqdm
from formats import read_fasta
from ioutils import prepare_output_file
c = args.input_file.split(':')
input_file = c[0]
dataset = c[1] if len(c) > 1 else '/'
logger.info('read input file: ' + input_file)
g_input = open_hdf5_group(args.input_file, 'r')
names = np.asarray(list(g_input.keys()))
reactivities = {name: g_input[name][:] for name in names}
logger.info('read sequence file: ' + args.sequence_file)
sequences = {
name: np.frombuffer(bytearray(seq, encoding='ascii'), dtype='S1')
for name, seq in read_fasta(args.sequence_file)
}
if args.offset is None:
offset = int(args.window_size) // 2
else:
offset = args.offset
if args.cv_split_file is not None:
cv_split = open_hdf5_group(args.cv_split_file, 'r')
train_index = cv_split['train'][:]
test_index = cv_split['test'][:]
names_train = names[train_index]
names_test = names[test_index]
X_train, y_train = create_single_point_dataset(sequences, reactivities,
names_train, offset,
args.window_size,
args.stride)
X_test, y_test = create_single_point_dataset(sequences, reactivities,
names_test, offset,
args.window_size,
args.stride)
if args.balanced:
logger.info('create balanced dataset')
X_train, y_train = balance_dataset(X_train, y_train)
logger.info('number of training samples: {}'.format(
y_train.shape[0]))
X_test, y_test = balance_dataset(X_test, y_test)
logger.info('number of test samples: {}'.format(y_test.shape[0]))
logger.info('create output file: ' + args.output_file)
prepare_output_file(args.output_file)
with h5py.File(args.output_file, 'w') as fout:
fout.create_dataset('names_train', data=names_train.astype('S'))
fout.create_dataset('X_train', data=X_train, compression=True)
fout.create_dataset('y_train', data=y_train, compression=True)
fout.create_dataset('names_test', data=names_test.astype('S'))
fout.create_dataset('X_test', data=X_test, compression=True)
fout.create_dataset('y_test', data=y_test, compression=True)
fout.create_dataset('offset', data=offset)
else:
X, y = create_single_point_dataset(sequences, reactivities, names,
offset, args.window_size,
args.stride)
logger.info('create output file: ' + args.output_file)
prepare_output_file(args.output_file)
with h5py.File(args.output_file, 'w') as fout:
fout.create_dataset('names', data=names.astype('S'))
fout.create_dataset('X', data=X, compression=True)
fout.create_dataset('y', data=y, compression=True)
def analyze_nucleotide_periodicity(args):
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
import seaborn as sns
sns.set()
from scipy.fftpack import fft
from formats import read_fasta
from ioutils import prepare_output_file
logger.info('read sequence file: ' + args.input_file)
sequences = {
name: np.frombuffer(seq, dtype='S1')
for name, seq in read_fasta(args.input_file)
}
aligned_length = args.aligned_length
alphabet = args.alphabet
def calc_nucleotide_freq(sequences,
direction,
alphabet='ATCG',
aligned_length=100):
alphabet = np.frombuffer(alphabet, dtype='S1')
m = np.full((len(sequences), aligned_length), 'N', dtype='S1')
for i, name in enumerate(sequences.keys()):
x = sequences[name]
L = min(x.shape[0], aligned_length)
if direction == '5p':
m[i, :L] = x[:L]
elif direction == '3p':
m[i, -L:] = x[-L:]
transcript_counts = np.sum(m != 'N', axis=0)
m_onehot = (m[:, :, np.newaxis] == alphabet[np.newaxis, np.newaxis, :])
m_counts = np.sum(m_onehot, axis=0).astype(np.float64)
m_freq = m_counts / np.sum(m_counts, axis=1)[:, np.newaxis]
return m_freq
logger.info('create output file: ' + args.output_file)
prepare_output_file(args.output_file)
with PdfPages(args.output_file) as pdf:
# 5'-end
nucleotide_freq_5p = calc_nucleotide_freq(
sequences, '5p', alphabet=alphabet, aligned_length=aligned_length)
fig, ax = plt.subplots(figsize=(18, 4))
for i, nucleotide in enumerate(alphabet):
ax.plot(np.arange(aligned_length),
nucleotide_freq_5p[:, i],
label=nucleotide)
ax.set_xlabel('Position in CDS from 5\'-end')
ax.set_ylabel('Nucleotide frequency')
ax.set_xlim(0, aligned_length)
ax.set_ylim(0, 1)
plt.legend()
pdf.savefig()
plt.close()
# 3'-end
nucleotide_freq_3p = calc_nucleotide_freq(
sequences, '3p', alphabet=alphabet, aligned_length=aligned_length)
fig, ax = plt.subplots(figsize=(18, 4))
for i, nucleotide in enumerate(alphabet):
ax.plot(np.arange(-aligned_length, 0),
nucleotide_freq_3p[:, i],
label=nucleotide)
ax.set_xlabel('Distance from CDS from 3\'-end')
ax.set_ylabel('Nucleotide frequency')
ax.set_xlim(-aligned_length, 0)
ax.set_ylim(0, 1)
plt.legend()
pdf.savefig()
plt.close()
# FFT
for i, nucleotide in enumerate(alphabet):
plot_fft(nucleotide_freq_5p[:, i],
'Nucleotide %s from 5\'-end' % nucleotide)
pdf.savefig()
plt.close()
for i, nucleotide in enumerate(alphabet):
plot_fft(nucleotide_freq_3p[:, i],
'Nucleotide %s from 3\'-end' % nucleotide)
pdf.savefig()
plt.close()
