from scripts.fix_sequence import fix_sequences
from scripts.fasta import batch_fasta_save, batch_to_fasta
def read_csv(file_path):
sequences_ = []
with open(file_path, 'r') as f:
raw = f.read().split('\n')
f.close()
raw.pop(-1)
for i in raw:
tmp = i.split(',')
if (tmp[2] == 'S'):
sequences_.append((tmp[0], tmp[1]))
return sequences_
if __name__ == '__main__':
sequences = read_csv('gram+.signalp.full.csv')
sequences = fix_sequences(sequences, 20)
sequences = batch_to_fasta(sequences)
print('At the end we have %s sequences that contain signal peptide' % str(len(sequences)))
batch_fasta_save('parse_gram+.signalp.fasta', sequences)
from scripts.fix_sequence import fix_sequences
from scripts.fasta import batch_fasta_save, batch_to_fasta
def read_csv(file_path):
sequences_ = []
negative_sequences_ = []
with open(file_path, 'r') as f:
raw = f.read().split('\n')
f.close()
raw.pop(-1)
for i in raw:
tmp = i.split(',')
if (tmp[2] == 'S'):
sequences_.append((tmp[0], tmp[1]))
else:
negative_sequences_.append((tmp[0], tmp[1]))
return sequences_, negative_sequences_
if __name__ == '__main__':
sequences, negative_sequences = read_csv('euk.signalp.full.csv')
sequences = fix_sequences(sequences, 96)
negative_sequences = fix_sequences(negative_sequences, 96)
sequences = batch_to_fasta(sequences)
negative_sequences = batch_to_fasta(negative_sequences)
print('At the end we have %s sequences that contain signal peptide' % str(len(sequences)))
print('At the end we have %s sequences that dont contain signal peptide' % str(len(negative_sequences)))
batch_fasta_save('parse_euk.signalp.fasta', sequences)
batch_fasta_save('parse_euk.-.signalp.fasta', negative_sequences)
Sequences = []
with open(file_path, 'r') as f:
Seqs = f.read().split('\n')
f.close()
Seqs.pop(-1)
for i in range(0, len(Seqs), 2):
Sequences.append((Seqs[i].split('>')[-1], Seqs[i + 1]))
return Sequences
def pick_Sequences(IDs, Sequences):
Sequences_ = []
for i in IDs:
for j in Sequences:
if (j[0] == i):
Sequences_.append(j)
return Sequences_
if __name__ == '__main__':
IDs = read_csv('gram-.spds17.csv')
Sequences = read_fasta('gram-.spds17.fasta')
print('At the begin we have %s sequences' % str(len(Sequences)))
Sequences = pick_Sequences(IDs, Sequences)
Sequences = fix_sequences(Sequences, 20)
print('At the end we have %s sequences that contain signal peptide' %
str(len(Sequences)))
Sequences = batch_to_fasta(Sequences)
print(Sequences)
batch_fasta_save('parse_gram-.-.spds17.fasta', Sequences)
for i in range(0, len(Seqs), 2):
Sequences.append((Seqs[i].split('>')[-1], Seqs[i + 1]))
return Sequences
def pick_Sequences(IDs, Sequences):
Sequences_ = []
for i in IDs:
for j in Sequences:
if (j[0] == i):
Sequences_.append(j)
return Sequences_
if __name__ == '__main__':
IDs, negative_IDs = read_csv('euk.spds17.csv')
Sequences = read_fasta('euk.spds17.fasta')
print('At the begin we have %s sequences' % str(len(Sequences)))
sequences = pick_Sequences(IDs, Sequences)
negative_sequences = pick_Sequences(negative_IDs, Sequences)
sequences = fix_sequences(sequences, 20)
negative_sequences = fix_sequences(negative_sequences, 20)
print('At the end we have %s sequences that contain signal peptide' %
str(len(sequences)))
print('At the end we have %s sequences that dont contain signal peptide' %
str(len(negative_sequences)))
sequences = batch_to_fasta(sequences)
negative_sequences = batch_to_fasta(negative_sequences)
batch_fasta_save('parse_euk.spds17.fasta', sequences)
batch_fasta_save('parse_euk.-.spds17.fasta', negative_sequences)
