def _get_seqs_data(raw_seqs):
raw_seqs = _fix_string_newlines(unicode(raw_seqs)) # This patch is required for some reason, because Django somehow corrupts uploaded files
LOGGER.info('Received a %d bytes long FASTA' % len(raw_seqs))
seqs_fasta = StringIO(_fix_fasta_if_needed(raw_seqs))
records = list(SeqIO.parse(seqs_fasta, 'fasta'))
LOGGER.info('About to process %d records' % len(records))
for record in records:
id = record.id
seq = str(record.seq)
LOGGER.info('Processing record %s: %s' % (id, seq))
cleavage_mask, cleavage_products = simple_cleavage_predictor.predict(seq, proba = True)
labeled_aa_chunks = split_to_chunks([_LabeledAminoAcid(aa, label) for aa, label in zip(seq, cleavage_mask)], _RESIDUES_TO_DISPAY_PER_ROW)
yield id, labeled_aa_chunks, cleavage_products
def _get_seqs_data(raw_seqs):
raw_seqs = _fix_string_newlines(
unicode(raw_seqs)
) # This patch is required for some reason, because Django somehow corrupts uploaded files
LOGGER.info('Received a %d bytes long FASTA' % len(raw_seqs))
seqs_fasta = StringIO(_fix_fasta_if_needed(raw_seqs))
records = list(SeqIO.parse(seqs_fasta, 'fasta'))
LOGGER.info('About to process %d records' % len(records))
for record in records:
id = record.id
seq = str(record.seq)
LOGGER.info('Processing record %s: %s' % (id, seq))
cleavage_mask, cleavage_products = simple_cleavage_predictor.predict(
seq, proba=True)
labeled_aa_chunks = split_to_chunks([
_LabeledAminoAcid(aa, label)
for aa, label in zip(seq, cleavage_mask)
], _RESIDUES_TO_DISPAY_PER_ROW)
yield id, labeled_aa_chunks, cleavage_products
def space_seq(seq, chunk_length=10):
return ' '.join(util.split_to_chunks(seq, chunk_length))
def space_seq(seq, chunk_length = 10):
return ' '.join(util.split_to_chunks(seq, chunk_length))