def construct_protein_records(proteins, main_data):
label = 'Constructing protein records: '
show_progress(label, 40, 0.0)
protein_records = []
# 1. process all main data
index = 1
for line in main_data:
# 1.1. construct peptide and peptide match from current analysis
current_peptide = Peptide(sequence=b2str(line['sequence']))
current_peptide_match = PeptideMatch(analysis_name=b2str(line['filename']), score=line['score'],
reverse_score=line['reverseScore'],
percent_of_scored_peak_intensity=line['percent_scored_peak_intensity'],
total_intensity=line['totalIntensity'],
precursor_averagine_chi_squared=line['precursorAveragineChiSquared'],
retention_time_min=line['retentionTimeMin'],
chromatographic_peak_width_in_seconds=line['chromatographicPeakWidthSec'])
# 1.2. get protein id for current analysis
current_protein_id = b2str(line['accession_number'])
# 1.3. find protein with such id
protein = find_protein_with_id(proteins,
current_protein_id) # TODO: if such protein not exists, extract Protein object and add to proteins
# 1.4. find record with such protein
protein_record = find_protein_record_with_protein(protein_records, protein)
# 1.5. if record with such protein exists, add current match to received peptides
if protein_record is not None:
# 1.5.1. if such peptide was already received, add peptide match
peptide_record = find_peptide_record_with_peptide(protein_record.received_peptide_records, current_peptide)
if peptide_record is not None:
peptide_record.matches.append(current_peptide_match)
# 1.5.2. if such peptide was not received yet, add peptide record with this one peptide match
else:
current_peptide_record = PeptideRecord(current_peptide, [current_peptide_match])
protein_record.received_peptide_records.append(current_peptide_record)
# 1.6. if protein record with such protein not exists, create new protein record
else:
current_peptide_record = PeptideRecord(current_peptide, [current_peptide_match])
protein_record = ProteinRecord(protein, received_peptide_records=[current_peptide_record])
protein_records.append(protein_record)
show_progress(label, 40, index / len(main_data))
index += 1
print()
# 2. sort peptide records by length (starting from longest)
label = 'Filling received peptide records: '
show_progress(label, 35, 0.0)
index = 1
for protein_record in protein_records:
protein_record.received_peptide_records = sorted(protein_record.received_peptide_records, key=lambda peptide_record: len(peptide_record.peptide.sequence), reverse=True)
show_progress(label, 35, index / len(protein_records))
index += 1
print()
return protein_records
def load_proteins_from_csv(file_name):
label = 'Loading proteins from \'{0}\': '.format(file_name)
show_progress(label, 40, 0.0)
data = genfromtxt(file_name, dtype=None, delimiter=';', names=True)
proteins = []
index = 1
for line in data:
proteins.append(Protein(id=b2str(line['id']), name=b2str(line['name']), sequence=b2str(line['sequence'])))
show_progress(label, 40, index / len(data))
index += 1
print()
return proteins
def construct_proteins(main_data):
proteins = []
label = 'Constructing proteins from main data: '
show_progress(label, 35, 0.0)
# 1. fill list with unique proteins
index = 1
for line in main_data:
# 1.1. construct protein from current line
current_protein = Protein(id=b2str(line['accession_number']), name=b2str(line['entry_name']))
# 1.2. add if not already exists in list
if current_protein not in proteins:
proteins.append(current_protein)
show_progress(label, 35, index / len(main_data))
index += 1
print()
return proteins
