def alignment_bioent(self, locus_identifier=None, strain_ids=None, are_ids=False):
if locus_identifier is not None:
if are_ids:
bioent_id = locus_identifier
else:
bioent_id = get_obj_id(str(locus_identifier).upper(), class_type='BIOENTITY', subclass_type='LOCUS')
alignment = get_bioentity_details(bioent_id, 'ALIGNMENT')
if alignment is None:
return alignment
if strain_ids is None:
return alignment
else:
alignment = json.loads(alignment)
try:
strain_ids = set([int(strain_id) for strain_id in strain_ids])
strain_ids.add(1)
except Exception:
return None
alignment['aligned_dna_sequences'] = [x for x in alignment['aligned_dna_sequences'] if x['strain_id'] in strain_ids]
alignment['aligned_protein_sequences'] = [x for x in alignment['aligned_protein_sequences'] if x['strain_id'] in strain_ids]
from src.sgd.backend import calculate_variant_data
alignment['variant_data_dna'] = calculate_variant_data('DNA', alignment['aligned_dna_sequences'], alignment['introns'])
alignment['variant_data_protein'] = calculate_variant_data('Protein', alignment['aligned_protein_sequences'], alignment['introns'])
return json.dumps(alignment)
return None
def alignment_bioent(self, locus_identifier=None, strain_ids=None, are_ids=False):
import view_sequence
from src.sgd.backend import calculate_variant_data
if are_ids:
locus_id = locus_identifier
else:
locus_id = None if locus_identifier is None else get_obj_id(locus_identifier, class_type='BIOENTITY', subclass_type='LOCUS')
alignment = json.dumps(view_sequence.make_alignment(locus_id=locus_id))
if strain_ids is None:
return alignment
else:
try:
strain_ids = [int(strain_id) for strain_id in strain_ids]
strain_ids.append(1)
except Exception:
return None
alignment = json.loads(alignment)
alignment['aligned_dna_sequences'] = [x for x in alignment['aligned_dna_sequences'] if x['strain_id'] in strain_ids]
alignment['aligned_protein_sequences'] = [x for x in alignment['aligned_protein_sequences'] if x['strain_id'] in strain_ids]
alignment['variant_data_dna'] = calculate_variant_data('DNA', alignment['aligned_dna_sequences'], alignment['introns'])
alignment['variant_data_protein'] = calculate_variant_data('Protein', alignment['aligned_protein_sequences'], alignment['introns'])
return json.dumps(alignment)
def make_alignment(locus_id=None):
if locus_id is None:
return {'Error': 'No locus_id given.'}
evidences = get_alignment_evidence(locus_id=locus_id)
if evidences is None:
return {'Error': 'Too much data to display.'}
try:
locus = DBSession.query(Locus).filter_by(id=locus_id).first()
obj_json = locus.to_min_json()
dnasequenceevidence = DBSession.query(DNAsequenceevidence).filter_by(strain_id=1).filter_by(dna_type='GENOMIC').filter_by(locus_id=locus_id).first()
if dnasequenceevidence is not None:
obj_json['coordinates'] = {
'start': dnasequenceevidence.start,
'end': dnasequenceevidence.end,
}
obj_json['contig'] = dnasequenceevidence.contig.to_min_json()
obj_json['strand'] = dnasequenceevidence.strand
obj_json['introns'] = []
obj_json['dna_length'] = len(dnasequenceevidence.residues)
proteinsequenceevidence = DBSession.query(Proteinsequenceevidence).filter_by(strain_id=1).filter_by(locus_id=locus_id).first()
if proteinsequenceevidence is not None:
obj_json['protein_length'] = len(proteinsequenceevidence.residues)
#Alignment data
alignment_evidences = get_alignment_evidence(locus_id=locus_id)
if evidences is None:
return {'Error': 'Too much data to display.'}
ordered_strains = ['S288C', 'X2180-1A', 'SEY6210', 'W303', 'JK9-3d', 'FL100', 'CEN.PK', 'D273-10B', 'Sigma1278b', 'RM11-1a', 'SK1', 'Y55']
alignment_evidences.sort(key=lambda x: float('infinity') if x.strain.display_name not in ordered_strains else ordered_strains.index(x.strain.display_name))
reference_aligment = [x for x in alignment_evidences if x.sequence_type == 'Genomic DNA' and x.strain_id == 1][0]
if dnasequenceevidence is not None:
for tag in dnasequenceevidence.tags:
if tag.class_type == 'INTRON':
coords = switch_to_alignment_coord(reference_aligment.residues_with_gaps, [tag.relative_start, tag.relative_end])
obj_json['introns'].append({'start': coords[0], 'end': coords[1]})
obj_json['aligned_dna_sequences'] = [{'strain_id': x.strain_id,
'strain_display_name': x.strain.display_name,
'strain_link': x.strain.link,
'sequence': x.residues_with_gaps} for x in alignment_evidences if x.sequence_type == 'Genomic DNA']
obj_json['aligned_protein_sequences'] = [{'strain_id': x.strain_id,
'strain_display_name': x.strain.display_name,
'strain_link': x.strain.link,
'sequence': x.residues_with_gaps} for x in alignment_evidences if x.sequence_type == 'Protein']
obj_json['variant_data_dna'] = calculate_variant_data('DNA', obj_json['aligned_dna_sequences'], obj_json['introns'])
obj_json['variant_data_protein'] = calculate_variant_data('Protein', obj_json['aligned_protein_sequences'], obj_json['introns'])
except:
print locus_id
return obj_json