def execute_annotateMutations_lineage(self,experiment_id,sample_names_I=[],
ref_genome_I='data/U00096.2.gb',
ref_I = 'genbank',biologicalmaterial_id_I='MG1655'):
'''Annotate mutations for date_stage01_resequencing_lineage
based on position, reference genome, and reference genome biologicalmaterial_id'''
genomeannotation = genome_annotations(annotation_I=ref_genome_I,annotation_ref_I=ref_I);
print('Executing annotateMutations_lineage...')
data_O = [];
# query sample names from the experiment
if sample_names_I:
sample_names = sample_names_I;
else:
sample_names = [];
sample_names = self.get_sampleNames_experimentID_dataStage01ResequencingLineage(experiment_id);
for sn in sample_names:
print('annotating mutation for sample_name ' + sn);
# query rows that match the sample name
rows = [];
rows = self.get_row_experimentIDAndSampleName_dataStage01ResequencingLineage(experiment_id,sn);
for row in rows:
# annotate each mutation based on the position
annotation = {};
annotation = genomeannotation._find_genesFromMutationPosition(row['mutation_data']['position']);
row['mutation_genes'] = annotation['gene']
row['mutation_locations'] = annotation['location']
row['mutation_annotations'] = annotation['product']
# generate a link to ecogene for the genes
row['mutation_links'] = [];
for bnumber in annotation['locus_tag']:
if bnumber:
ecogenes = [];
ecogenes = self.get_ecogeneAccessionNumber_biologicalmaterialIDAndOrderedLocusName_biologicalMaterialGeneReferences(biologicalmaterial_id_I,bnumber);
if ecogenes:
ecogene = ecogenes[0];
ecogene_link = genomeannotation._generate_httplink2gene_ecogene(ecogene['ecogene_accession_number']);
row['mutation_links'].append(ecogene_link)
else: print('no ecogene_accession_number found for ordered_locus_location ' + bnumber);
data_O.append(row);
# update rows in the database
self.update_dataStage01ResequencingLineage(data_O);
def execute_mutateFilteredMutations(self,experiment_id,sample_names_I=[],
annotation_I='data/U00096.2.gb',
annotation_ref_I = 'genbank',
sequence_I='data/U00096.2.fas',
sequence_ref_I = 'fasta',
codonUsageTable_I='data/ecoli_codonUsageTable.csv',
IS_sequences_I='data/ecoli_IS_sequences.fasta',
IS_sequences_ref_I = 'fasta',
translation_table_I='Bacterial',
):
'''Mutate filtered mutations to determine the change in dna, rna, and peptide sequences
INPUT:
experiment_id = string
sample_names_I = [] of strings
annotation_I = string, reference file for the sequencing annotation
annotation_ref_I = string, reference file data base source
sequence_I = string, reference file for the sequence
sequence_I = string, reference file format
codonUsageTable_I = string, reference file for the codon usage table
IS_sequences_I = string, reference file for the insertion element sequences
IS_sequences_ref_I = string, reference file format
translation_table_I = string, translation table to use when converting from rna to peptide sequence
'''
genomeannotation = genome_annotations(annotation_I=annotation_I,annotation_ref_I=annotation_ref_I,
sequence_I=sequence_I,sequence_ref_I=sequence_ref_I,
IS_sequences_I=IS_sequences_I,IS_sequences_ref_I=IS_sequences_ref_I,
codonUsageTable_I=codonUsageTable_I);
print('Executing annotation of filtered mutations...')
data_O = [];
# query sample names
if sample_names_I:
sample_names = sample_names_I;
else:
sample_names = [];
sample_names = self.get_sampleNames_experimentID_dataStage01ResequencingMutationsFiltered(experiment_id);
for sn in sample_names:
print('analyzing sample_name ' + sn);
data_O = [];
data_codon_O=[];
# query mutation data:
mutations = [];
mutations = self.get_mutations_experimentIDAndSampleName_dataStage01ResequencingMutationsFiltered(experiment_id,sn);
for end_cnt,mutation in enumerate(mutations):
print('analyzing mutations')
data_tmp = {};
# annotate each mutation based on the position
annotation = {};
annotation = genomeannotation._mutate_peptideFromMutationData(mutation['mutation_data'],translation_table_I=translation_table_I);
if not annotation['gene']: continue;
data_tmp['mutation_genes'] = annotation['gene']
data_tmp['mutation_locations'] = annotation['location']
data_tmp['mutation_data'] = annotation['mutation_data']
data_tmp['dna_sequence_ref'] = annotation['dna_sequence_ref'];
data_tmp['dna_sequence_new'] = annotation['dna_sequence_new'];
data_tmp['rna_sequence_ref'] = annotation['rna_sequence_ref'];
data_tmp['rna_sequence_new'] = annotation['rna_sequence_new'];
data_tmp['peptide_sequence_ref'] = annotation['peptide_sequence_ref'];
data_tmp['peptide_sequence_new'] = annotation['peptide_sequence_new'];
data_tmp['mutation_class'] = annotation['mutation_class'];
data_tmp['dna_feature_position'] = annotation['dna_feature_position']
data_tmp['dna_feature_ref'] = annotation['dna_feature_ref']
data_tmp['dna_feature_new'] = annotation['dna_feature_new']
data_tmp['rna_feature_position'] = annotation['rna_feature_position']
data_tmp['rna_feature_ref'] = annotation['rna_feature_ref']
data_tmp['rna_feature_new'] = annotation['rna_feature_new']
data_tmp['peptide_feature_position'] = annotation['peptide_feature_position']
data_tmp['peptide_feature_ref'] = annotation['peptide_feature_ref']
data_tmp['peptide_feature_new'] = annotation['peptide_feature_new']
data_tmp['experiment_id'] = mutation['experiment_id'];
data_tmp['sample_name'] = mutation['sample_name'];
data_tmp['dna_features_region'] = None;
data_tmp['rna_features_region'] = None;
data_tmp['peptide_features_region'] = None;
frequency = 1.0;
if 'frequency' in mutation['mutation_data']:
frequency = mutation['mutation_data']['frequency'];
data_tmp['mutation_frequency'] = frequency
data_tmp['mutation_position'] = mutation['mutation_data']['position']
data_tmp['mutation_type'] = mutation['mutation_data']['type']
#data_tmp['mutation_data'] = mutation['mutation_data'];
data_tmp['used_'] = True;
data_tmp['comment_'] = None;
#split into different tables depending on whether the peptide sequence changed
if mutation['mutation_data']['type']=='SNP' and 'synonymous' in annotation['mutation_class']:
data_tmp['codon_triplet_ref'] = annotation['codon_triplet_ref'];
data_tmp['codon_triplet_new'] = annotation['codon_triplet_new'];
data_tmp['codon_triplet_position'] = annotation['codon_triplet_position']
data_tmp['codon_fraction_ref'] = annotation['codon_fraction_ref']
data_tmp['codon_fraction_new'] = annotation['codon_fraction_new']
data_tmp['codon_frequency_ref'] = annotation['codon_frequency_ref']
data_tmp['codon_frequency_new'] = annotation['codon_frequency_new']
data_tmp['codon_frequency_units'] = annotation['codon_frequency_units']
data_codon_O.append(data_tmp);
else:
data_O.append(data_tmp);
#upload the data to the database (each sample)
if data_O:
self.add_dataStage01ResequencingMutationsSeqChanges(data_O);
if data_codon_O:
self.add_rows_table('data_stage01_resequencing_mutationsCodonChanges',data_codon_O);
def execute_annotateFilteredMutations(self,experiment_id,sample_names_I=[],
annotation_I='data/U00096.2.gb',
annotation_ref_I = 'genbank',
biologicalmaterial_id_I='MG1655',
):
'''Annotate filtered mutations using a reference annotation
INPUT:
experiment_id = string
sample_names_I = [] of strings
annotation_I = string, reference file for the sequencing annotation
annotation_ref_I = string, reference file data base source
biologicalmaterial_id_I = string
'''
genomeannotation = genome_annotations(annotation_I=annotation_I,annotation_ref_I=annotation_ref_I);
print('Executing annotation of filtered mutations...')
genotype_phenotype_O = [];
# query sample names
if sample_names_I:
sample_names = sample_names_I;
else:
sample_names = [];
sample_names = self.get_sampleNames_experimentID_dataStage01ResequencingMutationsFiltered(experiment_id);
for sn in sample_names:
print('analyzing sample_name ' + sn);
# query mutation data:
mutations = [];
mutations = self.get_mutations_experimentIDAndSampleName_dataStage01ResequencingMutationsFiltered(experiment_id,sn);
mutation_data_O = [];
for end_cnt,mutation in enumerate(mutations):
print('analyzing mutations')
data_tmp = {};
# annotate each mutation based on the position
annotation = {};
annotation = genomeannotation._find_genesFromMutationPosition(mutation['mutation_data']['position']);
data_tmp['mutation_genes'] = annotation['gene']
data_tmp['mutation_locations'] = annotation['location']
data_tmp['mutation_annotations'] = annotation['product']
# generate a link to ecogene for the genes
data_tmp['mutation_links'] = [];
for bnumber in annotation['locus_tag']:
if bnumber:
ecogenes = [];
ecogenes = self.get_ecogeneAccessionNumber_biologicalmaterialIDAndOrderedLocusName_biologicalMaterialGeneReferences(biologicalmaterial_id_I,bnumber);
if ecogenes:
ecogene = ecogenes[0];
ecogene_link = genomeannotation._generate_httplink2gene_ecogene(ecogene['ecogene_accession_number']);
data_tmp['mutation_links'].append(ecogene_link)
else: print('no ecogene_accession_number found for ordered_locus_location ' + bnumber);
data_tmp['experiment_id'] = mutation['experiment_id'];
data_tmp['sample_name'] = mutation['sample_name'];
frequency = 1.0;
if 'frequency' in mutation['mutation_data']:
frequency = mutation['mutation_data']['frequency'];
data_tmp['mutation_frequency'] = frequency
data_tmp['mutation_position'] = mutation['mutation_data']['position']
data_tmp['mutation_type'] = mutation['mutation_data']['type']
data_tmp['mutation_data'] = mutation['mutation_data'];
data_tmp['mutation_chromosome'] = 1;
mutation_data_O.append(data_tmp);
# add data to the database
row = [];
row = data_stage01_resequencing_mutationsAnnotated(data_tmp['experiment_id'],
data_tmp['sample_name'],
data_tmp['mutation_frequency'],
data_tmp['mutation_type'],
data_tmp['mutation_position'],
data_tmp['mutation_data'],
data_tmp['mutation_annotations'],
data_tmp['mutation_genes'],
data_tmp['mutation_locations'],
data_tmp['mutation_links'],
True,
None);
self.session.add(row);
self.session.commit();
def execute_annotateAmplifications(self,experiment_id_I,sample_names_I=[],ref_genome_I='data/U00096.2.gb',ref_I = 'genbank',biologicalmaterial_id_I='MG1655'):
'''Annotate mutations for date_stage01_resequencing_endpoints
based on position, reference genome, and reference genome biologicalmaterial_id'''
genomeannotation = genome_annotations(annotation_I=ref_genome_I,annotation_ref_I=ref_I);
print('Executing annotateAmplifications...')
data_O = [];
experiment_id = experiment_id_I;
if sample_names_I:
sample_names = sample_names_I;
else:
sample_names = [];
sample_names = self.get_sampleNames_experimentID_dataStage01ResequencingAmplifications(experiment_id);
for cnt,sn in enumerate(sample_names):
print('annotating amplifications for sample_name ' + sn);
# get chromosomes
chromosomes = [];
chromosomes = self.get_chromosomes_experimentIDAndSampleName_dataStage01ResequencingAmplifications(experiment_id_I,sn);
for chromosome in chromosomes:
# get strands
strands = []
strands = self.get_strands_experimentIDAndSampleNameAndChromosome_dataStage01ResequencingAmplifications(experiment_id_I,sn,chromosome);
# remove visualization regions
strands = [s for s in strands if not 'mean' in s];
for strand in strands:
# get the start and stop of the indices
genomic_starts,genomic_stops = [],[]
genomic_starts,genomic_stops = self.get_startAndStops_experimentIDAndSampleNameAndChromosomeAndStrand_dataStage01ResequencingAmplifications(experiment_id_I,sn,chromosome,strand);
# get the start and stop regions
starts,stops = [],[]
starts,stops = self.get_amplificationRegions_experimentIDAndSampleNameAndChromosomeAndStrand_dataStage01ResequencingAmplifications(experiment_id_I,sn,chromosome,strand);
for start_cnt,start in enumerate(starts):
# annotate each mutation based on the position
annotations = [];
annotations = genomeannotation._find_genesInRegion(start,stops[start_cnt])
for annotation in annotations:
# record the data
tmp = {
'experiment_id':experiment_id,
'sample_name':sn,
'genome_chromosome':chromosome,
'genome_strand':strand,
'strand_start':genomic_starts[0],
'strand_stop':genomic_stops[0],
'amplification_start':start,
'amplification_stop':stops[start_cnt],
'used_':True,
'comment_':None};
tmp['feature_genes'] = annotation['gene']
tmp['feature_locations'] = annotation['location']
tmp['feature_annotations'] = annotation['product']
tmp['feature_start'] = annotation['start'];
tmp['feature_stop'] = annotation['stop'];
tmp['feature_types'] = annotation['type']
# generate a link to ecogene for the genes
tmp['feature_links'] = [];
for bnumber in annotation['locus_tag']:
if bnumber:
ecogenes = [];
ecogenes = self.get_ecogeneAccessionNumber_biologicalmaterialIDAndOrderedLocusName_biologicalMaterialGeneReferences(biologicalmaterial_id_I,bnumber);
if ecogenes:
ecogene = ecogenes[0];
ecogene_link = genomeannotation._generate_httplink2gene_ecogene(ecogene['ecogene_accession_number']);
tmp['feature_links'].append(ecogene_link)
else: print('no ecogene_accession_number found for ordered_locus_location ' + bnumber);
data_O.append(tmp);
# update rows in the database
self.add_dataStage01ResequencingAmplificationAnnotations(data_O);