def perform_alignment_based_estimation(self):
print('\nmultiple identified strains in group')
print('performing composition estimation')
self.perform_setup()
self.create_database()
self.load_genomes()
self.create_fragments()
#print('estimating transition probabilities')
self.align_sample_reads()
self.align_simulated_reads()
self.create_symbols()
self.create_accessions_filenames_mapping()
empirical_pooled_summary, empirical_organism_summary = self.get_read_classifications(
self.fragment_paf_file, empirical=True)
observed_counts = self.get_read_classifications(self.sample_paf_file)
path = self.context.project_path + '/runtimefiles/abundance_estimation/'
write_json(empirical_pooled_summary,
path + 'empirical_pooled_summary.json')
write_json(empirical_organism_summary,
path + 'empirical_organism_summary.json')
write_json(observed_counts, path + 'observed_counts.json')
empirical_organism_summary = load_json(
path + 'empirical_organism_summary.json')
observed_counts = load_json(path + 'observed_counts.json')
print('EM rounds start')
self.estimate_proportions(empirical_organism_summary, observed_counts)
self.update_sample_proportions()
def __init__(self, paf_file, database_path, include_plasmids_mitochondria):
self.paf_file = paf_file
self.include_plasmids_mitochondria = include_plasmids_mitochondria
self.ag_dict = load_json(database_path +
'taxonomy/accessions_genomes.json')
self.af_dict = load_json(database_path +
'taxonomy/accessions_filenames.json')
def __init__(self, reads_alignments, context):
self.reads_alignments = reads_alignments
self.context = context
self.af_dict = load_json(self.context.database_path +
'taxonomy/accessions_filenames.json')
self.an_dict = load_json(self.context.database_path +
'taxonomy/accessions_genomes.json')
def __init__(self, paf_file, database_path):
self.paf_file = paf_file
self.min_pid = 0.1
self.min_collinearity = 0.8
self.min_read_length = 700
self.ag_dict = load_json(database_path +
'taxonomy/accessions_genomes.json')
self.af_dict = load_json(database_path +
'taxonomy/accessions_filenames.json')
def __init__(self, classifications, collinearities, group_id, group_abundance, context):
self.group_id = group_id
self.group_abundance = group_abundance
self.classifications = classifications
self.collinearities = collinearities
self.context = context
self.min_cec_ratio = 2
self.af_dict = load_json(context.database_path + 'taxonomy/accessions_filenames.json')
self.ag_dict = load_json(context.database_path + 'taxonomy/accessions_genomes.json')
def remove_plasmids_mitochondria(self):
ct = self.context
taxonomy_file = ct.database_path + 'taxonomy/accessions_genomes.json'
taxonomy = load_json(taxonomy_file)
clean_classifications = []
while len(self.classifications) > 0:
chromosome_accessions = []
read_id, accessions = self.classifications.pop()
for accession in accessions:
sequence_name = taxonomy[accession.upper()]
if 'plasmid' not in sequence_name.lower(
) and 'mitochond' not in sequence_name.lower():
chromosome_accessions.append(accession)
if len(chromosome_accessions) > 0:
clean_classifications.append([read_id, chromosome_accessions])
self.classifications = clean_classifications
def __init__(self, paf_file, database_path):
self.paf_file = paf_file
self.ag_dict = load_json(database_path +
'taxonomy/accessions_genomes.json')
self.af_dict = load_json(database_path +
'taxonomy/accessions_filenames.json')