def get_contigs_db_info_dict(contigs_db_path,
run=run,
progress=progress,
include_AA_counts=False,
split_names=None):
"""Returns an info dict for a given contigs db"""
class Args:
def __init__(self):
self.contigs_db = contigs_db_path
args = Args()
run = run
progress = progress
run.verbose = False
progress.verbose = False
c = ContigsSuperclass(args, r=run, p=progress)
info_dict = {'path': contigs_db_path}
for key in c.a_meta:
info_dict[key] = c.a_meta[key]
if split_names:
split_names = set(split_names)
if split_names:
c.init_split_sequences()
seq = ''.join(
[c.split_sequences[split_name] for split_name in split_names])
info_dict['total_length'] = len(seq)
info_dict['gc_content'] = sequence.Composition(seq).GC_content
info_dict['gene_caller_ids'] = set([
e['gene_callers_id'] for e in c.genes_in_splits.values()
if e['split'] in split_names
])
info_dict['num_genes'] = len(info_dict['gene_caller_ids'])
info_dict['avg_gene_length'] = numpy.mean([
(c.genes_in_contigs_dict[gene_caller_id]['stop'] -
c.genes_in_contigs_dict[gene_caller_id]['start'])
for gene_caller_id in info_dict['gene_caller_ids']
])
info_dict['num_genes_per_kb'] = info_dict[
'num_genes'] * 1000.0 / info_dict['total_length']
info_dict['num_splits'] = len(split_names)
else:
c.init_contig_sequences()
seq = ''.join([e['sequence'] for e in c.contig_sequences.values()])
info_dict['gc_content'] = sequence.Composition(seq).GC_content
info_dict['num_genes'] = len(c.genes_in_contigs_dict)
info_dict['gene_caller_ids'] = set(c.genes_in_contigs_dict.keys())
info_dict['avg_gene_length'] = numpy.mean([
(gene['stop'] - gene['start'])
for gene in c.genes_in_contigs_dict.values() if not gene['partial']
])
info_dict['num_genes_per_kb'] = info_dict[
'num_genes'] * 1000.0 / info_dict['total_length']
# get completeness / contamination estimates
if split_names:
comp = completeness.Completeness(contigs_db_path).get_info_for_splits(
split_names)
else:
comp = completeness.Completeness(contigs_db_path).get_info_for_splits(
set(c.splits_basic_info.keys()))
if comp.has_key('Campbell_et_al'):
info_dict['percent_complete'] = comp['Campbell_et_al'][
'percent_complete']
info_dict['percent_redundancy'] = comp['Campbell_et_al'][
'percent_redundancy']
# lets get all amino acids used in all complete gene calls:
if include_AA_counts:
if split_names:
AA_counts_dict = c.get_AA_counts_dict(split_names=split_names)
else:
AA_counts_dict = c.get_AA_counts_dict()
info_dict['AA_counts'] = AA_counts_dict['AA_counts']
info_dict['total_AAs'] = AA_counts_dict['total_AAs']
return info_dict
def get_contigs_db_info_dict(contigs_db_path, run = run, progress = progress, include_AA_counts = False, split_names = None):
"""Returns an info dict for a given contigs db"""
class Args:
def __init__(self):
self.contigs_db = contigs_db_path
args = Args()
run = run
progress = progress
run.verbose = False
progress.verbose = False
c = ContigsSuperclass(args, r = run, p = progress)
info_dict = {'path': contigs_db_path}
for key in c.a_meta:
info_dict[key] = c.a_meta[key]
if split_names:
split_names = set(split_names)
if split_names:
c.init_split_sequences()
seq = ''.join([c.split_sequences[split_name] for split_name in split_names])
info_dict['total_length'] = len(seq)
info_dict['gc_content'] = sequence.Composition(seq).GC_content
info_dict['gene_caller_ids'] = set([e['gene_callers_id'] for e in c.genes_in_splits.values() if e['split'] in split_names])
info_dict['num_genes'] = len(info_dict['gene_caller_ids'])
info_dict['avg_gene_length'] = numpy.mean([(c.genes_in_contigs_dict[gene_caller_id]['stop'] - c.genes_in_contigs_dict[gene_caller_id]['start']) for gene_caller_id in info_dict['gene_caller_ids']])
info_dict['num_genes_per_kb'] = info_dict['num_genes'] * 1000.0 / info_dict['total_length']
info_dict['num_splits'] = len(split_names)
else:
c.init_contig_sequences()
seq = ''.join([e['sequence'] for e in c.contig_sequences.values()])
info_dict['gc_content'] = sequence.Composition(seq).GC_content
info_dict['num_genes'] = len(c.genes_in_contigs_dict)
info_dict['gene_caller_ids'] = set(c.genes_in_contigs_dict.keys())
info_dict['avg_gene_length'] = numpy.mean([(gene['stop'] - gene['start']) for gene in c.genes_in_contigs_dict.values() if not gene['partial']])
info_dict['num_genes_per_kb'] = info_dict['num_genes'] * 1000.0 / info_dict['total_length']
# get completeness / contamination estimates
if split_names:
comp = completeness.Completeness(contigs_db_path).get_info_for_splits(split_names)
else:
comp = completeness.Completeness(contigs_db_path).get_info_for_splits(set(c.splits_basic_info.keys()))
if comp.has_key('Campbell_et_al'):
info_dict['percent_complete'] = comp['Campbell_et_al']['percent_complete']
info_dict['percent_redundancy'] = comp['Campbell_et_al']['percent_redundancy']
# lets get all amino acids used in all complete gene calls:
if include_AA_counts:
if split_names:
AA_counts_dict = c.get_AA_counts_dict(split_names = split_names)
else:
AA_counts_dict = c.get_AA_counts_dict()
info_dict['AA_counts'] = AA_counts_dict['AA_counts']
info_dict['total_AAs'] = AA_counts_dict['total_AAs']
return info_dict
def get_contigs_db_info_dict(contigs_db_path, run=run, progress=progress, include_AA_counts=False, split_names=None, exclude_partial_gene_calls=True):
"""Returns an info dict for a given contigs db"""
class Args:
def __init__(self):
self.contigs_db = contigs_db_path
args = Args()
run = run
progress = progress
run.verbose = False
progress.verbose = False
c = ContigsSuperclass(args, r=run, p=progress)
info_dict = {'path': contigs_db_path}
for key in c.a_meta:
info_dict[key] = c.a_meta[key]
# Two different strategies here depending on whether we work with a given set if split ids or
# everything in the contigs database.
if split_names:
split_names = set(split_names)
c.init_split_sequences()
seq = ''.join([c.split_sequences[split_name] for split_name in split_names])
candidate_gene_caller_ids = set([e['gene_callers_id'] for e in c.genes_in_splits.values() if e['split'] in split_names])
else:
c.init_contig_sequences()
seq = ''.join([e['sequence'] for e in c.contig_sequences.values()])
candidate_gene_caller_ids = c.genes_in_contigs_dict.keys()
gene_caller_ids = set([])
excluded_gene_ids = set([])
for gene_caller_id in candidate_gene_caller_ids:
if c.genes_in_contigs_dict[gene_caller_id]['partial'] and exclude_partial_gene_calls:
excluded_gene_ids.add(gene_caller_id)
else:
gene_caller_ids.add(gene_caller_id)
info_dict['gene_caller_ids'] = gene_caller_ids
info_dict['excluded_gene_ids'] = excluded_gene_ids
info_dict['num_genes'] = len(gene_caller_ids)
info_dict['gene_lengths'] = dict([(gene_caller_id, (c.genes_in_contigs_dict[gene_caller_id]['stop'] - c.genes_in_contigs_dict[gene_caller_id]['start'])) for gene_caller_id in gene_caller_ids])
info_dict['avg_gene_length'] = numpy.mean(info_dict['gene_lengths'].values())
info_dict['num_genes_per_kb'] = info_dict['num_genes'] * 1000.0 / info_dict['total_length']
info_dict['gc_content'] = sequence.Composition(seq).GC_content
info_dict['total_length'] = len(seq)
# get completeness / contamination estimates
if split_names:
comp = completeness.Completeness(contigs_db_path).get_info_for_splits(split_names)
else:
comp = completeness.Completeness(contigs_db_path).get_info_for_splits(set(c.splits_basic_info.keys()))
if 'Campbell_et_al' in comp:
info_dict['percent_complete'] = comp['Campbell_et_al']['percent_complete']
info_dict['percent_redundancy'] = comp['Campbell_et_al']['percent_redundancy']
# lets get all amino acids used in all complete gene calls:
if include_AA_counts:
if split_names:
AA_counts_dict = c.get_AA_counts_dict(split_names=split_names)
else:
AA_counts_dict = c.get_AA_counts_dict()
info_dict['AA_counts'] = AA_counts_dict['AA_counts']
info_dict['total_AAs'] = AA_counts_dict['total_AAs']
return info_dict
def get_contigs_db_info_dict(contigs_db_path, run=run, progress=progress, include_AA_counts=False, split_names=None, exclude_partial_gene_calls=True):
"""Returns an info dict for a given contigs db"""
class Args:
def __init__(self):
self.contigs_db = contigs_db_path
args = Args()
run = run
progress = progress
run.verbose = False
progress.verbose = False
c = ContigsSuperclass(args, r=run, p=progress)
info_dict = {'path': contigs_db_path}
for key in c.a_meta:
info_dict[key] = c.a_meta[key]
# Two different strategies here depending on whether we work with a given set if split ids or
# everything in the contigs database.
if split_names:
split_names = set(split_names)
c.init_split_sequences()
seq = ''.join([c.split_sequences[split_name] for split_name in split_names])
candidate_gene_caller_ids = set([e['gene_callers_id'] for e in c.genes_in_splits.values() if e['split'] in split_names])
else:
c.init_contig_sequences()
seq = ''.join([e['sequence'] for e in c.contig_sequences.values()])
candidate_gene_caller_ids = c.genes_in_contigs_dict.keys()
info_dict['gc_content'] = sequence.Composition(seq).GC_content
info_dict['total_length'] = len(seq)
gene_caller_ids = set([])
excluded_gene_ids = set([])
for gene_caller_id in candidate_gene_caller_ids:
if c.genes_in_contigs_dict[gene_caller_id]['partial'] and exclude_partial_gene_calls:
excluded_gene_ids.add(gene_caller_id)
else:
gene_caller_ids.add(gene_caller_id)
info_dict['gene_caller_ids'] = gene_caller_ids
info_dict['excluded_gene_ids'] = excluded_gene_ids
info_dict['num_genes'] = len(gene_caller_ids)
info_dict['gene_lengths'] = dict([(gene_caller_id, (c.genes_in_contigs_dict[gene_caller_id]['stop'] - c.genes_in_contigs_dict[gene_caller_id]['start'])) for gene_caller_id in gene_caller_ids])
info_dict['avg_gene_length'] = numpy.mean(info_dict['gene_lengths'].values())
info_dict['num_genes_per_kb'] = info_dict['num_genes'] * 1000.0 / info_dict['total_length']
# get completeness / contamination estimates
p_completion, p_redundancy, domain, domain_confidence, results_dict = completeness.Completeness(contigs_db_path).get_info_for_splits(split_names if split_names else set(c.splits_basic_info.keys()))
info_dict['percent_complete'] = p_completion
info_dict['percent_redundancy'] = p_redundancy
info_dict['scg_domain'] = domain
info_dict['scg_domain_confidence'] = domain_confidence
# lets get all amino acids used in all complete gene calls:
if include_AA_counts:
if split_names:
AA_counts_dict = c.get_AA_counts_dict(split_names=split_names)
else:
AA_counts_dict = c.get_AA_counts_dict()
info_dict['AA_counts'] = AA_counts_dict['AA_counts']
info_dict['total_AAs'] = AA_counts_dict['total_AAs']
return info_dict