def build_pass_track(target, args):
"""
Builds a specific track of Good transcripts for the current mode.
"""
colors = {
"coding": "59,101,69",
"noncoding": "98,124,191",
"not_pass": "******"
}
con, cur = sql_lib.attach_databases(args.outDir, args.mode)
biotype_map = sql_lib.get_transcript_biotype_map(cur, args.refGenome)
if args.mode == "augustus":
query = etc.config.augustusEval(args.genome, args.refGenome)
pass_ids = sql_lib.get_query_ids(cur, query)
out_pass_bed_path, out_pass_big_bed_path = get_bed_paths(
args.outDir, "augustus", args.genome)
gp_dict = seq_lib.get_transcript_dict(args.augustusGp)
elif args.mode == "reference": # for reference, we are more interested in what is NOT Good
query = etc.config.refEval(args.refGenome)
pass_ids = biotype_map.viewkeys() - sql_lib.get_query_ids(
cur, query) # actually not pass
out_pass_bed_path, out_pass_big_bed_path = get_bed_paths(
args.outDir, "reference", args.refGenome)
gp_dict = seq_lib.get_transcript_dict(args.annotationGp)
elif args.mode == "transMap":
pass_ids = get_all_tm_pass(cur, args.refGenome, args.genome)
out_pass_bed_path, out_pass_big_bed_path = get_bed_paths(
args.outDir, "transMap", args.genome)
gp_dict = seq_lib.get_transcript_dict(args.targetGp)
else:
raise RuntimeError(
"Somehow your argparse object does not contain a valid mode.")
with open(out_pass_bed_path, "w") as outf:
for aln_id, rec in gp_dict.iteritems():
tx_id = psl_lib.strip_alignment_numbers(aln_id)
if aln_id in pass_ids:
if biotype_map[tx_id] == "protein_coding":
bed = rec.get_bed(rgb=colors["coding"])
outf.write("".join(["\t".join(map(str, bed)), "\n"]))
else:
bed = rec.get_bed(rgb=colors["noncoding"])
outf.write("".join(["\t".join(map(str, bed)), "\n"]))
else:
bed = rec.get_bed(rgb=colors["not_pass"])
outf.write("".join(["\t".join(map(str, bed)), "\n"]))
make_big_bed(out_pass_bed_path, args.sizes, out_pass_big_bed_path)
def get_all_tm_pass(cur, ref_genome, genome):
"""
transMap pass varies depending on if the transcript is coding or noncoding. We will build a set of IDs for both.
"""
biotypes = sql_lib.get_all_biotypes(cur, genome, gene_level=False)
all_ids = set()
for biotype in biotypes:
query = etc.config.transMapEval(ref_genome,
genome,
biotype=biotype,
passing=False)
query_ids = sql_lib.get_query_ids(cur, query)
all_ids |= query_ids
return all_ids
def categorized_plot(cur, highest_cov_dict, genomes, out_path, file_name,
biotype, biotype_ids, gencode, query_fn):
results = []
for g in genomes:
best_ids = set(zip(*highest_cov_dict[g].itervalues())[0])
query = query_fn(g, biotype, details=False)
categorized_ids = sql_lib.get_query_ids(cur, query)
num_categorized = len({
x
for x in categorized_ids if x in best_ids
and psl_lib.remove_alignment_number(x) in biotype_ids
})
norm = num_categorized / (0.01 * len(biotype_ids))
results.append([g, norm, num_categorized])
title_string = "Proportion of {:,} {} transcripts in {}\ncategorized as {}"
title_string = title_string.format(len(biotype_ids), biotype, gencode,
query_fn.__name__)
plot_lib.barplot(results,
out_path,
file_name,
title_string,
adjust_y=False)
def consensus_by_biotype(cur, ref_genome, genome, biotype, gps,
transcript_gene_map, gene_transcript_map, stats, mode,
ref_intervals, tgt_intervals):
"""
Main consensus finding function.
"""
fail_ids, pass_specific_ids, excel_ids = sql_lib.get_fail_passing_excel_ids(
cur, ref_genome, genome, biotype, best_cov_only=False)
# hacky way to avoid duplicating code in consensus finding - we will always have an aug_id set, it just may be empty
if mode == "augustus" and biotype == "protein_coding":
aug_query = etc.config.augustusEval(genome, ref_genome)
aug_ids = sql_lib.get_query_ids(cur, aug_query)
id_names = ["fail_ids", "pass_specific_ids", "excel_ids", "aug_ids"]
id_list = [fail_ids, pass_specific_ids, excel_ids, aug_ids]
else:
id_names = ["fail_ids", "pass_specific_ids", "excel_ids"]
id_list = [fail_ids, pass_specific_ids, excel_ids]
data_dict = build_data_dict(id_names, id_list, transcript_gene_map,
gene_transcript_map)
binned_transcripts = find_best_transcripts(data_dict, stats, mode, biotype)
consensus = find_consensus(binned_transcripts, stats, gps, ref_intervals,
tgt_intervals, mode)
return binned_transcripts, consensus
if aug_cov > tm_cov and aug_ident > tm_ident:
r["higher_both"].append(aug_id)
elif aug_cov > tm_cov:
r["higher_cov"].append(aug_id)
elif aug_ident > tm_ident:
r["higher_ident"].append(aug_id)
else:
r["worse"].append(aug_id)
transcript_gene_map = sql_lib.get_transcript_gene_map(cur, ref_genome, biotype=None, filter_chroms=filter_chroms)
gene_transcript_map = sql_lib.get_gene_transcript_map(cur, ref_genome, biotype=biotype, filter_chroms=filter_chroms)
stats = merge_stats(cur, 'gorilla')
fail_ids, good_specific_ids, pass_ids = sql_lib.get_fail_good_pass_ids(cur, ref_genome, genome, biotype)
aug_query = etc.config.augustusEval(genome, ref_genome)
aug_ids = sql_lib.get_query_ids(cur, aug_query)
id_names = ["fail_ids", "good_specific_ids", "pass_ids", "aug_ids"]
id_list = [fail_ids, good_specific_ids, pass_ids, aug_ids]
data_dict = build_data_dict(id_names, id_list, transcript_gene_map, gene_transcript_map)
binned_transcripts = find_best_transcripts(data_dict, stats)
consensus = find_consensus(binned_transcripts, stats)
aug_cons = {x for x in consensus if 'aug' in x}
transcript_evaluation = OrderedDict((x, []) for x in ["PassTM", "PassAug", "PassTie", "GoodTM", "GoodAug", "GoodTie",
"FailTM", "FailAug", "FailTie", "NoTransMap"])
gene_evaluation = OrderedDict((x, []) for x in ["Pass", "Good", "Fail", "NoTransMap"])
gene_fail_evaluation = OrderedDict((x, []) for x in ["Fail", "NoTransMap"])
for gene_id in binned_transcripts:
categories = set()
for ens_id in binned_transcripts[gene_id]: