def calc_ontarget_rate(tree,
gene_info,
input_fasta,
sam_filename,
output_filename=None):
query_len_dict = dict(
(r.id, len(r.seq)) for r in SeqIO.parse(open(input_fasta), 'fasta'))
if output_filename is None:
f = sys.stdout
else:
f = open(output_filename, 'w')
f.write(
"read_id\tread_len\tis_fl\tnum_probe\tnum_base_overlap\tloci\tgenes\n")
reader = BioReaders.GMAPSAMReader(sam_filename,
True,
query_len_dict=query_len_dict)
for r in reader:
if r.sID == '*': continue
num_probe, base_hit, genes_seen = get_probe_hit(tree, gene_info, r)
f.write("{0}\t{1}\tY\t{2}\t{3}\t{4}:{5}-{6}\t{7}\n".format(
r.qID, r.qLen, num_probe, base_hit, r.sID, r.sStart, r.sEnd,
",".join(genes_seen)))
f.close()
def calc_ontarget_rate(tree,
gene_info,
input_fasta,
is_gtf,
sam_or_gtf,
output_filename=None):
type = 'fasta' if input_fasta.upper().endswith(
'.FA') or input_fasta.upper().endswith('.FASTA') else 'fastq'
query_len_dict = dict(
(r.id, len(r.seq)) for r in SeqIO.parse(open(input_fasta), type))
if output_filename is None:
f = sys.stdout
else:
f = open(output_filename, 'w')
FIELDS = [
'read_id', 'read_len', 'num_probe', 'num_base_overlap', 'loci', 'genes'
]
writer = DictWriter(f, FIELDS, delimiter='\t')
writer.writeheader()
if is_gtf:
reader = collapseGFFReader(sam_or_gtf)
for r in reader:
num_probe, base_hit, genes_seen = get_probe_hit(
tree, gene_info, r, is_gtf)
rec = {
'read_id': r.seqid,
'read_len': 'NA',
'num_probe': num_probe,
'num_base_overlap': base_hit,
'loci': "{0}:{1}-{2}".format(r.chr, r.start, r.end),
'genes': ",".join(genes_seen)
}
writer.writerow(rec)
else:
reader = BioReaders.GMAPSAMReader(sam_or_gtf,
True,
query_len_dict=query_len_dict)
for r in reader:
if r.sID == '*': continue
num_probe, base_hit, genes_seen = get_probe_hit(
tree, gene_info, r, is_gtf)
rec = {
'read_id': r.qID,
'read_len': r.qLen,
'num_probe': num_probe,
'num_base_overlap': base_hit,
'loci': "{0}:{1}-{2}".format(r.sID, r.sStart, r.sEnd),
'genes': ",".join(genes_seen)
}
writer.writerow(rec)
f.close()
def summarize_GMAP_sam(input_fa_or_fq, input_sam):
d = dict((r.id, len(r.seq)) for r in SeqIO.parse(
open(input_fa_or_fq), type_fa_or_fq(input_fa_or_fq)))
map_count = defaultdict(lambda: 0)
for r in BioReaders.GMAPSAMReader(input_sam, True):
map_count[r.qID] += 1
multi = [x for x in map_count if map_count[x] > 1]
f = open(input_sam + '.summary.txt', 'w')
f.write("id\tqLength\tqCoverage\tidentity\tunique\n")
for r in BioReaders.GMAPSAMReader(input_sam, True, query_len_dict=d):
if r.sID == '*': continue
if r.qID in multi: uni = 'N'
else: uni = 'Y'
f.write("{0}\t{1}\t{2:.4f}\t{3:.4f}\t{4}\n".format(
r.qID, d[r.qID], r.qCoverage, r.identity, uni))
f.close()
print("Output written to: {0}".format(f.name), file=sys.stderr)
def err_correct(genome_file, sam_file, output_err_corrected_fasta, genome_dict=None):
if genome_dict is None:
genome_dict = {}
for r in SeqIO.parse(open(genome_file), 'fasta'):
genome_dict[r.name] = r
print >> sys.stderr, "done reading", genome_file
f = open(output_err_corrected_fasta, 'w')
reader = BioReaders.GMAPSAMReader(sam_file, True)
for r in reader:
if r.sID == '*': continue
seq = sp.consistute_genome_seq_from_exons(genome_dict, r.sID, r.segments, r.flag.strand)
f.write(">{0}\n{1}\n".format(r.qID, seq))
f.close()
print >> sys.stderr, "output written to", output_err_corrected_fasta
def categorize_aln_by_annotation(gene_annotation_file,
input_fasta,
input_sam,
output_prefix,
min_overlap_bp=200,
min_query_overlap=.5,
min_gene_overlap=.8):
t = defaultdict(lambda: {
'+': IntervalTree(),
'-': IntervalTree()
}) # chr -> strand -> IntervalTree
info = {}
#reader = DictReader(open('ProteinTable149_154224.txt'),delimiter='\t')
for r in DictReader(open(gene_annotation_file), delimiter='\t'):
if r['#Replicon Name'] != 'chr':
print("Ignore", r, file=sys.stderr)
continue
info[r['Locus tag']] = (int(r['Start']), int(r['Stop']),
r['Locus tag'])
t[r['Replicon Accession']][r['Strand']].add(int(r['Start']),
int(r['Stop']),
r['Locus tag'])
#pdb.set_trace()
result = defaultdict(lambda: []) # gene -> list of rec
d = dict(
(r.id, len(r.seq)) for r in SeqIO.parse(open(input_fasta), 'fasta'))
reader = BioReaders.GMAPSAMReader(input_sam, True, query_len_dict=d)
for r in reader:
#if r.qID == 'm151125_055539_42275_c100921822550000001823204305121656_s1_p0/121461/30_2108_CCS':
# pdb.set_trace()
ans = match_w_annotation(t, r, info, min_overlap_bp, min_query_overlap,
min_gene_overlap)
# ans is AMatch(name, strand, start, end, record)
result[ans.name].append(ans)
novel_ct = defaultdict(lambda: {
'+': ClusterTree(0, 0),
'-': ClusterTree(0, 0)
})
novel_list = []
novel_index = 0
f = open(output_prefix + '.sam', 'w')
f.write(reader.header)
f1 = open(output_prefix + '.report.txt', 'w')
f1.write("id\tread_group\tgene_name\tserial_number\tstrand\tstart\tend\n")
for k, v in result.items():
# v is: list of AMatch(name, strand, start, end, record)
if k.startswith('novel-unannotated'):
# write novel later, we are grouping them by loci first
#tagRG='novel'
for x in v:
novel_ct[x.record.sID][x.strand].insert(
x.start, x.end, novel_index)
novel_index += 1
novel_list.append(x)
continue
elif k.startswith('novel-antisense'):
tagRG = 'novel-antisense'
elif k.startswith('novel-partial'):
tagRG = 'novel-partial'
elif k.startswith('poly-'):
tagRG = 'poly'
else:
tagRG = 'single'
v.sort(key=lambda x: (x.start, x.end),
reverse=True
if v[0].strand == '-' else False) # sort by start, then end
for i, x in enumerate(v):
f.write("{0}\tSN:Z:{1:06d}\tRG:Z:{2}\tgn:Z:{3}\n".format(
x.record.record_line, i + 1, tagRG, k))
if x.strand == '+':
f1.write("{0}\t{1}\t{2}\t{3:06d}\t{4}\t{5}\t{6}\n".format(\
x.record.qID, tagRG, k, i+1, x.strand, x.start+1, x.end))
else: # - strand, start is end, end is start
f1.write("{0}\t{1}\t{2}\t{3:06d}\t{4}\t{5}\t{6}\n".format(\
x.record.qID, tagRG, k, i+1, x.strand, x.end, x.start+1))
# now write the novel stuff, grouped by regions
novel_region_index = 1
for d1 in novel_ct.values():
for ct in d1.values():
gn = 'novel-' + str(novel_region_index)
for _start, _end, _indices in ct.getregions():
v = [novel_list[ind] for ind in _indices]
v.sort(key=lambda x: (x.start, x.end),
reverse=True if v[0].strand == '-' else
False) # sort by start, then end
for i, x in enumerate(v):
f.write("{0}\tSN:Z:{1:06d}\tRG:Z:{2}\tgn:Z:{3}\n".format(
x.record.record_line, i + 1, "novel-unannotated", gn))
if x.strand == '+':
f1.write("{0}\t{1}\t{2}\t{3:06d}\t{4}\t{5}\t{6}\n".format(\
x.record.qID, "novel-unannotated", gn, i+1, x.strand, x.start+1, x.end))
else:
f1.write("{0}\t{1}\t{2}\t{3:06d}\t{4}\t{5}\t{6}\n".format(\
x.record.qID, "novel-unannotated", gn, i+1, x.strand, x.end, x.start+1))
novel_region_index += 1
f.close()
f1.close()
print("Output written to:", f.name, file=sys.stderr)
print("Output written to:", f1.name, file=sys.stderr)