def main():
args = get_args()
# global config
global g_force_search
if args.force_search:
g_force_search = True
# set defaults
if args.out is None:
args.out = args.fasta + ".annotated"
# translate fasta?
query = args.fasta
if args.seqtype == "cds":
query = os.path.split(query)[1]
query = os.path.join(args.temp, query)
query = query + ".translated"
say("Translating input fasta to:\n ", query)
translate_fasta(args.fasta, query)
args.seqtype = "prot"
# perform uniref90 search
uniref90hits = uniref_search(
diamond=args.diamond,
database=args.uniref90db,
query=query,
seqtype=args.seqtype,
temp=args.temp,
diamond_options=args.diamond_options,
)
'''
uniref90hits = query + ".uniref90.hits"
uniref90map = parse_results( uniref90hits )
# perform uniref50 search
uniref50hits = uniref_search(
diamond=args.diamond,
database=args.uniref50db,
query=query,
seqtype=args.seqtype,
temp=args.temp,
diamond_options=args.diamond_options, )
uniref50hits = query + ".uniref50.hits"
uniref50map = parse_results( uniref50hits )
# override mappings?
overrides = {}
if args.transitive_map is not None:
overrides = trans_mapping( uniref90map, args.transitive_map )
# reannoate the fasta
reannotate(
query=args.fasta,
out=args.out,
uniref90map=uniref90map,
uniref50map=uniref50map,
overrides=overrides, )
# done
'''
say("Finished successfully.")
def parse_results(results):
say("Parsing results file:\n ", results)
check_path(results)
mapping = {}
mode = get_mode(results)
min_pident = float(mode.replace("uniref", ""))
with open(results) as fh:
for row in csv.reader(fh, csv.excel_tab):
h = Hit(row, config=c_output_format)
if h.qseqid not in mapping:
if float(h.pident) >= float(min_pident) and float(
h.mcov) >= float(c_min_coverage):
uniref = h.sseqid.split("|")[0]
mapping[h.qseqid] = uniref
return mapping
def trans_mapping(uniref90map, p_trans_map):
say("Loading transitive mapping file:\n ", p_trans_map)
check_path(p_trans_map)
overrides = {}
uniref90map_r = {}
for header, uniref90 in uniref90map.items():
# modify by yancong
uniref90 = re.sub("-[0-9]+$", "", uniref90)
uniref90map_r.setdefault(uniref90, set()).add(header)
with open(p_trans_map) as fh:
for row in csv.reader(fh, csv.excel_tab):
uniref90, uniref50 = row
headers = uniref90map_r.get(uniref90, set())
for h in headers:
overrides[h] = uniref50
return overrides
def uniref_search(diamond=None,
database=None,
query=None,
seqtype=None,
temp=None,
diamond_options=None):
if which(diamond) is None:
die("<diamond> is not executable as: {}".format(diamond))
for path in [database, query, temp]:
check_path(path)
binary = {"nuc": "blastx", "prot": "blastp"}[seqtype]
mode = get_mode(database)
results = os.path.split(query)[1]
results = os.path.join(temp, results)
results = ".".join([results, mode, "hits"])
command = [
diamond,
binary,
"--db",
database,
"--query",
query,
"--outfmt",
c_output_format,
"--tmpdir",
temp,
"--out",
results,
#"--id", get_mode( results ).replace( "uniref", "" ),
c_diamond_filters,
]
command = " ".join([str(k) for k in command])
command += (" " + diamond_options) if diamond_options is not None else ""
if not os.path.exists(results) or g_force_search:
say("Executing:\n ", command)
os.system(command)
else:
say("Using existing results file:\n ", results)
return results
def reannotate(query=None,
out=None,
uniref90map=None,
uniref50map=None,
overrides=None):
say("Writing new output file:\n ", out)
oh = open(out, "w")
ntot, nmap90, ninf50, nmap50 = [0 for i in range(4)]
with open(query) as fh:
for line in fh:
line = line.strip()
if line == "":
continue
elif line[0] != ">":
print(line, file=oh)
else:
# diamond breaks the header on whitespace
header = line[1:].split()[0]
ntot += 1
uniref90code = "UniRef90_unknown"
if header in uniref90map:
uniref90code = uniref90map[header]
nmap90 += 1
uniref50code = "UniRef50_unknown"
if header in overrides:
uniref50code = overrides[header]
ninf50 += 1
elif header in uniref50map:
uniref50code = uniref50map[header]
nmap50 += 1
print("|".join([line, uniref90code, uniref50code]), file=oh)
oh.close()
# report
say("Summary of annotations:")
say(" Genes in input FASTA: {:,}".format(ntot))
say(" UniRef90 codes assigned: {:,} ({:.1f}%)".format(
nmap90, 100 * nmap90 / float(ntot)))
say(" UniRef50 codes assigned: {:,} ({:.1f}%)".format(
nmap50 + ninf50, 100 * (nmap50 + ninf50) / float(ntot)))
say(" UniRef50 codes inferred from UniRef90 codes: {:,} ({:.1f}%)".format(
ninf50, 100 * ninf50 / float(ntot)))
# done
return None