else:
print("No sequence for: " + rec.query_name)
#print("rpos: " + str(rpos) + " qpos: " + str(qpos))
return(seqs)
#sys.exit()
# Logfile
loghandle = None
if args.logfile:
loghandle = open(args.logfile,"w+")
print("Nr. of Contigs: " + str(len(contigs)))
scafs = Longreads(args.inputfiles, blacklist, args.linename)
#scafs.filter_low_quality_contigs(0.76)
scafs.turn_longreads_around(logging=loghandle)
scafs.sort_by_starts()
scafs.filter_contigs_by_coverage(0.5,ignore_ends=True, verbose = False)
print("Nr. of reads: " + str(len(scafs.lreads)))
# Parse Recipe File
needed_reads = set()
items = []
with open(args.contigstringfile) as f:
for line in f:
if line.startswith("#"):
continue
if len(line.split()) == 2:
parser.add_argument("--blacklistfile", help="File containing long read ids where certain contig mappings should be ignored.")
args = parser.parse_args()
blacklist = defaultdict(list)
if args.blacklistfile:
with open(args.blacklistfile) as f:
for line in f:
sline = line.split()
if sline[0] == "contig":
blacklist[sline[1]] = "y"
else:
blacklist[sline[0]].append(sline[1])
#print(set([args.lrid]))
scafs = Longreads(args.inputfiles, blacklist, args.linename, whitelist_lreads=set([args.lrid]))
scafs.turn_longreads_around()
scafs.sort_by_starts()
#print(scafs.lreads)
lrseqs = dict()
for read in SeqIO.parse(args.sequencefile, "fastq"):
lrseqs[read.id] = str(read.seq)
ctg1, ctg2 = args.contigs.split("-")
read = scafs.lreads[args.lrid]
sc = 0
ec = 0
for ctg in read["maps"]:
if ctg["name"] == ctg1:
#print("\t".join([ctg["name"], str(ctg["scr"]), str(ctg["ecr"]), str(ctg["scc"]), str(ctg["ecc"])]))
sccs.append(ctgs[ctgn][ctgidx]["scc"])
eccs.append(ctgs[ctgn][ctgidx]["ecc"])
strands.append(ctgs[ctgn][ctgidx]["strand"])
newctg = {
"strand": round(mean(strands)),
"name": ctgn,
"scc": round(mean(sccs)),
"ecc": round(mean(eccs)),
"scr": round(mean(cluster)) + round(mean(sccs)),
"ecr": round(mean(cluster)) + round(mean(eccs))
}
p["maps"].append(newctg)
return pseudolongreads
scafs = Longreads(args.inputfiles, blacklist, args.linename)
#scafs.filter_whitelist_ctgs(set(["1115APD"]))
scafs.filter_small_contigs(300)
scafs.filter_reverse_small_contigs(600)
scafs.filter_low_quality_contigs(0.81)
scafs.turn_longreads_around()
scafs.sort_by_starts()
scafs.filter_contigcounts(args.mincontigs)
#scafs.copy()
print("Nr. of reads: " + str(len(scafs.lreads)))
status = 0
for iteration in range(10):
print("Pseudoaligning all... ", end="")
lr_scores, lr_dists = scafs.pseudoalign_all()
for line in f:
if line.startswith(">"):
break
else:
format = "paf"
celllinestr = line.split()[0]
m = re.search('[A-Z]+', celllinestr)
cellline = m.group(0)
print("cell line detected: " + cellline)
break
if format == "fasta":
for read in SeqIO.parse(args.inputfile, "fasta"):
seqs[read.id] = str(read.seq).upper()
elif format == "paf":
scaf = Longreads.init_from_reverse_paf(args.inputfile)
scaf.sort_by_starts()
lread = scaf.lreads
else:
print("Problem! Format unknown")
sys.exit()
image = LongReadSVG(args.output, zoom=800)
dwg = image.dwg
ypad = 7
xpad = 20
col1 = "black"
col2 = "lightgrey"
col = col1
whitelist_ctgs = set()
whitelist_lreads = set()
if (args.whitelist):
with open(args.whitelist) as f:
for line in f:
whitelist_ctgs.add(line.strip())
elif (args.whitelist_lrs):
with open(args.whitelist_lrs) as f:
for line in f:
whitelist_lreads.add(line.strip())
contigs = {}
for read in SeqIO.parse(args.contigfile, "fasta"):
contigs[read.id] = len(read.seq)
scafs = Longreads(args.inputfiles, blacklist, args.linename, whitelist_lreads)
if whitelist_ctgs:
scafs.filter_whitelist_ctgs(whitelist_ctgs)
scafs.filter_contigcounts(int(args.mincontigs))
reverse_mappers = set()
reverse_mappers.add("344DBB")
reverse_mappers.add("472DBB")
scafs.turn_longreads_around(reverse_mappers)
scafs.sort_by_starts()
#scafs.filter_small_contigs(300)
#scafs.filter_overlapped_contigs(0.5)
scafs.filter_contigcounts(int(args.mincontigs))
scafs.print_ids()
print("Reads meeting criteria: " + str(len(scafs.lreads)))
print("Pseudoaligning all...")
for read in SeqIO.parse(args.contigfile, "fasta"):
contigs[read.id] = len(read.seq)
print("Nr. of scaffolds: " + str(len(contigs)))
blacklist = defaultdict(list)
if args.blacklistfile:
with open(args.blacklistfile) as f:
for line in f:
sline = line.split()
if sline[0] == "contig":
blacklist[sline[1]] = "y"
else:
blacklist[sline[0]].append(sline[1])
lrs = Longreads(args.inputfiles, blacklist, args.linename)
lrs.filter_contigcounts(2)
lrs.turn_longreads_around()
lrs.sort_contigs_in_reads()
greads = lrs.lreads
# cluster np-reads
print("scaffolding long reads ....")
contig2cluster = {}
creads = {}
clusternr = 0
while len(greads) > 0:
clusternr += 1
current_cluster = {}
current_contigs = set()
# take a random read and build a cluster from it
reads = {}
cgreads = []
blacklist = defaultdict(list)
if args.blacklistfile:
with open(args.blacklistfile) as f:
for line in f:
sline = line.split()
if sline[0] == "contig":
blacklist[sline[1]] = "y"
else:
blacklist[sline[0]].append(sline[1])
lrs = Longreads(args.inputfiles, blacklist, args.linename)
lrs.filter_contigcounts(2)
lrs.filter_small_contigs(300)
#lrs.filter_reverse_small_contigs(600)
reverse_mappers = set()
reverse_mappers.add("344DBB")
reverse_mappers.add("472DBB")
lrs.turn_longreads_around(reverse_mappers)
lrs.sort_by_starts()
contig2lrid = lrs.ctg2lreads
def get_full_name(short_ctgn):
if "_" in short_ctgn:
nr = short_ctgn.split("_")[0]