def main(fasta, prefix):
# load data
prots = {}
with open(fasta, 'r') as infile:
for rec in fasta_iter(infile):
prot = Protein(rec)
prots[prot.name] = prot
# look for subsumed sequences
subsumed = set()
cnt = 0
for key, value in list(prots.items()):
cnt += 1
if cnt % 100 == 0:
print(f'{cnt} proteins checked')
qry = value.sqn
for rec in prots:
# skip finding itself
if key == rec:
continue
subj = prots[rec].sqn
if qry in subj:
subsumed.add(key)
break
# write out non-subsumed sequences
print(f'Number of input sequences is {cnt}')
print(f'Number of sequences subsumed within another is {len(subsumed)}')
outname = '-'.join([prefix, 'nonSubsumed.fa'])
outfile = open(outname, 'w')
for key, value in list(prots.items()):
if key not in subsumed:
print(value.print_prot(), file=outfile)
outfile.close()
def main():
"""distribute-gff.py
Extract annotations on the given scaffolds
usage: distribute-gff.py annotations.gff sequences.fa
output: sequences.gff
"""
gff = sys.argv[1]
fasta = sys.argv[2]
seqs = set()
with open(fasta, "r") as fastafile:
for rec in fasta_iter(fastafile):
seqs.add(rec[0])
# clumsy way of getting base name of fasta file
fastaname = re.sub(".fa", "", re.sub(".fasta", "", fasta))
outfile = open(fastaname + ".gff", "w")
with open(gff, "r") as file_object:
for line in file_object:
if line[0] == "#":
continue
feature = GFF(line)
if feature.seqid in seqs:
outfile.write(line)
outfile.close()
def main():
# read in gene locus_tags
tags = 'version3-gene-locus-tags.tsv'
genes = {}
with open(tags, 'r') as infile:
for line in infile:
gid, loc = line.strip().split('\t')
genes[gid] = Gene(gid)
genes[gid].add_tag(loc)
# read in sequence IDs
transcripts = '/projects/bullfrog_assembly/genome/ARCS/annotation/fresh-Oct2018/shared-with-uvic/compare-proteins/v3-proteins.fa'
with open(transcripts, 'r') as infile:
for sid, sqn in fasta_iter(infile):
gid = sid.split('-mRNA')[0]
try:
genes[gid].add_mrna(sid)
except KeyError:
print f'{sid} not in gene table!'
# write out all tags
outname = 'version3-transcript-locus-tags.tsv'
with open(outname, 'w') as outfile:
for entry in genes:
this_gene = genes[entry]
for tag in this_gene.get_tags():
this_mrna, this_tag = tag
outbuff = ''.join([this_mrna, '\t', this_tag, '\n'])
outfile.write(outbuff)
#!/usr/bin/env python
import sys
from fastatools import fasta_iter
infile = sys.argv[1]
bueno = ["A", "C", "G", "T", "N"]
with open(infile, "r") as fasta:
for rec in fasta_iter(fasta):
seqn = rec[1].upper()
nam = ">" + rec[0]
print nam
for base in seqn:
if base not in bueno:
sys.stdout.write("N")
continue
sys.stdout.write(base)
sys.stdout.write("\n")
def main():
"""Extract CDS coordinates for each mRNA in a gff file,
then print the corresponding sequence.
The subfeatures MUST be sorted by their start coordinate
Usage: extract-cds.py genes.gff genome.fa > genes-cds.fa
"""
if len(sys.argv) is not 3:
print main.__doc__
sys.exit(1)
gff = sys.argv[1]
fasta = sys.argv[2]
cds_coords = {}
with open(gff, "r") as file_object:
for line in file_object:
if line[0] == "#":
sys.stdout.write(line)
continue
feature = gfftools.GFF(line)
if feature.type == "CDS":
for parent in feature.parent:
if parent in cds_coords:
if feature.strand == "+":
cds_coords[parent]['coords'].append(
[feature.start, feature.end])
else:
cds_coords[parent]['coords'].insert(
0, [feature.start, feature.end])
else:
cds_coords[parent] = {
'coords': [[feature.start, feature.end]],
'scaf': feature.seqid,
'strand': feature.strand
}
sequences = {}
with open(fasta, "r") as file_object:
for rec in fastatools.fasta_iter(file_object):
sequences[rec[0]] = rec[1]
for record in cds_coords:
whole = ""
for coords in cds_coords[record]['coords']:
seqid = cds_coords[record]['scaf']
if cds_coords[record]['strand'] == "-":
piece = fastatools.revcomp(
sequences[seqid][int(coords[0]) -
1:int(coords[1])]) ### watch for OBO
else:
piece = sequences[seqid][int(coords[0]) -
1:int(coords[1])] ### watch for OBO
whole += piece
else:
sys.stdout.write(">" + record + "_CDS\n" + whole + "\n")
args = parser.parse_args()
oldsqn = args.OldFASTA
if args.NewFASTA:
newsqn = args.NewFASTA
# read in old scaffs with sqn as key and id as value
# then read in new scaffs and compare sqn to keys and write out old and new ids upon match
# or, if only one FASTA given, output unique sequences
seqdict = {}
collisions = open("collisions.txt","w")
with open(oldsqn,"r") as infile:
for rec in fasta_iter(infile):
seqid = rec[0]
sqn = rec[1]
if sqn in seqdict:
print >> collisions, "Collision between " + seqid + " AND previously added " + seqdict[sqn]
else:
seqdict[sqn] = seqid
collisions.close()
if args.NewFASTA:
print "OldID\tNewID"
with open(newsqn,"r") as infile:
for rec in fasta_iter(infile):
seqid = rec[0]
sqn = rec[1]