def test_stream_fasta(self):
"""
Test streaming a fasta file
"""
fastafile = os.path.join(os.environ['HOME'], 'Dropbox/Metagenomics/51.hits_small.fa')
if os.path.exists(fastafile):
idline, seq = sequences.stream_fasta(fastafile)
self.assertEqual(idline, "aaa")
self.assertEqual(seq, 'GGG')
def test_stream_fasta(self):
"""
Test streaming a fasta file
"""
fastafile = os.path.join(os.environ['HOME'],
'Dropbox/Metagenomics/51.hits_small.fa')
if os.path.exists(fastafile):
idline, seq = sequences.stream_fasta(fastafile)
self.assertEqual(idline, "aaa")
self.assertEqual(seq, 'GGG')
def parse_fasta(fastafile, srr):
"""
Given the srr hash and the fasta file add the data from one to the other!
"""
for (seqid, seq) in sequences.stream_fasta(fastafile):
m=re.match('([^_]*)', seqid)
srrid=m.groups()[0]
if srrid in srr:
sys.stdout.write(">{} [country={}] [date={}] [lat_lon={}]\n{}\n".format(
seqid, srr[srrid][0], srr[srrid][1], srr[srrid][2], seq))
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Extract genotypes from metagenomes by concatenating matching sequences")
parser.add_argument('-f', help='fasta sequence alignment file', required=True)
parser.add_argument('-n', help='minimum number of sequences a genotype must be in (default = 1)', default=1, type=int)
parser.add_argument('-b', help='plot start position', type=int)
parser.add_argument('-e', help='plot end position', type=int)
parser.add_argument('-c', help='cutoff to print the values (e.g. 0.8)', type=float)
parser.add_argument('-p', help='make the plot', action="store_true")
parser.add_argument('-a', help='print all results by base (the default is to sort the possibilities)', action="store_true")
args = parser.parse_args()
# to start we are just going to merge identical sequences
byseq = {}
for (seqid, seq) in sequences.stream_fasta(args.f):
seq = seq.upper() # make sure we have only upper case
seq = seq.strip() # strip of leading/trailing whitespace
#seq = seq.replace('N', '-') # remove any N's in the sequence
seq = replace_leading_trailing(seq)
seq = seq.rstrip('-') # remove all the trailing -s
keep_seq = True
for k in seq:
if k not in bases and k != "-":
if keep_seq:
sys.stderr.write("Skipped {} becuase it has base {}\n".format(seqid, k))
keep_seq = False
if not keep_seq:
continue
"""
Stream a fasta file and print it out
"""
import os
import sys
import argparse
from roblib import sequences
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="stream the contents of a fasta file")
parser.add_argument('-f', help='file to stream', required=True)
args = parser.parse_args()
for (seqid, seq) in sequences.stream_fasta(args.f):
print("{}\t{}".format(seqid, seq))
return all_genotypes
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Generate a collectors curve of kmer profiles from a directory of alignment files")
parser.add_argument('-d', help='directory of files to use')
args = parser.parse_args()
existing = []
current_file_no = 0
for aln_file in os.listdir(args.d):
# sys.stderr.write("{}\t{}\n".format(current_file_no, aln_file))
current_file_no += 1
seqs = []
seqids = []
for sid, sq in sequences.stream_fasta(os.path.join(args.d, aln_file)):
seqids.append(sid)
seqs.append(sq)
newresults = [set() for x in seqs[0]]
if not existing:
existing = [set() for x in seqs[0]]
newresults = average_genotype_frequency(seqs, newresults, 10, 2, False)
new_genotypes = []
for i in range(len(newresults)):
new = 0
for kmer in newresults[i]:
if kmer not in existing[i]:
existing[i].add(kmer)
new += 1
if new > 0:
new_genotypes.append(new)
if snps > 0:
all_genotypes.append(snps)
sites += 1
sys.stdout.write("Alignment length: {} Informative kmers: {} ".format(len(seqs[0]), sites))
if sites == 0:
print("Average number of genotypes: 1")
else:
print("Average number of genotypes: {}".format(1.0 * sum(all_genotypes) / len(all_genotypes)))
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Calculate the average number of SNPs at informative sites")
parser.add_argument('-a', help='Alignment file in fasta format')
parser.add_argument('-s', help='Count SNPs', action='store_true')
parser.add_argument('-g', help='Count genotypes', action='store_true')
parser.add_argument('-k', help='k-mer size to estimate genotypes. Default=10', default=10, type=int)
parser.add_argument('-m', help='minimum number of reads for site to be informative', default=2, type=int)
args = parser.parse_args()
seqids = []
seqs = []
for rid, seq in sequences.stream_fasta(args.a):
seqids.append(rid)
seqs.append(seq)
if args.s:
average_snp_frequency(seqs, min_num_reads=args.m)
if args.g:
average_genotype_frequency(seqs, kmer=args.k, min_num_reads=args.m)