def break_contigs(contigs_file, sam_file, output_file):
contigs = list(SeqIO.parse(open(contigs_file, "rU"), "fasta"))
# sam = sam_parser.SamChain([sam_parser.Samfile(sam_file) for sam_file in sam_files])
sam = sam_parser.Samfile(sam_file)
# last two arguments: K, min0 stretch length to break
coverage_breaker = break_by_coverage.ContigBreaker(contigs, sam, 100, 50)
coverage_breaker.OutputBroken(output_file)
def collect_contigs(dataset, output_dir, output_base, format):
output = open(output_base + "." + format, "w")
for barcode in dataset:
file = os.path.join(output_dir, barcode.id, "truseq_long_reads." + format)
if os.path.exists(file):
contigs = SeqIO.parse(open(file), format)
for contig in contigs:
contig.id = barcode.id + "-" + contig.id
SeqIO.write(contig, output, format)
output.close()
def collect_contigs(dataset, barcodes_dir, output_base, format):
output = open(output_base + "." + format, "w")
for barcode in dataset:
file = os.path.join(barcodes_dir, barcode.id,
"truseq_long_reads." + format)
if os.path.exists(file):
contigs = SeqIO.parse(open(file), format)
for contig in contigs:
contig.id = barcode.id + "-" + contig.id
SeqIO.write(contig, output, format)
output.close()
def main():
# Params
parser = argparse.ArgumentParser()
parser.add_argument("--refseq_in", required=True, help="RefSeq fasta file", type=str)
parser.add_argument("--tss_in", required=True, help="RefSeq fasta file", type=str)
parser.add_argument("--wigs_in", required=True,
help="Term-Seq coverage file(s) (.wig), Must contain forward and reverse files", type=str)
parser.add_argument("--gff_out", required=True, help="GFF output file name for terminators", type=str)
parser.add_argument("--distance", required=True, help="Distance to look for terminator after a TSS", type=int)
args = parser.parse_args()
# ---------------------------
print("Loading sequence file...")
fasta_parsed = SeqIO.parse(glob.glob(args.refseq_in)[0], "fasta")
wig_files = glob.glob(args.wigs_in)
f_wigs_parsed, r_wigs_parsed = WM(wig_files, fasta_parsed).build_matrix()
accession = ""
# The following line is repeated due to the previous iterator exhaustion
fasta_parsed = SeqIO.parse(glob.glob(args.refseq_in)[0], "fasta")
for seq_record in fasta_parsed:
f_seq_str = str(seq_record.seq)
accession = seq_record.id
print(f_wigs_parsed[accession].to_string())
def moleculo_postprocessing(contigs_file, output_file, sam_files, log):
log.info("===== Starting postprocessing based on read alignment")
log.info("Processing scaffolds from " + contigs_file)
log.info("Using read alignments to break and filter scaffolds")
contigs = list(SeqIO.parse(open(contigs_file, "rU"), "fasta"))
sam = sam_parser.SamChain([sam_parser.Samfile(sam_file) for sam_file in sam_files])
generate_quality.GenerateQuality(contigs, sam)
pattern_filter = moleculo_filter_contigs.PatternContigFilter(contigs, sam, pattern, rc_pattern)
length_filter = moleculo_filter_contigs.ContigLengthFilter(1500)
coverage_breaker = break_by_coverage.ContigBreaker(contigs, sam, 100, 50)
pattern_breaker = break_by_coverage.PatternBreaker(pattern, rc_pattern, 150)
n_breaker = break_by_coverage.NBreaker(3)
result = SplitAndFilter(contigs, coverage_breaker, length_filter, n_breaker, pattern_breaker, pattern_filter)
OutputResults(output_file, "fasta", result)
OutputResults(output_file, "fastq", result)
log.info("===== Postprocessing finished. Results can be found in " + output_file + ".fastq")
def moleculo_postprocessing(contigs_file, output_file, sam_files, log):
log.info("===== Starting postprocessing based on read alignment")
log.info("Processing scaffolds from " + contigs_file)
log.info("Using read alignments to break and filter scaffolds")
contigs = list(SeqIO.parse(open(contigs_file, "rU"), "fasta"))
sam = sam_parser.SamChain(
[sam_parser.Samfile(sam_file) for sam_file in sam_files])
generate_quality.GenerateQuality(contigs, sam)
pattern_filter = moleculo_filter_contigs.PatternContigFilter(
contigs, sam, pattern, rc_pattern)
length_filter = moleculo_filter_contigs.ContigLengthFilter(1500)
coverage_breaker = break_by_coverage.ContigBreaker(contigs, sam, 100, 50)
pattern_breaker = break_by_coverage.PatternBreaker(pattern, rc_pattern,
150)
n_breaker = break_by_coverage.NBreaker(3)
result = SplitAndFilter(contigs, coverage_breaker, length_filter,
n_breaker, pattern_breaker, pattern_filter)
OutputResults(output_file, "fasta", result)
OutputResults(output_file, "fastq", result)
log.info("===== Postprocessing finished. Results can be found in " +
output_file + ".fastq")
import numpy
import SeqIO from Bio
clusters=[]
linkage_matrix = numpy.zeroes(num_records-1,4)
with open(filename, "r") as datafile:
records = list(SeqIO.parse(datafile, "fasta"))
num_records = len(records)
def init_clusters():
clusters=[list(range(num_records)))]
def split_cluster():
max_c = None
max_sum = -1
max_i=-1
max_j=-1
for c in clusters:
sum=0
max_di=-1
max_dj=-1
for i in range(len(c)):
for j in range(i + 1, len(c)):
d = get_distance(c[i],c[j])
if(d>max_d):
max_di = c[i]
max_dj = c[j]
sum= sum + d
if sum > max_sum:
l += len(ins[i][1])
last = ins[i][0]
i += 1
else:
if last < d[j][0]:
result.append(seq[last:d[j][0]])
l += d[j][0] - last
sys.stdout.write("Deletion: " + str(l) + " " + str(d[j][1]) +
"\n")
last = d[j][0] + d[j][1]
j += 1
result.append(seq[last:])
return "".join(result)
def Generate(input, output, numins, numdel):
reference = list(input)
result = "".join([ch.seq for ch in reference])
l = sum([len(ch) for ch in reference])
ins = GroupByChrom(GenerateInsertions(numins, result), reference)
d = GroupByChrom(GenerateDeletions(numdel, result), reference)
for ch_ins, ch_d, chrom in itertools.izip(ins, d, reference):
sys.stdout.write("Chromosome " + chrom.id + "\n")
rec = SeqIO.SeqRecord(Apply(chrom.seq, ch_ins, ch_d), chrom.id)
SeqIO.write(rec, output, "fasta")
if __name__ == '__main__':
Generate(SeqIO.parse(open(sys.argv[1], "r"), "fasta"),
open(sys.argv[2], "w"), int(sys.argv[3]), int(sys.argv[3]))
df['qstart'] = df['qstart'] - BUFFER #npwhere (column, change, column to apply), pybedtools?
if df['qstart'] <0:
df['qstart'] = 0
else:
pass
df.apply(Xbuffer)
df.apply(Ybuffer)
#rerank blast file by e value
df.sort_values(by=['evalue', 'bitscore'], ascending=[True, False])
#create new file for each blasted TE
file = open(TE'.fas', "w+")
for record in SeqIO.parse(INPUT, "fasta"):
TEfile = open(TE'.fas', "a+")
re.sub('__'(.*) '___', '#'\1'/', record.id)
record.id = 'CONSENSUS' + record.id
TEfile.write(record.id + '\n', "w+")
#add top 40 blast hits to the new file
n=0
while n <41:
if seqIO.record == df['qseqid']
TEfile.write(record.id, fasta, "a+") #write record,not record.id;
n += 1
else:
pass
#align with muscle
3/168: import SeqIO from Bio
3/169: from Bio import SeqIO
3/170: SeqIO
4/1: import sys
4/2:
from Bio import SeqIO
from Bio.Alphabet import DNAAlphabet
sprot = SeqIO.parse("uniprot_sprot.fasta", "fasta", DNAAlphabet)
4/3: len(sprot)
4/4: sprot
4/5:
from Bio import SeqIO
from Bio.Alphabet import ProteinAlphabet
sprot = SeqIO.parse("uniprot_sprot.fasta", "fasta", ProteinAlphabet())
4/6: sprot
4/7: len(sprot)
4/8:
from Bio import SeqIO
from Bio.Alphabet import ProteinAlphabet
sprot = SeqIO.parse("uniprot_sprot.fasta", "fasta")
4/9: sprot
4/10: len(sprot)
4/11: sprot
4/12:
from Bio import SeqIO
from Bio.Alphabet import ProteinAlphabet
sprot_raw = "uniprot_sprot.fasta"