def import_fasta(fastaFile):
seqDict = fol.blast_dict(fastaFile)
longList = fol.one_line_d(fastaFile).keys()
descDict = {}
lenDict = {}
for header in seqDict.keys():
lenDict[header] = len(seqDict[header])
for header in longList:
parts = header.rstrip("\n").lstrip(">").split(" ")
descDict[parts[0]] = " ".join(parts[1:])
return lenDict, descDict, seqDict
import Fasta_one_line as fol
seqDict = fol.one_line_d("ncbi_plasmid.fna")
outfile = open("Plasmid_lengths.txt", 'w')
outfile.write("locus\tlength\n")
for header in seqDict.keys():
locus = header.split("|")[1].split(".")[0]
outfile.write("{}\t{}\n".format(locus, len(seqDict[header])))
outfile.close()
import Fasta_one_line as fol
infile = open("transposase_clusters.txt", 'r')
fasta = fol.blast_dict(
"/work/mpesesky/Plasmids/NCBI_Plasmids/taxonAnalysis/transposases.faa")
used_families = []
for line in infile:
nodes = line.rstrip().split("\t")
clusterName = nodes[0]
if clusterName in used_families:
print(clusterName)
exit()
outfileName = clusterName + ".faa"
outfile = open(outfileName, 'w')
for node in nodes[1:]:
if "|" not in node:
continue
if node.startswith("ref"):
nodeName = node
else:
nodeName = "ref|{}|".format(node.split("|")[1])
try:
seq = fasta[nodeName]
except KeyError:
print(nodeName)
exit()
outfile.write(">{}\n{}\n".format(nodeName, seq))
from Bio import SeqIO
import Fasta_one_line as Fol
import argparse
parser = argparse.ArgumentParser(
description="Remove plasmids by accession prefix")
parser.add_argument("Infile")
parser.add_argument("Outfile")
args = parser.parse_args()
if args.Infile.endswith("fna"):
outfile = open(args.Outfile, 'w')
seqs = Fol.one_line_d(args.Infile)
for header in seqs.keys():
if ("NC_" in header) or ("NZ_" in header):
outfile.write("{}\n{}\n".format(header, seqs[header]))
outfile.close()
elif args.Infile.endswith("gbff"):
outlist = []
records = SeqIO.parse(args.Infile, 'genbank')
for record in records:
if record.id.startswith("NC_") or record.id.startswith("NZ_"):
outlist.append(record)
SeqIO.write(outlist, args.Outfile, "genbank")
else:
print("Extension not recognized")
"--binSize",
metavar="S",
type=float,
default=10,
help="Set bin size (must also set max)")
args = parser.parse_args()
if args.binMax == 0:
binBoundaries = args.bins
else:
binBoundaries = np.arange(args.binMin, args.binMax, args.binSize)
df = pd.read_table(args.BLASTFile, sep="\t")
fastaDict = fol.one_line_d(args.FastaFile)
trans = import_genes(args.TransposaseFile)
abres = import_genes(args.AbresFile)
lenDict = seq_lens(fastaDict)
shortDF = full_len_filter(lenDict, df)
countDF = pd.DataFrame(shortDF.groupby('qseqid').size(),
columns=['Occurrences'])
countDF['qseqid'] = countDF.index
geneAddedDF = add_genes(countDF, transTable=trans, abresTable=abres)
#print(geneAddedDF[(geneAddedDF['Occurrences'].map(float) >= 100.0) & (geneAddedDF['Associated Genes'] != 'Transposase')])
def combine_fastas(fastaList):
fastaDict = {}
for fastaFile in fastaList:
fastaDict.update(fol.one_line_d(fastaFile))
return fastaDict
parser.add_argument("-w", "--width", default=0, help="Fix line length at 'width' characters")
parser.add_argument("-o", "--outfile", default=None, help="Output file")
parser.add_argument("-n", "--name", type=str, default=None, help="Name to add to headers")
parser.add_argument("-l", "--length", action='store_true', help="Print total number of nucleotides in fasta")
parser.add_argument("-s", "--stats", action='store_true', help="Print some basic stats on the fasta file(s)")
parser.add_argument("-t", "--trim", type=int, default=0, help="Remove seqs under given size")
args = parser.parse_args()
if args.fastas is None:
raise NoFasta("You must input at least one fasta")
if len(args.fastas) > 1:
fastaDict = combine_fastas(args.fastas)
else:
fastaDict = fol.one_line_d(args.fastas[0])
if args.trim > 0:
fastaDict = rem_short(fastaDict, args.trim)
if args.name is not None:
fastaDict = rename_headers(fastaDict, args.name)
if args.length:
seqLen = get_seq_len(fastaDict)
print("Cumulative Sequence Length: {}".format(seqLen))
if args.stats:
statDict = stats(fastaDict)
for key in statDict.keys():
print("{}: {}".format(key, statDict[key]))
regionDict = {}
for line in regionFile:
fields = line.split("\t")
newRegion = sfh.Region(fields[0], int(fields[1]), int(fields[2]),
args.length)
newRegion.numOccur = int(fields[4].rstrip("\n"))
if fields[0] in regionDict.keys():
regionDict[fields[0]].append(newRegion)
else:
regionDict[fields[0]] = [newRegion]
regionFile.close()
print(len(list(regionDict.keys())))
fastaDict = fol.one_line_d(args.FASTA)
for header in fastaDict.keys():
uid = header.lstrip(">").split(" ")[0]
if uid in regionDict:
for reg in regionDict[uid]:
reg.seq = fastaDict[header][(reg.start - 1):reg.stop]
outfile = open(args.outfile, 'w')
for plasmid in regionDict.keys():
for reg in regionDict[plasmid]:
outfile.write(">{}_{}_{}_numOccur:{}\n{}\n".format(
reg.uid, reg.start, reg.stop, reg.numOccur, reg.seq))
outfile.close()
if targetAnnotation.lower() in header.lower():
retDict[seqDict[header]] = header
invDict = {v: k for k, v in retDict.items()}
return invDict
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Subset a fasta file based on header keywords")
parser.add_argument("Fasta", help="Input fasta file")
parser.add_argument(
"Keyword",
type=str,
help="Word or phrase used to identify sequences to be collected.")
parser.add_argument("-o",
"--output",
default="subset.fna",
type=argparse.FileType('w'),
help="Output file name")
args = parser.parse_args()
inDict = fol.one_line_d(args.Fasta)
subDict = gather_seqs(inDict, args.Keyword)
for header in subDict.keys():
args.output.write("{}\n{}\n".format(header, subDict[header]))
args.output.close()