def main():
#Specify CTD interface
# Every CTD Model has to have at least a name and a version, plus any of the optional attributes below them.
model = argparse.ArgumentParser(
description='Commandline tool for cleavage site prediction', )
model.add_argument(
'-m',
'--method',
type=str,
choices=CleavageSitePredictorFactory.available_methods().keys(),
default="pcm",
help='The name of the prediction method')
model.add_argument('-v',
'--version',
type=str,
default="",
help='The version of the prediction method')
model.add_argument('-i',
'--input',
type=str,
required=True,
help='Path to the input file (in fasta format)')
model.add_argument('-l',
'--length',
type=int,
default=0,
help='The length of peptides')
model.add_argument(
'-op',
'--options',
type=str,
default="",
help="Additional options that get directly past to the tool")
model.add_argument('-o',
'--output',
type=str,
required=True,
help='Path to the output file')
args = model.parse_args()
#fasta protein
peptides = read_fasta(args.input, in_type=Protein)
if args.version == "":
predictor = CleavageSitePredictorFactory(args.method)
result = predictor.predict(peptides, options=args.method)
else:
predictor = CleavageSitePredictorFactory(args.method,
version=args.version)
result = predictor.predict(peptides, options=args.method)
#if length is specified, than generate compact output
if int(args.length) > 0:
length = int(args.length)
with open(args.output, "w") as f:
f.write("Sequence\tMethod\tScore\tProtein ID\tPosition\n")
for seq_id in set(result.index.get_level_values(0)):
seq = "".join(result.ix[seq_id]["Seq"])
for start in xrange(len(seq) - (length - 1)):
pep_seq = seq[start:(start + length)]
score = result.loc[(seq_id, start + (length - 1)),
predictor.name]
f.write(pep_seq + "\t" + predictor.name + "\t" +
"%.3f" % score + "\t" + seq_id + "\t" +
str(start) + "\n")
else:
result.to_csv(args.output, float_format="%.3f", sep="\t")
return 0
def main():
model = argparse.ArgumentParser(
description='Commandline tool for TAP prediction',
)
model.add_argument('-m',
'--method',
type=str,
choices=TAPPredictorFactory.available_methods().keys(),
default="svmtap",
help='The name of the prediction method'
)
model.add_argument('-v',
'--version',
type=str,
default="",
help='The version of the prediction method'
)
model.add_argument('-i',
'--input',
type=str,
required=True,
help='Path to the input file'
)
model.add_argument('-t',
'--type',
choices=["fasta", "peptide"],
type=str,
default="fasta",
help='The data type of the input (fasta, peptide list)'
)
model.add_argument('-l',
'--length',
type=int,
default=9,
help='The length of peptides'
)
model.add_argument('-op',
'--options',
type=str,
default="",
help="Additional options that get directly past to the tool"
)
model.add_argument('-o',
'--output',
type=str,
required=True,
help='Path to the output file'
)
args = model.parse_args()
#fasta protein
if args.type == "fasta":
with open(args.input, 'r') as f:
first_line = f.readline()
sep_pos = 1 if first_line.count("|") else 0
proteins = read_fasta(args.input, in_type=Protein, id_position=sep_pos)
peptides = generate_peptides_from_proteins(proteins, int(args.length))
elif args.type == "peptide":
peptides = read_lines(args.input, in_type=Peptide)
else:
sys.stderr.write('Input type not known\n')
return -1
if args.version == "":
result = TAPPredictorFactory(args.method).predict(peptides, options=args.options)
else:
result = TAPPredictorFactory(args.method, version=args.version).predict(peptides, options=args.options)
#write to TSV columns sequence method score...,protein-id/transcript-id
with open(args.output, "w") as f:
proteins = "\tProtein ID" if args.type == "fasta" else ""
f.write("Sequence\tMethod\t"+"Score"+proteins+"\n")
for index, row in result.iterrows():
p = index
proteins = ",".join(prot.transcript_id for prot in p.get_all_proteins()) if args.type == "fasta" else ""
f.write(str(p)+"\t"+"\t".join("%s\t%.3f"%(method, score) for
method, score in row.iteritems())+"\t"+proteins+"\n")
return 0
# download the fasta file
if __name__ == "__main__":
arguments = docopt(__doc__)
PEPTIDE_LENGTH = 9
# get arguments
if arguments["--alleles"]:
alleles = arguments["--alleles"].split(",")
else:
alleles = None
file_in = arguments["--input"]
file_out = arguments["--output"]
print("read fasta")
proteins = read_fasta(file_in, id_position=0, in_type=Protein)
# restrict to only top N proteins if provided
if arguments["--top_N"]:
Nargs = int(arguments["--top_N"])
N = min(Nargs, len(proteins))
proteins = proteins[0:N]
# parse peptide/protein information from Peptide list and Protein list
print("setup peptide/protein information table")
peptides = generate_peptides_from_proteins(proteins, PEPTIDE_LENGTH)
peptides_list = [peptide for peptide in peptides]
proteins_list = [peptide.proteins.keys()[0] for peptide in peptides_list]
peptides_str_list = [peptide.tostring() for peptide in peptides_list]
peptides_position_list = [
peptide.proteinPos.items()[0][1][0] for peptide in peptides_list
def main():
#Specify CTD interface
# Every CTD Model has to have at least a name and a version, plus any of the optional attributes below them.
model = argparse.ArgumentParser(description='Process some integers.')
model.add_argument('-m',
'--method',
type=str,
choices=EpitopePredictorFactory.available_methods().keys(),
default="bimas",
help='The name of the prediction method'
)
model.add_argument('-v',
'--version',
type=str,
default="",
help='The version of the prediction method'
)
model.add_argument('-i',
'--input',
type=str,
required=True,
help='Path to the input file'
)
model.add_argument('-t',
'--type',
choices=["fasta","peptide"],
type=str,
default="fasta",
help='The data type of the input (fasta, peptide list)'
)
model.add_argument('-l',
'--length',
choices=range(8, 18),
type=int,
default=9,
help='The length of peptides'
)
model.add_argument('-a',
'--alleles',
type=str,
required=True,
help='Path to the allele file (one per line in new nomenclature)'
)
model.add_argument('-op',
'--options',
type=str,
default="",
help="Additional options that get directly past to the tool"
)
model.add_argument('-o',
'--output',
type=str,
required=True,
help='Path to the output file'
)
args = model.parse_args()
#fasta protein
if args.type == "fasta":
with open(args.input, 'r') as f:
first_line = f.readline()
sep_pos = 1 if first_line.count("|") else 0
proteins = read_fasta(args.input, in_type=Protein, id_position=sep_pos)
peptides = generate_peptides_from_proteins(proteins, args.length)
elif args.type == "peptide":
peptides = read_lines(args.input, in_type=Peptide)
else:
sys.stderr.write('Input type not known\n')
return -1
#read in alleles
alleles = read_lines(args.alleles, in_type=Allele)
if args.version == "":
result = EpitopePredictorFactory(args.method).predict(peptides, alleles, options=args.options)
else:
result = EpitopePredictorFactory(args.method, version=args.version).predict(peptides, alleles,
options=args.options)
#write to TSV columns sequence method allele-scores...,protein-id/transcript-id
with open(args.output, "w") as f:
proteins = "\tAntigen ID" if args.type == "fasta" else ""
alleles = result.columns
f.write("Sequence\tMethod\t"+"\t".join(a.name for a in alleles)+proteins+"\n")
for index, row in result.iterrows():
p = index[0]
method = index[1]
proteins = "\t"+",".join( prot.transcript_id for prot in p.get_all_proteins()) if args.type == "fasta" else ""
f.write(str(p)+"\t"+method+"\t"+"\t".join("%.3f"%row[a] for a in alleles)+proteins+"\n")
return 0
def main():
#Specify CTD interface
# Every CTD Model has to have at least a name and a version, plus any of the optional attributes below them.
model = argparse.ArgumentParser(
description='Commandline tool for cleavage site prediction',
)
model.add_argument('-m',
'--method',
type=str,
choices=CleavageSitePredictorFactory.available_methods().keys(),
default="pcm",
help='The name of the prediction method'
)
model.add_argument('-v',
'--version',
type=str,
default="",
help='The version of the prediction method'
)
model.add_argument('-i',
'--input',
type=str,
required=True,
help='Path to the input file (in fasta format)'
)
model.add_argument('-l',
'--length',
type=int,
default=0,
help='The length of peptides'
)
model.add_argument('-op',
'--options',
type=str,
default="",
help="Additional options that get directly past to the tool"
)
model.add_argument('-o',
'--output',
type=str,
required=True,
help='Path to the output file'
)
args = model.parse_args()
#fasta protein
peptides = read_fasta(args.input, in_type=Protein)
if args.version == "":
predictor = CleavageSitePredictorFactory(args.method)
result = predictor.predict(peptides, options=args.method)
else:
predictor = CleavageSitePredictorFactory(args.method, version=args.version)
result = predictor.predict(peptides, options=args.method)
#if length is specified, than generate compact output
if int(args.length) > 0:
length = int(args.length)
with open(args.output, "w") as f:
f.write("Sequence\tMethod\tScore\tProtein ID\tPosition\n")
for seq_id in set(result.index.get_level_values(0)):
seq = "".join(result.ix[seq_id]["Seq"])
for start in xrange(len(seq)-(length-1)):
pep_seq = seq[start:(start+length)]
score = result.loc[(seq_id, start+(length-1)), predictor.name]
f.write(pep_seq+"\t"+predictor.name+"\t"+"%.3f"%score+"\t"+seq_id+"\t"+str(start)+"\n")
else:
result.to_csv(args.output, float_format="%.3f", sep="\t")
return 0
