def test_peptides_from_varaints(self):
coding = {}
coding['NM_080751'] = MutationSyntax('NM_080751',2629,876,'c.2630C>T','p.Pro877Leu')
var = Variant('line0',0,20,2621905,'C','T',coding,True,False)
var.gene = 'TMC2'
ma = MartsAdapter(biomart="http://ensembl.org")
vars = [var, Variant("testInsertion", 2, 20, 2621899, "", "AAAAAA", {'NM_080751':MutationSyntax('NM_080751',2625,876,'c.2630C>T','p.Pro877Leu')}, True, False)]
test = Generator.generate_peptides_from_variants(vars, 9, ma, id_type=EIdentifierTypes.REFSEQ, peptides=None)
test2 = [x for x in test]
print(len(test2))
ts = list()
#using a tweaked generator that takes another sequence source if the sequence is too short in respect to the given variants
#in this case a newer/older sequence from mart in respect to what was given as reference in the annotation process
t = Generator.generate_transcripts_from_variants(vars, ma, id_type=EIdentifierTypes.REFSEQ)
ts = [x for x in t]
print(len(ts[0]))
p = Generator.generate_proteins_from_transcripts(ts, to_stop=True)
ps = [x for x in p]
e = Generator.generate_peptides_from_proteins(ps, 9)
es = [x for x in e]
print(len(es))
#print vars
print len(vars)
def setUp(self):
self.trid = "NM_001114377" # FOXP3
# self, id, type, chrom, genomePos, ref, obs, coding, isHomozygous,
# isSynonymous, metadata=None)
self.non_syn_hetero_snp = Variant("COSM1122493", VariationType.SNP, "X",
49111949, "G", "T",
{"NM_001114377": MutationSyntax( \
"NM_001114377", 756, 217, "", "")
}, False, False)
self.non_frame_shift_del = Variant("COSM1122495", VariationType.DEL, "X",
49113232, "CTT", "",
{"NM_001114377": MutationSyntax( \
"NM_001114377", 615, 205, "", "")
}, True, False)
self.syn_homo_snp = Variant("COSM1122494", VariationType.SNP, "X",
49112257, "C", "T",
{"NM_001114377": MutationSyntax( \
"NM_001114377", 653, 217, "", "")
}, False, True)
self.db_adapter = MartsAdapter(biomart="http://grch37.ensembl.org/biomart/martservice?query=")
def test_real_life_test(self):
mart = MartsAdapter(
biomart="http://grch37.ensembl.org/biomart/martservice?query=")
ano_path = os.path.join(os.path.dirname(inspect.getfile(Fred2)),
"Data/examples/test_annovar.out")
vars = read_annovar_exonic(ano_path)
peps = set(
map(
lambda x: str(x),
Generator.generate_peptides_from_variants(
vars, 9, mart, EIdentifierTypes.REFSEQ)))
peps_from_prot = set(
map(
str,
Generator.generate_peptides_from_proteins(
Generator.generate_proteins_from_transcripts(
Generator.generate_transcripts_from_variants(
vars, mart, EIdentifierTypes.REFSEQ)), 9)))
self.assertTrue(len(peps - peps_from_prot) == 0)
self.assertTrue(len(peps_from_prot - peps) == 0)
def main():
model = argparse.ArgumentParser(
description='Neoepitope prediction for TargetInsepctor.')
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',
'--vcf',
type=str,
default=None,
help='Path to the vcf input file')
model.add_argument(
'-t',
'--type',
type=str,
choices=["VEP", "ANNOVAR", "SNPEFF"],
default="VEP",
help=
'Type of annotation tool used (Variant Effect Predictor, ANNOVAR exonic gene annotation, SnpEff)'
)
model.add_argument('-p',
'--proteins',
type=str,
default=None,
help='Path to the protein ID input file (in HGNC-ID)')
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(
'-r',
'--reference',
type=str,
default='GRCh38',
help='The reference genome used for varinat annotation and calling.')
model.add_argument(
'-fINDEL',
'--filterINDEL',
action="store_true",
help='Filter insertions and deletions (including frameshifts)')
model.add_argument('-fFS',
'--filterFSINDEL',
action="store_true",
help='Filter frameshift INDELs')
model.add_argument('-fSNP',
'--filterSNP',
action="store_true",
help='Filter SNPs')
model.add_argument('-o',
'--output',
type=str,
required=True,
help='Path to the output file')
model.add_argument('-etk',
'--etk',
action="store_true",
help=argparse.SUPPRESS)
args = model.parse_args()
martDB = MartsAdapter(biomart=MARTDBURL[args.reference.upper()])
transcript_to_genes = {}
if args.vcf is None and args.proteins is None:
sys.stderr.write(
"At least a vcf file or a protein id file has to be provided.\n")
return -1
# if vcf file is given: generate variants and filter them if HGNC IDs ar given
if args.vcf is not None:
protein_ids = []
if args.proteins is not None:
with open(args.proteins, "r") as f:
for l in f:
l = l.strip()
if l != "":
protein_ids.append(l)
if args.type == "VEP":
variants = read_variant_effect_predictor(args.vcf,
gene_filter=protein_ids)
elif args.type == "SNPEFF":
variants = read_vcf(args.vcf)[0]
else:
variants = read_annovar_exonic(args.vcf, gene_filter=protein_ids)
variants = filter(lambda x: x.type != VariationType.UNKNOWN, variants)
if args.filterSNP:
variants = filter(lambda x: x.type != VariationType.SNP, variants)
if args.filterINDEL:
variants = filter(
lambda x: x.type not in [
VariationType.INS, VariationType.DEL, VariationType.FSDEL,
VariationType.FSINS
], variants)
if args.filterFSINDEL:
variants = filter(
lambda x: x.type not in
[VariationType.FSDEL, VariationType.FSINS], variants)
if not variants:
sys.stderr.write(
"No variants left after filtering. Please refine your filtering criteria.\n"
)
return -1
epitopes = filter(
lambda x: any(
x.get_variants_by_protein(tid)
for tid in x.proteins.iterkeys()),
generate_peptides_from_variants(variants, int(args.length), martDB,
EIdentifierTypes.ENSEMBL))
for v in variants:
for trans_id, coding in v.coding.iteritems():
if coding.geneID != None:
transcript_to_genes[trans_id] = coding.geneID
else:
transcript_to_genes[trans_id] = 'None'
#else: generate protein sequences from given HGNC IDs and than epitopes
else:
proteins = []
with open(args.proteins, "r") as f:
for l in f:
ensembl_ids = martDB.get_ensembl_ids_from_id(
l.strip(), type=EIdentifierTypes.HGNC)[0]
protein_seq = martDB.get_product_sequence(
ensembl_ids[EAdapterFields.PROTID])
if protein_seq is not None:
transcript_to_genes[ensembl_ids[
EAdapterFields.TRANSID]] = l.strip()
proteins.append(
Protein(
protein_seq,
gene_id=l.strip(),
transcript_id=ensembl_ids[EAdapterFields.TRANSID]))
epitopes = generate_peptides_from_proteins(proteins, int(args.length))
#read in allele list
alleles = read_lines(args.alleles, in_type=Allele)
result = EpitopePredictorFactory(args.method).predict(epitopes,
alleles=alleles)
with open(args.output, "w") as f:
alleles = result.columns
var_column = " Variants" if args.vcf is not None else ""
f.write("Sequence\tMethod\t" + "\t".join(a.name for a in alleles) +
"\tAntigen ID\t" + var_column + "\n")
for index, row in result.iterrows():
p = index[0]
method = index[1]
proteins = ",".join(
set([
transcript_to_genes[prot.transcript_id.split(":FRED2")[0]]
for prot in p.get_all_proteins()
]))
vars_str = ""
if args.vcf is not None:
vars_str = "\t" + "|".join(
set(
prot_id.split(":FRED2")[0] + ":" + ",".join(
repr(v)
for v in set(p.get_variants_by_protein(prot_id)))
for prot_id in p.proteins.iterkeys()
if p.get_variants_by_protein(prot_id)))
f.write(
str(p) + "\t" + method + "\t" + "\t".join("%.3f" % row[a]
for a in alleles) +
"\t" + proteins + vars_str + "\n")
if args.etk:
with open(args.output.rsplit(".", 1)[0] + "_etk.tsv", "w") as g:
alleles = result.columns
g.write("Alleles:\t" + "\t".join(a.name for a in alleles) + "\n")
for index, row in result.iterrows():
p = index[0]
proteins = " ".join(
set([
transcript_to_genes[prot.transcript_id.split(
":FRED2")[0]] for prot in p.get_all_proteins()
]))
g.write(
str(p) + "\t" + "\t".join("%.3f" % row[a]
for a in alleles) + "\t" +
proteins + "\n")
return 0
def main():
model = argparse.ArgumentParser(
description='Neoepitope protein fasta generation from variant vcf')
model.add_argument('-v',
'--vcf',
type=str,
default=None,
help='Path to the vcf input file')
model.add_argument(
'-t',
'--type',
type=str,
choices=["VEP", "ANNOVAR", "SnpEff"],
default="VEP",
help=
'Type of annotation tool used (Variant Effect Predictor, ANNOVAR exonic gene annotation, SnpEff)'
)
model.add_argument('-p',
'--proteins',
type=str,
default=None,
help='Path to the protein ID input file (in HGNC-ID)')
model.add_argument(
'-r',
'--reference',
type=str,
default='GRCh38',
help='The reference genome used for varinat annotation and calling.')
model.add_argument(
'-fINDEL',
'--filterINDEL',
action="store_true",
help='Filter insertions and deletions (including frameshifts)')
model.add_argument('-fFS',
'--filterFSINDEL',
action="store_true",
help='Filter frameshift INDELs')
model.add_argument('-fSNP',
'--filterSNP',
action="store_true",
help='Filter SNPs')
model.add_argument('-o',
'--output',
type=str,
required=True,
help='Path to the output file')
args = model.parse_args()
martDB = MartsAdapter(biomart=MARTDBURL[args.reference.upper()])
if args.vcf is None:
sys.stderr.write(
"At least a vcf file or a protein id file has to be provided.\n")
return -1
# if vcf file is given: generate variants and filter them if HGNC IDs ar given
if args.vcf is not None:
protein_ids = []
if args.proteins is not None:
with open(args.proteins, "r") as f:
for l in f:
l = l.strip()
if l != "":
protein_ids.append(l)
if args.type == "VEP":
variants = read_variant_effect_predictor(args.vcf,
gene_filter=protein_ids)
elif args.type == "SNPEFF":
variants = read_vcf(args.vcf)[0]
else:
variants = read_annovar_exonic(args.vcf, gene_filter=protein_ids)
if args.filterSNP:
variants = filter(lambda x: x.type != VariationType.SNP, variants)
if args.filterINDEL:
variants = filter(
lambda x: x.type not in [
VariationType.INS, VariationType.DEL, VariationType.FSDEL,
VariationType.FSINS
], variants)
if args.filterFSINDEL:
variants = filter(
lambda x: x.type not in
[VariationType.FSDEL, VariationType.FSINS], variants)
if not variants:
sys.stderr.write(
"No variants left after filtering. Please refine your filtering criteria.\n"
)
return -1
variants = filter(lambda x: x.type != VariationType.UNKNOWN, variants)
#generate transcripts
transcripts = generate_transcripts_from_variants(
variants, martDB, EIdentifierTypes.ENSEMBL)
#generate proteins
proteins = filter(
lambda x: any(
x.get_variants_by_protein(tid)
for tid in x.proteins.iterkeys()),
generate_proteins_from_transcripts(transcripts))
#write fasta file
with open(output, "w") as f:
for p in proteins:
f.write('>' + str(p.transcript_id) + '|' + str(p.vars) +
'_var_' + '\n')
f.write(str(p) + '\n')
else:
sys.stderr.write(
"At least a vcf file or a protein id file has to be provided.\n")
return -1
return 0
def main():
model = argparse.ArgumentParser(description='Neoepitope prediction for TargetInsepctor.')
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', '--vcf',
type=str,
default=None,
help='Path to the vcf input file'
)
model.add_argument(
'-t', '--type',
type=str,
choices=["VEP", "ANNOVAR", "SNPEFF"],
default="VEP",
help='Type of annotation tool used (Variant Effect Predictor, ANNOVAR exonic gene annotation, SnpEff)'
)
model.add_argument(
'-p','--proteins',
type=str,
default=None,
help='Path to the protein ID input file (in HGNC-ID)'
)
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(
'-r' ,'--reference',
type=str,
default='GRCh38',
help='The reference genome used for varinat annotation and calling.'
)
model.add_argument(
'-fINDEL' ,'--filterINDEL',
action="store_true",
help='Filter insertions and deletions (including frameshifts)'
)
model.add_argument(
'-fFS' ,'--filterFSINDEL',
action="store_true",
help='Filter frameshift INDELs'
)
model.add_argument(
'-fSNP' ,'--filterSNP',
action="store_true",
help='Filter SNPs'
)
model.add_argument(
'-o','--output',
type=str,
required=True,
help='Path to the output file'
)
model.add_argument(
'-etk','--etk',
action="store_true",
help=argparse.SUPPRESS
)
args = model.parse_args()
martDB = MartsAdapter(biomart=MARTDBURL[args.reference.upper()])
transcript_to_genes = {}
if args.vcf is None and args.proteins is None:
sys.stderr.write("At least a vcf file or a protein id file has to be provided.\n")
return -1
# if vcf file is given: generate variants and filter them if HGNC IDs ar given
if args.vcf is not None:
protein_ids = []
if args.proteins is not None:
with open(args.proteins, "r") as f:
for l in f:
l = l.strip()
if l != "":
protein_ids.append(l)
if args.type == "VEP":
variants = read_variant_effect_predictor(args.vcf, gene_filter=protein_ids)
elif args.type == "SNPEFF":
variants = read_vcf(args.vcf)[0]
else:
variants = read_annovar_exonic(args.vcf, gene_filter=protein_ids)
variants = filter(lambda x: x.type != VariationType.UNKNOWN, variants)
if args.filterSNP:
variants = filter(lambda x: x.type != VariationType.SNP, variants)
if args.filterINDEL:
variants = filter(lambda x: x.type not in [VariationType.INS,
VariationType.DEL,
VariationType.FSDEL,
VariationType.FSINS], variants)
if args.filterFSINDEL:
variants = filter(lambda x: x.type not in [VariationType.FSDEL, VariationType.FSINS], variants)
if not variants:
sys.stderr.write("No variants left after filtering. Please refine your filtering criteria.\n")
return -1
epitopes = filter(lambda x:any(x.get_variants_by_protein(tid) for tid in x.proteins.iterkeys()),
generate_peptides_from_variants(variants,
int(args.length), martDB, EIdentifierTypes.ENSEMBL))
for v in variants:
for trans_id,coding in v.coding.iteritems():
if coding.geneID!=None:
transcript_to_genes[trans_id] = coding.geneID
else:
transcript_to_genes[trans_id] = 'None'
#else: generate protein sequences from given HGNC IDs and than epitopes
else:
proteins = []
with open(args.proteins, "r") as f:
for l in f:
ensembl_ids = martDB.get_ensembl_ids_from_id(l.strip(), type=EIdentifierTypes.HGNC)[0]
protein_seq = martDB.get_product_sequence(ensembl_ids[EAdapterFields.PROTID])
if protein_seq is not None:
transcript_to_genes[ensembl_ids[EAdapterFields.TRANSID]] = l.strip()
proteins.append(Protein(protein_seq, gene_id=l.strip(), transcript_id=ensembl_ids[EAdapterFields.TRANSID]))
epitopes = generate_peptides_from_proteins(proteins, int(args.length))
#read in allele list
alleles = read_lines(args.alleles, in_type=Allele)
result = EpitopePredictorFactory(args.method).predict(epitopes, alleles=alleles)
with open(args.output, "w") as f:
alleles = result.columns
var_column = " Variants" if args.vcf is not None else ""
f.write("Sequence\tMethod\t"+"\t".join(a.name for a in alleles)+"\tAntigen ID\t"+var_column+"\n")
for index, row in result.iterrows():
p = index[0]
method = index[1]
proteins = ",".join(set([transcript_to_genes[prot.transcript_id.split(":FRED2")[0]] for prot in p.get_all_proteins()]))
vars_str = ""
if args.vcf is not None:
vars_str = "\t"+"|".join(set(prot_id.split(":FRED2")[0]+":"+",".join(repr(v) for v in set(p.get_variants_by_protein(prot_id)))
for prot_id in p.proteins.iterkeys()
if p.get_variants_by_protein(prot_id)))
f.write(str(p)+"\t"+method+"\t"+"\t".join("%.3f"%row[a] for a in alleles)+"\t"+proteins+vars_str+"\n")
if args.etk:
with open(args.output.rsplit(".",1)[0]+"_etk.tsv", "w") as g:
alleles = result.columns
g.write("Alleles:\t"+"\t".join(a.name for a in alleles)+"\n")
for index, row in result.iterrows():
p = index[0]
proteins = " ".join(set([transcript_to_genes[prot.transcript_id.split(":FRED2")[0]] for prot in p.get_all_proteins()]))
g.write(str(p)+"\t"+"\t".join("%.3f"%row[a] for a in alleles)+"\t"+proteins+"\n")
return 0