def predict(self, df, mutation_window_size = None):
"""
Given a dataframe of mutated amino acid sequences, run each sequence
through NetMHCpan.
If mutation_window_size is not None then only make predictions for that
number residues away from mutations.
Expects the input DataFrame to have the following fields:
- SourceSequence
- MutationStart
- MutationEnd
- GeneInfo
- Gene
- GeneMutationInfo
- PeptideMutationInfo
- TranscriptId
"""
input_filename, peptide_entries = create_input_fasta_file(
df,
mutation_window_size=mutation_window_size
)
alleles_str = \
",".join(allele.replace("*", "") for allele in self.alleles)
output_file = tempfile.NamedTemporaryFile(
"r+",
prefix="netMHCpan_output",
delete=False)
command = [
self.netmhc_command,
"-xls",
"-xlsfile", output_file.name,
"-l", "9",
"-f", input_filename,
"-a", alleles_str]
print " ".join(command)
with CleanupFiles(
filenames = [input_filename],
files = [output_file]):
run_command(command)
results = parse_xls_file(
output_file.read(),
peptide_entries,
mutation_window_size=mutation_window_size)
assert len(results) > 0, "No epitopes from netMHCpan"
return pd.DataFrame.from_records(results)
def predict(self, df, mutation_window_size=None):
"""
Given a dataframe of mutated amino acid sequences, run each sequence
through NetMHCpan.
If mutation_window_size is not None then only make predictions for that
number residues away from mutations.
Expects the input DataFrame to have the following fields:
- SourceSequence
- MutationStart
- MutationEnd
- GeneInfo
- Gene
- GeneMutationInfo
- PeptideMutationInfo
- TranscriptId
"""
input_filename, peptide_entries = create_input_fasta_file(
df, mutation_window_size=mutation_window_size)
alleles_str = \
",".join(allele.replace("*", "") for allele in self.alleles)
output_file = tempfile.NamedTemporaryFile("r+",
prefix="netMHCpan_output",
delete=False)
command = [
self.netmhc_command, "-xls", "-xlsfile", output_file.name, "-l",
"9", "-f", input_filename, "-a", alleles_str
]
print " ".join(command)
with CleanupFiles(filenames=[input_filename], files=[output_file]):
run_command(command)
results = parse_xls_file(output_file.read(),
peptide_entries,
mutation_window_size=mutation_window_size)
assert len(results) > 0, "No epitopes from netMHCpan"
return pd.DataFrame.from_records(results)
def predict(self, df, mutation_window_size = None):
"""
Given a dataframe of mutated amino acid sequences, run each sequence
through NetMHCcons.
If mutation_window_size is not None then only make predictions for that
number residues away from mutations.
Expects the input DataFrame to have the following fields:
- SourceSequence
- MutationStart
- MutationEnd
- GeneInfo
- Gene
- GeneMutationInfo
- PeptideMutationInfo
- TranscriptId
"""
input_filename, peptide_entries = create_input_fasta_file(
df,
mutation_window_size=mutation_window_size
)
output_files = {}
commands = {}
dirs = []
for i, allele in enumerate(self.alleles):
temp_dirname = tempfile.mkdtemp(prefix="tmp_netmhccons_")
logging.info("Created temporary directory %s for allele %s",
allele,
temp_dirname
)
dirs.append(temp_dirname)
output_file = tempfile.NamedTemporaryFile(
"w",
prefix="netMHCcons_output_%d" % i,
delete=False)
command = [
self.netmhc_command,
"-length", "9",
"-f", input_filename,
"-a", allele,
'-tdir', temp_dirname]
commands[output_file] = command
results = []
# Cleanup either when finished or if an exception gets raised by
# deleting the input and output files
filenames_to_delete = [input_filename]
for f in output_files.keys():
filenames_to_delete.append(f.name)
with CleanupFiles(
filenames = filenames_to_delete,
directories = dirs):
run_multiple_commands_redirect_stdout(
commands, print_commands = True)
for output_file, command in commands.iteritems():
# closing/opening looks insane
# but I was getting empty files otherwise
output_file.close()
with open(output_file.name, 'r') as f:
rows = parse_netmhc_stdout(
f.read(),
peptide_entries,
mutation_window_size=mutation_window_size)
results.extend(rows)
assert len(results) > 0, "No epitopes from netMHCcons"
df = pd.DataFrame.from_records(results)
unique_alleles = set(df.Allele)
assert len(unique_alleles) == len(self.alleles), \
"Expected %d alleles (%s) but got %d (%s)" % (
len(self.alleles), self.alleles,
len(unique_alleles), unique_alleles
)
return df
