Fred2.EpitopePrediction Module¶

EpitopePrediction.External¶

class Fred2.EpitopePrediction.External.AExternalEpitopePrediction¶

Bases: Fred2.Core.Base.AEpitopePrediction, Fred2.Core.Base.AExternal

Abstract class representing an external prediction function. Implementations shall wrap external binaries by following the given abstraction.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts alleles into the internal allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The alleles for which the internal predictor representation is needed
Returns:	Returns a string representation of the input alleles
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from self.__command
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to _file in the specific format

NO return value!

Param:	list(str) _input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid allele models

supportedLength¶: A list of supported peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetCTLpan_1_1¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Interface for NetCTLpan 1.1.

Note

NetCTLpan - Pan-specific MHC class I epitope predictions Stranzl T., Larsen M. V., Lundegaard C., Nielsen M. Immunogenetics. 2010 Apr 9. [Epub ahead of print]

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHCII_2_2¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implements a wrapper for NetMHCII

Note

Nielsen, M., & Lund, O. (2009). NN-align. An artificial neural network-based alignment algorithm for MHC class II peptide binding prediction. BMC Bioinformatics, 10(1), 296.

Nielsen, M., Lundegaard, C., & Lund, O. (2007). Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method. BMC Bioinformatics, 8(1), 238.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to _file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHCIIpan_3_0¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implements a wrapper for NetMHCIIpan.

Note

Andreatta, M., Karosiene, E., Rasmussen, M., Stryhn, A., Buus, S., & Nielsen, M. (2015). Accurate pan-specific prediction of peptide-MHC class II binding affinity with improved binding core identification. Immunogenetics, 1-10.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to _file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHCIIpan_3_1¶

Bases: Fred2.EpitopePrediction.External.NetMHCIIpan_3_0

Implementation of NetMHCIIpan 3.1 adapter.

Note

Andreatta, M., Karosiene, E., Rasmussen, M., Stryhn, A., Buus, S., & Nielsen, M. (2015). Accurate pan-specific prediction of peptide-MHC class II binding affinity with improved binding core identification. Immunogenetics, 1-10.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to _file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHC_3_0¶

Bases: Fred2.EpitopePrediction.External.NetMHC_3_4

Implements the NetMHC binding (for netMHC3.0):

.. note::

NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8-11. Lundegaard C, Lamberth K, Harndahl M, Buus S, Lund O, Nielsen M. Nucleic Acids Res. 1;36(Web Server issue):W509-12. 2008

Accurate approximation method for prediction of class I MHC affinities for peptides of length 8, 10 and 11 using prediction tools trained on 9mers. Lundegaard C, Lund O, Nielsen M. Bioinformatics, 24(11):1397-98, 2008.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	dict

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

NO return value!

Param:	list(str) input: The : sequences to write into _file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHC_3_4¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implements the NetMHC binding (in current form for netMHC3.4).

Note

NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8-11. Lundegaard C, Lamberth K, Harndahl M, Buus S, Lund O, Nielsen M. Nucleic Acids Res. 1;36(Web Server issue):W509-12. 2008

Accurate approximation method for prediction of class I MHC affinities for peptides of length 8, 10 and 11 using prediction tools trained on 9mers. Lundegaard C, Lund O, Nielsen M. Bioinformatics, 24(11):1397-98, 2008.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	dict

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

NO return value!

Param:	list(str) input: The : sequences to write into _file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHC_4_0¶

Bases: Fred2.EpitopePrediction.External.NetMHC_3_4

Implements the NetMHC 4.0 binding

Note

Andreatta M, Nielsen M. Gapped sequence alignment using artificial neural networks: application to the MHC class I system. Bioinformatics (2016) Feb 15;32(4):511-7

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

NO return value!

Param:	list(str) input: The : sequences to write into _file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHCpan_2_4¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implements the NetMHC binding (in current form for netMHCpan 2.4). Supported MHC alleles currently only restricted to HLA alleles.

Note

Nielsen, Morten, et al. “NetMHCpan, a method for quantitative predictions of peptide binding to any HLA-A and-B locus protein of known sequence.” PloS one 2.8 (2007): e796.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

NO return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHCpan_2_8¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implements the NetMHC binding (in current form for netMHCpan 2.8). Supported MHC alleles currently only restricted to HLA alleles.

Note

Nielsen, Morten, et al. “NetMHCpan, a method for quantitative predictions of peptide binding to any HLA-A and-B locus protein of known sequence.” PloS one 2.8 (2007): e796.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.External.NetMHCpan_3_0¶

Bases: Fred2.EpitopePrediction.External.NetMHCpan_2_8

Implements the NetMHC binding version 3.0 Supported MHC alleles currently only restricted to HLA alleles.

Note

Nielsen, M., & Andreatta, M. (2016). NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets. Genome Medicine, 8(1), 1.

command¶

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of valid Allele models

supportedLength¶: A list of supported Peptide lengths

version¶

class Fred2.EpitopePrediction.External.NetMHCstabpan_1_0¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implements a wrapper to NetMHCstabpan 1.0

Pan-specific prediction of peptide-MHC-I complex stability; a correlate of T cell immunogenicity M Rasmussen, E Fenoy, M Nielsen, Buus S, Accepted JI June, 2016

command¶

convert_alleles(alleles)¶

Converts Allele into the internal allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `self.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

NO return value!

Param:	list(str) input: The `Peptide` sequences to write into file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶

supportedLength¶

version¶

class Fred2.EpitopePrediction.External.PickPocket_1_1¶

Bases: Fred2.EpitopePrediction.External.AExternalEpitopePrediction

Implementation of PickPocket adapter.

Note

Zhang, H., Lund, O., & Nielsen, M. (2009). The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: application to MHC-peptide binding. Bioinformatics, 25(10), 1293-1299.

command¶: Defines the commandline call for external tool

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (`Allele`) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

get_external_version(path=None)¶

Returns the external version of the tool by executing >{command} –version

might be dependent on the method and has to be overwritten therefore it is declared abstract to enforce the user to overwrite the method. The function in the base class can be called with super()

Parameters:	path (str) – Optional specification of executable path if deviant from `elf.__command`
Returns:	The external version of the tool or None if tool does not support versioning
Return type:	str

is_in_path()¶

Checks whether the specified execution command can be found in PATH

Returns:	Whether or not command could be found in PATH
Return type:	bool

name¶: The name of the predictor

parse_external_result(file)¶

Parses external results and returns the result

Parameters:	file (str) – The file path or the external prediction results
Returns:	A dictionary containing the prediction results
Return type:	dict

predict(peptides, alleles=None, command=None, options=None, **kwargs)¶

Overwrites AEpitopePrediction.predict

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A list of or a single `Peptide` object alleles (list(`Allele`)/`Allele`) – A list of or a single `Allele` object. If no `Allele` are provided, predictions are made for all `Allele` supported by the prediction method command (str) – The path to a alternative binary (can be used if binary is not globally executable) options (str) – A string of additional options directly past to the external tool. chunksize – denotes the chunksize in which the number of peptides are bulk processed
Returns:	A `EpitopePredictionResult` object
Return type:	`EpitopePredictionResult`

prepare_input(input, file)¶

Prepares input for external tools and writes them to file in the specific format

No return value!

Param:	list(str) input: The `Peptide` sequences to write into _file
Parameters:	file (File) – File-handler to input file for external tool

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

EpitopePrediction.PSSM¶

class Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction¶

Bases: Fred2.Core.Base.AEpitopePrediction

Abstract base class for PSSM predictions. Implements predict functionality

convert_alleles(alleles)¶

Converts alleles into the internal allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The alleles for which the internal predictor representation is needed
Returns:	Returns a string representation of the input alleles
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of valid allele models

supportedLength¶: A list of supported peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.ARB¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Implements IEDBs ARB method.

Note

Bui HH, Sidney J, Peters B, Sathiamurthy M, Sinichi A, Purton KA, Mothe BR, Chisari FV, Watkins DI, Sette A. 2005. Automated generation and evaluation of specific MHC binding predictive tools: ARB matrix applications. Immunogenetics 57:304-314.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.BIMAS¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Represents the BIMAS PSSM predictor.

Note

Parker, K.C., Bednarek, M.A. and Coligan, J.E. Scheme for ranking potential HLA-A2 binding peptides based on independent binding of individual peptide side-chains. The Journal of Immunology 1994;152(1):163-175.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.CalisImm¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Implements the Immunogenicity propensity score proposed by Calis et al.

..note:

Calis, Jorg JA, et al.(2013). Properties of MHC class I presented peptides that enhance immunogenicity. PLoS Comput Biol 9.10 e1003266.

convert_alleles(alleles)¶

Converts alleles into the internal allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The alleles for which the internal predictor representation is needed
Returns:	Returns a string representation of the input alleles
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` kwargs – optional parameter (not used yet)
Returns:	Returns a `pandas.DataFrame` object with the prediction results
Return type:	`pandas.DataFrame`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.ComblibSidney2008¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Implements IEDBs Comblib_Sidney2008 PSSM method.

Note

Sidney J, Assarsson E, Moore C, Ngo S, Pinilla C, Sette A, Peters B. 2008. Quantitative peptide binding motifs for 19 human and mouse MHC class I molecules derived using positional scanning combinatorial peptide libraries. Immunome Res 4:2.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.Epidemix¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Represents the Epidemix PSSM predictor.

Note

Feldhahn, M., et al. FRED-a framework for T-cell epitope detection. Bioinformatics 2009;25(20):2758-2759.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.Hammer¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Represents the virtual pockets approach by Sturniolo et al.

Note

Sturniolo, T., et al. Generation of tissue-specific and promiscuous HLA ligand databases using DNA microarrays and virtual HLA class II matrices. Nature biotechnology 1999;17(6):555-561.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.SMM¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Implements IEDBs SMM PSSM method.

Note

Peters B, Sette A. 2005. Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method. BMC Bioinformatics 6:132.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.SMMPMBEC¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Implements IEDBs SMMPMBEC PSSM method.

Note

Kim, Y., Sidney, J., Pinilla, C., Sette, A., & Peters, B. (2009). Derivation of an amino acid similarity matrix for peptide: MHC binding and its application as a Bayesian prior. BMC Bioinformatics, 10(1), 394.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.Syfpeithi¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Represents the Syfpeithi PSSM predictor.

Note

Rammensee, H. G., Bachmann, J., Emmerich, N. P. N., Bachor, O. A., & Stevanovic, S. (1999). SYFPEITHI: database for MHC ligands and peptide motifs. Immunogenetics, 50(3-4), 213-219.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.PSSM.TEPITOPEpan¶

Bases: Fred2.EpitopePrediction.PSSM.APSSMEpitopePrediction

Implements TEPITOPEpan.

Note

TEPITOPEpan: Extending TEPITOPE for Peptide Binding Prediction Covering over 700 HLA-HLA-DR Molecules Zhang L, Chen Y, Wong H-S, Zhou S, Mamitsuka H, et al. (2012) TEPITOPEpan: Extending TEPITOPE for Peptide Binding Prediction Covering over 700 HLA-HLA-DR Molecules. PLoS ONE 7(2): e30483.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an Allele. If no Allele are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or class:~Fred2.Core.Allele.Allele) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

EpitopePrediction.SVM¶

class Fred2.EpitopePrediction.SVM.ASVMEpitopePrediction¶

Bases: Fred2.Core.Base.AEpitopePrediction, Fred2.Core.Base.ASVM

Implements default prediction routine for SVM based epitope prediction tools

convert_alleles(alleles)¶

Converts alleles into the internal allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The alleles for which the internal predictor representation is needed
Returns:	Returns a string representation of the input alleles
Return type:	list(str)

encode(peptides)¶

Returns the feature encoding for peptides

Parameters:	peptides (list(`Peptide`)/`Peptide`) – List of or a single `Peptide` object
Returns:	Feature encoding of the Peptide objects
Return type:	list(Object)

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an alleles. If no alleles are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or `Allele`) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of valid allele models

supportedLength¶: A list of supported peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.SVM.SVMHC¶

Bases: Fred2.EpitopePrediction.SVM.ASVMEpitopePrediction

Implements SVMHC epitope prediction for MHC-I alleles (SYFPEITHI models).

Note

Doennes, P. and Kohlbacher, O. SVMHC: a server for prediction of MHC-binding peptides. Nucleic Acids Res, 2006, 34, W194-W197

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

encode(peptides)¶

Encodes the input with binary sparse encoding of the Peptide

Parameters:	peptides (str) – A list of `Peptide` sequences
Returns:	Dictionary with `Peptide` as key and feature encoding as value (see svmlight encoding scheme http://svmlight.joachims.org/)
Return type:	dict(`Peptide`, (tuple(int, list(tuple(int,float))))

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an alleles. If no alleles are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or `Allele`) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

class Fred2.EpitopePrediction.SVM.UniTope¶

Bases: Fred2.EpitopePrediction.SVM.ASVMEpitopePrediction

Implements UniTope prediction for MHC-I.

Note

Toussaint, N. C., Feldhahn, M., Ziehm, M., Stevanovic, S., & Kohlbacher, O. (2011, August). T-cell epitope prediction based on self-tolerance. In Proceedings of the 2nd ACM Conference on Bioinformatics, Computational Biology and Biomedicine (pp. 584-588). ACM.

convert_alleles(alleles)¶

Converts Allele into the internal Allele representation of the predictor and returns a string representation

Parameters:	alleles (list(`Allele`)) – The `Allele` for which the internal predictor representation is needed
Returns:	Returns a string representation of the input `Allele`
Return type:	list(str)

encode(peptides, allele)¶

Encodes the input with binary sparse encoding of the Peptide

Parameters:	peptides (str) – A list of `Peptide` sequences allele (str) – The HLA `Allele` represented by a string
Returns:	Dictionary with `Peptide` as key and feature encoding as value (see svmlight encoding scheme http://svmlight.joachims.org/)
Return type:	dict(`Peptide`, (tuple(int, list(tuple(int,float))))`

name¶: The name of the predictor

predict(peptides, alleles=None, **kwargs)¶

Returns predictions for given peptides an alleles. If no alleles are given, predictions for all available models are made.

Parameters:	peptides (list(`Peptide`) or `Peptide`) – A single `Peptide` or a list of `Peptide` alleles (list(`Allele`) or `Allele`) – A list of `Allele` kwargs – optional parameter (not used yet)
Returns:	Returns a `EpitopePredictionResult` object with the prediction results
Return type:	`EpitopePredictionResult`

supportedAlleles¶: A list of supported Allele models

supportedLength¶: A list of supported Peptide lengths

version¶: The version of the predictor

Fred2.EpitopePrediction Module¶

EpitopePrediction.External¶

EpitopePrediction.PSSM¶

EpitopePrediction.SVM¶

Module contents¶