TABLE 2.

In silico analysis for peptide‐based therapeutic cancer vaccines

Year	Database	Method	Methodology	Website	Characteristics
1994	BIMAS	Experimental verification	A total of 154 peptides were combined together to generate a table containing 180 coefficients (20 amino acids x 9 positions), each of which represents the contribution of one particular amino acid residue at a specified position within the peptide to binding to HLA‐A2. Provides a predicted t1/2 of dissociation	http://www‐bimas.cit.nih.gov / molbio / hla_bind
1997	SYFPEITHI	Experimental verification	The algorithm takes into account a number of characteristics of both the HLA haplotype as well as the peptide of interest, and uses these data to provide a binding score	http:// /www.syfpeithi.de /
2000	IEDB	Experimental verification	The IEDB combined all published data associated with epitopes and a large scale of experimentally determined peptides	www.immuneepitope.org	IEDB could provide consistent and accurate data with improved interoperability
2002	RANKPEP	PSSM	The binding potential of any peptide sequence (query) to a given MHC molecule is linked to its similarity to a group of aligned peptides known to bind to that MHC	www.mifoundation.org/Tools/ rankpep.html
2005	NetCTL	Bioinformatics prediction	Integration the predictions of proteasomal cleavage, TAP transport efficiency and MHC class I affinity	http://www.cbs.dtu.dk/services/NetCTL
2008	NetMHC	PSSM	The software integrates affinity measurements of IEDB database and data of eluting ligands in SYFPEITHI database to train 55 MHC allele‐specific artificial neural networks and additional position‐specific scoring matrix (PSSM) of 67 HLA allele	http://www.cbs.dtu.dk/services/NetMHC.	The binding affinity measurements of 8‐, 10‐ and 11‐mer were predicted based on properties of 9‐mer
2009	PMBEC	PSSM	PMBEC is derived from the binding affinity data of combinatorial peptide mixtures to build up matrix properties of amino sequence		The software could compensate for missing information on specific residues in the training data
2015	ANN‐Hydr	Machine learning			Training on a relative hydrophobicity scale

Abbreviations: ANN, artificial neural network; BIMAS, bioinformatics and molecular analysis section; CTL, cytotoxic T lymphocyte; HLA, human leucocyte antigen; IEDB, the immune epitope database; MHC, major histocompatibility complex; PSSM, position‐specific scoring matrix; TAP, transporter associated with antigen processing.