Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method

By Bjoern Peters, Alessandro Sette. BMC Bioinformatics, 2005

562 citations recorded by the source corpus.

BackgroundMany processes in molecular biology involve the recognition of short sequences of nucleic-or amino acids, such as the binding of immunogenic peptides to major histocompatibility complex (MHC) molecules. From experimental data, a model of the sequence specificity of these processes can be constructed, such as a sequence motif, a scoring matrix or an artificial neural network. The purpose of these models is two-fold. First, they can provide a summary of experimental results, allowing for a deeper understanding of the mechanisms involved in sequence recognition. Second, such models can be used to predict the experimental outcome for yet untested sequences. In the past we reported the development of a method to generate such models called the Stabilized Matrix Method (SMM). This method has been successfully applied to predicting peptide binding to MHC molecules, peptide transport by the transporter associated with antigen presentation (TAP) and proteasomal cleavage of protein sequences.ResultsHerein we report the implementation of the SMM algorithm as a publicly available software package. Specific features determining the type of problems the method is most appropriate for are discussed. Advantageous features of the package are: (1) the output generated is easy to interpret, (2) input and output are both quantitative, (3) specific computational strategies to handle experimental noise are built in, (4) the algorithm is designed to effectively handle bounded experimental data, (5) experimental data from randomized peptide libraries and conventional peptides can easily be combined, and (6) it is possible to incorporate pair interactions between positions of a sequence.ConclusionMaking the SMM method publicly available enables bioinformaticians and experimental biologists to easily access it, to compare its performance to other prediction methods, and to extend it to other applications.

Subfields: Microbiology, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/1c51ac88df96d12086b46e764a833c1847b5a1ab

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Microbiology

In Molecular Biology

Citations in the corpus

The Immune Epitope Database and Analysis Resource in Epitope Discovery and Synthetic Vaccine Design (2017, background): “Machine learning approaches can develop a function that predicts affinity binding for a given peptide sequence (4, 5).”
IEDB-AR: immune epitope database—analysis resource in 2019 (2019, background): “0 Peters and Sette (26) Comblib sidney2008 1.”
High-order neural networks and kernel methods for peptide-MHC binding prediction (2015, background): “In Peters and Sette (2005), the peptide binding task was solved as a matrix-vector regression problem.”
NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets (2016, methodology): “Examples of the two types of prediction tools are (reflected by high performance in the IEDB weekly automated MHC class I benchmark [5]): allele-specific (NetMHC [6, 7], SMM [8, 9]) and pan-specific (NetMHCpan [2, 3], NetMHCcons [10]).”
Immune epitope database analysis resource (2012, background): “The first, SMM (2) is an improvement of the SMM scoring matrix-based predictor (3).”
Immunotherapy of non-Hodgkin lymphoma with a defined ratio of CD8+ and CD4+ CD19-specific chimeric antigen receptor-modified T cells (2016, unknown): “Predictions of major histocompatibility complex class I binding by peptides shared between the candidate pools were made using the Immune Epitope Database and Analysis Resource Consensus tool (32), which combines predictions from NetMHC (3.4) (33, 34), SMM (35), and Comblib (36).”
A Systematic Assessment of MHC Class II Peptide Binding Predictions and Evaluation of a Consensus Approach (2008, methodology): “For example, when SMM [44] was applied to predict epitopes for several MHC class I molecules, it achieved an average AUC of 0.874, which is substantially higher than that for class II (0.783).”
In silico SARS-CoV-2 vaccine development for Omicron strain using reverse vaccinology (2022, unknown): “ 2003, 2007; Peters and Sette 2005; Sturniolo et al.”
A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction (2020, methodology): “In order for the final predictions to be represented with a normal distribution and to fit the experimental data well [75], the IC50 value of an aminoacid aa attheresidueposition pos foragiven MHC allotype was log transformed to approximate the relative binding energy contribution as follows: where…”