Prediction of B‐cell Linear Epitopes with a Combination of Support Vector Machine Classification and Amino Acid Propensity Identification

TLDR

Epitopes trigger B‑cell antibody production and T‑cell activation, and bioinformatics enables rapid prediction of such antigenic determinants. The study introduces LEPS, a B‑cell linear epitope predictor that integrates physicochemical propensity analysis with SVM classification. LEPS was evaluated on four datasets (AntiJen, HIV, PC, and AHP) by first selecting peptides with high physicochemical propensities as candidate epitopes, then classifying them with an SVM based on amino‑acid segment features. LEPS reduced the number of predicted epitopes, increased PPV, and outperformed four other systems with 72.52 % accuracy, 84.22 % specificity, 32.07 % PPV, and a 10.36 % Matthews correlation coefficient.

Abstract

Epitopes are antigenic determinants that are useful because they induce B‐cell antibody production and stimulate T‐cell activation. Bioinformatics can enable rapid, efficient prediction of potential epitopes. Here, we designed a novel B‐cell linear epitope prediction system called LEPS, Linear Epitope Prediction by Propensities and Support Vector Machine, that combined physico‐chemical propensity identification and support vector machine (SVM) classification. We tested the LEPS on four datasets: AntiJen, HIV, a newly generated PC, and AHP, a combination of these three datasets. Peptides with globally or locally high physicochemical propensities were first identified as primitive linear epitope (LE) candidates. Then, candidates were classified with the SVM based on the unique features of amino acid segments. This reduced the number of predicted epitopes and enhanced the positive prediction value (PPV). Compared to four other well‐known LE prediction systems, the LEPS achieved the highest accuracy (72.52%), specificity (84.22%), PPV (32.07%), and Matthews′ correlation coefficient (10.36%).