ME-p <i>K</i> _a : A Deep Learning Method with Multimodal Learning for Protein p <i>K</i> _a Prediction

Proteins are crucial in biological processes and are important substances that mediate biochemical reactions, regulate cellular processes, and facilitate drug binding through their active sites and surface residues. The p<i>K</i>_a values of proteins determine the protonation state of ionizable amino acids under specific pH conditions, profoundly impacting protein structure, function, and drug design. However, experimental determination of p<i>K</i>_a values is normally laborious and complex. Moreover, existing prediction methods are limited by the data quantity and quality, as well as their inability to address the intricate structural and physicochemical attributes of proteins, thereby hindering accuracy and generalization, especially in predicting p<i>K</i>_a values for buried residues. In this study, we developed a multimodal protein p<i>K</i>_a prediction model named ME-p<i>K</i>_a (Multimodal ESM p<i>K</i>_a), which leverages the multimodal information and employs a multifidelity learning strategy to speedily and accurately predict molecular p<i>K</i>_a values. The ME-p<i>K</i>_a method facilitates data augmentation by integrating the local environmental attributes of amino acids with the FASTA sequence characteristics of proteins. Furthermore, the incorporation of multifidelity learning has addressed the challenge of limited data availability to some extent. Our ME-p<i>K</i>_a model outperforms several state-of-the-art models in predicting protein p<i>K</i>_a values, achieving impressive results with a low RMSE of 0.845 ± 0.09 and MAE of 0.641 ± 0.07, a high <i>R</i>² of 0.921 ± 0.02, and R of 0.959 ± 0.01 on the PE-p<i>K</i>_a data set. Notably, ME-p<i>K</i>_a demonstrated balanced and robust performance across major ionizable residue types (ASP, GLU, HIS, LYS). It demonstrates superior accuracy in predicting p<i>K</i>_a values for buried residues (RSA < 0.2), achieving the lowest MAE values of 0.921 ± 0.05 on the PE-p<i>K</i>_a data set and 0.911 ± 0.06 on the Small Set data set, which collectively excel in capturing complex environmental influences on p<i>K</i>_a. Moreover, our method confirmed pH-dependent binding of PD-L1 antibodies mediated by the protonation state of His-69 in PD-L1, emphasizing the critical role of amino acid protonation states in drug design. The source code of ME-p<i>K</i>_a can be found at https://github.com/yzjyg215/ME-pKa.