Accurate and Rapid Prediction of Protein p <i>K</i> _a : Protein Language Models Reveal the Sequence–p <i>K</i> _a Relationship

Protein p<i>K</i>_a prediction is a key challenge in computational biology. In this study, we present pKALM, a novel deep learning-based method for high-throughput protein p<i>K</i>_a prediction. pKALM uses a protein language model (PLM) to capture the complex sequence-structure relationships of proteins. While traditionally considered a structure-based problem, our results show that a PLM pretrained on large-scale protein sequence databases can effectively learn this relationship and achieve state-of-the-art performance. pKALM accurately predicts the p<i>K</i>_a values of six residues (Asp, Glu, His, Lys, Cys, and Tyr) and two termini with high precision and efficiency. It performs well at predicting both exposed and buried residues, which often deviate from standard p<i>K</i>_a values measured in the solvent. We demonstrate a novel finding that predicted protein isoelectric points (pI) can be used to improve the accuracy of p<i>K</i>_a prediction. High-throughput p<i>K</i>_a prediction of the human proteome using pKALM achieves a speed of 4,965 p<i>K</i>_a predictions per second, which is several orders of magnitude faster than existing state-of-the-art methods. The case studies illustrate the efficacy of pKALM in estimating p<i>K</i>_a values and the constraints of the method. pKALM will thus be a valuable tool for researchers in the fields of biochemistry, biophysics, and drug design.