Comparative Performance of High-Throughput Methods for Protein pK_a Predictions

The medically relevant field of protein-based therapeutics has triggered a demand for protein engineering in different pH environments of biological relevance. In silico engineering workflows typically employ high-throughput screening campaigns that require evaluating large sets of protein residues and point mutations by fast yet accurate computational algorithms. While several high-throughput pK_a prediction methods exist, their accuracies are unclear due to the lack of a current comprehensive benchmarking. Here, seven fast, efficient, and accessible approaches including PROPKA3, DeepKa, PKAI, PKAI+, DelPhiPKa, MCCE2, and H++ were systematically tested on a nonredundant subset of 408 measured protein residue pK_a shifts from the pK_a database (PKAD). While no method outperformed the null hypotheses with confidence, as illustrated by statistical bootstrapping, DeepKa, PKAI+, PROPKA3, and H++ had utility. More specifically, DeepKa consistently performed well in tests across multiple and individual amino acid residue types, as reflected by lower errors, higher correlations, and improved classifications. Arithmetic averaging of the best empirical predictors into simple consensuses improved overall transferability and accuracy up to a root-mean-square error of 0.76 pK_a units and a correlation coefficient (R²) of 0.45 to experimental pK_a shifts. This analysis should provide a basis for further methodological developments and guide future applications, which require embedding of computationally inexpensive pK_a prediction methods, such as the optimization of antibodies for pH-dependent antigen binding.