AI-Based Protein–Protein Docking

Protein-protein interactions (PPIs) govern virtually all cellular processes -- signal transduction, immune recognition,enzymatic regulation, and macromolecular assembly -- yet experimental structure determination of protein complexescovers fewer than 5% of known PPIs. Computational protein-protein docking predicts the 3D structure of complexes fromindividual protein structures, but traditional docking methods (ZDOCK, HADDOCK, ClusPro) achieve acceptableaccuracy (<5 Angstrom interface RMSD) for only 30-50% of benchmark targets due to inadequate scoring functions andconformational sampling limitations. AlphaFold-Multimer has dramatically improved complex prediction but struggles withtransient interactions, antibody-antigen complexes, and cases lacking co-evolutionary signal. This study developed andbenchmarked six protein-protein docking approaches -- rigid-body FFT-based (ZDOCK 3.0.2), information-driven(HADDOCK 2.4), template-based (SWISS-MODEL), AlphaFold-Multimer (v2.3), diffusion-based (DiffDock-PP), and aproposed Deep Integrative Docking Engine (DIDE) combining AlphaFold-Multimer confidence-guided initial placement,physics-informed refinement via equivariant graph neural network, interface residue prediction from co-evolutionaryanalysis and cross-linking mass spectrometry data integration, and flexible side-chain optimisation -- across threebenchmark sets: Docking Benchmark 5.5 (DB5.5, 230 non-redundant complexes), CAPRI scoring targets (Rounds47-54, 42 targets), and a custom antibody-antigen set (86 complexes from SAbDab). DIDE achieved the highest successrate across all benchmarks: DB5.5 acceptable-or-better 78.4% (vs AlphaFold-Multimer 64.2%, HADDOCK 42.8%,ZDOCK 36.2%; p < 0.001), CAPRI 72.4% (vs AF-Multimer 58.6%), and antibody-antigen 62.8% (vs AF-Multimer 38.4%;p < 0.001). The antibody-antigen improvement (+24.4 percentage points over AF-Multimer) was driven by DIDE'sinterface prediction module that compensates for the lack of co-evolutionary signal in antibody-antigen pairs. DIDE'smedian interface RMSD for successful predictions was 1.42 Angstrom (high accuracy), enabling reliable identification ofbinding hotspots for drug design. These results establish deep integrative docking as the state-of-the-art for proteincomplex structure predictio