Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization

The structure of protein-protein complexes is critical for understanding binding dynamics, biological mechanisms, and intervention strategies. Rigid protein docking, a fundamental problem in this field, aims to predict the 3D structure of complexes from their unbound states without conformational changes. In this scenario, we have access to two types of valuable information: sequence-modal information, such as coevolutionary data obtained from multiple sequence alignments, and structure-modal information, including the 3D conformations of rigid structures. However, existing docking methods typically utilize single-modal information, resulting in suboptimal predictions. In this paper, we propose xTrimoBiDock α (or BiDock for short) 4 , a novel rigid docking model that effectively integrates sequenceand structure-modal information through bi-level optimization. Specifically, a crossmodal transformer combines multimodal information to predict an inter-protein distance map. To achieve rigid docking, the roto-translation transformation is optimized to align the docked pose with the predicted distance map. In order to tackle this bi-level optimization problem, we unroll the gradient descent of the inner loop and further derive a better initialization for roto-translation transformation based on spectral estimation. Compared to baselines, BiDock achieves a promising result of a maximum 234% relative improvement in challenging antibody-antigen docking problem. * Work done during an internship at BioMap † Contributed equally to this research. Each author's contribution is provided in Section 5. ‡ Corresponding authors 4 xTrimoBiDock is a member of BioMap's large-scale AI engine "xTrimo" series. "α" denotes the academic version, to distinguish it from the commercial product xTrimoBiDock. 37th Conference on Neural Information Processing Systems (NeurIPS 2023).