DualMPNN: Harnessing Structural Alignments for High-Recovery Inverse Protein Folding

Xuhui Liao (Harbin Institute of Technology, Shen Zhen) · qiyu wang (Harbin Institute of Technology) · Zhiqiang Liang (Harbin Institute of Technology) · Liwei Xiao (Harbin Institute of Technology) · Junjie Chen (Jiangxi University of Finance and Economics)

alignment-aware attention mechanismsamino acid sequencescath benchmarksco-evolutionary signalsdualmpnngeometric signalsinverse protein foldingmessage passing neural networkmultiple sequence alignmentssequence designstructural foldability assessmentstructurally homologous templatesstructure predictiontemplate quality analysistertiary structure

Inverse protein folding addresses the challenge of designing amino acid sequences that fold into a predetermined tertiary structure, bridging geometric and evolutionary constraints to advance protein engineering. Inspired by the pivotal role of multiple sequence alignments (MSAs) in structure prediction models like AlphaFold, we hypothesize that structural alignments can provide an informative prior for inverse folding. In this study, we introduce DualMPNN, a dual-stream message passing neural network that leverages structurally homologous templates to guide amino acid sequence design of predefined query structures. DualMPNN processes the query and template proteins via two interactive branches, coupled through alignment-aware cross-stream attention mechanisms that enable exchange of geometric and co-evolutionary signals. Comprehensive evaluations across on CATH 4.2, TS50 and T500 benchmarks demonstrate DualMPNN achieves state-of-the-art recovery rates of 65.51\%, 70.99\%, and 70.37\%, significantly outperforming base model ProteinMPNN by 15.64\%, 16.56\%, 12.29\%, respectively. Further template quality analysis and structural foldability assessment underscore the value of structural alignment priors for protein design.