Filling the Missing Puzzle: Integrating Interaction and Evolutionary Information to Enhance Protein Fitness Prediction in Inverse Folding
- 1Shanghai Zelixir Biotech
Abstract
Protein inverse folding, which infers compatible amino acid sequences from a given backbone structure, is central to rational protein design. Current methods rely largely on sequence recovery rate as the evaluation metric, emphasizing structural compatibility but seldom addressing function. Yet functional activity depends on the proper network of non-covalent interactions-protein-ligand contacts being a prime example. We argue that function-oriented protein design is governed by three complementary constraints: structural, interaction, and evolutionary, none of which are handled in a unified manner by existing pretrained models. To bridge this gap, we introduce zPolaron, a graph neural network built on protein-ligand complexes for functional protein design. zPolaron represents residues and ligand atoms as a heterogeneous graph and jointly encodes structural, interaction, and evolutionary information by fusing physical-interaction-enhanced graph representations with ESM-2 embeddings. Across multiple fitness prediction benchmarks, zPolaron outperforms all baselines, with gains evident across structural, interaction, and evolutionary dimensions. Wet-lab experiments further confirm its utility in functional enzyme screening and design: the optimized CalA6-D205A-S160G mutant achieves a 17.84-fold improvement in activity, while the CalB-I121M mutant yields a 1.91-fold increase. Together, these results show that integrating interaction and evolutionary information fills the missing puzzle of inverse folding, enhancing protein fitness prediction beyond structural compatibility. zPolaron is available at https://github.com/zelixirSH/zPolaron.
Related
- Pre-season bare-soil spectral proxies complement pod-filling canopy indices for field-scale soybean-yield prediction from UAV imagery
- Genome-Wide Characterization of the DELLA Gene Family in Hevea brasiliensis Reveals Evolutionary Diversification and Potential HbDELLA3/4-HbbHLH25 Interaction.
- Eco-evolutionary cycles in a matching type predator-prey interaction
- Integrating complementary biological information for multi-objective enzyme engineering
- Beyond prediction accuracy by integrating GWAASB into wheat stability assessment across environments in Saudi Arabia
BibTeX
@misc{wang2026filling,
title = {{Filling the Missing Puzzle: Integrating Interaction and Evolutionary Information to Enhance Protein Fitness Prediction in Inverse Folding}},
author = {Z. Wang and Z. Zhang and Y. Yang and Y. Qu and Y. Mu and S. Wang and N. Han and L. Zheng and W. Li},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.756918},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.756918v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Filling the Missing Puzzle: Integrating Interaction and Evolutionary Information to Enhance Protein Fitness Prediction in Inverse Folding
AU - Z. Wang
AU - Z. Zhang
AU - Y. Yang
AU - Y. Qu
AU - Y. Mu
AU - S. Wang
AU - N. Han
AU - L. Zheng
AU - W. Li
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.756918
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.756918v1
AB - Protein inverse folding, which infers compatible amino acid sequences from a given backbone structure, is central to rational protein design. Current methods rely largely on sequence recovery rate as the evaluation metric, emphasizing structural compatibility but seldom addressing function. Yet functional activity depends on the proper network of non-covalent interactions-protein-ligand contacts being a prime example. We argue that function-oriented protein design is governed by three complementary constraints: structural, interaction, and evolutionary, none of which are handled in a unified manner by existing pretrained models. To bridge this gap, we introduce zPolaron, a graph neural network built on protein-ligand complexes for functional protein design. zPolaron represents residues and ligand atoms as a heterogeneous graph and jointly encodes structural, interaction, and evolutionary information by fusing physical-interaction-enhanced graph representations with ESM-2 embeddings. Across multiple fitness prediction benchmarks, zPolaron outperforms all baselines, with gains evident across structural, interaction, and evolutionary dimensions. Wet-lab experiments further confirm its utility in functional enzyme screening and design: the optimized CalA6-D205A-S160G mutant achieves a 17.84-fold improvement in activity, while the CalB-I121M mutant yields a 1.91-fold increase. Together, these results show that integrating interaction and evolutionary information fills the missing puzzle of inverse folding, enhancing protein fitness prediction beyond structural compatibility. zPolaron is available at https://github.com/zelixirSH/zPolaron.
ER -