From single-sequence structure prediction to protein fitness landscape through a composable, epistasis-aware mutation atlas
- 1Zhongnan University of Economics and Law
Abstract
Mapping the multi-mutant fitness landscape is vital to protein engineering, but is challenging due to the vast combinatorial sequence space awaiting exploration. A central difficulty lies in the accurate and efficient modeling of non-additive epistatic effects among individual mutations, which partially arise from the physical inter-residue interactions prescribed by the protein structure. Existing fitness predictors usually perform well on single mutants but become less powerful for higher-order mutants, due to the lack of explicitly considering the relationship between sequence, structure and function of the target protein. Here, we present an end-to-end framework named Cerebra-Epistasis, which couples a single-sequence structure predictor that explicitly endows the structure awareness beyond the conventional sequence-fitness mapping with a downstream fitness prediction network that deliberately models the non-linear epistatic effects beyond the traditional additive terms. When evaluated across diverse assays, Cerebra-Epistasis outperforms the other state-of-the-art baselines in multi-mutant fitness prediction, with enhanced advantage over increasing mutation orders. Moreover, our special design on the epistasis modeling allows reliable extrapolation from low-order mutant data to unseen higher-order combinations, enabling one-shot inference of the overall mutation atlas from the starting sequence, a benefit that supposedly introduces three orders of magnitude acceleration in the landscape-scale prediction.
Related
- Recurrence in Sequence Space: How Epistasis Mimics Shared Ancestry
- Repurposing PeTriBERT for Protein Protein Interaction Prediction with Sequence Structure Fusion
- Sequence-only prediction of VHH nanobody epitopes and paratopes on HER2 with a frozen protein language model ( ESM2) and a structure-derived residue prior
- GeoEPred: A multimodal structure-aware geometric deep learning framework for Gram-negative bacterial secreted effector prediction with sequence semantics
- GLOM TGITO: multiscale protein modelling and multiview landscape-guided sequence discovery
BibTeX
@misc{wang2026from,
title = {{From single-sequence structure prediction to protein fitness landscape through a composable, epistasis-aware mutation atlas}},
author = {W. Wang and Z. Yu and E. Yang and Z. Shi and S. Yu and J. Hu and Y. Xu and H. Gong},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.753701},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.753701v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - From single-sequence structure prediction to protein fitness landscape through a composable, epistasis-aware mutation atlas
AU - W. Wang
AU - Z. Yu
AU - E. Yang
AU - Z. Shi
AU - S. Yu
AU - J. Hu
AU - Y. Xu
AU - H. Gong
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.753701
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.753701v1
AB - Mapping the multi-mutant fitness landscape is vital to protein engineering, but is challenging due to the vast combinatorial sequence space awaiting exploration. A central difficulty lies in the accurate and efficient modeling of non-additive epistatic effects among individual mutations, which partially arise from the physical inter-residue interactions prescribed by the protein structure. Existing fitness predictors usually perform well on single mutants but become less powerful for higher-order mutants, due to the lack of explicitly considering the relationship between sequence, structure and function of the target protein. Here, we present an end-to-end framework named Cerebra-Epistasis, which couples a single-sequence structure predictor that explicitly endows the structure awareness beyond the conventional sequence-fitness mapping with a downstream fitness prediction network that deliberately models the non-linear epistatic effects beyond the traditional additive terms. When evaluated across diverse assays, Cerebra-Epistasis outperforms the other state-of-the-art baselines in multi-mutant fitness prediction, with enhanced advantage over increasing mutation orders. Moreover, our special design on the epistasis modeling allows reliable extrapolation from low-order mutant data to unseen higher-order combinations, enabling one-shot inference of the overall mutation atlas from the starting sequence, a benefit that supposedly introduces three orders of magnitude acceleration in the landscape-scale prediction.
ER -