# TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness Prediction

Source: [TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness Prediction](<https://www.sota2.com/research/paper/69df1b9c7d0172140ec7b967>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-16T05:00:04.684Z

Authors: Seungik Cho

Published: 2026-04-13T20:11:09.000Z

## Abstract

Predicting the functional impact of single amino acid substitutions (SAVs) is central to understanding genetic disease and engineering therapeutic proteins. While protein language models and structure-based methods have achieved strong performance on this task, they systematically neglect protein dynamics; residue flexibility, correlated motions, and allosteric coupling are well-established determinants of mutational tolerance in structural biology, yet have not been incorporated into supervised variant effect predictors. We present TriFit, a multimodal framework that integrates sequence, structure, and protein dynamics through a four-expert Mixture-of-Experts (MoE) fusion module with trimodal cross-modal contrastive learning. Sequence embeddings are extracted via masked marginal scoring with ESM-2 (650M); structural embeddings from AlphaFold2-predicted C-alpha geometries; and dynamics embeddings from Gaussian Network Model (GNM) B-factors, mode shapes, and residue-residue cross-correlations. The MoE router adaptively weights modality combinations conditioned on the input, enabling protein-specific fusion without fixed modality assumptions. On the ProteinGym substitution benchmark (217 DMS assays, 696k SAVs), TriFit achieves AUROC 0.897 +/- 0.0002, outperforming all supervised baselines including Kermut (0.864) and ProteinNPT (0.844), and the best zero-shot model ESM3 (0.769). Ablation studies confirm that dynamics provides the largest marginal contribution over pairwise modality combinations, and TriFit achieves well-calibrated probabilistic outputs (ECE = 0.044) without post-hoc correction.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Mutation Fitness Prediction on ProteinGym](<https://www.sota2.com/research/sota/mutation-fitness-prediction-on-proteingym.md>): Mutation Fitness Prediction; ProteinGym; AUROC: 89.74.

- [Mutation Fitness Prediction on ProteinGym substitution benchmark (217 proteins) (fold 4 test)](<https://www.sota2.com/research/sota/mutation-fitness-prediction-on-proteingym-substitution-benchmark-217-proteins-fold-4-test.md>): Mutation Fitness Prediction; ProteinGym substitution benchmark (217 proteins) (fold 4 test); AUROC: 89.74.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.12026>)

[PDF](<https://arxiv.org/pdf/2604.12026.pdf>)