Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.04637 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912877444595712 |
|---|---|
| author | Yuan, Sisi Chen, Jiehuang Cai, Junchuang Xu, Dong Li, Xueliang Zhu, Zexuan Ji, Junkai |
| author_facet | Yuan, Sisi Chen, Jiehuang Cai, Junchuang Xu, Dong Li, Xueliang Zhu, Zexuan Ji, Junkai |
| contents | Protein inverse folding, the task of predicting amino acid sequences for desired structures, is pivotal for de novo protein design. However, existing GNN-based methods typically suffer from restricted receptive fields that miss long-range dependencies and a "single-pass" inference paradigm that leads to error accumulation. To address these bottlenecks, we propose RIGA-Fold, a framework that synergizes Recurrent Interaction with Geometric Awareness. At the micro-level, we introduce a Geometric Attention Update (GAU) module where edge features explicitly serve as attention keys, ensuring strictly SE(3)-invariant local encoding. At the macro-level, we design an attention-based Global Context Bridge that acts as a soft gating mechanism to dynamically inject global topological information. Furthermore, to bridge the gap between structural and sequence modalities, we introduce an enhanced variant, RIGA-Fold*, which integrates trainable geometric features with frozen evolutionary priors from ESM-2 and ESM-IF via a dual-stream architecture. Finally, a biologically inspired ``predict-recycle-refine'' strategy is implemented to iteratively denoise sequence distributions. Extensive experiments on CATH 4.2, TS50, and TS500 benchmarks demonstrate that our geometric framework is highly competitive, while RIGA-Fold* significantly outperforms state-of-the-art baselines in both sequence recovery and structural consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04637 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RIGA-Fold: A General Framework for Protein Inverse Folding via Recurrent Interaction and Geometric Awareness Yuan, Sisi Chen, Jiehuang Cai, Junchuang Xu, Dong Li, Xueliang Zhu, Zexuan Ji, Junkai Machine Learning Protein inverse folding, the task of predicting amino acid sequences for desired structures, is pivotal for de novo protein design. However, existing GNN-based methods typically suffer from restricted receptive fields that miss long-range dependencies and a "single-pass" inference paradigm that leads to error accumulation. To address these bottlenecks, we propose RIGA-Fold, a framework that synergizes Recurrent Interaction with Geometric Awareness. At the micro-level, we introduce a Geometric Attention Update (GAU) module where edge features explicitly serve as attention keys, ensuring strictly SE(3)-invariant local encoding. At the macro-level, we design an attention-based Global Context Bridge that acts as a soft gating mechanism to dynamically inject global topological information. Furthermore, to bridge the gap between structural and sequence modalities, we introduce an enhanced variant, RIGA-Fold*, which integrates trainable geometric features with frozen evolutionary priors from ESM-2 and ESM-IF via a dual-stream architecture. Finally, a biologically inspired ``predict-recycle-refine'' strategy is implemented to iteratively denoise sequence distributions. Extensive experiments on CATH 4.2, TS50, and TS500 benchmarks demonstrate that our geometric framework is highly competitive, while RIGA-Fold* significantly outperforms state-of-the-art baselines in both sequence recovery and structural consistency. |
| title | RIGA-Fold: A General Framework for Protein Inverse Folding via Recurrent Interaction and Geometric Awareness |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.04637 |