Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2505.16896 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915682128494592 |
|---|---|
| author | Chen, Can Heurtel-Depeiges, David Vernon, Robert M. Langmead, Christopher James Bengio, Yoshua Fournier, Quentin |
| author_facet | Chen, Can Heurtel-Depeiges, David Vernon, Robert M. Langmead, Christopher James Bengio, Yoshua Fournier, Quentin |
| contents | Protein language models (pLMs) pre-trained on vast protein sequence databases excel at various downstream tasks but often lack the structural knowledge essential for some biological applications. To address this, we introduce a method to enrich pLMs with structural knowledge by leveraging pre-trained protein graph neural networks (pGNNs). First, a latent-level contrastive learning task aligns residue representations from pLMs with those from pGNNs across multiple proteins, injecting inter-protein structural information. Additionally, a physical-level task integrates intra-protein information by training pLMs to predict structure tokens. Together, the proposed dual-task framework effectively incorporates both inter- and intra-protein structural knowledge into pLMs. Given the variability in the quality of protein structures in PDB, we further introduce a residue loss selection module that uses a small model trained on high-quality structures to select reliable yet challenging residue losses for the pLM to learn. Applying our structure alignment method as a simple, lightweight post-training step to the state-of-the-art ESM2 and AMPLIFY yields notable performance gains. These improvements are consistent across a wide range of tasks, including substantial gains in deep mutational scanning (DMS) fitness prediction and a 59% increase in P@L for ESM2 650M contact prediction on CASP16. Furthermore, we demonstrate that these performance gains are robust, scaling with model sizes from 8M to 650M and extending to different downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16896 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Structure-Aligned Protein Language Model Chen, Can Heurtel-Depeiges, David Vernon, Robert M. Langmead, Christopher James Bengio, Yoshua Fournier, Quentin Machine Learning Artificial Intelligence Protein language models (pLMs) pre-trained on vast protein sequence databases excel at various downstream tasks but often lack the structural knowledge essential for some biological applications. To address this, we introduce a method to enrich pLMs with structural knowledge by leveraging pre-trained protein graph neural networks (pGNNs). First, a latent-level contrastive learning task aligns residue representations from pLMs with those from pGNNs across multiple proteins, injecting inter-protein structural information. Additionally, a physical-level task integrates intra-protein information by training pLMs to predict structure tokens. Together, the proposed dual-task framework effectively incorporates both inter- and intra-protein structural knowledge into pLMs. Given the variability in the quality of protein structures in PDB, we further introduce a residue loss selection module that uses a small model trained on high-quality structures to select reliable yet challenging residue losses for the pLM to learn. Applying our structure alignment method as a simple, lightweight post-training step to the state-of-the-art ESM2 and AMPLIFY yields notable performance gains. These improvements are consistent across a wide range of tasks, including substantial gains in deep mutational scanning (DMS) fitness prediction and a 59% increase in P@L for ESM2 650M contact prediction on CASP16. Furthermore, we demonstrate that these performance gains are robust, scaling with model sizes from 8M to 650M and extending to different downstream tasks. |
| title | Structure-Aligned Protein Language Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.16896 |