Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2507.02624 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913924336582656 |
|---|---|
| author | Honoré, Antoine Gálvez, Borja Rodríguez Park, Yoomi Zhou, Yitian Lauschke, Volker M. Xiao, Ming |
| author_facet | Honoré, Antoine Gálvez, Borja Rodríguez Park, Yoomi Zhou, Yitian Lauschke, Volker M. Xiao, Ming |
| contents | Variant effect predictors (VEPs) aim to assess the functional impact of protein variants, traditionally relying on multiple sequence alignments (MSAs). This approach assumes that naturally occurring variants are fit, an assumption challenged by pharmacogenomics, where some pharmacogenes experience low evolutionary pressure. Deep mutational scanning (DMS) datasets provide an alternative by offering quantitative fitness scores for variants. In this work, we propose a transformer-based matrix variational auto-encoder (matVAE) with a structured prior and evaluate its performance on 33 DMS datasets corresponding to 26 drug target and ADME proteins from the ProteinGym benchmark. Our model trained on MSAs (matVAE-MSA) outperforms the state-of-the-art DeepSequence model in zero-shot prediction on DMS datasets, despite using an order of magnitude fewer parameters and requiring less computation at inference time. We also compare matVAE-MSA to matENC-DMS, a model of similar capacity trained on DMS data, and find that the latter performs better on supervised prediction tasks. Additionally, incorporating AlphaFold-generated structures into our transformer model further improves performance, achieving results comparable to DeepSequence trained on MSAs and finetuned on DMS. These findings highlight the potential of DMS datasets to replace MSAs without significant loss in predictive performance, motivating further development of DMS datasets and exploration of their relationships to enhance variant effect prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02624 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Matrix Variational Auto-Encoder for Variant Effect Prediction in Pharmacogenes Honoré, Antoine Gálvez, Borja Rodríguez Park, Yoomi Zhou, Yitian Lauschke, Volker M. Xiao, Ming Machine Learning Variant effect predictors (VEPs) aim to assess the functional impact of protein variants, traditionally relying on multiple sequence alignments (MSAs). This approach assumes that naturally occurring variants are fit, an assumption challenged by pharmacogenomics, where some pharmacogenes experience low evolutionary pressure. Deep mutational scanning (DMS) datasets provide an alternative by offering quantitative fitness scores for variants. In this work, we propose a transformer-based matrix variational auto-encoder (matVAE) with a structured prior and evaluate its performance on 33 DMS datasets corresponding to 26 drug target and ADME proteins from the ProteinGym benchmark. Our model trained on MSAs (matVAE-MSA) outperforms the state-of-the-art DeepSequence model in zero-shot prediction on DMS datasets, despite using an order of magnitude fewer parameters and requiring less computation at inference time. We also compare matVAE-MSA to matENC-DMS, a model of similar capacity trained on DMS data, and find that the latter performs better on supervised prediction tasks. Additionally, incorporating AlphaFold-generated structures into our transformer model further improves performance, achieving results comparable to DeepSequence trained on MSAs and finetuned on DMS. These findings highlight the potential of DMS datasets to replace MSAs without significant loss in predictive performance, motivating further development of DMS datasets and exploration of their relationships to enhance variant effect prediction. |
| title | A Matrix Variational Auto-Encoder for Variant Effect Prediction in Pharmacogenes |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.02624 |