Two-Stage Pretraining for Molecular Property Prediction in the Wild
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918096660332544 |
|---|---|
| author | Wijaya, Kevin Tirta Guo, Minghao Sun, Michael Seidel, Hans-Peter Matusik, Wojciech Babaei, Vahid |
| author_facet | Wijaya, Kevin Tirta Guo, Minghao Sun, Michael Seidel, Hans-Peter Matusik, Wojciech Babaei, Vahid |
| contents | Molecular deep learning models have achieved remarkable success in property prediction, but they often require large amounts of labeled data. The challenge is that, in real-world applications, labels are extremely scarce, as obtaining them through laboratory experimentation is both expensive and time-consuming. In this work, we introduce MoleVers, a versatile pretrained molecular model designed for various types of molecular property prediction in the wild, i.e., where experimentally-validated labels are scarce. MoleVers employs a two-stage pretraining strategy. In the first stage, it learns molecular representations from unlabeled data through masked atom prediction and extreme denoising, a novel task enabled by our newly introduced branching encoder architecture and dynamic noise scale sampling. In the second stage, the model refines these representations through predictions of auxiliary properties derived from computational methods, such as the density functional theory or large language models. Evaluation on 22 small, experimentally-validated datasets demonstrates that MoleVers achieves state-of-the-art performance, highlighting the effectiveness of its two-stage framework in producing generalizable molecular representations for diverse downstream properties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03537 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Two-Stage Pretraining for Molecular Property Prediction in the Wild Wijaya, Kevin Tirta Guo, Minghao Sun, Michael Seidel, Hans-Peter Matusik, Wojciech Babaei, Vahid Machine Learning Artificial Intelligence Chemical Physics Biomolecules Molecular deep learning models have achieved remarkable success in property prediction, but they often require large amounts of labeled data. The challenge is that, in real-world applications, labels are extremely scarce, as obtaining them through laboratory experimentation is both expensive and time-consuming. In this work, we introduce MoleVers, a versatile pretrained molecular model designed for various types of molecular property prediction in the wild, i.e., where experimentally-validated labels are scarce. MoleVers employs a two-stage pretraining strategy. In the first stage, it learns molecular representations from unlabeled data through masked atom prediction and extreme denoising, a novel task enabled by our newly introduced branching encoder architecture and dynamic noise scale sampling. In the second stage, the model refines these representations through predictions of auxiliary properties derived from computational methods, such as the density functional theory or large language models. Evaluation on 22 small, experimentally-validated datasets demonstrates that MoleVers achieves state-of-the-art performance, highlighting the effectiveness of its two-stage framework in producing generalizable molecular representations for diverse downstream properties. |
| title | Two-Stage Pretraining for Molecular Property Prediction in the Wild |
| topic | Machine Learning Artificial Intelligence Chemical Physics Biomolecules |
| url | https://arxiv.org/abs/2411.03537 |