Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.01693 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916189182099456 |
|---|---|
| author | Han, Rong Huang, Wenbing Luo, Lingxiao Han, Xinyan Shen, Jiaming Zhang, Zhiqiang Zhou, Jun Chen, Ting |
| author_facet | Han, Rong Huang, Wenbing Luo, Lingxiao Han, Xinyan Shen, Jiaming Zhang, Zhiqiang Zhou, Jun Chen, Ting |
| contents | Understanding and leveraging the 3D structures of proteins is central to a variety of biological and drug discovery tasks. While deep learning has been applied successfully for structure-based protein function prediction tasks, current methods usually employ distinct training for each task. However, each of the tasks is of small size, and such a single-task strategy hinders the models' performance and generalization ability. As some labeled 3D protein datasets are biologically related, combining multi-source datasets for larger-scale multi-task learning is one way to overcome this problem. In this paper, we propose a neural network model to address multiple tasks jointly upon the input of 3D protein structures. In particular, we first construct a standard structure-based multi-task benchmark called Protein-MT, consisting of 6 biologically relevant tasks, including affinity prediction and property prediction, integrated from 4 public datasets. Then, we develop a novel graph neural network for multi-task learning, dubbed Heterogeneous Multichannel Equivariant Network (HeMeNet), which is E(3) equivariant and able to capture heterogeneous relationships between different atoms. Besides, HeMeNet can achieve task-specific learning via the task-aware readout mechanism. Extensive evaluations on our benchmark verify the effectiveness of multi-task learning, and our model generally surpasses state-of-the-art models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01693 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning Han, Rong Huang, Wenbing Luo, Lingxiao Han, Xinyan Shen, Jiaming Zhang, Zhiqiang Zhou, Jun Chen, Ting Machine Learning Understanding and leveraging the 3D structures of proteins is central to a variety of biological and drug discovery tasks. While deep learning has been applied successfully for structure-based protein function prediction tasks, current methods usually employ distinct training for each task. However, each of the tasks is of small size, and such a single-task strategy hinders the models' performance and generalization ability. As some labeled 3D protein datasets are biologically related, combining multi-source datasets for larger-scale multi-task learning is one way to overcome this problem. In this paper, we propose a neural network model to address multiple tasks jointly upon the input of 3D protein structures. In particular, we first construct a standard structure-based multi-task benchmark called Protein-MT, consisting of 6 biologically relevant tasks, including affinity prediction and property prediction, integrated from 4 public datasets. Then, we develop a novel graph neural network for multi-task learning, dubbed Heterogeneous Multichannel Equivariant Network (HeMeNet), which is E(3) equivariant and able to capture heterogeneous relationships between different atoms. Besides, HeMeNet can achieve task-specific learning via the task-aware readout mechanism. Extensive evaluations on our benchmark verify the effectiveness of multi-task learning, and our model generally surpasses state-of-the-art models. |
| title | HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.01693 |