Evaluating representation learning on the protein structure universe
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917699540484096 |
|---|---|
| author | Jamasb, Arian R. Morehead, Alex Joshi, Chaitanya K. Zhang, Zuobai Didi, Kieran Mathis, Simon V. Harris, Charles Tang, Jian Cheng, Jianlin Lio, Pietro Blundell, Tom L. |
| author_facet | Jamasb, Arian R. Morehead, Alex Joshi, Chaitanya K. Zhang, Zuobai Didi, Kieran Mathis, Simon V. Harris, Charles Tang, Jian Cheng, Jianlin Lio, Pietro Blundell, Tom L. |
| contents | We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13864 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating representation learning on the protein structure universe Jamasb, Arian R. Morehead, Alex Joshi, Chaitanya K. Zhang, Zuobai Didi, Kieran Mathis, Simon V. Harris, Charles Tang, Jian Cheng, Jianlin Lio, Pietro Blundell, Tom L. Machine Learning Biomolecules We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop. |
| title | Evaluating representation learning on the protein structure universe |
| topic | Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2406.13864 |