arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.06125cs.LG
收藏

基于几何结构预训练的蛋白质表示学习

Protein Representation Learning by Geometric Structure Pretraining

Mila - Québec AI Institute(米拉-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);University of Cambridge(剑桥大学);IBM Research(IBM研究院);HEC Montréal(蒙特利尔高等商学院)

Zuobai Zhang, Minghao Xu, Arian Jamasb, Vijil Chenthamarakshan, Aurelie Lozano, Payel Das, Jian Tang

摘要:

学习有效的蛋白质表示在生物学中的各种任务中至关重要,例如预测蛋白质功能或结构。现有的方法通常在大量未标记的氨基酸序列上预训练蛋白质语言模型,然后在下游任务中使用一些标记的数据对模型进行微调。尽管基于序列的方法是有效的,但对已知蛋白质结构的预训练的能力(仅在较小数量中可用)尚未被探索用于蛋白质性质预测,尽管蛋白质结构已知是蛋白质功能的决定因素。在本文中,我们提出了预训练蛋白质表示,根据其3D结构。我们首先提出了一个简单而有效的编码器来学习蛋白质的几何特征。我们通过利用多视图对比学习和不同的自我预测任务来预训练蛋白质图编码器。函数预测和折叠分类任务的实验结果表明,我们提出的预训练方法优于或与最先进的基于序列的方法相当,同时使用更少的预训练数据。我们的实现可以在https://github.com/DeepGraphLearning/GearNet上获得。

英文摘要:

Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein function or structure. Existing approaches usually pretrain protein language models on a large number of unlabeled amino acid sequences and then finetune the models with some labeled data in downstream tasks. Despite the effectiveness of sequence-based approaches, the power of pretraining on known protein structures, which are available in smaller numbers only, has not been explored for protein property prediction, though protein structures are known to be determinants of protein function. In this paper, we propose to pretrain protein representations according to their 3D structures. We first present a simple yet effective encoder to learn the geometric features of a protein. We pretrain the protein graph encoder by leveraging multiview contrastive learning and different self-prediction tasks. Experimental results on both function prediction and fold classification tasks show that our proposed pretraining methods outperform or are on par with the state-of-the-art sequence-based methods, while using much less pretraining data. Our implementation is available at https://github.com/DeepGraphLearning/GearNet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑