Exploration of chemical space with partial labeled noisy student self-training and self-supervised graph embedding

Background: Drug discovery is time-consuming and costly. Machine learning, especially deep learning, shows great potential in quantitative structure–activity relationship (QSAR) modeling to accelerate drug discovery process and reduce its cost. A big challenge in developing robust and generalizable...

Full description

Bibliographic Details
Main Authors:	Lim, H. (Author), Liu, Y. (Author), Xie, L. (Author)
Format:	Article
Language:	English
Published:	BioMed Central Ltd 2022
Subjects:	algorithm Algorithms Artificial intelligence Benchmarking Binding energy Chemical embedding Computational chemistry Deep neural network Deep neural networks Drug discovery Drug metabolism Drug metabolisms Drug toxicity Drug-target interaction Drug-target interactions Embeddings Forecasting Graph isomorphism Graph neural network Graph neural networks human Humans machine learning Machine Learning Metabolism Neural Networks, Computer quantitative structure activity relation Quantitative Structure-Activity Relationship Self-supervised learning Self-training Semi-supervised learning student Students Toxicity
Online Access:	View Fulltext in Publisher

Internet

View Fulltext in Publisher

Exploration of chemical space with partial labeled noisy student self-training and self-supervised graph embedding

Internet

Similar Items