Neural multi-task learning in drug design

S Allenspach, JA Hiss, G Schneider - Nature Machine Intelligence, 2024‏ - nature.com
Multi-task learning (MTL) is a machine learning paradigm that aims to enhance the
generalization of predictive models by leveraging shared information across multiple tasks …

A survey of drug-target interaction and affinity prediction methods via graph neural networks

Y Zhang, Y Hu, N Han, A Yang, X Liu, H Cai - Computers in Biology and …, 2023‏ - Elsevier
The tasks of drug-target interaction (DTI) and drug-target affinity (DTA) prediction play
important roles in the field of drug discovery. However, biological experiment-based …

A knowledge-guided pre-training framework for improving molecular representation learning

H Li, R Zhang, Y Min, D Ma, D Zhao, J Zeng - Nature Communications, 2023‏ - nature.com
Learning effective molecular feature representation to facilitate molecular property prediction
is of great significance for drug discovery. Recently, there has been a surge of interest in pre …

[PDF][PDF] KGNN: Knowledge graph neural network for drug-drug interaction prediction.

X Lin, Z Quan, ZJ Wang, T Ma, X Zeng - IJCAI, 2020‏ - xuanlin1991.github.io
Drug-drug interaction (DDI) prediction is a challenging problem in pharmacology and
clinical application, and effectively identifying potential D-DIs during clinical trials is critical …

Difficulty in chirality recognition for Transformer architectures learning chemical structures from string representations

Y Yoshikai, T Mizuno, S Nemoto, H Kusuhara - Nature Communications, 2024‏ - nature.com
Recent years have seen rapid development of descriptor generation based on
representation learning of extremely diverse molecules, especially those that apply natural …

A novel molecular representation with BiGRU neural networks for learning atom

X Lin, Z Quan, ZJ Wang, H Huang… - Briefings in …, 2020‏ - academic.oup.com
Molecular representations play critical roles in researching drug design and properties, and
effective methods are beneficial to assisting in the calculation of molecules and solving …

Compound–protein interaction prediction by deep learning: databases, descriptors and models

BX Du, Y Qin, YF Jiang, Y Xu, SM Yiu, H Yu, JY Shi - Drug discovery today, 2022‏ - Elsevier
The screening of compound–protein interactions (CPIs) is one of the most crucial steps in
finding hit and lead compounds. Deep learning (DL) methods for CPI prediction can address …

IIFDTI: predicting drug–target interactions through interactive and independent features based on attention mechanism

Z Cheng, Q Zhao, Y Li, J Wang - Bioinformatics, 2022‏ - academic.oup.com
Motivation Identifying drug–target interactions is a crucial step for drug discovery and
design. Traditional biochemical experiments are credible to accurately validate drug–target …

DeepGS: Deep representation learning of graphs and sequences for drug-target binding affinity prediction

X Lin, K Zhao, T **ao, Z Quan, ZJ Wang, PS Yu - ECAI 2020, 2020‏ - ebooks.iospress.nl
Accurately predicting drug-target binding affinity (DTA) in silico is a key task in drug
discovery. Most of the conventional DTA prediction methods are simulation-based, which …

A merged molecular representation learning for molecular properties prediction with a web-based service

H Kim, J Lee, S Ahn, JR Lee - Scientific Reports, 2021‏ - nature.com
Deep learning has brought a dramatic development in molecular property prediction that is
crucial in the field of drug discovery using various representations such as fingerprints …