Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Multi-task learning with a natural metric for quantitative structure activity relationship learning

Sadawi, N, Olier, I, Vanschoren, J, van Rijn, JN, Besnard, J, Bickerton, R, Grosan, C, Soldatova, L and King, RD Multi-task learning with a natural metric for quantitative structure activity relationship learning. Journal of Cheminformatics. ISSN 1758-2946 (Accepted)

[img]
Preview
Text
Multi_Task_Learning_with_a_Natural_Metric_for_Quantitative_Structure___Activity_Relationship_Learning.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (318kB) | Preview

Abstract

The goal of Quantitative Structure Activity Relationship (QSAR) Learning is to learn a function that, given the structure of a small molecule (a potential drug), outputs the predicted activity of the compound. We employed multi-task learning (MTL) to exploit commonalities in drug targets and assays. We used datasets containing curated records about the activity of speci c compounds on drug targets provided by ChEMBL. Totally, 1091 assays have been analysed. As a baseline, a single task learning approach that trains random forest to predict drug activity for each drug target individually was considered. We then carried out feature-based and instance-based MTL to predict drug activities. We introduced a natural metric of evolutionary distance between drug targets as a measure of tasks relatedness. Instance-based MTL signi cantly outperformed both, feature-based MTL and the base learner, on 741 drug targets out of 1091. Feature-based MTL won on 179 occasions and the base learner performed best on 171 drug targets. We conclude that MTL QSAR is improved by incorporating the evolutionary distance between targets. These results indicate that QSAR learning can be performed effectively, even if little data is available for speci c drug targets, by leveraging what is known about similar drug targets.

Item Type: Article
Uncontrolled Keywords: Multi-Task Learning; Quantitative Structure Activity Relationship; Sequence-Based Similarity; Random Forest
Subjects: Q Science > QA Mathematics
Divisions: Applied Mathematics
Publisher: BioMed Central
Date Deposited: 06 Nov 2019 11:45
Last Modified: 06 Nov 2019 11:46
URI: http://researchonline.ljmu.ac.uk/id/eprint/11710

Actions (login required)

View Item View Item