Cangea, Cătălina, Grauslys, Arturas, Liò, Pietro and Falciani, Francesco 
ORCID: 0000-0003-1432-2871
(2018)
Structure-Based Networks for Drug Validation.
CoRR, abs/18.
|
Text
1811.09714v1.pdf - Published Version Download (301kB) | Preview |
Abstract
Classifying chemicals according to putative modes of action (MOAs) is of paramount importance in the context of risk assessment. However, current methods are only able to handle a very small proportion of the existing chemicals. We address this issue by proposing an integrative deep learning architecture that learns a joint representation from molecular structures of drugs and their effects on human cells. Our choice of architecture is motivated by the significant influence of a drug's chemical structure on its MOA. We improve on the strong ability of a unimodal architecture (F1 score of 0.803) to classify drugs by their toxic MOAs (Verhaar scheme) through adding another learning stream that processes transcriptional responses of human cells affected by drugs. Our integrative model achieves an even higher classification performance on the LINCS L1000 dataset - the error is reduced by 4.6%. We believe that our method can be used to extend the current Verhaar scheme and constitute a basis for fast drug validation and risk assessment.
| Item Type: | Article |
|---|---|
| Additional Information: | Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216 |
| Uncontrolled Keywords: | q-bio.QM, q-bio.QM, cs.AI, cs.LG, stat.ML |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 02 Mar 2020 11:27 |
| Last Modified: | 19 Jan 2023 00:00 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3076791 |
Share
Share
