Journal
CHEMICAL RESEARCH IN TOXICOLOGY
Volume 34, Issue 2, Pages 634-640Publisher
AMER CHEMICAL SOC
DOI: 10.1021/acs.chemrestox.0c00464
Keywords
-
Funding
- [HHSN273201700001C]
Ask authors/readers for more resources
Molecular structure-based predictive models offer a cost-effective and efficient alternative to animal testing, with the need for interpretable descriptors to provide chemistry-backed predictive reasoning. Saagar, a novel chemistry-aware substructure, outperformed publicly available fingerprint sets in extracting compounds with higher scaffold similarity, showcasing its ability to efficiently characterize diverse chemical collections.
Molecular structure-based predictive models provide a proven alternative to costly and inefficient animal testing. However, due to a lack of interpretability of predictive models built with abstract molecular descriptors they have earned the notoriety of being black boxes. Interpretable models require interpretable descriptors to provide chemistry-backed predictive reasoning and facilitate intelligent molecular design. We developed a novel set of extensible chemistry-aware substructures, Saagar, to support interpretable predictive models and read-across protocols. Performance of Saagar in chemical characterization and search for structurally similar actives for read-across applications was compared with four publicly available fingerprint sets (MACCS (166), PubChem (881), ECFP4 (1024), ToxPrint (729)) in three benchmark sets (MUV, ULS, and Tox21) spanning similar to 145 000 compounds and 78 molecular targets at 1%, 2%, 5%, and 10% false discovery rates. In 18 of the 20 comparisons, interpretable Saagar features performed better than the publicly available, but less interpretable and fixed-bit length, fingerprints. Examples are provided to show the enhanced capability of Saagar in extracting compounds with higher scaffold similarity. Saagar features are interpretable and efficiently characterize diverse chemical collections, thus making them a better choice for building interpretable predictive in silico models and read-across protocols.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available