F-CPI: A Multimodal Deep Learning Approach for Predicting Compound Bioactivity Changes Induced by Fluorine Substitution
- 20 December 2024
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Medicinal Chemistry
- Vol. 68 (1) , 706-718
Abstract
Fluorine (F) substitution is a common method of drug discovery and development. However, there are no accurate approaches available for predicting the bioactivity changes after F-substitution, as the effect of substitution on the interactions between compounds and proteins (CPI) remains a mystery. In this study, we constructed a data set with 111,168 pairs of fluorine-substituted and nonfluorine-substituted compounds. We developed a multimodal deep learning model (F-CPI). In comparison with traditional machine learning and popular CPI task models, the accuracy, precision, and recall of F-CPI (∼90, ∼79, and ∼45%) were higher than those of GraphDTA (∼86, ∼58, and ∼40%). The application of the F-CPI for the structural optimization of hit compounds against SARS-CoV-2 3CLpro by F-substitution achieved a more than 100-fold increase in bioactivity (IC50: 0.23 μM vs 28.19 μM). Therefore, the multimodal deep learning model F-CPI would be a veritable and effective tool in the context of drug discovery and design.Keywords
Funding Information
- the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0830000)
This publication has 51 references indexed in Scilit:
- A review: FDA-approved fluorine-containing small molecules from 2015 to 2022European Journal of Medicinal Chemistry, 2023
- Fluorine in anti-HIV drugs approved by FDA from 1981 to 2023European Journal of Medicinal Chemistry, 2023
- Fluorinated Cycloalkyl Building Blocks for Drug DiscoveryChemMedChem, 2022
- Fluorinated Nucleosides: Synthesis, Modulation in Conformation and Therapeutic ApplicationThe Chemical Record, 2022
- Discovery of 9,10-dihydrophenanthrene derivatives as SARS-CoV-2 3CLpro inhibitors for treating COVID-19European Journal of Medicinal Chemistry, 2021
- Flavonoids in Ampelopsis grossedentata as covalent inhibitors of SARS-CoV-2 3CLpro: Inhibition potentials, covalent binding sites and inhibitory mechanismsInternational Journal of Biological Macromolecules, 2021
- Discovery of naturally occurring inhibitors against SARS-CoV-2 3CLpro from Ginkgo biloba leaves via large-scale screeningFitoterapia, 2021
- From machine learning to deep learning: Advances in scoring functions for protein–ligand dockingWIREs Computational Molecular Science, 2019
- Role of Trifluoromethyl Substitution in Design of Antimalarial Quinolones: a Comprehensive ReviewTopics in Current Chemistry, 2019
- Assessment of domain boundary predictions and the prediction of intramolecular contacts in CASP8Proteins: Structure, Function, and Bioinformatics, 2009