Dr. Miteva has completed their PhD in 2000 in the Institute of Organic Chemistry, Bulgarian Academy of Science. She has been working in the fields of bioinformatics, chemoinformatics, drug discovery and toxicity prediction in Bulgaria, Sweden and France. Currently she is a Research Director at the Inserm Institute in France and co-director of the Inserm lab U1268 “Medicinal chemistry and translational research” at the Faculty of Pharmacy, University of Paris. She published 97 scientific articles in peer-reviewed journals and she edited a book “In silico lead discovery“ (Bentham Sci 2011). She is an appointed member of the editorial board of five international journals in the field of bioinformatics and drug design, and Associated Editor for BMC Pharmacology and Toxicology.

OpenTox Euro 2019 talk: Integrated Mechanistic and Machine Learning Approach to predict Drug-Drug Interactions of CYP

Cytochrome P450 enzymes (CYP) are responsible for the metabolism of 90 % drugs and thus they play a central role in drug metabolism (1,2), drug-drug interactions and pharmacogenetics. While their principal role is to detoxify organisms by metabolizing compounds, such as pollutants or drugs, for a rapid excretion, in some cases they render their substrates more toxic thereby inducing adverse drug reactions, or their inhibition can lead to drug-drug interactions. The malfunction of CYP, e.g. due to single nucleotide polymorphism (3-5), could lead to decreased drug metabolism causing toxicity, or affected prodrug activation. Predicting potential inhibition of CYP is important in early-stage drug discovery. We developed an original in silico approach for prediction of CYP inhibition for two CYP isoforms combining the knowledge of the protein structure and its dynamic behavior in response to the binding of various ligands and machine learning modeling (6). This approach includes structural information for CYP based on the available crystal structures and molecular dynamic simulations (MD) that we performed to take into account conformational changes of the binding site. We performed modeling using two learning algorithms, Support Vector Machine (SVM) and RandomForest combining chemicals, protein-ligand interactions and protein structure and dynamics information. The experimental validation of our original approach is in progress. Our inhibition models predict CYP inhibition for two isoforms with an accuracy of >80 % on large external validation sets.

Bibliographic references:

1. Testa B, Pedretti A, Vistoli G (2012) Reactions and enzymes in the metabolism of drugs and other xenobiotics. Drug Discov Today 17: 549-560 

2. Moroy G, Martiny VY, Vayer P, Villoutreix BO, Miteva MA (2012) Toward in silico structure-based ADMET prediction in drug discovery. Drug Discov Today. 17(1-2):44-55

3. Martiny VY , Miteva MA (2013) Advances in molecular modeling of human cytochrome P450 polymorphism.  J Mol Biol. 425 (21): 3978-92

4. Isvoran A, Louet M, Vladoiu DL, Craciun D, Loriot MA, Villoutreix BO, Miteva MA. (2017) Pharmacogenomics of the cytochrome P450 2C family: impacts of amino acid variations on drug metabolism. Drug Discov Today. 22(2):366-376

5. Louet M, Labbé CM , Fagnen C, Aono CM, Homem-de-Mello P, Villoutreix BO, Miteva MA (2018) Insights into molecular mechanisms of drug metabolism dysfunction of human CYP2C9*30. PLoS One 13(5) : 1-21

6. Martiny VY, Carbonell P, Chevillard F, Moroy G, Nicot A B, Vayer P, Villoutreix BO, Miteva MA (2015) Integrated structure- and ligand-based in silico approach to predict inhibition of cytochrome P450 2D6. Bioinformatics 31(24) : 3930-7