Research
The Laboratory for Molecular Modeling (MML) develops and applies computational methods and software to address outstanding problems in the areas of molecular and materials design and discovery. Our methods and technologies afford rigorous processing of domain-specific data streams and the creation of predictive models that reliably prioritize experimental studies. Specific projects include the development of methods and models to accelerate drug discovery (supported by NIH grants R01GM140154) and enable chemical safety assessment and the selection or design of novel drug candidates with optimal ADMET (Adsorption, Distribution, Metabolism, Excretion, Toxicity) properties (supported by NIH grants R41ES033857 and R41ES033589), with applications to several pharmaceutical areas including Alzheimer’s Disease (previously supported by NIH grant R56AG059428), cancer (previously supported by NIH grant U01CA207160), and viral diseases (supported by NIH grant U19AI171292). We are also actively working in the emerging area of biomedical knowledge graph mining (supported by NIH grants U24ES035214 and 3OT2TR003441 and a UNC Creativity Hub grant) building tools and methodologies for addressing complex biomedical questions. Another area of active research is materials informatics where we collaborate with colleagues in the UNC Departments of Chemistry and Applied Physical Sciences to support the AI accelerated discovery of solar energy materials (supported by a UNC Creativity Hub grant).
See Funding for more information about our funding sources
Selected publications by areas of research:
Computer-Aided Drug Discovery
-
Tropsha A. Best Practices for QSAR Model Development, Validation, and Exploitation. Mol Inform [Internet] 2010 [cited 2013 Jun 10];29(6–7):476–88. Available from: http://doi.wiley.com/10.1002/minf.201000061
-
Cherkasov A, Muratov EN, Fourches D, et al. QSAR Modeling: Where have you been? Where are you going to? J Med Chem [Internet] 2014 [cited 2013 Dec 22];57(12):4977–5010. Available from: http://www.ncbi.nlm.nih.gov/pubmed/24351051
-
Popova M, Isayev O, Tropsha A. Deep reinforcement learning for de novo drug design. Sci Adv 2018;4(7):eaap7885
-
Muratov EN, Amaro R, Andrade CH, et al. A critical overview of computational approaches employed for COVID-19 drug discovery. Chem Soc Rev [Internet] 2021 [cited 2021 Jul 21];50:9121–51. Available from: https://pubs.rsc.org/en/content/articlehtml/2021/cs/d0cs01065k
-
Muratov EN, Bajorath J, Sheridan RP, et al. QSAR without borders. Chem Soc Rev [Internet] 2020 [cited 2020 Jul 9];49(11):3525–64. Available from: https://pubs.rsc.org/en/content/articlehtml/2020/cs/d0cs00098a
ADME/Tox Modeling
-
Borba JVVB, Alves V, Braga R, et al. STopTox: An in-silico alternative to animal testing for acute Systemic and Topical Toxicity. Environ Health Perspect 2022;130(2):27012.
-
Alves VM, Capuzzi SJ, Braga RC, et al. A Perspective and a New Integrated Computational Strategy for Skin Sensitization Assessment. ACS Sustain Chem Eng [Internet] 2018 [cited 2018 Feb 12];6:2845–2859. Available from: http://pubs.acs.org/doi/10.1021/acssuschemeng.7b04220
-
Alves V, Muratov E, Capuzzi S, et al. Alarms about structural alerts. Green Chem 2016;18(16):4348–60.
Biomedical Knowledge graph mining
-
Bizon C, Cox S, Balhoff J, et al. ROBOKOP KG and KGB: Integrated Knowledge Graphs from Federated Sources. J Chem Inf Model 2019;59(12):4968–73.
-
Korn D, Thieme AJ, Alves VM, et al. Defining clinical outcome pathways. Drug Discov Today 2022;27(6):1671–8.
Materials Informatics
-
Isayev O, Tropsha A, Curtarolo S, editors. Materials Informatics : Methods, Tools, and Applications. Wiley-VCH; 2019.
-
Moot T, Isayev O, Call RW, et al. Material informatics driven design and experimental validation of lead titanate as an aqueous solar photocathode. Mater Discov 2016;6:9–16.
-
Isayev O, Fourches D, Muratov EN, et al. Materials Cartography: Representing and Mining Materials Space Using Structural and Electronic Fingerprints. Chem Mater [Internet] 2015 [cited 2015 Jun 26];27(3):735–43. Available from: http://dx.doi.org/10.1021/cm503507h