Principal Scientist, Cheminformatics & Machine Learning

• Jan 2023 - Present

Senior Scientist II, Cheminformatics & Computational Chemistry

• Aug 2021 - Jan 2023

Review Editor on the Editorial Board of Medicinal and Pharmaceutical Chemistry

• Sep 2019 - Present

Review Editor on the Editorial Board of Theoretical and Computational Chemistry

• Aug 2019 - Present

Scientist, Cheminformatics & Computational Chemistry

• Mar 2019 - Jul 2021

• Lead Biogen computational ADME-Tox predictive modeling with state-of-the-art machine learning and deep learning algorithms. (https://doi.org/10.1021/acs.jcim.3c00160). • Co-lead the developments and deployments of de novo molecule design tools. (See our perspective on generative molecule design in synthesizable space https://link.springer.com/protocol/10.1007/978-1-0716-1787-8_17) • Support the development and deployment of Biogen molecular informatics platform • Support a kinase… Show more • Lead Biogen computational ADME-Tox predictive modeling with state-of-the-art machine learning and deep learning algorithms. (https://doi.org/10.1021/acs.jcim.3c00160). • Co-lead the developments and deployments of de novo molecule design tools. (See our perspective on generative molecule design in synthesizable space https://link.springer.com/protocol/10.1007/978-1-0716-1787-8_17) • Support the development and deployment of Biogen molecular informatics platform • Support a kinase inhibitor project with molecular modeling and informatics • Lead the collaborations with Biogen process chemistry team and pre-formulation team to deliver predictive models for chemical reactions and crystal solvates. • Support the evaluations of external software and techniques in AI-inspired drug discovery Show less • Lead Biogen computational ADME-Tox predictive modeling with state-of-the-art machine learning and deep learning algorithms. (https://doi.org/10.1021/acs.jcim.3c00160). • Co-lead the developments and deployments of de novo molecule design tools. (See our perspective on generative molecule design in synthesizable space https://link.springer.com/protocol/10.1007/978-1-0716-1787-8_17) • Support the development and deployment of Biogen molecular informatics platform • Support a kinase… Show more • Lead Biogen computational ADME-Tox predictive modeling with state-of-the-art machine learning and deep learning algorithms. (https://doi.org/10.1021/acs.jcim.3c00160). • Co-lead the developments and deployments of de novo molecule design tools. (See our perspective on generative molecule design in synthesizable space https://link.springer.com/protocol/10.1007/978-1-0716-1787-8_17) • Support the development and deployment of Biogen molecular informatics platform • Support a kinase inhibitor project with molecular modeling and informatics • Lead the collaborations with Biogen process chemistry team and pre-formulation team to deliver predictive models for chemical reactions and crystal solvates. • Support the evaluations of external software and techniques in AI-inspired drug discovery Show less

Research Scientist in Computational Modeling and Simulation Program

• Aug 2014 - Feb 2019

• Integrate quantum mechanical calculations, ab initio & force field molecular dynamics simulations, energy decomposition analysis, and machine learning to investigate the mechanism, reactivity and selectivity in polymer and organic chemical reactions. • Developed the first computational model for the mechanism and reactivity of one of the most important polymer synthesis reaction (Atom Transfer Radical Polymerization, ATRP) in both copper and photoredox catalyzed systems. • Published 10… Show more • Integrate quantum mechanical calculations, ab initio & force field molecular dynamics simulations, energy decomposition analysis, and machine learning to investigate the mechanism, reactivity and selectivity in polymer and organic chemical reactions. • Developed the first computational model for the mechanism and reactivity of one of the most important polymer synthesis reaction (Atom Transfer Radical Polymerization, ATRP) in both copper and photoredox catalyzed systems. • Published 10 papers including 6 in JACS and 1 in Angew Chem

Pharmacometrician in Center for Clinical Pharmaceutical Sciences

• May 2014 - Aug 2014

• Develop computational kinetic model to study the pathophysiological mechanism of Gestational Diabetes Mellitus (GDM). Estimated parameters obtained from the model provides insights to study insulin sensitivity and beta­‐cell function in GDM.

Research Scientist in Department of Pharmaceutical Sciences

• Aug 2012 - Apr 2014

• Performed polypharmacology analysis for FDA-proved anti-osteoporosis drugs via high-throughput molecular docking and 2D-similarity search. • Built computational models for multiple domain protein Sequestosome-1/p62 with homology modeling and MD simulation. • Analyzed the novelty and diversity of chemical libraries using cheminformatics techniques (i.e. BCUT-defined chemistry space partition and 2D similarity calculation.)

Associate Specialist in Modeling & Informatics

• Jun 2018 - Aug 2018

Develop a genetic algorithm-based molecule evolver as a digital assistant for de novo drug design • Built a Pipeline Pilot workflow to streamline molecule generator, molecule annotator, and molecule selector for automatic generation of new compounds with desirable properties. • Implemented deep learning models for molecule generation and assessment of synthetic complexity for proposed idea molecules. • Worked closely and effectively with discovery project modelers and applied the… Show more Develop a genetic algorithm-based molecule evolver as a digital assistant for de novo drug design • Built a Pipeline Pilot workflow to streamline molecule generator, molecule annotator, and molecule selector for automatic generation of new compounds with desirable properties. • Implemented deep learning models for molecule generation and assessment of synthetic complexity for proposed idea molecules. • Worked closely and effectively with discovery project modelers and applied the molecule evolver to 4 ongoing Merck projects for lead compound discovery & optimization. Show less Develop a genetic algorithm-based molecule evolver as a digital assistant for de novo drug design • Built a Pipeline Pilot workflow to streamline molecule generator, molecule annotator, and molecule selector for automatic generation of new compounds with desirable properties. • Implemented deep learning models for molecule generation and assessment of synthetic complexity for proposed idea molecules. • Worked closely and effectively with discovery project modelers and applied the… Show more Develop a genetic algorithm-based molecule evolver as a digital assistant for de novo drug design • Built a Pipeline Pilot workflow to streamline molecule generator, molecule annotator, and molecule selector for automatic generation of new compounds with desirable properties. • Implemented deep learning models for molecule generation and assessment of synthetic complexity for proposed idea molecules. • Worked closely and effectively with discovery project modelers and applied the molecule evolver to 4 ongoing Merck projects for lead compound discovery & optimization. Show less

Computational Chemistry-Machine Learning Intern

• Jun 2017 - Aug 2017

Developed machine learning models to predict P-Glycoprotein substrate for in-house compounds • Developed 5 single and 3 ensemble classifiers for prediction of P-gp substrates for 3000+ compounds. The best model achieves more than 85% accuracy. • Developed a workflow to automate feature selection, hyper-parameter tuning, model validation, and model evolution for each learning models. Developed machine learning models to predict P-Glycoprotein substrate for in-house compounds • Developed 5 single and 3 ensemble classifiers for prediction of P-gp substrates for 3000+ compounds. The best model achieves more than 85% accuracy. • Developed a workflow to automate feature selection, hyper-parameter tuning, model validation, and model evolution for each learning models.

Application Specialist Intern

• May 2012 - Jul 2012

Application scientist of computational chemistry scientific software (MOE/LeadIT/Derek) for drug design, lead compound optimization, toxicity prediction. Application scientist of computational chemistry scientific software (MOE/LeadIT/Derek) for drug design, lead compound optimization, toxicity prediction.

Research Assistant in Institute of Materia Medica

• Sep 2008 - May 2012

Computer-Aided design and discovery of novel CDK9 inhibitors as anti‐HIV agents. • Developed the first 3D-QSAR pharmacophore model for CDK9 inhibitors. • Built a virtual combinatorial library from representative CDK9 lead compounds. • Performed virtual screening and scaffold-hopping to discover novel CDK9 inhibitors. Develop a computational virtual screening platform for anti-diabetic leads & target identification for Traditional Chinese Medicine (In collaboration with Novo… Show more Computer-Aided design and discovery of novel CDK9 inhibitors as anti‐HIV agents. • Developed the first 3D-QSAR pharmacophore model for CDK9 inhibitors. • Built a virtual combinatorial library from representative CDK9 lead compounds. • Performed virtual screening and scaffold-hopping to discover novel CDK9 inhibitors. Develop a computational virtual screening platform for anti-diabetic leads & target identification for Traditional Chinese Medicine (In collaboration with Novo Nordisk). Show less Computer-Aided design and discovery of novel CDK9 inhibitors as anti‐HIV agents. • Developed the first 3D-QSAR pharmacophore model for CDK9 inhibitors. • Built a virtual combinatorial library from representative CDK9 lead compounds. • Performed virtual screening and scaffold-hopping to discover novel CDK9 inhibitors. Develop a computational virtual screening platform for anti-diabetic leads & target identification for Traditional Chinese Medicine (In collaboration with Novo… Show more Computer-Aided design and discovery of novel CDK9 inhibitors as anti‐HIV agents. • Developed the first 3D-QSAR pharmacophore model for CDK9 inhibitors. • Built a virtual combinatorial library from representative CDK9 lead compounds. • Performed virtual screening and scaffold-hopping to discover novel CDK9 inhibitors. Develop a computational virtual screening platform for anti-diabetic leads & target identification for Traditional Chinese Medicine (In collaboration with Novo Nordisk). Show less