Wendy Cornell

Wendy is IBM Research Strategy Co-Lead for Drug Discovery Technologies Ecosystem and Partnerships where she leverages her in-depth knowledge of pharmaceutical industry use cases and technology solutions to guide development of new molecular technologies incorporating latest AI and mechanistic chemistry and biomedical information and to validate the technology in partnership with collaborators at Cleveland Clinic and pharmaceutical and biotechnology companies.

Wendy joined IBM in 2016 after twenty years in the pharmaceutical industry where she led teams at Merck and Novartis in the development, application, and evaluation of technologies for chemistry modeling, cheminformatics, machine learning, text mining, and knowledge management to support science-based pipeline decisions for lead finding and optimization, target assessment, preclinical safety, and preclinical competitive intelligence.

A Fellow of the American Chemical Society (ACS), Wendy has held multiple leadership roles in ACS governance, including past Chair and past Program Chair of the Computers in Chemistry (COMP) technical division. She was a member of the SAB for the Stony Brook University Institute of Chemical Biology and Drug Discovery (ICB&DD) and adjunct faculty member at Robert Wood Johnson Medical School, where she served as primary thesis advisor for a Ph.D. student. She has also served on multiple NIH panels.

Wendy received her Ph.D. from the University of California at San Francisco (UCSF) working with the late Peter Kollman and resulting in a primary publication describing the AMBER classical force field which has received > 15,000 citations.  After UCSF she did a brief postdoctoral stint at European Molecular Biology Laboratory (EMBL) in Heidelberg. Wendy received an MBA from Case Western Reserve University Weatherhead School of Management in Cleveland, OH on the Cleveland Clinic Healthcare track and enjoys studying the business impact of information technologies.

Representative publications from IBM and from previous pharmaceutical industry roles

In-Pocket 3D Graphs Enhance Ligand-Target Compatibility in Generative Small-Molecule Creation Seung-gu Kang, Jeffrey K. Weber, Joseph A. Morrone, Leili Zhang, Tien Huynh, and Wendy D. Cornell arXiv 2022

Deep generative molecular design reshapes drug discovery Xiangxiang Zeng, Fei Wang, Yuan Luo, Seung-gu Kang, Jian Tang, Felice C. Lightstone, Evandro F. Fang, Wendy Cornell, Ruth Nussinov, and Feixiong Cheng Cell Reports Medicine 2022

CACHE (Critical Assessment of Computational Hit-finding Experiments): A public-private partnership benchmarking initiative to enable the development of computational methods for hit-finding Suzanne Ackloo, Suzanne Ackloo, Rima Al-awar, Rima Al-awar, Rommie E. Amaro, Cheryl H. Arrowsmith, Cheryl H. Arrowsmith, Hatylas Azevedo, Robert A. Batey, Yoshua Bengio, Ulrich A.K. Betz, Cristian G. Bologa, John D. Chodera, Wendy D. Cornell, Ian Dunham, Gerhard F. Ecker, Kristina Edfeldt, Aled M. Edwards, Aled M. Edwards, Michael K. Gilson, Claudia R. Gordijo, Claudia R. Gordijo, Gerhard Hessler, Alexander Hillisch, Anders Hogner, John J. Irwin, Johanna M. Jansen, Daniel Kuhn, Andrew R. Leach, Alpha A. Lee, Uta Lessel, John Moult, Ingo Muegge, Tudor I. Oprea, Benjamin G. Perry, Patrick Riley, Kumar Singh Saikatendu, Vijayaratnam Santhakumar, Vijayaratnam Santhakumar, Matthieu Schapira, Matthieu Schapira, Cora Scholten, Matthew H. Todd, Masoud Vedadi, Masoud Vedadi, Andrea Volkamer, Timothy M. Willson Nat Rev Chem 2022

On the Choice of Active Site Sequences for Kinase-Ligand Affinity Prediction Jannis Born, Yoel Shoshan, Tien Huynh, Wendy D. Cornell, Eric J. Martin, and Matteo Manica J Chem Info Model  2022

Active Site Sequence Representations of Human Kinases Outperform Full Sequence Representations for Affinity Prediction and Inhibitor Generation: 3D Effects in a 1D Model Jannis Born, Tien Huynh, Astrid Stroobants, Wendy D. Cornell, and Matteo Manica J Chem Info Model  2022

Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder – Insights for practical AI-driven molecule generation Seung-gu Kang, Joseph A. Morrone, Jeffrey K. Weber, and Wendy D. Cornell J Chem Info Model  2021

Simplified, interpretable graph convolutional neural networks for small molecule activity prediction Jeffrey K. Weber, Joseph A. Morrone, Sugato Bagchi, Jan D. Estrada Pabon, Seung-gu Kang, Leili Zhang & Wendy D. Cornell  J Comput-Aided Mol Des 2021

Combining Docking Pose Rank and Structure with Deep Learning Improves Protein–Ligand Binding Mode Prediction over a Baseline Docking Approach Joseph A. Morrone, Jeffrey K. Weber, Tien Huynh, Heng Luo, and Wendy D. Cornell J Chem Info Model 2020 

Role of chronic toxicology studies in revealing new toxicities 
Galijatovic-Idrizbegovic, Alema and Miller, Judith E and Cornell, Wendy D and Butler, James A and Wollenberg, Gordon K and Sistare, Frank D and DeGeorge, Joseph J 
Regulatory Toxicology and Pharmacology 2016

Application of an automated natural language processing (NLP) workflow to enable federated search of external biomedical content in drug discovery and development McEntire, Robin and Szalkowski, Debbie and Butler, James and Kuo, Michelle S and Chang, Meiping and Chang, Man and Freeman, Darren and McQuay, Sarah and Patel, Jagruti and McGlashen, Michael and others 
Drug Discovery Today 2016

Developing timely insights into comparative effectiveness research with a text-mining pipeline  Chang, Meiping and Chang, Man and Reed, Jane Z and Milward, David and Xu, Jinghai James and Cornell, Wendy D 
Drug Discovery Today 2016

QSAR Prediction of Passive Permeability in the LLC-PK1 Cell Line: Trends in Molecular Properties and Cross-Prediction of Caco-2 Permeabilities Sherer, Edward C and Verras, Andreas and Madeira, Maria and Hagmann, William K and Sheridan, Robert P and Roberts, Drew and Bleasby, Kelly and Cornell, Wendy D Molecular Informatics 2012

Drug-like density: a method of quantifying the “bindability” of a protein target based on a very large set of pockets and drug-like ligands from the Protein Data Bank 
Sheridan, Robert P and Maiorov, Vladimir N and Holloway, M Katharine and Cornell, Wendy D and Gao, Ying-Duo 
J Chem Info Model 2010

QSAR models for predicting the similarity in binding profiles for pairs of protein kinases and the variation of models between experimental data sets 
Sheridan, Robert P and Nam, Kiyean and Maiorov, Vladimir N and McMasters, Daniel R and Cornell, Wendy D 
J Chem Info Model_2009

Comparison of topological, shape, and docking methods in virtual screening 
McGaughey, Georgia B and Sheridan, Robert P and Bayly, Christopher I and Culberson, J Chris and Kreatsoulas, Constantine and Lindsley, Stacey and Maiorov, Vladimir and Truchon, Jean-Francois and Cornell, Wendy D 
Journal of chemical information and modeling 47(4), 1504--1519, ACS Publications, 2007

Recent evaluations of high throughput docking methods for pharmaceutical lead finding--consensus and caveats 
Cornell, Wendy D 
Annual Reports in Computational Chemistry 2006

A second generation force field for the simulation of proteins, nucleic acids, and organic molecules 
Cornell, Wendy D and Cieplak, Piotr and Bayly, Christopher I and Gould, Ian R and Merz, Kenneth M and Ferguson, David M and Spellmeyer, David C and Fox, Thomas and Caldwell, James W and Kollman, Peter A 
J Am Chem Soc 1995