Wendy Cornell  Wendy Cornell photo       

contact information

Drug Discovery Strategy Lead, Manager Drug Discovery Technologies, PRSM, Healthcare and Life Science Research
Thomas J. Watson Research Center, Yorktown Heights, NY USA


Professional Associations

Professional Associations:  American Chemical Society

more information

More information:  LinkedIn profile  |  Google Scholar profile



 IBM Role

Dr. Cornell joined IBM in 2016 after twenty years in the pharmaceutical industry where she led chemistry modeling, cheminformatics, text mining, and knowledge management groups at Merck and Novartis in the development and application of science-based pipeline decision support solutions.  At IBM Dr. Cornell leverages her broad experience base in technologies and use cases as Strategy Lead for Drug Discovery across the IBM Research Labs, investigating opportunities to leverage quantum computing, deep learning, and other emerging technologies. She personally leads the SmartRx project to semi-automate structure-based lead finding and optimization using molecular dynamics approaches.  Dr. Cornell also explores the use of dynamic information to define determinants of selectivity and ligand residence time.

Pharmaceutical Industry Experience

During her time in the pharmaceutical industry, Dr. Cornell recruited and led science and solutions groups located in the Research, Licensing, and IT organizations:

As Director of Knowledge Discovery and Management at Merck (2011-2015) her competitive intelligence (CI) team developed NLP-based text mining solutions to support preclinical CI and Licensing using content from Medline abstracts, ClinicalTrials.gov, NIH Reporter, patents, conference abstracts, other external sources, and proprietary content. Teams supporting proprietary document management extracted conclusions from internal preclinical safety assessment study reports to correlate short term and long term results and identify capability gaps and also protected, integrated, and exposed at-risk legacy paper files.

As Director of Chemistry Modeling and Informatics at Merck (2004-2010), her group supported drug discovery projects in the four therapeutic areas present at Rahway, Merck’s then largest research site, using similarity methods, QSAR, docking, molecular dynamics, and other approaches to identify new leads, maximize on-target potency, and minimize off-target effects.  She managed teams that developed novel solutions to assess target bindability and kinase selectability by integrating 3D protein structure, protein sequence, and activity data.  

At Merck Dr. Cornell also served on the New Technologies Review and Licensing Committee as chair of the Chemistry working group and member of the IT working group, identifying internal capability gaps and evaluating and integrating external solutions.  Her group initiated the first major collaboration between Modeling and Process Chemistry to establish vibrational CD capabilities which led to an ongoing and greatly expanded engagement.

 Professional Service

A Fellow of the American Chemical Society (ACS), Dr. Cornell is active in ACS governance, currently serving as Chair of the Committee on Chemical Abstracts Service (CCAS), connecting ACS members with CAS, an ACS division which provides chemical information and has $1B in assets and $500M in annual revenues. She is past Program Chair and past Chair of the Computers in Chemistry (COMP) technical division and currently serves as COMP Leadership Development Chair. She is also a member of the SAB for the Stony Brook University Institute of Chemical Biology and Drug Discovery (ICB&DD). A former adjunct faculty member at Robert Wood Johnson Medical School, Dr. Cornell served as primary thesis advisor for a Ph.D. student. She has also served on multiple NIH Small Business Innovation Research (SBIR) panels.


Dr. Cornell received her Ph.D. from the University of California at San Francisco (UCSF) working with the late Peter Kollman and the primary publication resulting from that collaboration describing the AMBER classical force field has received greater than 10,000 citations.  After UCSF she did a brief postdoctoral stint at European Molecular Biology Laboratory (EMBL) in Heidelberg. Dr. Cornell 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.

Key Publications

Text Mining/NLP

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 Pharmacology82, 94--98, Elsevier, 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 21(5), 826--835, Elsevier, 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 21(3), 473--480, Elsevier, 2016

QSAR/Machine Learning

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 31(3-4), 231--245, Wiley Online Library, 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
Journal of chemical information and modeling 50(11), 2029--2040, ACS Publications, 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
Journal of chemical information and modeling 49(8), 1974--1985, ACS Publications, 2009

Similarity Searching and Docking

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 Chemistry2, 297--323, Elsevier, 2006

Classical Force Fields (10,000+ citations)

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
Journal of the American Chemical Society 117(19), 5179--5197, ACS Publications, 1995