Co-authored by Thijs Beuming, Ph.D., “Are Deep Learning Structural Models Sufficiently Accurate for Virtual Screening? Application of Docking Algorithms to AlphaFold2 Predicted Structures” was recently published in the Journal of Chemical Information and Modeling (JCIM).
“AlphaFold has gained an enormous amount of attention, and people claim all kinds of wild things about how it is going to revolutionize the drug discovery process,” says Dr. Beuming. “My co-authors and I back up or invalidate some of these claims in a realistic benchmark experiment.”
Dr. Beuming and his co-authors wrote a previous paper titled “Are Deep Learning Structural Models Sufficiently Accurate for Free-Energy Calculations? Application of FEP+ to AlphaFold2-Predicted Structures.” This paper was published in JCIM in September 2022.
“Both papers are similar in that they try to assess the utility of a new class of models of proteins for prospective computational experiments,” says Dr. Beuming. “We showed that FEP+ calculations can be successful (with caveats) but that virtual screening calculations dramatically fail.”
Dr. Beuming leads the In Silico Drug Discovery Services at LBG. He has more than 15 years of experience applying computational biophysics, computational chemistry, bioinformatics, and cheminformatics to problems in biology and drug discovery in academia and industry.
Prior to joining LBG, Dr. Beuming spent more than a decade at Schrödinger, Inc., the global leader in providing computational chemistry and molecular modeling solutions to the biopharmaceutical and materials industries. He held a leading role in the Application Science department at Schrödinger, where he managed project and customer support for clients in the New York, New Jersey, and Pennsylvania regions.
Dr. Beuming has supervised technology implementations in a variety of fields, including ligand- and structure-based small molecule discovery and biologics research. He also made extensive contributions to Schrödinger’s in-house drug discovery projects while serving in the role of Research Leader in the Drug Discovery Applications Group.
To learn more, visit pubs.acs.org/journal/jcisd8.
