Support The World's Smartest Network

Help the New York Academy of Sciences bring late-breaking scientific information about the COVID-19 pandemic to global audiences. Please make a tax-deductible gift today.

This site uses cookies.
Learn more.


This website uses cookies. Some of the cookies we use are essential for parts of the website to operate while others offer you a better browsing experience. You give us your permission to use cookies, by continuing to use our website after you have received the cookie notification. To find out more about cookies on this website and how to change your cookie settings, see our Privacy policy and Terms of Use.

We encourage you to learn more about cookies on our site in our Privacy policy and Terms of Use.


Understanding the Applications of AI in Chemical Biology

Understanding the Applications of AI in Chemical Biology
Reported by
Barbara Knappmeyer, PhD

Posted June 11, 2021

Presented By

Chemical Biology Discussion Group

The New York Academy of Sciences

Rapid developments in machine learning, natural language processing and other aspects of Artificial Intelligence (AI) have revolutionized many fields over the last decades. Chemical biology is no exception. Broad applications that include predicting reaction chemistry, automating lab processes, detangling complex biochemical processes, and hastening drug discovery and developments, have the potential to enhance our understanding of chemical biology in unprecedented ways.

However, keeping up with latest developments and appropriately integrating these novel methodologies into chemical biology research can be a daunting. To address these challenges, this e-Briefing features recent advances in chemical biology that were enabled by AI and highlight best practices for employing AI techniques in this field. 

Topics include, deep learning approaches to antibiotic discovery, AI in the automation process of analog synthesis, machine learning for molecular and materials design, and novel methods of visualizing molecular machines. These topics and more were illuminated from both the basic science and the industry perspective.


  • Samples of the latest research in chemical biology that was enabled through the use of artificial intelligence. >
  • Benefits and challenges for employing artificial intelligence in chemical biology. >
  • New applications for artificial intelligence in drug discovery and development of new therapeutics in the field of chemical biology. >


James Collins, PhD
James Collins, PhD

Massachusetts Institute of Technology

Peter Madrid
Peter Madrid, PhD

SRI International

Alán Aspuru-Guzik
Álan Aspuru-Guzik, PhD

University of Toronto

Roy Nassar, MSc
Roy Nassar, MSc

Stony Brook University

Fabio Urbina, PhD
Fabio Urbina, PhD

Collaborations Pharmaceuticals, Inc.

Joseph (Joey) Davis
Joseph (Joey) Davis, PhD

Massachusetts Institute of Technology

Cesar de la Fuente
César de la Fuente, PhD

University of Pennsylvania

Timothy Cernak
Timothy Cernak, PhD

University of Michigan

Georgia McGaughey
Georgia McGaughey, PhD

Vertex Pharmaceuticals

AI in Chemical Biology: New Frontiers


Keynote: A Deep Learning Approach to Antibiotic Discovery

James Collins, PhD Massachusetts Institute of Technology

Jim Collins is the Termeer Professor of Medical Engineering & Science and Professor of Biological Engineering at MIT, as well as a Member of the Harvard-MIT Health Sciences & Technology Faculty. He is also a Core Founding Faculty member of the Wyss Institute for Biologically Inspired Engineering at Harvard University, and an Institute Member of the Broad Institute of MIT and Harvard. He is one of the founders of the field of synthetic biology, and his research group is currently focused on using synthetic biology to create next-generation diagnostics and therapeutics. Professor Collins' patented technologies have been licensed by over 25 biotech, pharma and medical devices companies, and he has helped to launch a number of companies, including Synlogic and Sherlock Biosciences. He has received numerous awards and honors, including a Rhodes Scholarship and a MacArthur "Genius" Award, and he is an elected member of all three national academies - the National Academy of Sciences, the National Academy of Engineering, and the National Academy of Medicine.

Keynote: A Deep Learning Approach to Antibiotic Discovery

James Collins (Massachusetts Institute of Technology)

Automating the Efficient Synthesis of Analogs from AI Designs

Peter Madrid,  PhD SRI International

Peter Madrid is the VP of the Applied Research group in the Biosciences division of SRI International. He has extensive experience setting up, leading and delivering on technology development programs in chemistry and biology. Dr. Madrid’s group primarily focuses on highthroughput discovery technologies and combining machine learning methods with automation.

He is currently the Principal Investigator (PI) on a DARPA DSO program called Accelerated Molecular Discovery (AMD) that is combining AI with synthesis automation to perform molecular discovery more rapidly. Dr. Madrid was also PI on DARPA program to develop discovery new classes of high-energy materials and was Co-PI on the DARPA Make-It program focused on chemical synthesis automation. Additionally, he has a broad background in infectious disease drug discovery, having lead programs that discovered new drug candidate compounds with potent anti-infective/anti-cancer activities. Dr. Madrid has over 40 publications and 10 issued patents. He received his Ph.D. in Chemistry and Chemical Biology from the University of California, San Francisco, and his B.S. in Chemistry with Highest Honors from the University of California, Santa Cruz.

Further Readings


Tan X, Letendre JH, Collins JJ, Wong WW.

Cell. 2021 Feb 18;184(4):881-898.

Stokes JM, Yang K, Swanson K, Jin W, Cubillos-Ruiz A, et al.

Cell. 2020 Feb; 180: 688-702.

Meeting Report Page Two


Machine Learning and Automation for Molecular and Materials Design

Álan Aspuru-Guzik, PhD University of Toronto

Alán Aspuru-Guzik’s research lies at the interface of computer science with chemistry and physics. He works in the integration of robotics, machine learning and high-throughput quantum chemistry for the development of materials acceleration platforms. These “self-driving laboratories¨ promise to accelerate the rate of scientific discovery, with applications to clean energy and optoelectronic materials. Alán also develops quantum computer algorithms for quantum machine learning and has pioneered quantum algorithms for the simulation of matter. He is jointly appointed as a Professor of Chemistry and Computer Science at the University of Toronto. Alán is a faculty member of the Vector Institute for Artificial Intelligence. Previously, Alán was a full professor at Harvard University where he started his career in 2006. Alán is currently the Canada 150 Research Chair in Quantum Chemistry as well as a CIFAR AI Chair at the Vector Institute. Amongst other awards, Alán is a recipient of the Google Focused Award in Quantum Computing, the MIT Technology Review 35 under 35, and the Sloan and Camille and Henry Dreyfus Fellowships. Alán is a fellow of the American Association of the Advancement of Science and the American Physical Society. He is a co-founder of Zapata Computing and Kebotix, two early-stage ventures in quantum computing and self-driving laboratories respectively.

Machine Learning and Automation for Molecular and Materials Design

Álan Aspuru-Guzik (University of Toronto)

Protein Folding with MELDxMD Guided by Machine Learning Predicted Contacts

Roy Nassar, MSc Stony Brook University

Roy Nassar is a PhD candidate in the Department of Chemistry at Stony Brook University. He is conducting his research at the Laufer Center for Physical and Quantitative Biology under the supervision of Prof Ken Dill. Roy’s current research is focused on developing and applying advanced molecular dynamics methods for computationally modeling proteins. Specifically, Roy is working on integrating information from machine learning to accelerate protein folding simulations in a physics-based framework.

Protein Folding with MELDxMD Guided by Machine Learning Predicted Contacts

Roy Nassar (Stony Brook University)

Comparing Recurrent Neural Networks, Generative Adversarial Networks and Variational Autoencoders for Drug Design​

Fabio Urbina, PhD Collaborations Pharmaceuticals, Inc.

Dr. Urbina received his Ph.D. in Cell Biology and Physiology from the University of North Carolina in 2020 before joining Collaborations Pharmaceuticals, Inc. At UNC, he developed image analysis tools used in conjunction with Total Internal Reflection Fluorescence microscopy used in neuronal imaging. He devised an automated image analysis pipeline which detected and classified exocytic events in primary neuron cultures. At Collaborations Pharmaceuticals, Inc., he continues his computational work by implementing and testing new generative models in drug discovery and development.

Comparing Recurrent Neural Networks, Generative Adversarial Networks and Variational
Autoencoders for Drug Design

Fabio Urbina (Collaborations Pharmaceuticals, Inc.)

Further Readings


Pollice R, dos Passos Gomes G, Aldeghi M, Hickman RJ, Krenn M, et al

Acc Chem Res. 2021 Feb 2; 54, 4, 849-860.

Meeting Report Page Three


Visualizing Molecular Machines in Motion using Cryo Electron Microscopy and Deep Learning

Joseph (Joey) Davis, PhD Massachusetts Institute of Technology

Professor Joseph (Joey) Davis received bachelor’s degrees in Computer Science and Biological Engineering at UC Berkeley and completed a Ph.D. in Biology at MIT under the direction of Profs. Bob Sauer and Tania Baker. Following an appointment as a senior scientist at Ginkgo BioWorks, Joey performed research at the Scripps Research Institute with Profs. Jamie Williamson and Malene Hansen as a Jane Coffin Childs’ and K99 Post-doctoral Fellow. In 2018, Joey returned to MIT as the Whitehead assistant professor in the Department of Biology. There, his lab develops and applies structural and biochemical techniques to understand ribosome biogenesis and the formation of eukaryotic  autophagosomes. This work is supported by the Alfred P. Sloan foundation, an NSF CAREER award and funding from the Jameel-Clinic for AI at MIT. Outside the lab, Joey enjoys surfing (even in New Hampshire), skiing in his hometown in Colorado, and watching his 18-month-old son begin to explore the world.

Visualizing Molecular Machines in Motion using Cryo Electron Microscopy and Deep Learning

Joseph (Joey) Davis (Massachusetts Institute of Technology)

Antibiotic Discovery by Means of Computers

César de la Fuente, PhD University of Pennsylvania

César de la Fuente is a Presidential Assistant Professor at the University of Pennsylvania, where he leads the Machine Biology Group whose goal is to combine the power of machines and biology to study, prevent, diagnose, and treat infectious diseases. Current application areas in his lab include developing novel approaches for antibiotic discovery, building tools for microbiome engineering, and creating low-cost diagnostics. Specifically, he pioneered the development of the first antibiotic designed by a computer with efficacy in animal, designed pattern recognition algorithms for antibiotic discovery, successfully reprogrammed venoms into novel antimicrobials, created novel resistance-proof antimicrobial materials, and invented rapid low-cost diagnostics for COVID-19 and other infectious diseases. De la Fuente is an NIH MIRA investigator, a BBRF Young Investigator, and has received recognition and research funding from numerous other groups.

Professor de la Fuente was recognized by MIT Technology Review in 2019 as one of the world’s top innovators for “digitizing evolution to make better antibiotics”. He was selected as the inaugural recipient of the Langer Prize (2019), an ACS Kavli Emerging Leader in Chemistry (2020), and received the Nemirovsky Prize (2020), AIChE’s 35 Under 35 Award (2020), and the ACS Infectious Diseases Young Investigator Award (2020). In addition, he was named a Boston Latino 30 Under 30, a 2018 Wunderkind by STAT News, a Top 10 Under 40 of 2019 by GEN, a Top 10 MIT Technology Review Innovator Under 35 (Spain), 30 Rising Leaders in the Life Sciences and received the 2019 Society of Hispanic Professional Engineers Young Investigator Award in addition to the 2021 Young Innovator in Cellular and Molecular Bioengineering and the 2021 Biomedical Engineering Society (BMES) CMBE Rising Star Award. His scientific discoveries have yielded over 85 peer-reviewed publications, including papers in Nature CommunicationsPNASACS NanoCellNature Communications Biology, and multiple patents.

Antibiotic Discovery by Means of Computers

César de la Fuente (University of Pennsylvania)

Synthesis in the Chemical Space Age

Timothy Cernak, PhD University of Michigan

Tim Cernak was born in Montreal, Canada in 1980. He obtained a B.Sc. in Chemistry from University of British Columbia Okanagan and there studied the aroma profile of Chardonnay wines. Following PhD training in total synthesis with Professor Jim Gleason at McGill University, Tim was a FQRNT Postdoctoral Fellow with Tristan Lambert at Columbia University. In 2009, Tim joined the Medicinal Chemistry team at Merck Sharp & Dohme in Rahway, New Jersey. There he developed technologies for miniaturized synthesis and late-stage functionalization. In 2013, Tim moved to Merck’s Boston site. In 2018, Dr. Cernak transitioned from industry to academia and launched a lab at the University of Michigan in Ann Arbor as an Assistant Professor of Medicinal Chemistry. The Cernak Lab is exploring an interface of chemical synthesis and data science.

Synthesis in the Chemical Space Age

Timothy Cernak (University of Michigan)

AI in Chemical Biology: A Perspective from Industry

Georgia McGaughey, PhD Vertex Pharmaceuticals

Georgia McGaughey is the Executive Director of the Data and Computational Sciences group at Vertex Pharmaceuticals Inc., comprised of computational chemistry, computational genomics and methods development. Through her twenty-plus year career in pharmaceuticals (Wyeth, Merck, Vertex) Georgia has contributed to the invention and advancement of several clinical candidates and marketed medicines (e.g. BACE, orexin, PDE10, CFTR and KDR) and has contributed to more than 100 publications and presentations. She is a past member of the editorial advisory board for the Journal of Medicinal Chemistry and participant of multiple study sections for the NIH. Currently, she volunteers in the Boston scientific community through mentorship with high school and college students, is an editorial board member of the Journal of Chemical Information and Modeling, serves on Silent Spring Institute’s board, is this year’s chair of the Computed Aided Drug Design GRC and is a member of the Scientific Advisory Board for the Cambridge Crystallographic Data Centre (CCDC).  Georgia earned her B.S. degree in chemistry from Kennesaw State College, her Ph.D. in physical chemistry from the University of Georgia and an Advanced Management Program (AMP199) business certificate from Harvard Business School .  She carried out her post-doctoral studies with focus on electronic structure theory at Colorado State University.  She is also an avid runner and plays the piano.

AI in Chemical Biology: A Perspective from Industry

Georgia McGaughey (Vertex Pharmaceuticals)

Further Readings


Davis JH*, Tan YZ*, Carragher B, Potter CS, Lyumkis D, Williamson JR.

Cell. 2016; 167(6):1610-1622.

Tan YZ, Baldwin PR, Davis JH, Williamson JR, Potter CS, Carragher B, Lyumkis D.

Nature Methods. 2017; 14(8):793-796.

de la Fuente

Torres MDT, Cao J, Franco OL, Lu TK, de la Fuente-Nunez C.

ACS Nano. 2021; 15(2):2143-2164

Marcelo Der Torossian Torres and Cesar de la Fuente-Nunez.

Chemical Communications. 2019 (100).


Shen Y, Borowski JE, Hardy MA, Sarpong R, Doyle AG, Cernak T.

Nat Rev Methods. Primers 1, 23 (2021)

Mahjour B, Shen Y, Liu W, and Cernak T.

Nature. 2020; 580:71-75.


McGaughey G, Swett R, Swift S, Chudyk E, Wong K.

J Chem Inf Model. 2019 May 28;59(5):1693-1696.

Bower MJ, Aronov AM, Cleveland T, Hariparsad N, McGaughey GB, McMasters DR, Zhang X, Goldman B.

J Chem Inf Model. 2020 Apr 27;60(4):2091-2099.