April 8, 2025
Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
“The Quest for A.I. ‘Scientific Superintelligence.’” That’s the headline for a New York Times article about Lila Sciences development of an AI program trained on published and experimental data, as well as the scientific process and reasoning. The start-up then lets that AI software run experiments in automated, physical labs with a few scientists to assist. “AI will power the next revolution of this most valuable thing humans ever stumbled across — the scientific method,” said Geoffrey von
Maltzahn, Lila’s Chief Executive, who has a Ph.D. in biomedical engineering and medical physics from the Massachusetts Institute of Technology. My own opinion is that the Internet was the most disruptive invention of our lifetime, because it brought all our brains and computers together and it set up the training set for modern AI. However, there is a large subset of the AI experts in the world who are betting on AGI (Artificial General Intelligence) emerging in our lifetime. The basic idea is AGI would match or surpass human intelligence generally. It is interesting to think about a world in which intelligence becomes more of a commodity. In any case, this article describes trays carrying 96 wells of DNA samples riding on magnetic tracks, shifting directions quickly for delivery to different lab stations, depending partly on what the AI suggests. Molly Gibson, a computational biologist and a Lila co-founder, said “Our goal is really to give AI access to run the scientific method — to come up with new ideas and actually go into the lab and test those ideas.” The article also quotes David Baker, a biochemist and Director of the Institute for Protein Design at the University of Washington, who last year shared the Nobel Prize in Chemistry for his work in computational protein design, who said: “More power to them, if they can do it. It seems beyond anything I’m familiar with in scientific discovery."
* * *
NVIDIA Tools for Accelerating Drug Discovery Pipelines. This one is timely in light of the CDD Vault integration with the NVIDIA BioNeMo™ NIM microservices for AlphaFold2 and DiffDock models. NVIDIA has released a brief, helpful guide to its BioNeMo for biopharma, a collection of frameworks, applications, generative AI solutions, and pretrained models. The guide looks at the NVIDIA BioNeMo Framework, an open-source machine learning framework for building and training deep learning models for biopharma; NVIDIA BioNeMo Blueprints, pretrained reference workflows designed for generative AI applications in drug discovery, offering biopharma teams a foundation to accelerate research and innovation; and NVIDIA BioNeMo NIM™, a set of optimized, easy-to-use AI microservices built to enable gigascale inference and enable new capabilities in drug design. Combining the CDD Vault AI Module, with generative bioisosteres and ultrafast chemistry deep learning search within the AlphaFold2 NIM model allows scientists to iteratively explore chemical and biological space within their natural workflows. NVIDIA announced it is building a Boston-based research center to provide cutting-edge technologies to advance quantum computing. The NVIDIA Accelerated Quantum Research Center, or NVAQC, will integrate leading quantum hardware with AI supercomputers, enabling what is known as accelerated quantum supercomputing. NVIDIA in the past has been Bullish and Bearish about Quantum computing, they are now putting their money where their mouth is: “Quantum computing will augment AI supercomputers to tackle some of the world’s most important problems, from drug discovery to materials development,” said Jensen Huang, founder and CEO of NVIDIA. “Working with the wider quantum research community to advance CUDA-quantum hybrid computing, the NVIDIA Accelerated Quantum Research Center is where breakthroughs will be made to create large-scale, useful, accelerated quantum supercomputers.”
* * *
"AI-Powered Databases Boost the Alzheimer’s Drug Discovery Process." That’s the headline from an article in the The Wall Street Journal about how researchers studying Alzheimer’s disease use AI-powered databases to sift through vast amounts of biomedical data. Scientists at the United Kingdom’s Oxford Drug Discovery Institute are using AI to more quickly prioritize which genes or proteins should be selected for further work to generate potential Alzheimer’s drugs. The article notes that picking genes to target for research can be tricky because there are so many genes that can increase the risk of developing disease, and because the disease has so many confounding environmental and socioeconomic risk factors. The researchers are using a knowledge graph, a database technology popularized by Google over a decade ago for its search engine, enabling staff to more quickly decipher a target’s properties across a large number of scientific journals and other sources—including the U.S. National Library of Medicine’s PubMed. Incidentally, as a side project, CDD’s PharmaKB.com tracks the keywords as an API accessible data feed for all the approved and clinical drugs, their targets and their disease and trends daily from PubMed Central Abstracts.
* * *
A New Open-Source Coronavirus Protease Inhibitor: “Enamine Has Already Prepared a Half Kilo of the Compound For Them.” Derek Lowe, in his blog in Science writes about work announced a few days ago at the Spring ACS meeting in San Diego from a team at the Drugs for Neglected Diseases Institute (DNDi). Given our long-term support of Neglected Diseases including support of all researchers in Africa working on NTD, this announcement was near and dear to my heart. Specifically, this is their AI/computational group, AViD-ASAP, and they've been working on coronavirus protease inhibitors, with an eye to making compounds that would be active on more than just the SARS-CoV-2 virus. Note that this is a completely open-source project involving people from a number of research sites around the world. Lowe writes: “DNDi is now concentrating its preclinical efforts on this newer molecule, as you can see from this October 2024 RFP document. According to a C&E News report, Enamine has already prepared a half kilo of the compound for them.” Here was our announcement back in 2023:
https://www.collaborativedrug.com/cdd-blog/cdd-vault-offer-africa.
* * *
Barry A. Bunin, PhD, is the Founder & CEO of Collaborative Drug Discovery, which provides a modern approach to drug discovery research informatics trusted globally by thousands of leading researchers. The CDD Vault is a hosted biological and chemical database that securely manages your private and external data.