Traditional wet lab scientists working on target discovery, drug identification, and drug optimization have an opportunity to catch up with their AI-enabled colleagues, but why and how should they do so? 3 In this article, the first in a series of parts, Dr. Raminderpal Singh outlines the big picture before touching on specific methods and finally discussing the risks and changes needed in the next two articles. We are trying to demystify this topic by doing so.
To calibrate our expectations for the use of AI, here's a sober perspective.1.
Patrick Malone, principal at KdT Ventures in the US, says clinical victories in biotechnology are rare, with an estimated 5 to 10 percent of drugs heading to human trials actually approved. It is said that1
“If you were to take the hype and PR of the last 10 years at face value, you would think that AI progress has gone from 5% to 90%,” Malone said of AI. “But if you know how these models work, that percentage will go from 5% to 6-7%.”
Of course, with billions of dollars being invested in AI-driven drug discovery programs, companies like Isomorphic Labs, Recursion, Exscientia, Flagship Pioneering, big biopharmaceuticals, and even the “$1 Billion+ Bet”2 About Xaira Therapeutics, which is investing heavily in the potential of AI.
As we take a closer look at the various uses of AI (and data), we begin to see new patterns in where AI is being applied and why it is inevitable. Consider the following example.
- Generate and analyze existing data
- Design of composite structures
- to design in vitro experiment
- Understanding and modeling biological mechanisms
- Extract deep insights from across literature and research reports
- Design proteins.
Being able to perform the above activities quickly and cost-effectively is great, but of course it's an understatement given the recent stress on early-stage (preclinical) biotechs with equity funding.3 Additionally, funding for preclinical platform biotechs is tightening as investors increasingly favor companies with clinical-stage assets (per Q1 2024 funding report).3
The value needed is not just about increasing the number of FDA approvals, but also about achieving milestones with limited capital: biotech survival.
As with most industries, there are early adopters and those who are waiting for the technology to “cross the chasm.”Four And become mainstream. The latter group (i.e. most of us) are waiting for wet lab validation, market demonstration (FDA approval), and a few other things (often undefinable). However, this tactic comes with its own risks. Just like when traditional automakers tried to catch up with Tesla, waiting can be too late.Five
There is no reason why early-stage biotechs cannot implement simple but effective AI. The next article in this series, published on Friday, May 24th, will provide some tips.
References
1 Dan A. Endpoint news. After years of hype, the first AI-designed drugs fall short in the clinic. [Internet] 2023 [updated 2023 October 19; cited 2024 April]. Available from: https://endpts.com/first-ai-designed-drugs-fall-short-in-the-clinic-following-years-of-hype/
2 Cross R, Dunn A. Endpoint news. Exclusive: In a $1B+ bet on AI, biopharmaceutical heavyweights back new startups that will transform drug research and development. [Internet] 2024 [updated 2024 April 23; cited 2024 April]. Available from: https://endpts.com/in-biggest-ever-bet-on-using-ai-to-design-drugs-biotech-heavyweights-launch-xaira-with-1b-in-backing/
3 Bants B. Drug discovery and development. In the first quarter of 2024, 20 biotech startups raised approximately $3 billion. [Internet] [2024 April 5, cited 2024 April]. Available from: https://www.drugdiscoverytrends.com/20-biotech-startups-attracted-almost-3b-in-q1-2024-funding/
Four Moore GA, McKenna R. 1999. Crossing the chasm: Marketing and selling high-tech products to mainstream customers. Harper Collins.
Five Randall T. Who are Tesla's EV competitors? economic times [Internet]. [updated 2023 October 5, cited 2024 April]. Available from: https://economictimes.indiatimes.com/industry/renewables/where-is-teslas-ev-competition/articleshow/104193382.cms?from=mdr
About the author
Dr. Raminderpal Singh is known as a key opinion leader in the technology bio industry. He has over 30 years of global experience leading and advising teams on building computational modeling systems that are cost effective and have high intellectual property value. His passion is to help early to mid-life science companies achieve new biological breakthroughs through the effective use of computer modeling.
Raminderpal currently leads the HitchhikersAI.org open source community to accelerate the adoption of AI technologies in early drug discovery. He is also his CEO and co-founder of Incubate Bio, a technology company serving life science companies seeking to accelerate research and reduce the cost of wet labs through in silico modeling. .
Raminderpal has extensive experience building businesses in both Europe and the United States. As an executive at his IBM Research in New York, Dr. Singh led the market development of IBM Watson Genomics Analytics. He was also Vice President and Head of Microbiome at Eagle Genomics Ltd in Cambridge. Raminderpal received his PhD in semiconductor modeling in 1997. He has published several papers and his two books and holds 12 patents. In 2003, he was named one of the top 13 most influential people in the semiconductor industry by EE Times.
For more information: http://raminderpalsingh.com ; http://hitchhikersAI.org ; http://incubate.bio
