Lessons Learned for AI in Small Molecule Drug Discovery
The article discusses the longstanding use of machine learning in small molecule drug discovery, highlights the recent surge of AI-driven start-ups amid industry hype, and emphasizes the need to temper expectations by learning from past technology challenges and other industries to successfully implement AI in drug discovery.
Despite the buzz around artificial intelligence (AI), most industry insiders know that the use of machine learning (ML) in drug discovery is nothing new. For more than a decade, researchers have used computational techniques for many purposes, such as finding hits, modeling drug-protein interactions, and predicting reaction rates.
What is new is the hype. As AI has taken off in other industries, countless start-ups have emerged promising to transform drug discovery and design with AI-based technologies. While a few “AI-native” candidates are in clinical trials, around 90% remain in discovery or preclinical development, so it will take years to see if the bets pay off. This begs the question: Is AI for drug discovery more hype than hope? Absolutely not. Do we need to adjust our expectations and position for success? Absolutely, yes.
In this webinar, we will discuss:
- Learnings from previous technology implementation challenges
- Learnings from adjacent industries
- Three Keys to Successful AI implementation
Related
Reasonable Expectations, Clean Data, Collaboration: The Three Keys to AI in Drug Discovery
The article explains that while AI and machine learning have long been used in drug discovery, recent hype and massive investments have led to unrealistic expectations, emphasizing that success depends on setting reasonable goals, ensuring clean and abundant data, and fostering collaboration, as most AI-driven drug candidates remain in early development stages and face complex biological and practical challenges.
Gray TV Washington DC: AI helping scientists make drug breakthroughs
The Gray TV Washington DC feature highlights how scientists, including Christian Olsen of Dotmatics, are leveraging AI and machine learning to accelerate drug discovery and expedite bringing new drugs to market.
Webinar: Three Key Considerations When Implementing AI in Drug Discovery
The webinar, led by Haydn Boehm, focuses on three key considerations—reasonable expectations, clean data, and collaboration—for successfully implementing AI in small molecule drug discovery amidst the current hype and ongoing preclinical development of AI-native candidates.
No big-bang moment: An AI-supported future in pharma will take time
Thomas Swalla, CEO of Dotmatics, discusses in a Fox News article how AI is poised to transform drug discovery by potentially saving billions and speeding up therapy delivery, while emphasizing that despite industry readiness, significant and growing barriers mean progress will be gradual through cumulative small advances rather than an immediate breakthrough.
NBC Las Vegas: AI is Accelerating Drug Discovery and Vaccine Development
In an NBC Las Vegas interview, Phil Mounteney, VP of Science and Technology at Dotmatics, explains how AI is transforming drug discovery and vaccine development by accelerating research timelines, reducing costs, enhancing drug safety through advanced data analysis, and optimizing development pipelines for faster and more efficient medical breakthroughs post-COVID.
CBS News: How AI Is Accelerating Safer, More Personalized Drug Discovery
In a CBS News interview, Dotmatics VP Phil Mounteney explains how their internally developed AI models accelerate drug discovery by analyzing early-phase research data to shorten development cycles, reduce costs, and deliver safer, personalized therapies while maintaining data privacy.