Simplistic neural network diagram (Adobe Stock)
One of the key promises of AI and machine learning in drug discovery is to reverse decades of declining productivity. But imagine if the technology lives up to its promise. And perhaps six or seven years from now, when productivity doubles, pharmaceutical companies will theoretically have early-stage production lines that are twice as large. “Now, how do pharmaceutical companies manage a production line that has doubled in size?” he asked. Dave Latshaw IIPh.D., Co-Founder, CEO and Chief Scientist of Biophysicsan AI-powered drug development company and author of “6 Signs AI Is Driving Drug Discovery.”
Faced with this reality, pharmaceutical companies can take two steps. “One is to increase staff and all activities in that seven- to 10-year period from discovery to regulatory and commercial approval,” Latshaw said. But the talent pool is not likely to be large enough to double the staff of every pharmaceutical company in development. “The only option left is technology,” Latshaw said. “How do you leverage technology to manage that process and so many additional molecules more efficiently?”
Separating fact from fiction when it comes to AI
While the potential of using AI-based tools like AlphaFold 3, RoseTTAFold All-Atom, machine learning for target identification, etc., is clear, the path to achieving the promised benefits is less straightforward. Pharmaceutical companies looking to figure out how AI can help improve the quality and quantity of their product lines must also navigate a landscape riddled with hype and misconceptions.
Dr Dave Latshaw
For all the hype (and often confusion) surrounding AI’s potential in drug development, Latshaw provides a dose of reality. “There is often a disconnect between what companies are doing and what they say they are doing,” he warns. While this is not necessarily intentional misleading, Latshaw sees a tendency to adapt narratives to popular trends, rather than letting the work speak for itself.
He cites the example of some so-called “AI-discovered” molecules, which often turn out to be the product of traditional research methods with AI applied after the fact for validation. This “veneer” in the narrative, as Latshaw described it, can distort public perception and create unrealistic expectations.
The true measure of AI’s impact lies not in marketing buzzwords, but in tangible progress. “My overall thesis,” he explained, “is that we will succeed in using AI to significantly increase productivity in discovery.” This optimism is based on the potential of tools like BioPhy’s BioLogicAI, which can predict clinical trial outcomes with significant accuracy.
But achieving success at the organization-wide level depends on one crucial factor: the ability to manage the later stages of drug development. “If there’s just a giant bottleneck in development, you’re not going to see any of the benefits of AI in discovery. You’re going to see basically the same level of productivity.”
Dimensional compression
Latshaw’s interest in using data science tools grew when he tried to make sense of a flood of data on the job after arriving at a large pharmaceutical company in 2014 as a technical operations scientist. Faced with a dizzying array of 60 charts tracking every batch of antibody production, he looked for ways to reduce this complexity while also uncovering the hidden relationships that traditional monitoring missed. Thus began his foray into dimensional compression, a technique that would transform not only data visualization but influence R&D efforts at scale.
When he presented the idea to his colleagues, some were initially skeptical. “What are you doing? We’ve been doing it this way for so long,” they said. But he managed to implement the pilot, which “not surprisingly, found that the univariate space was not sufficient to really understand the process,” Latshaw recalled.
By applying dimensional compression, Latshaw’s system transformed the way J&J monitored drug production. Instead of tracking 60 individual data points, the system extracted key features and combined them into a smaller set of latent variables. This provided a much clearer view of the manufacturing process.
Over time, Latshaw’s initial project grew into a large-scale ML R&D program that was implemented across multiple product lines and geographic regions. The project would receive external recognition from the World Economic Forum and McKinsey & Company.
BioPhy’s two-pronged approach to tackling data heterogeneity
Latshaw’s current company, BioPhy, has Two different AI platformseach designed to address a critical aspect of the drug development process. BioLogicAI uses patent-pending technology to shed light on molecular interactions, analyzing the structural and chemical properties of drugs themselves, the structural properties of biological entities, and the structural relationships between all those biological things. This approach, which reportedly has more than 80% accuracy By forecasting clinical trial outcomes, BioPhy can predict drug efficacy and potential toxicity. BioLogicAI guides assets through each phase of clinical trials by continuously assessing the likelihood of success based on multivariate data such as mechanism of action, trial design, personnel, and operations.
In contrast, BioPhyRx is a proprietary generative AI platform developed by BioPhy, specifically designed for life science and drug development applications. It focuses on improving productivity across regulatory, quality, clinical, and operational workflows in the pharmaceutical industry. BioPhyRx provides on-demand scientific and regulatory guidance, as well as automating key processes such as standard operating procedure (SOP) gap analysis. This enables experts to accelerate core drug development functions, from rapid access to and interpretation of regulatory standards to generating pre-submissions tailored to regional requirements in real-time.
Both platforms work in parallel to identify candidates with the greatest potential while dynamically generating insights to efficiently accelerate your development process. This comprehensive approach solves bottlenecks from the preclinical stage to approvals and beyond.
The joint approach between BioLogicAI and BioPhyRx exemplifies Latshaw’s vision for a comprehensive AI-driven transformation of the pharmaceutical industry. “The question is not whether AI will transform drug development,” Latshaw says, “but whether pharmaceutical companies will transform themselves to take full advantage of its potential.”
Filed under: clinical trials, drug discovery, drug discovery and development, machine learning and artificial intelligence
Tagged with: AI in drug discovery, BioLogicAI, BioPhy, BioPhyRx, clinical trial optimization, Dave Latshaw II, pharmaceutical productivity
JOBs Apply News
For the Latest JOBs Apply News, Follow ©JOBs Apply News on Twitter and Linkedin Page.
