Artificial intelligence (AI) has become a familiar part of early drug discovery, where it is now commonly used for target identification, virtual screening, and managing large biological datasets. Industry adoption has accelerated quickly: a growing share of large pharma companies now report using AI or machine learning in discovery workflows, and global investment in AI-driven drug discovery has climbed into the tens of billions of dollars over the past decade. Still, as these tools move deeper into development, their limitations become harder to ignore — especially when it comes to predicting how a drug will perform in humans.
That challenge shows up most clearly in the translational gap between preclinical research and clinical outcomes. Despite decades of advances, industry data consistently show that roughly 90 percent of drug candidates that enter clinical trials fail, most often because of lack of efficacy or unexpected safety issues.
According to Jo Varshney, CEO and Founder of VeriSIM Life, this is one of the toughest areas for AI to meaningfully improve outcomes. “One of the most challenging areas to integrate AI into has been the translational phase: bridging the gap between preclinical data and human outcomes,” Varshney told DDN. “The underlying issue is that much of the biological data we collect from animal models or cell-based assays doesn’t directly translate to human physiology.”
Because AI models learn from existing datasets, those biological gaps carry forward into predictions. Species differences, experimental variability, and incomplete data can all limit how well a model generalizes to human biology, reducing confidence in AI-driven decisions before a drug ever reaches the clinic.
From pattern recognition to biological understanding
That translational challenge is closely tied to another issue: understanding why a drug works, not just whether it might.
Many machine learning models are excellent at finding correlations across large datasets, but correlation alone is rarely enough to guide late-stage development decisions. “Traditional machine learning excels at finding correlations, but understanding causation in complex biological systems requires hybrid modeling approaches,” Varshney said.
Mechanistic insight becomes increasingly important as programs advance, when developers need to understand dose response, off-target effects, and system-level interactions. Approaches that combine AI with computational biology and physics-based modeling aim to move beyond pattern recognition by grounding predictions in biological mechanisms that better reflect human physiology.
Validation is a critical part of that process, particularly in a regulated environment. “Regulators need confidence that these models are not just statistically robust, but biologically grounded,” Varshney said. That means testing predictions across multiple biological scales, from molecular and cellular effects to whole-organism pharmacology. “Importantly, these validations should not only test the predictions themselves but also probe the assumptions and constraints of the AI models,” she added.
Cross-validation against experimental data remains essential, including comparisons with historical datasets and prospective in vitro, ex vivo, and in vivo studies. Where available, early clinical results can help assess whether predictions extend beyond their training data. Transparency around how models generate outputs is also becoming increasingly important, both for regulatory review and for internal development teams deciding which programs to advance.
Even with these constraints, AI is already delivering measurable value in parts of the pipeline. Its strength lies in integrating and analyzing complex, multi-scale datasets that would be difficult for human teams to manage alone. “AI can process these datasets rapidly, identify patterns that may be invisible to human eyes, and prioritize candidate molecules with far greater efficiency than traditional methods,” Varshney said. Simulation-based approaches can also help reduce reliance on animal studies, lowering costs and shortening timelines in early development.
Human expertise, however, remains central. Scientists and clinicians still play a critical role in interpreting predictions, assessing biological plausibility, and weighing ethical and regulatory considerations. “AI can generate predictions, but humans must evaluate whether those predictions make sense in context,” Varshney said.
As regulators signal growing openness to non-animal and computational approaches, AI is likely to play a larger role in development decision-making. Still, expectations need to remain grounded. “AI is a powerful amplifier of human expertise, not a replacement,” Varshney told DDN.
Looking ahead, whether AI can consistently shorten development timelines without compromising safety will depend on data quality, mechanistic transparency, rigorous validation, and regulatory alignment. If those pieces come together, AI may not eliminate risk from drug development — but it could help teams identify and manage it earlier across the pipeline.
