By using foundation models to analyze vast datasets, companies can create a synthetic 'standard of care' arm for single-arm Phase 1 trials. The AI matches patients based on deep clinical and genomic parameters, providing insights comparable to a much larger Phase 3 trial.

The long-term strategy for AI in drug discovery is a two-step process. First, create an AI platform to design effective drugs. Second, after a dozen or so AI-designed drugs succeed, use that data to convince regulators to trust AI predictions, potentially allowing future drugs to skip steps like animal testing and accelerate trials.

The transition to an engineering discipline in drug discovery, analogous to aeronautics, means using powerful in silico models to get much closer to a final product before physical testing. This reduces reliance on iterative, expensive, and time-consuming wet lab experiments.

The push away from animal models is a technical necessity, not just an ethical one. Advanced therapeutics like T-cell engagers and multispecific antibodies depend on human-specific biological pathways. These mechanisms are not accurately reproduced in animal models, rendering them ineffective for testing these new drug classes.

Unlearn.ai's method for late-phase trials (PROCOVA) is acceptable to regulators because it's designed to statistically correct for any bias in the digital twin model. This ensures the model's inaccuracy doesn't affect the trial's final decision procedure or error rate, a critical feature distinguishing it from simply replacing the control arm.

Despite hype around alternative methods, animal models will remain essential in drug development for the foreseeable future. The CEO argues that AI and ML will primarily make these studies more efficient by reducing the number of animals needed and improving data interpretation, not by eliminating the preclinical animal testing stage entirely.

Instead of the high-risk approach of replacing a trial's control arm with digital twins, Unlearn.ai adds counterfactual data to every participant. This method increases a trial's statistical power, allowing for smaller control arms or a higher chance of success, while satisfying regulatory constraints for pivotal trials.

It's impossible to generate human data at the scale of in silico experiments. The key is to create highly accurate simulations of human physiology (digital twins) and then validate their predictions with limited, strategic human data. If the model proves reliable, it could drastically accelerate R&D.

Conquer's Farsight Twin can predict a patient's response to a novel drug, standard of care, and the combination therapy separately. This allows pharma companies to determine if a positive response in an early-phase trial is truly driven by their new asset or just the background therapy, providing crucial efficacy data.