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.

Non-human primate models are poor predictors of human immunogenicity. The industry has shifted to human-relevant ex vivo assays using whole blood or PBMCs. These tests can assess risks like complement activation upfront, enabling proactive protein engineering to improve a drug's safety profile.

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.

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.

The FDA is abandoning rigid, fixed-length clinical trials for a "continuous" model. Using AI and Bayesian statistics, regulators can monitor data in real-time and approve a drug the moment efficacy is proven, rather than waiting for an arbitrary end date, accelerating access for patients.

The FDA's traditional focus on risk avoidance overlooks the inherent risk of delay. Unnecessary bureaucratic steps, like months of animal trials, prevent dying patients from accessing potentially life-saving treatments. The cost of inaction is measured in lives lost.

Contrary to the perception that drug development is all about human trials, the first five years of the typical decade-long journey are dedicated to rigorous preclinical work. This foundational stage involves chemistry and non-human testing before a molecule ever reaches a patient.

Using safety and preliminary efficacy data from its lead drug for MPS1, Immusoft successfully requested an FDA waiver for definitive toxicology studies for its next program in MPS2. This platform approach saves significant time and capital, accelerating the entire pipeline without 'reinventing the wheel'.

The NIH will no longer award funding to new grant proposals that rely exclusively on animal models. This policy forces a shift towards New Approach Methodologies (NAMs), such as organoids and organ-on-chips, serving as a major catalyst for innovation and adoption in the preclinical testing space.