EP 63

The Era of NAMs

The pharmaceutical industry is undergoing a profound shift in how new medicines are discovered, tested, and validated. The era of New Approach Methodologies (NAMs) is upon us, with a focus on using human biology and artificial intelligence to create a safer and more accurate pipeline for drug development. This episode explores the current state of NAMs, the challenges and limitations of traditional animal testing, and the potential of hybrid approaches that combine physical and computational models.

NAMsNew Approach MethodologiesMicrophysiological SystemsArtificial IntelligenceDrug DiscoveryToxicity Testing

play_arrowListen to episode

Key Concepts

New Approach Methodologies (NAMs)

NAMs are a new approach to testing human drugs on actual human biology before they reach clinical trials.
NAMs include microphysiological systems, such as organ-on-a-chip technologies, and artificial intelligence.

Microphysiological Systems

Microphysiological systems are used to replicate human biology and test drug efficacy and toxicity.
Examples include organ-on-a-chip technologies and 3D spheroids.

Artificial Intelligence in Drug Discovery

AI is being used to predict drug-induced liver injury and improve the accuracy of toxicity testing.
AI can also be used to design better physical assays and extract latent phenotypes from high-content imaging.

Hybrid Approach

A hybrid approach combines NAMs, AI, and limited animal testing.
This approach is the most scientifically justified approach for now, as it reduces the number of animals used and filters out obvious toxic failures.

Fair Data Standards

Fair data standards are essential for ensuring regulatory confidence in AI-driven results.
The NIH Data Hub and ORIVA office are critical in enforcing fair data standards.

Episode Summary

check_circleThe pharmaceutical industry is moving away from traditional animal testing due to its limitations and unreliability.
check_circleNew Approach Methodologies (NAMs) are being developed to test human drugs on actual human biology before they reach clinical trials.
check_circleThe NIH is investing $150 million in awards to support the development of NAMs and create a unified ecosystem for biological data.
check_circleThe FDA's 2025 roadmap emphasizes the need for structured, auditable evidence packages to replace animal testing.
check_circleMicrophysiological systems, such as organ-on-a-chip technologies, are being used to replicate human biology and test drug efficacy and toxicity.
check_circleArtificial intelligence is being integrated with physical biological systems to speed up the testing process and correct for physical limitations.
check_circleThe combination of AI and physical biology has shown promising results in predicting drug-induced liver injury and improving the accuracy of toxicity testing.
check_circleHowever, there are risks associated with relying on AI, including dataset bias and domain shift, which can lead to inaccurate predictions.
check_circleThe NIH Data Hub and ORIVA office are critical in enforcing fair data standards and ensuring regulatory confidence in AI-driven results.
check_circleA hybrid approach that combines NAMs, AI, and limited animal testing is the most scientifically justified approach for now.

Full Transcript

Discussion

Join the discussion — sign in to leave a comment.