Instead of waiting for allergy patients to have symptoms on study days, Dr. Abelson’s team created a model to induce the allergic reaction in a controlled way. This 'Conjunctival Allergy Challenge' allowed for precise, predictable testing of new drugs, dramatically speeding up development.

A major cause of clinical trial failure is unforeseen toxicity. By creating AI-powered models based on single-cell atlases, researchers can predict which unintended cells express a drug's target receptor. This allows them to anticipate side effects, like kidney toxicity, in silico, saving billions in failed drug development.

Instead of testing a single drug candidate in cheap models before moving to expensive ones, Gordian's parallel testing platform makes it cost-effective to use clinically relevant large animals, like horses, at the very beginning of the discovery process. This flips the traditional R&D funnel on its head.

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 $5 billion cost to develop a drug is primarily driven by the high failure rate (9 out of 10) in late-stage trials. AI's biggest financial impact will be predicting which drugs will succeed, drastically reducing wasted R&D. This efficiency is what will ultimately make drugs more affordable.

Pharmaceutical companies like Pfizer have vast amounts of human genetic data (GWAS hits) linked to diseases but struggle to determine which are viable drug targets. Gordian's high-throughput in vivo screening directly tests the causal effects of hundreds of these targets, rapidly identifying the most promising candidates.

The process of testing drugs in humans—clinical development—is a massive, under-studied bottleneck, accounting for 70% of drug development costs. Despite its importance, there is surprisingly little public knowledge, academic research, or even basic documentation on how to improve this crucial stage.

With over 5,000 oncology drugs in development and a 9-out-of-10 failure rate, the current model of running large, sequential clinical trials is not viable. New diagnostic platforms are essential to select drugs and patient populations more intelligently and much earlier in the process.

The FDA is eliminating mandatory animal testing because it's often misleading—90% of drugs passing animal studies fail in humans. The agency is embracing modern alternatives like computational modeling and organ-on-a-chip technology to get faster, more accurate safety data.