The company focuses on disease-specific 3D protein conformations, which exposes new binding sites (epitopes) not present on the same protein in healthy cells. This allows for highly selective drugs that avoid the toxicity common with targets defined by genetic sequence alone.

Unlike traditional approaches, Immunethep's vaccine doesn't kill bacteria. Instead, it neutralizes a virulence mechanism bacteria use to shut down the immune system. This restores the body's natural ability to fight infection, a novel strategy analogous to checkpoint inhibitors in oncology.

Professor Collins' AI models, trained only to kill a specific pathogen, unexpectedly identified compounds that were narrow-spectrum—sparing beneficial gut bacteria. This suggests the AI is implicitly learning structural features correlated with pathogen-specificity, a highly desirable but difficult-to-design property.

Instead of the traditional 'disease-target-drug' approach, Soleil finds compounds that create a desired cellular change first. Only after identifying a promising, well-tolerated molecule with a known cellular mechanism do they use bioinformatics to determine which disease and patient population it's best suited for.

While biologics get much attention, a significant investment opportunity lies in next-generation small molecules like degraders and hetero-bifunctional molecules. These advanced chemistries allow companies to target known, de-risked biological pathways in novel ways, hitting previously 'undruggable' targets and creating powerful new drugs.

The field of infectious disease is moving away from empirical treatment toward its own version of precision medicine. Similar to how oncology uses companion diagnostics to guide therapy, new rapid molecular tests are enabling clinicians to identify the specific organism and its resistance profile to prescribe the right antibiotic at the right time.

Haya's approach redefines the drug target. Instead of focusing on single proteins or pathways, they identify the "causal unit" of disease as the cellular behaviors that dictate how patients feel, function, and survive, and then work backwards to find a target.

The AI-discovered antibiotic Halicin showed no evolved resistance in E. coli after 30 days. This is likely because it hits multiple protein targets simultaneously, a complex property that AI is well-suited to identify and which makes it exponentially harder for bacteria to develop resistance.

Profluent CEO Ali Madani frames the history of medicine (like penicillin) as one of random discovery—finding useful molecules in nature. His company uses AI language models to move beyond this "caveman-like" approach. By designing novel proteins from scratch, they are shifting the paradigm from finding a needle in a haystack to engineering the exact needle required.