To evolve AI from pattern matching to understanding physics for protein engineering, structural data is insufficient. Models need physical parameters like Gibbs free energy (delta-G), obtainable from affinity measurements, to become truly predictive and transformative for therapeutic development.

The industry's focus on antibodies, which are easy to generate, may be a case of technology dictating the science. Dr. Radvanyi argues that natural ligand-receptor interactions, which often rely on lower affinity and higher avidity, could offer a more nuanced and effective way to modulate immune pathways than high-affinity agonist antibodies.

An anecdote about a "wonky" BindCraft design with disconnected beta sheets, which experts predicted would fail, highlights a key trend. The resulting binder was one of the best ever produced, suggesting AI models are extracting structural principles that go beyond traditional human "protein literacy" and intuition.

For a modest 100-amino-acid protein, there are 10^130 possible sequences, while all life on Earth has only explored ~10^43. This vast, unexplored space means we can now design binders for "undruggable" targets that evolution never needed to create.

The concept of an "undruggable" target is a misnomer, according to Pacesa. Any failure to create a binder for a specific protein site is a limitation of the current design method or modality, not an intrinsic property of the target. He posits that, with the right approach, a binder can be designed for any site.

Current tools excel at the static binding problem. To advance to creating true therapeutics, models must incorporate the physics of displacing solvent and ions from an interface—currently neglected but one of the "biggest enemies" of strong binding in a physiological context.

The design tool isn't a passive executor. Its multi-component loss function, optimizing for properties like foldedness, can override a user's chosen binding site if it's suboptimal. This "AI agency" is a key feature that contributes to its high success rate in the lab.

Instead of screening billions of nature's existing proteins (a search problem), AI-powered de novo design creates entirely new proteins for specific functions from scratch. This moves the paradigm from hoping to find a match to intentionally engineering the desired molecule.

The pipeline's high success rate stems from its final filter, which uses an AlphaFold model trained only on single proteins (monomers) to predict a protein complex. The rationale is that if a model naive to complexes can still predict the interaction, the interface must be exceptionally strong and well-defined.