Comment by cyberax

Both "yes" and "no". AI has been doing great in protein structure prediction.

It's a task that is well suited for the current generation of AIs, (most) proteins consist of a constrained "alphabet" of components, and the alphabet then forms recognizable shapes ("motifs"). So working backwards and generating a protein that binds with another protein is the logical next step.

The problem is in the efficacy. Monoclonal antibodies work surprisingly poorly as antivenoms. They are too specific, and real venom is a mix of multiple kinds of proteins with a lot of variation. Which makes sense, as venoms are under high selective pressure, so there's going to be a lot of genetic variability within a single species (never mind _across_ species).

Snake antivenoms are a major underserved area with a decent amount of research. But so far the century-old method of producing antivenoms (injecting horses and then collecting their blood plasma) is the best one.