The AI × AAV Interpreter

TL;Dr Do not set your collaboration to failure from Day 1.  Learn how to speak with ML teams.  The typical AAV-ML collaboration failure scenario goes like this:  The collaboration looked good on paper. An ML team with a strong publication record, an experimental team with three years of capsid library data, a shared interest in CNS targeting. The first few meetings were energizing, the kind where everyone leaves feeling like something real is about to happen. Six months later : a ranked list of 200 variants, a brief methods section explaining that a transformer-based model was trained on the pooled screen data and optimized for predicted transduction scores, and a looming decision about which 20 variants to actually synthesize.  Nobody can clearly explain why variant 47 ranked above variant 12. Nobody wants to be the one to say that out loud. The experimental team is wondering whether to trust the list or quietly fall back on their own instincts. The ML team is wait...

TL;DR   Structure prediction tools answer a question about shape. AAV capsid engineering requires answers about function. These are not the same question, and confusing them is how engineering programs fail. The conversation that prompted this article A gene therapy program recently asked me to advise them on a potential computational collaboration. The pitch from the computational side was straightforward: they would use AlphaFold-like tools to identify functional AAV capsid variants. Not as a starting point for further screening. Not as a filter to eliminate obvious failures before experimental testing. As the primary discovery engine. Zero-shot. Predict the structure, identify the functional capsid, done. I did not advise them to proceed. Not because the computational team was incompetent. They were not. Not because structure prediction tools are bad. They are not. But because the entire proposal was built on a category error: the assumption that predicting what a capsid looks l...

TL;DR   The scientist who knows when to trust ML results, and when to push back, is the most useful scientist in the room. Be that Scientist.  There is an as ymmetry built into every conversation between an ML practitioner and an experimental AAV scientist, and it works against you. ML practitioners report results in a language that was not designed for experimental decision-making: AUC, precision-recall, held-out accuracy, latent space coverage. These are real concepts with real meaning, but they are also words that land with the weight of rigor even when the underlying work does not earn that weight.  A 90% accuracy sounds like a good thing.   AAV scientists are trained, correctly, to trust quantitative results. You were taught that numbers mean something. That discipline is a virtue. In this context, it is also a vulnerability. The result is a field where genuinely useful ML work gets adopted uncritically because the metrics looked good, and where other genuinely ...