Structure Prediction Models Degrade Without Co-Evolutionary Sequence Data
Jeremy Wohlwend · 🔬Generating Molecules, Not Just Models · Feb 12, 2026 · at 10:24
Jeremy Wohlwend, co-founder of Boltz, explains how protein structure models rely heavily on evolutionary correlations rather than purely learning physical folding principles from scratch.
0:00 / 0:07exact quote · 7.3s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“What it implies also is that, you know, in absence of that co-evolutionary landscape, the models don't quite perform as well.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Jeremy Wohlwend
AI Excels at Structure Prediction but Fails to Model Physical Folding
“Folding is the more complex process of actually understanding, like, how it goes from, like, this disordered state into, like, a structured, like, state, and that I don't think we've made that much progress on, but the idea of, like, yeah, going straight to th…”
ML Folding Models Only Possess Localized Understanding of Physics
“I think one of the thing, at least I believe is that once you're in that sort of approximate, you know, area of the solution space, then the models have like some understanding, you know, of how to get you to like, you know, the low energy low energy state. An…”
Compute Constraints Forced Boltz-1 to Train Once With In-Flight Bug Fixes
“And actually we only trained the big model once. That's how much compute we had. We could only train it once. And so like, while the model was training, we were like finding bugs left and right. A lot of them that I wrote. Yeah. And like, I would, I remember l…”
Models Excel at Monomeric Proteins but Struggle on Other Biomolecular Modalities
“And, you know, we've seen in some of the latest GASP competitions, like, while we're becoming really, really good at proteins, especially monomeric proteins you know, other modalities still remain pretty difficult.”
Current Models Fail to Predict Protein Conformational Dynamics and States
“Proteins are not static. They move, they take different shapes based on their energy states. And I think we are also not that good at understanding the different states that the protein can be in and at what frequency, what probability.”
Pairwise Representation Mechanisms Have Survived Since AlphaFold 2
“And yeah, I think too, it's really survived the test of time. I mean, you know, this thing came out in 20, 21 and it's largely the same. I mean, there's been this change to the structure module that's been like largely simplified, but where a lot of the magic …”