Prediction is overhead when verification is cheap.

We've spent years building a system where verification is cheap -- generationally so.

This changes the logic of discovery in ways that are easy to underestimate. I tried to write a little about what that means: www.jurabio.com/blog/onebill...

Today we're releasing a technical blogpost on LIFT, a system that increases the information density of wetlab experiments by orders of magnitude without requiring more cells, more reagents, or more sequencing.

Paper: arxiv.org/abs/2510.16612
Blog: www.jura.bio/blog/leavs
Team: @lizbwood.bsky.social @highvariance.bsky.social @mgollub.bsky.social

We demonstrate empirically and prove theoretically that LeaVS can dramatically accelerate learning, increasing the effective dataset size by orders of magnitude.

Crucially, it depends on jointly modifying the experimental protocol and the training algorithm: on their own, neither modification helps.

This approach lets you focus limited measurements on the most informative datapoints, maximizing information gain without compromising reliability.

Second, modify the training algorithm: compensate for the missing negatives by incorporating the generative variational synthesis model into the objective.

First, modify the experiment: only measure positive examples of functional proteins. Don't spend a limited sequencing budget on any negatives.

In this paper we describe a method to overcome this measurement bottleneck.

To test, we can deliver billions of designs to different cells. But there is a cost to recovering those designs' function, to obtain (x,y) data.

With variational synthesis, we can now build quadrillions of generative model-designed sequences. The bottleneck is now testing, not synthesis.

Scaling up protein ML requires understanding and eliminating bottlenecks in the design-build-test-learn cycle.

You can read more in our post at www.jurabio.com/blog/leavs; preprint forthcoming.

@jura.bsky.social @eliweinstein.bsky.social @mgollub.bsky.social @highvariance.bsky.social

If you are interested in working with me as a student or postdoc, or otherwise collaborating, please reach out.