One strategy to scale up ML-driven science is to increase wet lab experiments' information density. We present a method based on a neural extension of compressed sensing to function space. We measure the activity of multiple different molecules simultaneously, rather than individually. Then, we deconvolute the molecule-activity map during model training. Co-design of wet lab experiments and learning algorithms provably leads to orders-of-magnitude gains in information density. We demonstrate on antibodies and cell therapies.
@article{arxiv.2512.15984,
title = {Lifting Biomolecular Data Acquisition},
author = {Eli N. Weinstein and Andrei Slabodkin and Mattia G. Gollub and Kerry Dobbs and Xiao-Bing Cui and Fang Zhang and Kristina Gurung and Elizabeth B. Wood},
journal= {arXiv preprint arXiv:2512.15984},
year = {2025}
}