# Information-Dense Synthesis for Molecular Discovery

arXiv: https://arxiv.org/abs/2610.08495 · HTML: https://mlsanity.com/paper/2610.08495/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 82 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 11 of 11)

- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro](https://mlsanity.com/paper/1912.11554/) (2019)
- [Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design](https://mlsanity.com/paper/2103.02438/) (2021)
- [Automated Variational Inference in Probabilistic Programming](https://mlsanity.com/paper/1301.1299/) (2013)
- [Biological Sequence Kernels with Guaranteed Flexibility](https://mlsanity.com/paper/2304.03775/) (2023)
- [Combined Global and Local Search for Optimization with Gaussian Process Models](https://mlsanity.com/paper/2107.03217/) (2021)
- [Purely Agent-Driven Black-Box Optimization for Biological Design](https://mlsanity.com/paper/2601.22382/) (2026)
- [Estimating the Causal Effects of T Cell Receptors](https://mlsanity.com/paper/2410.14127/) (2024)
- [Wasserstein Gradient Flows for Batch Bayesian Optimal Experimental Design](https://mlsanity.com/paper/2603.12102/) (2026)
- [AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning](https://mlsanity.com/paper/2605.28287/) (2026)
- [Flexible Kernels for Protein Property Prediction](https://mlsanity.com/paper/2606.11057/) (2026)

## Abstract (arXiv)

Machine learning can accelerate molecular discovery by designing molecules and planning experiments. However, many scientific challenges demand molecules with very rare properties, and in this sparse setting, existing algorithms offer little gain over random guessing. We propose a method to efficiently search large regions of molecular space using algorithmically controlled stochastic synthesis. Rather than design, make and test individual molecules, we design and make complex mixtures, test them as a pool, then deconvolute the molecule-activity map. We optimize synthesis to encode maximal information. Theoretically, this approach can reduce the number of experiments required to find the optimal molecule among d candidates from O(d) to O(log d) or O(1). In simulation, on estimated protein fitness landscapes, it finds active molecules with an order of magnitude fewer experiments than existing Bayesian optimization methods.