Information-Dense Synthesis for Molecular Discovery

Key points

• Machine learning can accelerate molecular discovery by designing molecules and planning experiments.1
• However, many scientific challenges demand molecules with very rare properties, and in this sparse setting, existing algorithms offer little gain over random guessing.1
• We optimize synthesis to encode maximal information.1
• Theoretically, this approach can reduce the number of experiments required to find the optimal molecule among $d$ candidates from $\mathcal{O}(d)$ to $\mathcal{O}(\log d)$ or $\mathcal{O}(1)$.1

Sources (1)

• [1]Information-Dense Synthesis for Molecular Discovery
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 03:04 PM

  We propose a method to efficiently search large regions of molecular space using algorithmically controlled stochastic synthesis.

  Machine learning can accelerate molecular discovery by designing molecules and planning experiments.

Extractive summary: sentences quoted from the sources.