Back

Reversing Erooms Law- Finitude and Dilution in Small-Molecule Discovery

Youngs, R.

2025-10-31 pharmacology and toxicology
10.1101/2025.10.29.685434 bioRxiv
Show abstract

Drug discovery productivity--measured as clinically viable new molecules per research has declined for decades, a trend known as Erooms Law. This paradox persists despite advances in screening, computing, and artificial intelligence. Here we show that it stems from two forces: the finite diversity of natures biosynthetic rules, leading to saturation of novel natural scaffolds, and the dilution of viable candidates in expanding synthetic chemical spaces, where success rates fall without improved specificity. We propose an optimized hybrid strategy that allocates effort to mining natural products and using their validated patterns to guide synthetic exploration, maximizing novelty per cost. This approach yields testable rules, such as optimal allocation thresholds and benchmarks for artificial intelligence tools. By embedding natural principles in modern discovery, this framework offers a path to reverse Erooms Law and boost pharmaceutical efficiency.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.