Designing the Haystack: Programmable Chemical Space for Generative Molecular Discovery

TL;DR

This paper introduces SpaceGFN, a novel framework that allows explicit design and adaptive exploration of structured chemical spaces for molecular discovery, enabling more controlled and efficient drug development processes.

Contribution

It presents a programmable chemical space model combined with flow-based sampling and reaction-aware editing, advancing the deliberate design and optimization of molecules.

Findings

Programmable space design enables natural product-like architectures.

Evolution-inspired space improves metabolic and toxicological profiles.

Effective lead optimization under synthetic constraints across multiple drug targets.

Abstract

Chemical space exploration underlies drug discovery, yet most generative models treat chemical space as a fixed, implicitly learned distribution, focusing on sampling molecules rather than deliberately designing the space itself. We introduce SpaceGFN, a generative framework that elevates chemical space to a programmable computational object: a controllable degree of freedom enabling explicit construction and adaptive traversal of structured molecular universes. SpaceGFN decouples space definition from exploration. Users specify building blocks and reaction rules to construct chemically and synthetically coherent spaces, while a GFlowNet performs efficient, property-biased sampling within them. In Discovery mode, we demonstrate programmable space design through two strategies. A pseudo-natural product space assembles natural product-like architectures. An evolution-inspired (Evo) space recombines endogenous metabolite fragments via enzyme-consistent transformations, introducing an evolutionary prior into chemical generation. This bias yields favorable shifts in predicted metabolic and toxicological profiles while preserving pharmacological diversity, supported by broad docking enrichment across therapeutic targets. In Editing mode, SpaceGFN enables reaction-consistent lead optimization through a curated toolkit of executable synthetic transformations, allowing local, synthesis-aware modification of existing compounds instead of unrestricted graph mutation. Across 96 drug targets, SpaceGFN achieves strong optimization performance while maintaining structural diversity under synthetic constraints. By integrating programmable chemical universe construction with flow-based exploration and reaction-level editing, SpaceGFN establishes a general paradigm for deliberate navigation of therapeutic chemical space.