Generating readily synthesizable small molecule fluorophore scaffolds with reinforcement learning

2026-01-12

arXiv.org

AI Summary

This work addresses the limited applicability of traditionally generated fluorescent dyes, which often suffer from poor synthetic feasibility. The authors propose a reinforcement learning framework that integrates synthetic accessibility constraints with multi-objective photophysical property prediction to efficiently design π-conjugated small-molecule scaffolds exhibiting both high fluorescence performance and synthesizability. By incorporating reaction libraries, molecular building blocks, and a multi-graph neural network, the method uniquely embeds synthetic pathway priors and property prediction jointly into the generative process. From 11,590 generated candidates, 14 molecules were successfully synthesized following computational screening, with 13 demonstrating fluorescence. The top-performing compound achieved a photoluminescence quantum yield (PLQY) of 0.62, a Stokes shift of 97 nm, and an excited-state lifetime of 11.5 ns.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Reinforcement Learning
• Computer Vision: Computational Photography, Image & Video Synthesis

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Developing new fluorophores for advanced imaging techniques requires exploring new chemical space. While generative AI approaches have shown promise in designing novel dye scaffolds, prior efforts often produced synthetically intractable candidates due to a lack of reaction constraints. Here, we developed SyntheFluor-RL, a generative AI model that employs known reaction libraries and molecular building blocks to create readily synthesizable fluorescent molecule scaffolds via reinforcement learning. To guide the generation of fluorophores, SyntheFluor-RL employs a scoring function built on multiple graph neural networks (GNNs) that predict key photophysical properties, including photoluminescence quantum yield, absorption, and emission wavelengths. These outputs are dynamically weighted and combined with a computed pi-conjugation score to prioritize candidates with desirable optical characteristics and synthetic feasibility. SyntheFluor-RL generated 11,590 candidate molecules, which were filtered to 19 structures predicted to possess dye-like properties. Of the 19 molecules, 14 were synthesized and 13 were experimentally confirmed. The top three were characterized, with the lead compound featuring a benzothiadiazole chromophore and exhibiting strong fluorescence (PLQY = 0.62), a large Stokes shift (97 nm), and a long excited-state lifetime (11.5 ns). These results demonstrate the effectiveness of SyntheFluor-RL in the identification of synthetically accessible fluorophores for further development.

Problem

• fluorophore design
• synthetic feasibility
• generative AI
• small molecule scaffolds
• reaction constraints

Innovation

• reinforcement learning
• synthesizable fluorophores
• graph neural networks
• reaction-constrained generation
• photophysical property prediction