Artificial intelligence driven workflow for accelerating design of novel photosensitizers

The discovery of high-performance photosensitizers has long been hindered by the time-consuming and resource-intensive nature of traditional trial-and-error approaches. Here, we present A I- A ccelerated P hoto S ensitizer I nnovation (AAPSI), a comprehensive workflow that integrates expert knowledge, scaffold-based molecule generation, and Bayesian optimization to accelerate the design of novel photosensitizers. The scaffold-driven generation in AAPSI ensures structural novelty and synthetic feasibility, while the iterative AI-experiment loop accelerates the discovery of novel photosensitizers. AAPSI leverages a curated database of 102,534 photosensitizer-solvent pairs and generate 6,148 synthetically accessible candidates. These candidates are screened via graph transformers trained to predict singlet oxygen quantum yield ( $\phi_\Delta$ ) and absorption maxima ( $\lambda_\mathrm{max}$ ), following experimental validation. This work generates several novel candidates for photodynamic therapy, among which the hypocrellin-based candidate HB4Ph exhibits exceptional performance at the Pareto frontier of high quantum yield of singlet oxygen and long absorption maxima among current photosensitizers ( $\phi_\Delta$ = 0.85, $\lambda_\mathrm{max}$ = 650 nm). The database is available at http://aapsi.online .