# Artificial Intelligence Driven Workflow for Accelerating Design of Novel Photosensitizers

arXiv: https://arxiv.org/abs/2511.19347 · HTML: https://mlsanity.com/paper/2511.19347/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 60 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [Graph Neural Networks with Learnable Structural and Positional Representations](https://mlsanity.com/paper/2110.07875/) (2021)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics](https://mlsanity.com/paper/1707.09571/) (2017)
- [Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement](https://mlsanity.com/paper/2105.08195/) (2021)
- [Vanilla Bayesian Optimization Performs Great in High Dimensions](https://mlsanity.com/paper/2402.02229/) (2024)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)
- [A predictive machine learning force field framework for liquid electrolyte development](https://mlsanity.com/paper/2404.07181/) (2024)
- [CrysToGraph: A Comprehensive Predictive Model for Crystal Materials Properties and the Benchmark](https://mlsanity.com/paper/2407.16131/) (2024)

## Abstract (arXiv)

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 AI-Accelerated PhotoSensitizer Innovation (AAPSI), a closed-loop 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 (φ_Delta) and absorption maxima (λmax), following experimental validation. This work generates several novel candidates for photodynamic therapy (PDT), 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 (φ_Delta=0.85, λmax=650nm).