Chen Kepeng, Zhang Xiaoting, Wang Jike, Li Dan, Hou Tingjun, Yang Wenbo, Kang Yu
College of Pharmaceutical Sciences, Zhejiang University Hangzhou Zhejiang 310058 China
School of Chemistry, State Key Laboratory of Fine Chemicals, Frontier Science Center for Smart Materials, Dalian Key Laboratory of Intelligent Chemistry, Dalian University of Technology Dalian 116024 China
Chem Sci. 2025 Jul 8. doi: 10.1039/d5sc03192c.
Photodynamic therapy (PDT) is a clinically approved therapeutic modality that has demonstrated significant potential for cancer treatment, and triplet photosensitizers (PSs) play a key role in its efficacy. Despite deep learning having emerged as a next-generation tool for material discovery, existing methods mainly target a limited subset of triplet PSs, such as thermally activated delayed fluorescence (TADF) materials, neglecting the critical intersystem crossing (ISC) between the high-lying singlet and triplet states (Δ ). To overcome this limitation, we compiled a comprehensive dataset (∼1.90 × 10) of triplet PSs encompassing various ISC mechanisms. Then, we proposed a novel strategy that incorporates two models: a fragment-based model (Frag-MD) and a character-based model (MD), both integrating a conditional transformer, recurrent neural networks, and reinforcement learning. experiments revealed that the Frag-MD model outperforms the MD model in generating larger conjugated motifs with higher average ring numbers and atom counts; while the MD model generates twice as many unique motifs and excels in novelty and diversity, as evaluated by conditional and MOSES metrics. Therefore, our approach is highly effective for modifying conjugated motifs and designing novel triplet PSs. Notably, the recently reported high-efficiency triplet PSs have been re-identified through ablation experiments using our proposed models, which target Δ and significantly outperform traditional baselines, achieving a prediction accuracy of 73% 4%. Our approach holds the potential to establish a new paradigm for discovering novel PSs applicable in PDT.
光动力疗法（PDT）是一种临床认可的治疗方式，已显示出在癌症治疗方面的巨大潜力，三线态光敏剂（PSs）在其疗效中起关键作用。尽管深度学习已成为材料发现的下一代工具，但现有方法主要针对三线态PSs的有限子集，如热激活延迟荧光（TADF）材料，而忽略了高能单线态和三线态之间的关键系间窜越（ISC）（Δ ）。为克服这一局限性，我们编制了一个包含各种ISC机制的三线态PSs综合数据集（约1.90×10）。然后，我们提出了一种新颖的策略，该策略结合了两个模型：基于片段的模型（Frag-MD）和基于字符的模型（MD），两者都集成了条件变压器、递归神经网络和强化学习。实验表明，Frag-MD模型在生成具有更高平均环数和原子数的更大共轭基序方面优于MD模型；而MD模型生成的独特基序数量是其两倍，并且在新颖性和多样性方面表现出色，这是通过条件和MOSES指标评估得出的。因此，我们的方法在修饰共轭基序和设计新型三线态PSs方面非常有效。值得注意的是，最近报道的高效三线态PSs已通过使用我们提出的模型进行的消融实验重新识别，这些模型针对Δ ，并且显著优于传统基线，预测准确率达到73%±4%。我们的方法有潜力建立一种发现适用于PDT的新型PSs的新范式。
