RingFormer: A Ring-Enhanced Graph Transformer for Organic Solar Cell Property Prediction
This work addresses the need for accurate machine learning models to accelerate the identification of OSC molecules for sustainable energy production, representing a domain-specific advancement.
The paper tackled the problem of predicting properties of Organic Solar Cell (OSC) molecules by developing RingFormer, a graph transformer that captures atom and ring structures, resulting in a 22.77% relative improvement over the nearest competitor on the CEPDB dataset.
Organic Solar Cells (OSCs) are a promising technology for sustainable energy production. However, the identification of molecules with desired OSC properties typically involves laborious experimental research. To accelerate progress in the field, it is crucial to develop machine learning models capable of accurately predicting the properties of OSC molecules. While graph representation learning has demonstrated success in molecular property prediction, it remains underexplored for OSC-specific tasks. Existing methods fail to capture the unique structural features of OSC molecules, particularly the intricate ring systems that critically influence OSC properties, leading to suboptimal performance. To fill the gap, we present RingFormer, a novel graph transformer framework specially designed to capture both atom and ring level structural patterns in OSC molecules. RingFormer constructs a hierarchical graph that integrates atomic and ring structures and employs a combination of local message passing and global attention mechanisms to generate expressive graph representations for accurate OSC property prediction. We evaluate RingFormer's effectiveness on five curated OSC molecule datasets through extensive experiments. The results demonstrate that RingFormer consistently outperforms existing methods, achieving a 22.77% relative improvement over the nearest competitor on the CEPDB dataset.