Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation
This addresses the problem of efficient molecular representation for computational chemistry and drug discovery, offering incremental improvements over existing methods.
The study introduced TSIS and its variants to complete the t-SMILES framework for molecular representation, finding that its hierarchical structure is easier to parse than expected and consistently outperforms other linear representations like SMILES, SELFIES, and SAFE with superior convergence speed and generalization.
Language models demonstrate fundamental abilities in syntax, semantics, and reasoning, though their performance often depends significantly on the inputs they process. This study introduces TSIS (Simplified TSID) and its variants:TSISD (TSIS with Depth-First Search), TSISO (TSIS in Order), and TSISR (TSIS in Random), as integral components of the t-SMILES framework. These additions complete the framework's design, providing diverse approaches to molecular representation. Through comprehensive analysis and experiments employing deep generative models, including GPT, diffusion models, and reinforcement learning, the findings reveal that the hierarchical structure of t-SMILES is more straightforward to parse than initially anticipated. Furthermore, t-SMILES consistently outperforms other linear representations such as SMILES, SELFIES, and SAFE, demonstrating superior convergence speed and enhanced generalization capabilities.