t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation
This work addresses the challenge of scalable and effective molecule generation for drug discovery and materials science, offering a flexible representation that enhances performance in de novo generation tasks.
The study tackled the problem of molecular representation for AI models by introducing t-SMILES, a fragment-based framework that uses tree-based SMILES strings, resulting in higher novelty scores and outperforming classical and state-of-the-art methods on datasets like ChEMBL, Zinc, and QM9.
Effective representation of molecules is a crucial factor affecting the performance of artificial intelligence models. This study introduces a flexible, fragment-based, multiscale molecular representation framework called t-SMILES (tree-based SMILES) with three code algorithms: TSSA, TSDY and TSID. It describes molecules using SMILES-type strings obtained by performing a breadth-first search on a full binary tree formed from a fragmented molecular graph. Systematic evaluations using JTVAE, BRICS, MMPA, and Scaffold show the feasibility of constructing a multi-code molecular description system, where various descriptions complement each other, enhancing the overall performance. In addition, it can avoid overfitting and achieve higher novelty scores while maintaining reasonable similarity on labeled low-resource datasets, regardless of whether the model is original, data-augmented, or pre-trained then fine-tuned. Furthermore, it significantly outperforms classical SMILES, DeepSMILES, SELFIES and baseline models in goal-directed tasks. And it surpasses state-of-the-art fragment, graph and SMILES based approaches on ChEMBL, Zinc, and QM9.