t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation

TL;DR

This paper introduces t-SMILES, a novel, scalable fragment-based molecular representation framework that improves de novo molecule generation by providing a multiscale, tree-based encoding system that enhances model performance and novelty.

Contribution

The study presents t-SMILES, a flexible, multiscale molecular representation framework with three algorithms, outperforming classical methods and state-of-the-art approaches in various molecular generation tasks.

Findings

Outperforms classical SMILES, DeepSMILES, SELFIES in goal-directed tasks.

Achieves higher novelty scores while maintaining similarity.

Surpasses state-of-the-art methods on ChEMBL, Zinc, and QM9 datasets.

Abstract

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.