Recent advancements in AI for biological research focus on integrating molecular data with natural language to accelerate drug discovery. However, the scarcity of high-quality annotations limits progress in this area. This paper introduces LA3, a Language-based Automatic Annotation Augmentation framework that leverages large language models to augment existing datasets, thereby improving AI training. We demonstrate the effectiveness of LA3 by creating an enhanced dataset, LaChEBI-20, where we systematically rewrite the annotations of molecules from an established dataset. These rewritten annotations preserve essential molecular information while providing more varied sentence structures and vocabulary. Using LaChEBI-20, we train LaMolT5 based on a benchmark architecture to learn the mapping between molecular representations and augmented annotations. Experimental results on text-based *de novo* molecule generation and molecule captioning demonstrate that LaMolT5 outperforms state-of-the-art models. Notably, incorporating LA3 leads to improvements of up to 301% over the benchmark architecture. Furthermore, we validate the effectiveness of LA3 notable applications in *image*, *text* and *graph* tasks, affirming its versatility and utility.
@article{arxiv.2502.06634,
title = {Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language},
author = {Zhiqiang Zhong and Simon Sataa-Yu Larsen and Haoyu Guo and Tao Tang and Kuangyu Zhou and Davide Mottin},
journal= {arXiv preprint arXiv:2502.06634},
year = {2025}
}