JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916712610267136 |
|---|---|
| author | Shi, Ji Xie, Chengxun Li, Zhonghao Zhang, Xinming Zhang, Miao |
| author_facet | Shi, Ji Xie, Chengxun Li, Zhonghao Zhang, Xinming Zhang, Miao |
| contents | The discovery of new molecules based on the original chemical molecule distributions is of great importance in medicine. The graph transformer, with its advantages of high performance and scalability compared to traditional graph networks, has been widely explored in recent research for applications of graph structures. However, current transformer-based graph decoders struggle to effectively utilize graph information, which limits their capacity to leverage only sequences of nodes rather than the complex topological structures of molecule graphs. This paper focuses on building a graph transformer-based framework for molecular generation, which we call \textbf{JTreeformer} as it transforms graph generation into junction tree generation. It combines GCN parallel with multi-head attention as the encoder. It integrates a directed acyclic GCN into a graph-based Transformer to serve as a decoder, which can iteratively synthesize the entire molecule by leveraging information from the partially constructed molecular structure at each step. In addition, a diffusion model is inserted in the latent space generated by the encoder, to enhance the efficiency and effectiveness of sampling further. The empirical results demonstrate that our novel framework outperforms existing molecule generation methods, thus offering a promising tool to advance drug discovery (https://anonymous.4open.science/r/JTreeformer-C74C). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20770 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation Shi, Ji Xie, Chengxun Li, Zhonghao Zhang, Xinming Zhang, Miao Machine Learning Artificial Intelligence The discovery of new molecules based on the original chemical molecule distributions is of great importance in medicine. The graph transformer, with its advantages of high performance and scalability compared to traditional graph networks, has been widely explored in recent research for applications of graph structures. However, current transformer-based graph decoders struggle to effectively utilize graph information, which limits their capacity to leverage only sequences of nodes rather than the complex topological structures of molecule graphs. This paper focuses on building a graph transformer-based framework for molecular generation, which we call \textbf{JTreeformer} as it transforms graph generation into junction tree generation. It combines GCN parallel with multi-head attention as the encoder. It integrates a directed acyclic GCN into a graph-based Transformer to serve as a decoder, which can iteratively synthesize the entire molecule by leveraging information from the partially constructed molecular structure at each step. In addition, a diffusion model is inserted in the latent space generated by the encoder, to enhance the efficiency and effectiveness of sampling further. The empirical results demonstrate that our novel framework outperforms existing molecule generation methods, thus offering a promising tool to advance drug discovery (https://anonymous.4open.science/r/JTreeformer-C74C). |
| title | JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.20770 |