TSMGen: Target-Specific Molecule Generation via Higher-Order Structural Dependencies and Context-Aware Bidirectional Fusion

Yaoyu Chen, Xiaoli Lin, Ziyi Gong, Jun Pang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:15356-15369, 2026.

Abstract

Efficiently designing high-quality molecules targeting disease-relevant targets is a critical challenge. Most existing methods can capture pairwise amino acid relations, neglecting the higher-order relations among multiple amino acids. This paper proposes a target-specific molecule generation framework, namely TSMGen, to comprehensively capture the local and global structural information of the protein pocket by modeling higher-order spatial dependencies both at the atomic and the amino acid levels. Furthermore, we design a context-aware bidirectional fusion module to learn the more detailed structural information about the protein pocket. This module simultaneously attends to features from both the protein pocket and the molecule, fully leveraging the structural information from both to optimize the generation process of targeted molecules, thereby enhancing the quality of generated molecules. Experiments show that TSMGen outperforms state-of-the-art methods in terms of Vina Score, High Affinity, QED, SA and Diversity, and a case study on $\beta$-secretase enzyme further confirms its ability to generate molecules with stronger binding affinity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-chen26bw, title = {{TSMG}en: Target-Specific Molecule Generation via Higher-Order Structural Dependencies and Context-Aware Bidirectional Fusion}, author = {Chen, Yaoyu and Lin, Xiaoli and Gong, Ziyi and Pang, Jun}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {15356--15369}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/chen26bw/chen26bw.pdf}, url = {https://proceedings.mlr.press/v306/chen26bw.html}, abstract = {Efficiently designing high-quality molecules targeting disease-relevant targets is a critical challenge. Most existing methods can capture pairwise amino acid relations, neglecting the higher-order relations among multiple amino acids. This paper proposes a target-specific molecule generation framework, namely TSMGen, to comprehensively capture the local and global structural information of the protein pocket by modeling higher-order spatial dependencies both at the atomic and the amino acid levels. Furthermore, we design a context-aware bidirectional fusion module to learn the more detailed structural information about the protein pocket. This module simultaneously attends to features from both the protein pocket and the molecule, fully leveraging the structural information from both to optimize the generation process of targeted molecules, thereby enhancing the quality of generated molecules. Experiments show that TSMGen outperforms state-of-the-art methods in terms of Vina Score, High Affinity, QED, SA and Diversity, and a case study on $\beta$-secretase enzyme further confirms its ability to generate molecules with stronger binding affinity.} }
Endnote
%0 Conference Paper %T TSMGen: Target-Specific Molecule Generation via Higher-Order Structural Dependencies and Context-Aware Bidirectional Fusion %A Yaoyu Chen %A Xiaoli Lin %A Ziyi Gong %A Jun Pang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-chen26bw %I PMLR %P 15356--15369 %U https://proceedings.mlr.press/v306/chen26bw.html %V 306 %X Efficiently designing high-quality molecules targeting disease-relevant targets is a critical challenge. Most existing methods can capture pairwise amino acid relations, neglecting the higher-order relations among multiple amino acids. This paper proposes a target-specific molecule generation framework, namely TSMGen, to comprehensively capture the local and global structural information of the protein pocket by modeling higher-order spatial dependencies both at the atomic and the amino acid levels. Furthermore, we design a context-aware bidirectional fusion module to learn the more detailed structural information about the protein pocket. This module simultaneously attends to features from both the protein pocket and the molecule, fully leveraging the structural information from both to optimize the generation process of targeted molecules, thereby enhancing the quality of generated molecules. Experiments show that TSMGen outperforms state-of-the-art methods in terms of Vina Score, High Affinity, QED, SA and Diversity, and a case study on $\beta$-secretase enzyme further confirms its ability to generate molecules with stronger binding affinity.
APA
Chen, Y., Lin, X., Gong, Z. & Pang, J.. (2026). TSMGen: Target-Specific Molecule Generation via Higher-Order Structural Dependencies and Context-Aware Bidirectional Fusion. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:15356-15369 Available from https://proceedings.mlr.press/v306/chen26bw.html.

Related Material