UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design

Xiangzhe Kong, Zishen Zhang, Ziting Zhang, Rui Jiao, Jianzhu Ma, Wenbing Huang, Kai Liu, Yang Liu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31397-31418, 2025.

Abstract

The design of target-specific molecules such as small molecules, peptides, and antibodies is vital for biological research and drug discovery. Existing generative methods are restricted to single-domain molecules, failing to address versatile therapeutic needs or utilize cross-domain transferability to enhance model performance. In this paper, we introduce Unified generative Modeling of 3D Molecules (UniMoMo), the first framework capable of designing binders of multiple molecular domains using a single model. In particular, UniMoMo unifies the representations of different molecules as graphs of blocks, where each block corresponds to either a standard amino acid or a molecular fragment. Based on these unified representations, UniMoMo utilizes a geometric latent diffusion model for 3D molecular generation, featuring an iterative full-atom autoencoder to compress blocks into latent space points, followed by an E(3)-equivariant diffusion process. Extensive benchmarks across peptides, antibodies, and small molecules demonstrate the superiority of our unified framework over existing domain-specific models, highlighting the benefits of multi-domain training.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-kong25b, title = {{U}ni{M}o{M}o: Unified Generative Modeling of 3{D} Molecules for De Novo Binder Design}, author = {Kong, Xiangzhe and Zhang, Zishen and Zhang, Ziting and Jiao, Rui and Ma, Jianzhu and Huang, Wenbing and Liu, Kai and Liu, Yang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {31397--31418}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/kong25b/kong25b.pdf}, url = {https://proceedings.mlr.press/v267/kong25b.html}, abstract = {The design of target-specific molecules such as small molecules, peptides, and antibodies is vital for biological research and drug discovery. Existing generative methods are restricted to single-domain molecules, failing to address versatile therapeutic needs or utilize cross-domain transferability to enhance model performance. In this paper, we introduce Unified generative Modeling of 3D Molecules (UniMoMo), the first framework capable of designing binders of multiple molecular domains using a single model. In particular, UniMoMo unifies the representations of different molecules as graphs of blocks, where each block corresponds to either a standard amino acid or a molecular fragment. Based on these unified representations, UniMoMo utilizes a geometric latent diffusion model for 3D molecular generation, featuring an iterative full-atom autoencoder to compress blocks into latent space points, followed by an E(3)-equivariant diffusion process. Extensive benchmarks across peptides, antibodies, and small molecules demonstrate the superiority of our unified framework over existing domain-specific models, highlighting the benefits of multi-domain training.} }
Endnote
%0 Conference Paper %T UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design %A Xiangzhe Kong %A Zishen Zhang %A Ziting Zhang %A Rui Jiao %A Jianzhu Ma %A Wenbing Huang %A Kai Liu %A Yang Liu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-kong25b %I PMLR %P 31397--31418 %U https://proceedings.mlr.press/v267/kong25b.html %V 267 %X The design of target-specific molecules such as small molecules, peptides, and antibodies is vital for biological research and drug discovery. Existing generative methods are restricted to single-domain molecules, failing to address versatile therapeutic needs or utilize cross-domain transferability to enhance model performance. In this paper, we introduce Unified generative Modeling of 3D Molecules (UniMoMo), the first framework capable of designing binders of multiple molecular domains using a single model. In particular, UniMoMo unifies the representations of different molecules as graphs of blocks, where each block corresponds to either a standard amino acid or a molecular fragment. Based on these unified representations, UniMoMo utilizes a geometric latent diffusion model for 3D molecular generation, featuring an iterative full-atom autoencoder to compress blocks into latent space points, followed by an E(3)-equivariant diffusion process. Extensive benchmarks across peptides, antibodies, and small molecules demonstrate the superiority of our unified framework over existing domain-specific models, highlighting the benefits of multi-domain training.
APA
Kong, X., Zhang, Z., Zhang, Z., Jiao, R., Ma, J., Huang, W., Liu, K. & Liu, Y.. (2025). UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:31397-31418 Available from https://proceedings.mlr.press/v267/kong25b.html.

Related Material