Toward Better Geometric Representations for Molecule Generative Models
Institute for Artificial Intelligence, PKU(北京大学人工智能学院);ByteDance AI Drug Discovery(字节跳动AI药物发现);School of Intelligence Science and Technology, PKU(北京大学智能科学与技术学院);Anew Labs(Anew实验室);Department of Electrical Engineering and Computer Science, MIT(麻省理工学院电子工程与计算机科学系);State Key Laboratory of General Artificial Intelligence, PKU(北京大学通用人工智能国家重点实验室)
Shaoheng Yan, Zian Li, Cai Zhou, Qiaojing Huang, Kai Liu, Muhan Zhang
Geometric representation-conditioned molecule generation provides an effective paradigm that decouples molecule representation modeling from structure generation. By decoupling molecule generation into two stages-first generating a meaningful molecule representation, and then generating a 3D molecule conditioned on this representation-the efficiency and quality of the generation process can be significantly enhanced. However, its effectiveness is fundamentally limited by the quality of the representation space: pretrained molecular encoders, such as UniMol, produce representations that are non-smooth and not fully exploited during the generative training process. In this work, we propose LENSEs, a framework that better exploits the potential of molecule representations in representation-conditioned generation methods. In particular, LENSEs introduces three complementary mechanisms: (1) a representation head, simultaneously trained during generative tasks, that extracts multi-level representations from the pretrained encoder; (2) a molecule perceptual loss that optimizes the generator in a semantic-informative representation space; and (3) a node-level representation alignment (REPA) loss that explicitly aligns the generator's hidden states with encoder representations, reducing the semantic gap between pretraining and generation. We demonstrate the effectiveness of these improvements through extensive molecule generation tasks. Specifically, on the challenging molecule generation dataset GEOM-DRUG, LENSEs achieves 97.28% validity and 98.51% molecule stability, surpassing existing advanced methods. Further analyses through Lipschitz constant reduction (4.6x) and QM9 probing tasks also demonstrate the smoother, more informative refined representations, establishing generative training with alignment objectives as a potential pretraining paradigm for molecular encoders.
UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
Tsinghua University(清华大学);Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院);Renmin University of China(中国人民大学);Bytedance(字节跳动)
Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
Institute of AI for Health, Helmholtz Zentrum Munchen(AI健康研究所,海姆霍兹慕尼黑研究中心);Faculty of Mathematics, Informatics and Mechanics, University of Warsaw(数学、信息学与力学系,华沙大学);Technical University of Munich, Campus Straubing for Biotechnology and Sustainability(慕尼黑技术大学,斯特拉布格生物技术与可持续性校区);University of Applied Sciences Weihenstephan Triesdorf(魏恩施泰恩特里埃斯多应用科学大学);Technical University of Munich, TUM School of Computation, Information and Technology(慕尼黑技术大学,TUM计算、信息与技术学院)
A Deep Generative Model for Molecule Optimization via One Fragment Modification
The Ohio State University(俄亥俄州立大学);NEC Labs America(NEC美国实验室);Translational Data Analytics Institute, The Ohio State University(俄亥俄州立大学转化数据分析研究所);Biomedical Informatics, The Ohio State University(俄亥俄州立大学生物医学信息学)
Inverse design of 3d molecular structures with conditional generative neural networks
Technische Universität Berlin(柏林工业大学);Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所);Korea University(高丽大学);Max-Planck-Institut für Informatik(马克斯·普朗克信息学研究所)
Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates
Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所);Department of Chemistry and Biochemistry, University of California Santa Barbara(加州大学圣芭芭拉分校化学与生物化学系)
Polyformer: a generative framework for thermodynamic modeling of polymeric molecules
PsiDagger;Department of Physics and Astronomy, University of Pittsburgh(物理与天文学系,匹兹堡大学);Department of Chemistry and The PULSE Institute, Stanford University(化学系和PULSE研究所,斯坦福大学);SLAC National Accelerator Laboratory(SLAC国家加速器实验室)
Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks
Biological Data Science Lab, Dept. of Computer Engineering, Hacettepe University(哈切塔佩大学计算机工程系生物数据科学实验室);Dept. of Computer Engineering, Hacettepe University(哈切塔佩大学计算机工程系);Dept. of Chemistry, Middle East Technical University(中东技术大学化学系);Dept. of Physics, Middle East Technical University(中东技术大学物理系);Dept. Of Artificial Intelligence Engineering, Bahcesehir University(巴切塞希尔大学人工智能工程系);Cancer Systems Biology Lab, Graduate School of Informatics, Middle East Technical University(中东技术大学信息研究生院癌症系统生物学实验室);Dept. of Pharmaceutical Chemistry, Faculty of Pharmacy, Gazi University(加齐大学药学系药剂化学系);Laboratory of Molecular Modeling, Evias Pharmaceutical R&D Ltd.(Evias制药研发有限公司分子建模实验室);Dept. of Electrical and Electronics Engineering, İskenderun Technical University(伊斯肯德伦技术大学电子与电气工程系);Institute for Computational Biomedicine, Heidelberg University(海德堡大学计算生物医学研究所);Dept. of Bioinformatics, Graduate School of Health Sciences, Hacettepe University(哈切塔佩大学健康科学研究生院生物信息学系)
Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder -- Insights for practical AI-driven molecule generation
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design
George Mason University(乔治梅森大学);Georgia Institute of Technology(佐治亚理工学院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Mila - Université de Montréal(米拉 - 蒙特利尔大学)