去噪扩散模型在多个研究领域展现出巨大潜力。现有的基于扩散的从头3D分子生成方法面临两大挑战。由于分子中大多数重原子允许通过单键连接多个原子，仅使用成对距离来建模分子几何结构是不充分的。因此，第一个挑战是提出一种有效的神经网络作为去噪核，能够捕获复杂的多体原子间关系并学习高质量特征。由于图的离散性质，主流的基于扩散的分子方法严重依赖预定义规则并以间接方式生成边。第二个挑战是使分子生成适应扩散过程并准确预测键的存在。在我们的研究中，我们认为扩散过程中更新分子构象的迭代方式与分子动力学一致，并引入了一种名为Geometric-Facilitated Molecular Diffusion (GFMDiff)的新型分子生成方法。针对第一个挑战，我们引入了Dual-Track Transformer Network (DTN)以充分挖掘全局空间关系并学习高质量表示，从而有助于准确预测特征和几何结构。对于第二个挑战，我们设计了Geometric-Facilitated Loss (GFLoss)，它在训练期间干预键的形成，而不是直接将边嵌入到潜在空间中。在当前基准上的综合实验证明了GFMDiff的优越性。
英文摘要：
Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. Since majority heavy atoms in molecules allow connections to multiple atoms through single bonds, solely using pair-wise distance to model molecule geometries is insufficient. Therefore, the first one involves proposing an effective neural network as the denoising kernel that is capable to capture complex multi-body interatomic relationships and learn high-quality features. Due to the discrete nature of graphs, mainstream diffusion-based methods for molecules heavily rely on predefined rules and generate edges in an indirect manner. The second challenge involves accommodating molecule generation to diffusion and accurately predicting the existence of bonds. In our research, we view the iterative way of updating molecule conformations in diffusion process is consistent with molecular dynamics and introduce a novel molecule generation method named Geometric-Facilitated Molecular Diffusion (GFMDiff). For the first challenge, we introduce a Dual-Track Transformer Network (DTN) to fully excevate global spatial relationships and learn high quality representations which contribute to accurate predictions of features and geometries. As for the second challenge, we design Geometric-Facilitated Loss (GFLoss) which intervenes the formation of bonds during the training period, instead of directly embedding edges into the latent space. Comprehensive experiments on current benchmarks demonstrate the superiority of GFMDiff.
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
Shanghai Academy of Artificial Intelligence for Science, SAIS（上海人工智能科学研究院，SAIS）；College of Chemistry and Chemical Engineering, Xiamen University（厦门大学化学与化工学院）；Artificial Intelligence Innovation and Incubation (AI 3 ) Institute, Fudan University（复旦大学人工智能创新与孵化（AI 3）研究院）
Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
Xinjiang Key Laboratory of Biological Resources and Genetic Engineering（新疆生物资源与基因工程重点实验室）；College of Life Science and Technology, Xinjiang University（新疆大学生命科学与技术学院）；School of Mathematics and System Sciences, Xinjiang University（新疆大学数学与系统科学学院）
Learning 3D Anisotropic Noise Distributions Improves Molecular Force Field Modeling
Fudan University（复旦大学）；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）；Renmin University of China（中国人民大学）；Microsoft Research（微软研究院）；Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究所）
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
Mila - Québec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；National Research Council Canada（加拿大国家研究委员会）；University of Ottawa（渥太华大学）；HEC Montréal（蒙特利尔高等商学院）
A 3D pocket-aware and affinity-guided diffusion model for lead optimization
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；West China School of Pharmacy, Sichuan University（四川大学华西药学院）；School of Pharmaceutical Science, Sun Yat-sen University（中山大学药学院）；Global Institute of Future Technology, Shanghai Jiao Tong University（上海交通大学未来技术全球研究院）
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（通用人工智能国家重点实验室，智能科学与技术学院，北京大学）；State Key Laboratory of General Artificial Intelligence, School of Intelligence Science（通用人工智能国家重点实验室，智能科学学院）；The University of Hong Kong（香港大学）
Recovering molecules from coarse-grained beads: free-energy-conditioned generative backmapping across chemical space
Institute for Theoretical Physics, Heidelberg University（海德堡大学理论物理研究所）；Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University（海德堡大学跨学科科学计算中心）
Oxford-Man Institute of Quantitative Finance, University of Oxford（牛津大学牛津-曼数量金融研究所）；Mathematical Institute, University of Oxford（牛津大学数学研究所）；University of Cambridge（剑桥大学）；Imperial College London（伦敦帝国学院）；Royal Brompton Hospital（皇家布朗普顿医院）；King’s College London（伦敦国王学院）
Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation
Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院）；INFTECH；Zhongshan Hospital（中山医院）
Exploring Gene Regulatory Interaction Networks and predicting therapeutic molecules for Hypopharyngeal Cancer and EGFR-mutated lung adenocarcinoma
Jagannath University（贾格纳特大学）；Deakin University（迪肯大学）；International University of Business Agriculture and Technology（国际工商农业技术大学）；Imam Mohammad Ibn Saud Islamic University (IMSIU)（伊玛目穆罕默德·本·沙特伊斯兰大学）；Mawlana Bhashani Science and Technology University（毛拉纳·巴沙尼科技大学）；Daffodil International University（水仙花国际大学）；King Khalid University（国王哈立德大学）
Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling
Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东人工智能与数字经济实验室（深圳））
