We note that most existing approaches for molecular graph generation fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models. In this work, we propose GraphEBM to generate molecular graphs using energy-based models. In particular, we parameterize the energy function in a permutation invariant manner, thus making GraphEBM permutation invariant. We apply Langevin dynamics to train the energy function by approximately maximizing likelihood and generate samples with low energies. Furthermore, to generate molecules with a desirable property, we propose a simple yet effective strategy, which pushes down energies with flexible degrees according to the properties of corresponding molecules. Finally, we explore the use of GraphEBM for generating molecules with multiple objectives in a compositional manner. Comprehensive experimental results on random, goal-directed, and compositional generation tasks demonstrate the effectiveness of our proposed method.
We propose a novel molecular fingerprint-based variational autoencoder applied for molecular generation on real-world drug molecules. We define more suitable and pharma-relevant baseline metrics and tests, focusing on the generation of diverse, drug-like, novel small molecules and scaffolds. When we apply these molecular generation metrics to our novel model, we observe a substantial improvement in chemical synthetic accessibility ($Δ\bar{SAS}$ = -0.83) and in computational efficiency up to 5.9x in comparison to an existing state-of-the-art SMILES-based architecture.
Frame-based Equivariant Diffusion Models for 3D Molecular Generation
University of Amsterdam（阿姆斯特丹大学）；AMLab；AI4Science Lab（AI4Science实验室）；Korteweg-de Vries Institute for Mathematics University of Amsterdam（Korteweg-de Vries数学研究所阿姆斯特丹大学）
We consider the problem of molecular graph generation using deep models. While graphs are discrete, most existing methods use continuous latent variables, resulting in inaccurate modeling of discrete graph structures. In this work, we propose GraphDF, a novel discrete latent variable model for molecular graph generation based on normalizing flow methods. GraphDF uses invertible modulo shift transforms to map discrete latent variables to graph nodes and edges. We show that the use of discrete latent variables reduces computational costs and eliminates the negative effect of dequantization. Comp…
Improving Molecular Graph Generation with Flow Matching and Optimal Transport
Institute of Computing Technology（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Central China Research Institute for Artificial Intelligence Technologies（华中人工智能技术研究院）；Western Institute of Computing Technology（西部计算技术研究院）；Phil Rivers Technology（菲尔里弗斯科技公司）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
We propose a hierarchical normalizing flow model for generating molecular graphs. The model produces new molecular structures from a single-node graph by recursively splitting every node into two. All operations are invertible and can be used as plug-and-play modules. The hierarchical nature of the latent codes allows for precise changes in the resulting graph: perturbations in the top layer cause global structural changes, while perturbations in the consequent layers change the resulting molecule marginally. The proposed model outperforms existing generative graph models on the distribution l…
MIT Computer Science & Artificial Intelligence Lab（麻省理工学院计算机科学与人工智能实验室）
We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direct realization of molecular graphs, a task previously approached by generating linear SMILES strings instead of graphs. Our junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network. This approach allows us…
Straight-Line Diffusion Model for Efficient 3D Molecular Generation
Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Huazhong University of Science and Technology（华中科技大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
We propose a framework using normalizing-flow based models, SELF-Referencing Embedded Strings, and multi-objective optimization that efficiently generates small molecules. With an initial training set of only 100 small molecules, FastFlows generates thousands of chemically valid molecules in seconds. Because of the efficient sampling, substructure filters can be applied as desired to eliminate compounds with unreasonable moieties. Using easily computable and learned metrics for druglikeness, synthetic accessibility, and synthetic complexity, we perform a multi-objective optimization to demonst…
Zero Shot Molecular Generation via Similarity Kernels
Engineering Laboratory, University of Cambridge, Trumpington St（剑桥大学工程实验室）；Institute for Computational Physics, University of Stuttgart, 70569 Stuttgart, Germany（斯图加特大学计算物理研究所）；Department of Energy Conversion and Storage, Technical University of Denmark, Anker Engelunds Vej 301, 2800 Kgs. Lyngby, Denmark（丹麦技术大学能源转换与存储系）
George Mason University（乔治梅森大学）；Emory University（埃默里大学）
Designing molecules with specific properties is a long-lasting research problem and is central to advancing crucial domains such as drug discovery and material science. Recent advances in deep graph generative models treat molecule design as graph generation problems which provide new opportunities toward the breakthrough of this long-lasting problem. Existing models, however, have many shortcomings, including poor interpretability and controllability toward desired molecular properties. This paper focuses on new methodologies for molecule generation with interpretable and controllable deep ge…
Latent Flow Matching for Molecular Graph Generation
École normale supérieure Paris-Saclay（巴黎-萨克雷高等师范学校）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；LIX, CNRS, École Polytechnique, IP Paris（巴黎综合理工学院，法国国家科学研究中心，LIX实验室，巴黎综合理工学院联盟）
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）；Peking University（北京大学）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；HEC Montréal（蒙特利尔高等商学院）
We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamics, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilis…
Molecule generation, especially generating 3D molecular geometries from scratch (i.e., 3D \textit{de novo} generation), has become a fundamental task in drug designs. Existing diffusion-based 3D molecule generation methods could suffer from unsatisfactory performances, especially when generating large molecules. At the same time, the generated molecules lack enough diversity. This paper proposes a novel diffusion model to address those two challenges. First, interatomic relations are not in molecules' 3D point cloud representations. Thus, it is difficult for existing generative models to captu…
3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
Artificial Intelligence Research Laboratory（人工智能研究实验室）；College of Information Sciences and Technology（信息科学与技术学院）；Center for Artificial Intelligence Foundations and Scientific Applications（人工智能基础与科学应用中心）；Institute for Computational and Data Sciences（计算与数据科学研究所）；The Pennsylvania State University（宾夕法尼亚州立大学）
De Novo AI Research（De Novo AI研究院）；University of Pennsylvania（宾夕法尼亚大学）
Deep learning has significantly advanced and accelerated de novo molecular generation. Generative networks, namely Variational Autoencoders (VAEs) can not only randomly generate new molecules, but also alter molecular structures to optimize specific chemical properties which are pivotal for drug-discovery. While VAEs have been proposed and researched in the past for pharmaceutical applications, they possess deficiencies which limit their ability to both optimize properties and decode syntactically valid molecules. We present a recurrent, conditional $β$-VAE which disentangles the latent space …
Unified Guidance for Geometry-Conditioned Molecular Generation
School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Munich Data Science Institute, Technical University of Munich（慕尼黑工业大学慕尼黑数据科学研究所）；Center for Computation Health, Helmholtz Munich（亥姆霍兹慕尼黑计算健康中心）
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）；Stanford University（斯坦福大学）；HEC Montréal（蒙特利尔高等商学院）
Predicting molecular conformations from molecular graphs is a fundamental problem in cheminformatics and drug discovery. Recently, significant progress has been achieved with machine learning approaches, especially with deep generative models. Inspired by the diffusion process in classical non-equilibrium thermodynamics where heated particles will diffuse from original states to a noise distribution, in this paper, we propose a novel generative model named GeoDiff for molecular conformation prediction. GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process …
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）
Tokyo Institute of Technology（东京工业大学）；Preferred Networks, Inc.（Preferred Networks公司）
We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with two novel reversible flows. We empirically demonstrate that our model efficiently generates valid molecular graphs with almost no duplicated molecules. In addition, we observe that the learned latent space can be used to generate molecules with desired chemical properties.
MIRRA: Fast, High-Fidelity Molecular Generation with Chemistry-Informed Discrete Flow Matching
Courant Institute of Mathematical Sciences, New York University（纽约大学柯朗数学科学研究所）；Tandon School of Engineering, New York University（纽约大学坦登工程学院）；Department of Physics, New York University（纽约大学物理系）
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）
MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China（人工智能科学（AI4S）优选计划，北京大学深圳研究生院，中国）；Faculty of Materials Science, Shenzhen MSU-BIT University, Shenzhen, China（材料科学学院，深圳MSU-BIT大学，中国）
Graph neural networks (GNNs) have been used extensively for addressing problems in drug design and discovery. Both ligand and target molecules are represented as graphs with node and edge features encoding information about atomic elements and bonds respectively. Although existing deep learning models perform remarkably well at predicting physicochemical properties and binding affinities, the generation of new molecules with optimized properties remains challenging. Inherently, most GNNs perform poorly in whole-graph representation due to the limitations of the message-passing paradigm. Furthe…
From Tokens to Blocks: A Block-Diffusion Perspective on Molecular Generation
School of Artificial Intelligence, Shenzhen University, Shenzhen 518060, China（人工智能学院，深圳大学，深圳518060，中国）；School of Computer Science, University of Nottingham Ningbo, Ningbo 315100, China（计算机科学学院，诺丁汉大学宁波分校，宁波315100，中国）
