Many crucial scientific problems involve designing novel molecules with desired properties, which can be formulated as a black-box optimization problem over the discrete chemical space. In practice, multiple conflicting objectives and costly evaluations (e.g., wet-lab experiments) make the diversity of candidates paramount. Computational methods have achieved initial success but still struggle with considering diversity in both objective and search space. To fill this gap, we propose a multi-objective Bayesian optimization (MOBO) algorithm leveraging the hypernetwork-based GFlowNets (HN-GFN) as an acquisition function optimizer, with the purpose of sampling a diverse batch of candidate molecular graphs from an approximate Pareto front. Using a single preference-conditioned hypernetwork, HN-GFN learns to explore various trade-offs between objectives. We further propose a hindsight-like off-policy strategy to share high-performing molecules among different preferences in order to speed up learning for HN-GFN. We empirically illustrate that HN-GFN has adequate capacity to generalize over preferences. Moreover, experiments in various real-world MOBO settings demonstrate that our framework predominantly outperforms existing methods in terms of candidate quality and sample efficiency. The code is available at https://github.com/violet-sto/HN-GFN.
Towards equilibrium molecular conformation generation with GFlowNets
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Intel Labs（英特尔实验室）；Ciela Institute（谢拉研究所）；Flatiron Institute（熨斗研究所）；Vector Institute（向量研究所）；University of Toronto（多伦多大学）
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data. Building upon the theory of generative flow networks (GFlowNets), we model the generation process by a stochastic data construction policy and thus amortize expensive MCMC exploration into a fixed number of actions sampled from a GFlowNet. We show how GFlowNets can approximately perform large-block Gibbs sampling to mix between modes. We propose a framework to jointly train a GFlowNet with an energy function, so that the GFlowNet learns to sample from the ener…
Order-Preserving (OP) GFlowNets have demonstrated remarkable success in tackling complex multi-objective (MOO) black-box optimization problems using stochastic optimization techniques. Specifically, they can be trained online to efficiently sample diverse candidates near the Pareto front. A key advantage of OP GFlowNets is their ability to impose a local order on training samples based on Pareto dominance, eliminating the need for scalarization - a common requirement in other approaches like Preference-Conditional GFlowNets. However, we identify an important limitation of OP GFlowNets: imposin…
Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives
LUMIA Lab, School of Artificial Intelligence, SJTU（LUMIA实验室，人工智能学院，上海交通大学）；School of Mathematical Sciences, SJTU（数学科学学院，上海交通大学）；Shanghai Advanced Institute of Finance, SJTU（上海先进金融研究院，上海交通大学）；School of Computer Science, SJTU（计算机科学学院，上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Center for Data Science, NYU Shanghai（上海数据科学中心，纽约大学上海学院）；NYU-ECNU Institute of Mathematical Sciences, NYU Shanghai（纽约大学-华东师范大学数学科学研究院，纽约大学上海学院）
Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design
Mila（米拉研究所）；École Polytechnique de Montréal（蒙特利尔综合理工学院）；Université de Montréal（蒙特利尔大学）；ServiceNow（ServiceNow公司）；Recursion Pharmaceuticals（Recursion制药公司）
RGFN: Synthesizable Molecular Generation Using GFlowNets
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）；University of Toronto（多伦多大学）；Jagiellonian University（雅盖隆大学）；McGill University（麦吉尔大学）；The Hospital for Sick Children Research Institute（病童医院研究所）；Acceleration Consortium（加速联盟）
Vancouver Prostate Centre（温哥华前列腺中心）；The University of British Columbia（不列颠哥伦比亚大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Recursion Pharmaceuticals（递归制药公司）
Generative Multi-Objective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design
Department of Chemical and Biological Engineering, University of Wisconsin--Madison, Madison, Wisconsin 53706, United States（化学与生物工程系，威斯康星大学麦迪逊分校）；Department of Chemical and Biomolecular Engineering, The Ohio State University, Columbus, Ohio 43210, United States（化学与生物分子工程系，俄亥俄州立大学）
Why Pool When You Can Flow? Active Learning with GFlowNets
School of Computer Science, Simon Fraser University, Burnaby, BC, Canada（Simon Fraser大学计算机科学学院，Burnaby, BC, Canada）；Vancouver Prostate Centre, University of British Columbia, Vancouver, BC, Canada（温哥华前列腺中心，不列颠哥伦比亚大学，Vancouver, BC, Canada）；Faculty of Medicine, University of British Columbia, Vancouver, BC, Canada（不列颠哥伦比亚大学医学院，Vancouver, BC, Canada）；Diagen AI
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Mila - Quebec AI Institute（Mila-魁北克人工智能研究所）；University Health Network（大学健康网络）；Université de Montréal（蒙特利尔大学）；Valence Labs（Valence实验室）
From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
California Institute of Technology（加州理工学院）；NVIDIA（英伟达）；Zuse Institute Berlin（柏林泽尼克研究所）；dida Datenschmiede GmbH（dida数据隐私公司）；Jagiellonian University（雅盖隆大学）；Mila, Université de Montréal（蒙特利尔大学机器学习研究所）；University of Edinburgh（爱丁堡大学）；CIFAR Fellow, Learning in Machines and Brains（CIFAR Fellow, 机器学习与大脑学习）
Multi-Objective Latent Space Optimization of Generative Molecular Design Models
Texas A&M University（德克萨斯农工大学）；Brookhaven National Laboratory（布鲁克海文国家实验室）；Frederick National Laboratory（弗雷德里克国家实验室）；Argonne National Laboratory（阿贡国家实验室）
The fundamental goal of generative drug design is to propose optimized molecules that meet predefined activity, selectivity, and pharmacokinetic criteria. Despite recent progress, we argue that existing generative methods are limited in their ability to favourably shift the distributions of molecular properties during optimization. We instead propose a novel Reinforcement Learning framework for molecular design in which an agent learns to directly optimize through a space of synthetically-accessible drug-like molecules. This becomes possible by defining transitions in our Markov Decision Proce…
Boltzmann-Expected Molecular Design with Decoupled Annealing Flows
Department of Computer Science and Engineering（计算机科学与工程系）；Chalmers University of Technology（楚姆勒技术大学）；University of Gothenburg（哥德堡大学）；Molecular AI Discovery Sciences, R&D（分子AI发现科学，研发）
ByteDance AI Lab（字节跳动AI实验室）；University of Michigan（密歇根大学）；Montréal Institute of Learning Algorithms（蒙特利尔学习算法研究所）；Shanghai Jiao Tong University（上海交通大学）
Searching for novel molecules with desired chemical properties is crucial in drug discovery. Existing work focuses on developing neural models to generate either molecular sequences or chemical graphs. However, it remains a big challenge to find novel and diverse compounds satisfying several properties. In this paper, we propose MARS, a method for multi-objective drug molecule discovery. MARS is based on the idea of generating the chemical candidates by iteratively editing fragments of molecular graphs. To search for high-quality candidates, it employs Markov chain Monte Carlo sampling (MCMC) …
The ultimate goal of various fields is to directly generate molecules with desired properties, such as finding water-soluble molecules in drug development and finding molecules suitable for organic light-emitting diode (OLED) or photosensitizers in the field of development of new organic materials. In this respect, this study proposes a molecular graph generative model based on the autoencoder for de novo design. The performance of molecular graph conditional variational autoencoder (MGCVAE) for generating molecules having specific desired properties is investigated by comparing it to molecula…
University of Delaware（特拉华大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
The aim of the inverse chemical design is to develop new molecules with given optimized molecular properties or objectives. Recently, generative deep learning (DL) networks are considered as the state-of-the-art in inverse chemical design and have achieved early success in generating molecular structures with desired properties in the pharmaceutical and material chemistry fields. However, satisfying a large number (larger than 10 objectives) of molecular objectives is a limitation of current generative models. To improve the model's ability to handle a large number of molecule design objective…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Monash University（莫纳什大学）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）；Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University（浙江大学药学院医学人工智能创新研究院）；Shanghai Innovation Institute（上海创新研究院）
Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models
Department of Computer Science and Engineering（计算机科学与工程系）；University of Notre Dame（诺克斯大学）；Department of Chemistry and Biochemistry（化学与生物化学系）；Lucy Family Institute for Data & Society（数据与社会学院）
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…
