With the advancing capabilities of computational methodologies and resources, ultra-large-scale virtual screening via molecular docking has emerged as a prominent strategy for in silico hit discovery. Given the exhaustive nature of ultra-large-scale virtual screening, active learning methodologies have garnered attention as a means to mitigate computational cost through iterative small-scale docking and machine learning model training. While the efficacy of active learning methodologies has been empirically validated in extant literature, a critical investigation remains in how surrogate models can predict docking score without considering three-dimensional structural features, such as receptor conformation and binding poses. In this paper, we thus investigate how active learning methodologies effectively predict docking scores using only 2D structures and under what circumstances they may work particularly well through benchmark studies encompassing six receptor targets. Our findings suggest that surrogate models tend to memorize structural patterns prevalent in high docking scored compounds obtained during acquisition steps. Despite this tendency, surrogate models demonstrate utility in virtual screening, as exemplified in the identification of actives from DUD-E dataset and high docking-scored compounds from EnamineReal library, a significantly larger set than the initial screening pool. Our comprehensive analysis underscores the reliability and potential applicability of active learning methodologies in virtual screening campaigns.
Cardinal Stefan Wyszynski University(斯特凡·维申斯基红衣主教大学);Warsaw University of Technology(华沙理工大学);IDEAS NCBR(IDEAS NCBR机构);IMPAN(波兰科学院生物化学与生物物理研究所);University of Warsaw(华沙大学)
Quantum-Inspired Machine Learning for Molecular Docking
School of Automation Science and Engineering, South China University of Technology(华南理工大学自动化科学与工程学院);Central Research Institute, 2012 Labs, Huawei Technologies(华为技术有限公司2012实验室中央研究院);Laboratory of AI for Science, Huawei Cloud Computing Technologies Co., Ltd(华为云计算技术有限公司科学人工智能实验室);Shenzhen Institute for Quantum Science and Engineering(深圳量子科学与工程研究院)
FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation
Huazhong University of Science and Technology(华中科技大学);Renmin University of China(中国人民大学);University of Science and Technology of China(中国科学技术大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
Q-Score: A Quantum-Native Scoring Function for Molecular Docking
Department of Computer Science(计算机科学系);The Chinese University of Hong Kong(香港中文大学);Department of Electrical and Computer Engineering(电气与计算机工程系);Rutgers University(罗格斯大学);The University of Chicago(芝加哥大学)
Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking
Ligand Pro;Skolkovo Institute of Science and Technology(斯克洛洛沃科学与技术研究院);Artificial Intelligence Center(人工智能中心);Center for Molecular and Cellular Biology(分子与细胞生物学中心);Artificial Intelligence Research Institute(人工智能研究 institute)
Dockformer: A transformer-based molecular docking paradigm for large-scale virtual screening
School of Computer Science, University of Nottingham Ningbo(诺丁汉大学宁波分校计算机学院);National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University(深圳大学大数据系统计算技术国家工程实验室);Center for Frontier AI Research, Institute of High Performance Computing, Singapore Institute of Manufacturing Technology, Agency for Science, Technology and Research (A*STAR)(新加坡制造技术研究院高性能计算研究所前沿人工智能研究中心(新加坡科技研究局));School of Computer Science, University of Birmingham(伯明翰大学计算机学院);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院)
Molecular Embedding-Based Algorithm Selection in Protein-Ligand Docking
Division of Natural and Applied Sciences, Duke Kunshan University(杜克昆山大学自然科学与应用科学系);Machine Learning Department, Mohamed bin Zayed University of Artificial Intelligence(莫扎德人工智能大学机器学习系)
In silico study on the cytotoxicity against Hela cancer cells of xanthones bioactive compounds from Garcinia cowa: QSAR based on Graph Deep Learning, Network Pharmacology, and Molecular Docking
Hanoi University of Science, Vietnam National University(越南国家大学河内科学大学);Institute of Natural Products Chemistry, Vietnam Academy of Science and Technology(越南科学技术科学院天然产物化学研究所)
CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
Huazhong University of Science and Technology(华中科技大学);Microsoft Research AI for Science(微软研究院人工智能科学部);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling
University of California San Diego(加利福尼亚大学圣迭戈分校);Universidade Federal de Santa Catarina(圣卡塔琳娜联邦大学);Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego(加利福尼亚大学圣迭戈分校斯卡格斯药学与制药科学学院)
Generative Active Learning for the Search of Small-molecule Protein Binders
Mila – Québec AI Institute(米拉-魁北克人工智能研究所);Dreamfold;McGill University(麦吉尔大学);Université de Montréal(蒙特利尔大学);IRIC, Université de Montréal(蒙特利尔大学IRIC研究所);Valence Labs(Valence实验室);X-Chem(X-Chem公司);MIT(麻省理工学院);AI Redefined
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning
Department of Computer Science and Engineering(计算机科学与工程系);Department of Chemistry and Biochemistry(化学与生物化学系);Skaggs School of Pharmacy and Pharmaceutical Sciences(斯卡格斯药学与药学科学学校)
Valid Property-Enhanced Contrastive Learning for Targeted Optimization & Resampling for Novel Drug Design
Department of Computer Science, University of North Carolina at Chapel Hill(北卡罗来纳大学 Chapel Hill 分校计算机科学系);Radiation Medicine Centre, Bhabha Atomic Research Centre(博哈原子研究中心放射医学中心);Homi Bhabha National Institute(霍米·巴布纳国家研究所);IITB-Monash Research Academy, IIT Bombay(印度理工学院 Bombay 的 IITB-Monash 研究学院);Department of Chemistry, Indian Institute of Technology Bombay(印度理工学院 Bombay 化学系)