Molecular machine learning has been maturing rapidly over the last few years. Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are benchmarked on different datasets making it challenging to gauge the quality of proposed methods. This work introduces MoleculeNet, a large scale benchmark for molecular machine learning. MoleculeNet curates multiple public datasets, establishes metrics for evaluation, and offers high quality open-source implementations of multiple previously proposed molecular featurization and learning algorithms (released as part of the DeepChem open source library). MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance. However, this result comes with caveats. Learnable representations still struggle to deal with complex tasks under data scarcity and highly imbalanced classification. For quantum mechanical and biophysical datasets, the use of physics-aware featurizations can be more important than choice of particular learning algorithm.
What drives performance in molecular MPNNs? An operator-level factorial benchmark
Materials Genome Institute, Shanghai University（上海大学材料基因组研究所）；School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；School of Materials Science and Engineering, Tongji University（同济大学材料科学与工程学院）
Evaluating machine learning models for predicting pesticide toxicity to honey bees
Faculty of Computer Science, AGH University of Krakow（克拉科夫AGH大学计算机科学系）；Institute of Biochemistry and Biophysics of the Polish Academy of Sciences（波兰科学院生物化学与生物物理学研究所）
Structure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties
Institute of Ion Physics and Applied Physics, University of Innsbruck（因斯布鲁克大学离子物理与应用物理研究所）；Tashkent Chemical Technological Institute（塔什干化工技术学院）；School of Molecular Science and Engineering, Vidyasirimedhi Institute of Science and Technology（维达西梅迪科学技术学院分子科学与工程学院）
Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs
Carnegie Mellon University（卡内基梅隆大学）；Federal University of Santa Maria（圣玛丽亚联邦大学）；Google DeepMind（谷歌DeepMind）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
Encrypted machine learning of molecular quantum properties
University of Vienna（维也纳大学）；University Kassel（卡塞尔大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Toronto（多伦多大学）；Technische Universität Berlin（柏林工业大学）；Institute for the Foundations of Learning and Data（学习与数据基础研究所）
Empowering Machines to Think Like Chemists: Unveiling Molecular Structure-Polarity Relationships with Hierarchical Symbolic Regression
Shanghai Jiao Tong University（上海交通大学）；Peking University（北京大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工宁波数字孪生研究院）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
Computer Science Department, Stanford University（斯坦福大学计算机科学系）；School of Computer Science and Technology, Wuhan University of Science and Technology（武汉科技大学计算机科学与技术学院）；School of Engineering, Westlake University（西湖大学工程学院）
