Deep learning in molecular and materials sciences is limited by the lack of integration between applied science, artificial intelligence, and high-performance computing. Bottlenecks with respect to the amount of training data, the size and complexity of model architectures, and the scale of the compute infrastructure are all key factors limiting the scaling of deep learning for molecules and materials. Here, we present $\textit{LitMatter}$, a lightweight framework for scaling molecular deep learning methods. We train four graph neural network architectures on over 400 GPUs and investigate the scaling behavior of these methods. Depending on the model architecture, training time speedups up to $60\times$ are seen. Empirical neural scaling relations quantify the model-dependent scaling and enable optimal compute resource allocation and the identification of scalable molecular geometric deep learning model implementations.
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
Hunter College, The City University of New York（纽约市立大学亨特学院）；Helen & Robert Appel Alzheimer’s Disease Research Institute（海伦与罗伯特·阿佩尔阿尔茨海默病研究所）；Feil Family Brain & Mind Research Institute（费尔家族脑与心智研究所）；Weill Cornell Medicine, Cornell University（康奈尔大学威尔医学院）；The Graduate Center, The City University of New York（纽约市立大学研究生中心）
PERM EQ x GRAPH EQ: Equivariant Neural Networks for Quantum Molecular Learning
Independent Researcher, College Park, Maryland, United States（独立研究者，马里兰州学院公园，美国）；Independent AI Researcher, San Francisco, California, United States（独立AI研究者，加利福尼亚州旧金山，美国）
Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
Princeton University（普林斯顿大学）；Institute of Applied Physics and Computational Mathematics（应用物理与计算数学研究所）；CAEP Software Center for High Performance Numerical Simulation（中国工程物理研究院高性能数值模拟软件中心）；Peking University（北京大学）
Learning inducing points and uncertainty on molecular data by scalable variational Gaussian processes
Institute for Chemical Reaction Design and Discovery (WPI-ICReDD)（化学反应设计与发现研究所（WPI-ICReDD））；Hokkaido University（北海道大学）；National Institute for Materials Science（物质・材料研究机构）
Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning
University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究院）；Harvard University（哈佛大学）；Canadian Institute for Advanced Research（加拿大高级研究院）
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）
BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
Insilico Medicine Canada Inc.（英矽智能加拿大公司）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Polytechnique Montréal（蒙特利尔工业大学）；Insilico Medicine AI Limited（英矽智能人工智能有限公司）；CIFAR AI Chair（加拿大高级研究院人工智能主席项目）
Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
Jagiellonian University, Faculty of Mathematics and Computer Science（雅盖隆大学数学与计算机科学学院）；Mila – Québec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；University of Toronto（多伦多大学）；The Hospital for Sick Children Research Institute（儿童医院研究所在）；Acceleration Consortium（加速联盟）；Vector Institute（向量研究所）
t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation
State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University（湖南大学化学生物传感与计量学国家重点实验室，化学化工学院）
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；School of Physical and Mathematical Sciences, Nanyang Technological University（南洋理工大学物理与数学科学学院）
GeoMFormer: A General Architecture for Geometric Molecular Representation Learning
School of EECS, Peking University（北京大学工程科学学院）；National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Microsoft Research AI4Science（微软研究院AI4Science部门）；Center for Machine Learning Research, Peking University（北京大学机器学习研究中心）
DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations
AI Research and Innovation Laboratory, School of Engineering, Westlake University（西湖大学工学院人工智能研究与创新实验室）；Institute of AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）
Pre-training Molecular Graph Representation with 3D Geometry
Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；University of Cambridge（剑桥大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；National Research Council Canada（加拿大国家研究委员会）；HEC Montréal（蒙特利尔高等商学院）；CIFAR（加拿大高等研究院）
Scalable Peptide Design via Memory-Efficient Equivariant Transformer
Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Department of Chemistry, Tsinghua University（清华大学化学系）
Learning Harmonic Molecular Representations on Riemannian Manifold
ByteDance Research（字节跳动研究院）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））
