Structure-based drug design (SBDD), which aims to generate molecules that can bind tightly to the target protein, is an essential problem in drug discovery, and previous approaches have achieved initial success. However, most existing methods still suffer from invalid local structure or unrealistic conformation issues, which are mainly due to the poor leaning of bond angles or torsional angles. To alleviate these problems, we propose AUTODIFF, a diffusion-based fragment-wise autoregressive generation model. Specifically, we design a novel molecule assembly strategy named conformal motif that preserves the conformation of local structures of molecules first, then we encode the interaction of the protein-ligand complex with an SE(3)-equivariant convolutional network and generate molecules motif-by-motif with diffusion modeling. In addition, we also improve the evaluation framework of SBDD by constraining the molecular weights of the generated molecules in the same range, together with some new metrics, which make the evaluation more fair and practical. Extensive experiments on CrossDocked2020 demonstrate that our approach outperforms the existing models in generating realistic molecules with valid structures and conformations while maintaining high binding affinity.
Tencent AI Lab（腾讯人工智能实验室）；Shenzhen University（深圳大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）
Retrosynthesis is a major task for drug discovery. It is formulated as a graph-generating problem by many existing approaches. Specifically, these methods firstly identify the reaction center, and break target molecule accordingly to generate synthons. Reactants are generated by either adding atoms sequentially to synthon graphs or directly adding proper leaving groups. However, both two strategies suffer since adding atoms results in a long prediction sequence which increases generation difficulty, while adding leaving groups can only consider the ones in the training set which results in poo…
The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize coherent multi-resolution representations by interweaving the encoding of substructure components with the atom-level encoding of the original molecular graph. Moreover, our graph decoder is fully autoregressive, and interleaves each step of adding a new substructure with the pro…
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）
Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fas…
Shape-based virtual screening is widely employed in ligand-based drug design to search chemical libraries for molecules with similar 3D shapes yet novel 2D chemical structures compared to known ligands. 3D deep generative models have the potential to automate this exploration of shape-conditioned 3D chemical space; however, no existing models can reliably generate valid drug-like molecules in conformations that adopt a specific shape such as a known binding pose. We introduce a new multimodal 3D generative model that enables shape-conditioned 3D molecular design by equivariantly encoding molec…
MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；Shanghai Institute of Materia Medica, Chinese Academy of Sciences（中国科学院上海药物研究所）
InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames
The Chinese University of Hong Kong（香港中文大学）；Alibaba DAMO Academy（阿里巴巴达摩院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Ottawa（渥太华大学）
Structure-based Drug Design with Equivariant Diffusion Models
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of Cambridge（剑桥大学）；Cornell University（康奈尔大学）；Prescient Design, Genentech（普雷赛特设计公司，基因泰克公司）；Chinese Academy of Mathematics and System Science（中国科学院数学与系统科学研究院）；Heart and Lung Research Institute, University of Cambridge（剑桥大学心肺研究所）；University of Rome “La Sapienza”（罗马大学）；Microsoft Research AI4Science（微软研究院AI4Science）；University of Amsterdam（阿姆斯特丹大学）；University of Oxford（牛津大学）；AITHYRA Institute（艾西拉研究所）
Deep learning based molecular graph generation and optimization has recently been attracting attention due to its great potential for de novo drug design. On the one hand, recent models are able to efficiently learn a given graph distribution, and many approaches have proven very effective to produce a molecule that maximizes a given score. On the other hand, it was shown by previous studies that generated optimized molecules are often unrealistic, even with the inclusion of mechanics to enforce similarity to a dataset of real drug molecules. In this work we use a hybrid approach, where the da…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Peking University（北京大学）；Tsinghua University（清华大学）
Rich data and powerful machine learning models allow us to design drugs for a specific protein target \textit{in silico}. Recently, the inclusion of 3D structures during targeted drug design shows superior performance to other target-free models as the atomic interaction in the 3D space is explicitly modeled. However, current 3D target-aware models either rely on the voxelized atom densities or the autoregressive sampling process, which are not equivariant to rotation or easily violate geometric constraints resulting in unrealistic structures. In this work, we develop a 3D equivariant diffusio…
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
Tsinghua University（清华大学）；University of Washington（华盛顿大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；ByteDance Inc.（字节跳动公司）；Helixon Inc.（Helixon公司）
SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling
University of Toronto（多伦多大学）；The Hospital for Sick Children（多伦多儿童医院）；University of Cambridge（剑桥大学）；ETH Zürich（苏黎世联邦理工学院）；Vector Institute（向量研究所）；Mila – Quebec AI Institute（魁北克AI研究所）；McGill University（麦吉尔大学）；Caltech（加州理工学院）
Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding
Lingang Laboratory（梁岗实验室）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究所）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究所）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Department of Pharmaceutical and Artificial-Intelligence Sciences, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院药学与人工智能科学系）；Institute of Medical Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学医学人工智能研究所）
