最近，基于模板（TB）和无模板（TF）的分子图学习方法已经显示出有希望的结果逆合成。TB方法使用预编码的反应模板更准确，TF方法通过将逆合成分解为子问题，即，中心识别和合成子完成。为了结合TB和TF的优点，我们建议将一个完整的模板分解为几个半模板，并将它们嵌入到两步TF框架中。由于许多半模板是重复的，因此可以减少模板冗余，同时仍然保留必要的化学知识以促进合成子完成。我们称我们的方法为SemiRetro，引入了一个新的GNN层（DRGAT）来增强中心识别，并提出了一个新的自校正模块来改进半模板分类。实验结果表明，SemiRetro显着优于现有的TB和TF方法。在可扩展性方面，SemiRetro使用150个半模板覆盖98.9%的数据，而之前基于模板的GLN需要11，647个模板才能覆盖93.3%的数据。在top-1准确度中，SemiRetro超过无模板G2 G 4.8\%（类别已知）和6.0\%（类别未知）。此外，SemiRetro具有比现有方法更好的训练效率。
英文摘要：
Recently, template-based (TB) and template-free (TF) molecule graph learning methods have shown promising results to retrosynthesis. TB methods are more accurate using pre-encoded reaction templates, and TF methods are more scalable by decomposing retrosynthesis into subproblems, i.e., center identification and synthon completion. To combine both advantages of TB and TF, we suggest breaking a full-template into several semi-templates and embedding them into the two-step TF framework. Since many semi-templates are reduplicative, the template redundancy can be reduced while the essential chemical knowledge is still preserved to facilitate synthon completion. We call our method SemiRetro, introduce a new GNN layer (DRGAT) to enhance center identification, and propose a novel self-correcting module to improve semi-template classification. Experimental results show that SemiRetro significantly outperforms both existing TB and TF methods. In scalability, SemiRetro covers 98.9\% data using 150 semi-templates, while previous template-based GLN requires 11,647 templates to cover 93.3\% data. In top-1 accuracy, SemiRetro exceeds template-free G2G 4.8\% (class known) and 6.0\% (class unknown). Besides, SemiRetro has better training efficiency than existing methods.
Retrosynthesis Prediction with Conditional Graph Logic Network
Georgia Institute of Technology（佐治亚理工学院）；Galixir Inc.（Galixir公司）；Massachusetts Institute of Technology（麻省理工学院）；Google Research（谷歌研究院）；Ant Financial（蚂蚁集团）
ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information
School of Computer Science and Technology, East China Normal University（东华师范大学计算机科学与技术学院）；Shanghai Institute of Artificial Intelligence for Education, East China Normal University（东华师范大学上海人工智能教育研究所）；Shanghai Frontiers Science Center of Molecule Intelligent Syntheses（上海分子智能合成前沿科学中心）
RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation
Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；ByteDance Research（字节跳动研究院）；Department of Computer Science, Stanford University（斯坦福大学计算机科学系）
RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction
School of Cyber Science and Engineering, Wuhan University（武汉大学网络安全学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；College of Chemistry and Molecular Sciences, Wuhan University（武汉大学化学与分子科学学院）
A Graph to Graphs Framework for Retrosynthesis Prediction
Peking University（北京大学）；Shanghai Jiao Tong University（上海交通大学）；National Research Council Canada（加拿大国家研究委员会）；Montréal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院）；HEC Montréal（蒙特利尔高等商学院）
RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Standigm；Samsung Electronics（三星电子）；Samsung Advanced Institute of Technology (SAIT)（三星先进技术研究院）；AITRICS
Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis
School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）；Shanghai Institute of Artificial Intelligence for Education, East China Normal University（东华大学上海人工智能教育研究所）
Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction
Johannes Kepler University Linz（约翰内斯·开普勒大学林茨分校）；Institute of Advanced Research in Artificial Intelligence (IARAI)（人工智能高级研究所）；Janssen Research & Development, Janssen Pharmaceutica N.V.（杨森制药有限公司杨森研发部）；Microsoft Research（微软研究院）
Accelerating the inference of string generation-based chemical reaction models for industrial applications
IDSIA（IDSIA研究所）；USI（瑞士意大利语区大学）；SUPSI（瑞士应用科学大学南部）；Machine Learning Research, Pfizer Research and Development（辉瑞研发部机器学习研究部门）；Institute for Digital Technologies for Personalized Healthcare, SUPSI（瑞士应用科学大学南部个性化医疗数字技术研究所）；AI Initiative, KAUST（阿卜杜拉国王科技大学人工智能倡议）
