paper-with-me

Papers

Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer

2022-01-29 · Yue Wan, Benben Liao, Chang-Yu Hsieh, Shengyu Zhang

Retrosynthesis prediction is one of the fundamental challenges in organic synthesis. The task is to predict the reactants given a core product. With the advancement of machine learning, computer-aided synthesis planning has gained increasing interest. Numerous methods were proposed to solve this problem with different levels of dependency on additional chemical knowledge. In this paper, we propose Retroformer, a novel Transformer-based architecture for retrosynthesis prediction without relying on any cheminformatics tools for molecule editing. Via the proposed local attention head, the model can jointly encode the molecular sequence and graph, and efficiently exchange information between the local reactive region and the global reaction context. Retroformer reaches the new state-of-the-art accuracy for the end-to-end template-free retrosynthesis, and improves over many strong baselines on better molecule and reaction validity. In addition, its generative procedure is highly interpretable and controllable. Overall, Retroformer pushes the limits of the reaction reasoning ability of deep generative models.

📄 PDF Abstract BibTeX arXiv:2201.12475

Code (1)

yuewan2/Retroformer 공식 구현 pytorch

Tasks

Retrosynthesis

Similar Papers 제목 키워드 기반

Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis

2025-08-14 · Xinyi Li, Sai Wang, Yutian Lin, Yu Wu arxiv

Retrosynthesis prediction aims to infer the reactant molecules based on a given product molecule, which is a fundamental task in chemical synthesis. However, existing methods rely on a static pattern-matching paradigm, w…

Reinforcement Learning

UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment

2024-03-25 · Kaipeng Zeng, Bo Yang, Xin Zhao, Yu Zhang 외

Motivation: Retrosynthesis planning poses a formidable challenge in the organic chemical industry. Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recen…

Graph-to-Sequencemolecular representationRepresentation LearningRetrosynthesis+1

MechRetro is a chemical-mechanism-driven graph learning framework for interpretable retrosynthesis prediction and pathway planning

2022-10-06 · Yu Wang, Chao Pang, Yuzhe Wang, Yi Jiang 외

Leveraging artificial intelligence for automatic retrosynthesis speeds up organic pathway planning in digital laboratories. However, existing deep learning approaches are unexplainable, like "black box" with few insights…

Drug DiscoveryGraph LearningMulti-step retrosynthesisRepresentation Learning+1

RetroPrime: A Diverse, plausible and Transformer-based method for Single-Step retrosynthesis predictions

2021-09-15 · Chemical Engineering Journal 2021 9 · Xiaorui Wang, Yuquan Li, Jiezhong Qiu, Guangyong Chen 외

Retrosynthesis prediction is a crucial task for organic synthesis. In this work, we propose a single-step template-free and Transformer-based method dubbed RetroPrime, integrating chemists’ retrosynthetic strategy of (1)…

DiversityRetrosynthesisSingle-step retrosynthesis

Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks

2019-07-02 · Shuangjia Zheng, Jiahua Rao, Zhongyue Zhang, Jun Xu 외

Synthesis planning is the process of recursively decomposing target molecules into available precursors. Computer-aided retrosynthesis can potentially assist chemists in designing synthetic routes, but at present it is c…

Machine TranslationRetrosynthesisTranslation