GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation
Authors: Shengyin Sun, Wenhao Yu, Yuxiang Ren, Weitao Du, Liwei Liu, Xuecang Zhang, Ying Hu, Chen Ma
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experimental findings reveal that GDiff Retro outperforms state-of-the-art semi-template models across various evaluative metrics. [...] 4 Experiments [...] We utilize the USPTO-50k dataset (Lowe 2017), detailed in Section C of the supplementary material, to assess the proposed method. [...] As shown in Table 1, the top-1 result of GDiff Retro surpasses all template-free/semi-template based baselines [...] 4.4 Ablation Study |
| Researcher Affiliation | Collaboration | 1Department of Computer Science, City University of Hong Kong 2Department of Computer Science and Engineering, The Chinese University of Hong Kong 3Advance Computing and Storage Lab, Huawei Technologies 4Academy of Mathematics and Systems Science, Chinese Academy of Sciences 5Department of Electronic Engineering, Tsinghua University |
| Pseudocode | No | The paper describes the methodology using mathematical equations and textual explanations (e.g., equations 1-18 in Section 3), but it does not contain a clearly labeled 'Pseudocode' or 'Algorithm' block, nor structured steps formatted like code. |
| Open Source Code | Yes | Code available at https://github.com/sunshy-1/GDiff Retro. |
| Open Datasets | Yes | We utilize the USPTO-50k dataset (Lowe 2017), detailed in Section C of the supplementary material, to assess the proposed method. The citation for the dataset is: Lowe, D. 2017. Chemical reactions from US patents (1976Sep2016). |
| Dataset Splits | Yes | We utilize the USPTO-50k dataset (Lowe 2017), detailed in Section C of the supplementary material, to assess the proposed method. The split of the dataset follows previous work (Liu et al. 2017; Shi et al. 2020). |
| Hardware Specification | No | The paper does not contain any specific details about the hardware (e.g., CPU, GPU models, memory, cloud resources) used for the experiments. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers (e.g., 'Python 3.8', 'PyTorch 1.9') that are needed to replicate the experiments. |
| Experiment Setup | No | More implementation details can be seen in Section F (supplementary material). |