RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

Authors: Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung Ju Hwang, Jinwoo Shin

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate the benefits of the proposed selectionbased approach. For example, when all 671k reactants in the USPTO database are given as candidates, our RETCL achieves top-1 exact match accuracy of 71.3% for the USPTO-50k benchmark, while a recent transformer-based approach achieves 59.6%. We also demonstrate that RETCL generalizes well to unseen templates in various settings in contrast to template-based approaches.
Researcher Affiliation Collaboration 1Korea Advanced Institute of Science and Technology 2Mohamed bin Zaayed University of Artificial Intelligence 3Standigm 4Samsung Electronics 5AITRICS
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper states: 'The supplementary material is available at ar Xiv:2105.00795.', but does not explicitly state that the source code for the methodology is provided within this material.
Open Datasets Yes We mainly evaluate our framework in USPTO-50k, which is a standard benchmark for the task of retrosynthesis. It contains 50k reactions of 10 reaction types derived from the US patent literature, and we divide it into training/validation/test splits following [Coley et al., 2017]. To apply our framework, we choose the candidate set of commercially available molecules C as the all reactants in the entire USPTO database as [Guo et al., 2020] did. This results in the candidate set with a size of 671,518.
Dataset Splits Yes We mainly evaluate our framework in USPTO-50k, which is a standard benchmark for the task of retrosynthesis. It contains 50k reactions of 10 reaction types derived from the US patent literature, and we divide it into training/validation/test splits following [Coley et al., 2017].
Hardware Specification No The paper does not explicitly describe the specific hardware used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions or other library versions).
Experiment Setup Yes Hyperparameters. We use a single shared 5-layer structure2vec [Dai et al., 2016; Dai et al., 2019] architecture and three separate 2-layer residual blocks with an embedding size of 256. To obtain graph-level embedding vectors, we use sum pooling over mean pooling since it captures the size information of molecules. For contrastive learning, we use a temperature of τ = 0.1 and K = 4 nearest neighbors for hard negative mining.