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

Lee, Hankook; Ahn, Sung Soo; Seo, Seung-Woo; Song, Yun-Jeong; Yang, Eunho; Hwang, Seung Sang; Shin, Jinwoo

doi:10.48550/arxiv.2105.00795

Cited by 3 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selection-based methods, such as reactant selection and template selection methods, aim to choose appropriate molecules or reaction rules from the given sets. Reactant selection methods [20,21] involve ranking molecules from a collection of candidates based on the target compounds.…”

Section: Introductionmentioning

confidence: 99%

Site-Specific Template Generative Approach for Retrosynthetic Planning

Shee,

Li,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

Retrosynthesis, the strategy of devising laboratory pathways for small molecules by working backwards from the target compound, remains a rate limiting step in multi-step synthesis of complex molecules, particularly in drug discovery. Enhancing retrosynthetic efficacy requires overcoming the vast complexity of chemical space, the limited known interconversions between molecules, and the challenges posed by limited experimental datasets. In this study, we introduce generative machine learning methods for retrosynthetic planning that generate reaction templates. Our approach features three key innovations. First, the models generate complete reactions, known as templates, instead of reactants or synthons. Through this abstraction, novel chemical transforms resembling those in the training dataset can be generated. Second, the approach optionally allows users to select the specific bond or bonds to be changed in the proposed reaction, enabling human interaction to influence the synthetic approach. Third, one of our models, based on the conditional kernel-elastic autoencoder (CKAE) architecture, employs a latent space to measure the similarity between generated and known reactions, providing insights into their chemical viability. Together, these features establish a coherent framework for retrosynthetic planning, as validated by our experimental work. We demonstrate the application of our machine learning methodology to design a synthetic pathway for a simple yet challenging small molecule of pharmaceutical interest. The pathway was experimentally proven viable through a 3-step process, which compares favorably to previous 5-9 step approaches. This improvement demonstrates the utility and robustness of the generative machine learning approaches described herein and highlights their potential to address a broad spectrum of challenges in chemical synthesis.

show abstract

Section: Introductionmentioning

confidence: 99%

Site-Specific Template Generative Approach for Retrosynthetic Planning

Shee,

Li,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Stärk et al[53] contrastively learn 3D and 2D molecule representations to inform the learned molecule encoder with 3D information. Lee et al[54] and Seidl et al[55] use contrastive learning for molecules and chemical reactions, and Vall et al[56] utilizes text representations of wet-lab procedures to enable zero-shot predictions. However, none of these methods have exploited the wealth of information contained in microscopy images of molecule-perturbed cells[29] and demonstrated strong transferability of the learned molecule encoders.…”

mentioning

confidence: 99%