Self-Supervised Molecular Pretraining Strategy for Low-Resource Reaction Prediction Scenarios

Wu, Zhipeng; Cai, Xiang; Zhang, Chenyun; Qiao, Haoran; Wu, Yejian; Zhang, Yun; Wang, Xinqiao; Hai-ying, Xie; Luo, Fei; Duan, Hongliang

doi:10.1021/acs.jcim.2c00588

Cited by 2 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies utilized SMILES as input and employed well-established models from the field of natural language processing (NLP) to encode the SMILES notations of chemical reactions into continuous vectors. These studies employed either pre-trained Transformer-based models [ 19 – 21 ] or Recurrent Neural Network (RNN) models [ 22 , 23 ] on large-scale datasets, and fine-tuned their models [ 3 , 24 ] with downstream tasks to capture task-specific representations of chemical reactions. Other studies incorporated molecular graph structures to represent chemical reactions.…”

Section: Introductionmentioning

confidence: 99%

Prediction of chemical reaction yields with large-scale multi-view pre-training

Shi,

Yu,

Huo

et al. 2024

J Cheminform

View full text Add to dashboard Cite

Developing machine learning models with high generalization capability for predicting chemical reaction yields is of significant interest and importance. The efficacy of such models depends heavily on the representation of chemical reactions, which has commonly been learned from SMILES or graphs of molecules using deep neural networks. However, the progression of chemical reactions is inherently determined by the molecular 3D geometric properties, which have been recently highlighted as crucial features in accurately predicting molecular properties and chemical reactions. Additionally, large-scale pre-training has been shown to be essential in enhancing the generalization capability of complex deep learning models. Based on these considerations, we propose the Reaction Multi-View Pre-training (ReaMVP) framework, which leverages self-supervised learning techniques and a two-stage pre-training strategy to predict chemical reaction yields. By incorporating multi-view learning with 3D geometric information, ReaMVP achieves state-of-the-art performance on two benchmark datasets. Notably, the experimental results indicate that ReaMVP has a significant advantage in predicting out-of-sample data, suggesting an enhanced generalization ability to predict new reactions. Scientific Contribution: This study presents the ReaMVP framework, which improves the generalization capability of machine learning models for predicting chemical reaction yields. By integrating sequential and geometric views and leveraging self-supervised learning techniques with a two-stage pre-training strategy, ReaMVP achieves state-of-the-art performance on benchmark datasets. The framework demonstrates superior predictive ability for out-of-sample data and enhances the prediction of new reactions.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of chemical reaction yields with large-scale multi-view pre-training

Shi,

Yu,

Huo

et al. 2024

J Cheminform

View full text Add to dashboard Cite

show abstract

Exploring Chemical Reaction Space with Machine Learning Models: Representation and Feature Perspective

Ding,

Qiang,

Chen

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Chemical reactions serve as foundational building blocks for organic chemistry and drug design. In the era of large AI models, data-driven approaches have emerged to innovate the design of novel reactions, optimize existing ones for higher yields, and discover new pathways for synthesizing chemical structures comprehensively. To effectively address these challenges with machine learning models, it is imperative to derive robust and informative representations or engage in feature engineering using extensive data sets of reactions. This work aims to provide a comprehensive review of established reaction featurization approaches, offering insights into the selection of representations and the design of features for a wide array of tasks. The advantages and limitations of employing SMILES, molecular fingerprints, molecular graphs, and physics-based properties are meticulously elaborated. Solutions to bridge the gap between different representations will also be critically evaluated. Additionally, we introduce a new frontier in chemical reaction pretraining, holding promise as an innovative yet unexplored avenue.

show abstract

Self-Supervised Molecular Pretraining Strategy for Low-Resource Reaction Prediction Scenarios

Cited by 2 publications

References 43 publications

Prediction of chemical reaction yields with large-scale multi-view pre-training

Prediction of chemical reaction yields with large-scale multi-view pre-training

Exploring Chemical Reaction Space with Machine Learning Models: Representation and Feature Perspective

Contact Info

Product

Resources

About