In this study, we introduce semi-supervised machine learning models designed to predict molecular properties. Our model employs a two-stage approach, involving pre-training and fine-tuning. Particularly, our leverages substantial amount of labeled unlabeled data consisting SMILES strings, text representation system for molecules. During the stage, capitalizes on Masked Language Model, which is ...

Abstract Effective molecular representation learning is of great importance to facilitate property prediction. Recent advances for have shown promise in applying graph neural networks model molecules. Moreover, a few recent studies design self-supervised methods address insufficient labelled molecules; however, these frameworks treat the molecules as topological graphs without fully utilizing g...

Recently, graph neural networks (GNNs) have been successfully applied to predicting molecular properties, which is one of the most classical cheminformatics tasks with various applications. Despite their effectiveness, we empirically observe that training a single GNN model for diverse molecules distinct structural patterns limits its prediction performance. In this paper, motivated by observat...

INTRODUCTION Information technology (IT) standards allow different technologies, including hardware, software, and even people, to interact, thereby forming systems. Without information technology standards, there can be no information systems (IS). Thus, standards development is one of the most important activities of technology vendors. It is also one of the most difficult because it requires...

Quantitative structure-property relationships (QSPRs) aid in understanding molecular properties as a function of structure. When the correlation between structure and property weakens, dataset is described ``rough,'' but...