Abstract Deep learning models can accurately predict molecular properties and help making the search for potential drug candidates faster more efficient. Many existing methods are purely data driven, focusing on exploiting intrinsic topology construction rules of molecules without any chemical prior information. The high dependency makes them difficult to generalize a wider space leads lack int...

Recently many efforts have been devoted to applying graph neural networks (GNNs) molecular property prediction which is a fundamental task for computational drug and material discovery. One of major obstacles hinder the successful by GNNs scarcity labeled data. Though contrastive learning (GCL) methods achieved extraordinary performance with insufficient data, most focused on designing data aug...

Molecular Machine Learning (ML) bears promise for efficient molecule property prediction and drug discovery. However, labeled data can be expensive time-consuming to acquire. Due the limited data, it is a great challenge supervised-learning ML models generalize giant chemical space. In this work, we present MolCLR: Contrastive of Representations via Graph Neural Networks (GNNs), self-supervised...

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular graph convolutions, a machine learning...

‎In addition to his countless contributions to spectral graph theory‎, some works of Dragos Cvetkovic are concerned with chemical problems‎. These are briefly outlined‎, ‎with emphasis on his collaboration with‎ ‎the present author‎.