ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction

Abstract

Molecular property prediction (e.g., energy) is an essential problem in chemistry and biology. Unfortunately, many supervised learning methods usually suffer from the problem of scarce labeled molecules in the chemical space, where such property labels are generally obtained by Density Functional Theory (DFT) calculation which is extremely computational costly. An effective solution is to incorporate the unlabeled molecules in a semi-supervised fashion. However, learning semi-supervised representation for large amounts of molecules is challenging, including the joint representation issue of both molecular essence and structure, the conflict between representation and property leaning. Here we propose a novel framework called Active Semi-supervised Graph Neural Network (ASGN) by incorporating both labeled and unlabeled molecules. Specifically, ASGN adopts a teacher-student framework. In the teacher model, we propose a novel semi-supervised learning method to learn general representation that jointly exploits information from molecular structure and molecular distribution. Then in the student model, we target at property prediction task to deal with the learning loss conflict. At last, we proposed a novel active learning strategy in terms of molecular diversities to select informative data during the whole framework learning. We conduct extensive experiments on several public datasets. Experimental results show the remarkable performance of our ASGN framework.

Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity

“…Graph Neural Networks for Drug Discovery. Inspired by the great advantage of graph neural networks (GNNs) in modeling graph data, much attention has been devoted to applying them in computational drug discovery [37], such as the prediction of molecular property [10] and protein interface [25]. Treating the molecule as a graph, GNNs can learn the graph-level representation for drug or protein by aggregating structural information.…”

Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers

“…These state-of-the-art ML methods have shown impressive performance on benchmark datasets such as the QM9 dataset which contains the ground state properties of molecules consisting of up to 9 non-hydrogen atoms. [42][43][44][45][46][47][48][49][50][51][52][53][54][55] Despite the remarkable progress of these graph ML methods, their application to conjugated long oligomers and polymers remains limited primarily due to the difficulty in obtaining sufficient training data using quantum chemical methods.…”

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction

“…Though GNNs have achieved remarkable accuracy on molecular property prediction, they are usually data-hungry, i.e. a large amount of labeled data (i.e., molecules with known property data) is required for training [8,12]. However, labeled molecules only occupy an extremely small portion of the enormous chemical space since they can only be obtained from wet-lab experiments or quantum chemistry calculations, which are time-consuming and expensive.…”