Improved Lipophilicity and Aqueous Solubility Prediction with Composite Graph Neural Networks

The accurate prediction of molecular properties, such as lipophilicity and aqueous solubility, are of great importance and pose challenges in several stages of the drug discovery pipeline. Machine learning methods, such as graph-based neural networks (GNNs), have shown exceptionally good performance in predicting these properties. In this work, we introduce a novel GNN architecture, called directed edge graph isomorphism network (D-GIN). It is composed of two distinct sub-architectures (D-MPNN, GIN) and achieves an improvement in accuracy over its sub-architectures employing various learning, and featurization strategies. We argue that combining models with different key aspects help make graph neural networks deeper and simultaneously increase their predictive power. Furthermore, we address current limitations in assessment of deep-learning models, namely, comparison of single training run performance metrics, and offer a more robust solution.

Improved Lipophilicity and Aqueous Solubility Prediction With Composite Graph Neural Networks

The accurate prediction of molecular properties such as lipophilicity and aqueous solubility is of great importance in several stages of the drug discovery pipeline. Machine learning methods like graph-based neural networks have shown exceptionally good performance in predicting these properties. In this work we introduce a novel graph neural network architecture composed of two distinct sub-architectures that achieves an improvement in accuracy over its individual parts employing various learning-, and featurization strategies. We argue that combining models with different key aspects might help make graph neural networks deeper while simultaneously increasing their predictive power. Additionally, we want to highlight the need to move beyond comparing single performance metrics to show machine learning model superiority.

The G-Convexity and the G-Centroids of Composite Graphs

The graph centroids defined through a topological property of a graph called g-convexity found its application in various fields. They have classified under the “facility location” problem. However, the g-centroid location for an arbitrary graph is NP-hard. Thus, it is necessary to devise an approximation algorithm for general graphs and polynomial-time algorithms for some special classes of graphs. In this paper, we study the relationship between the g-centroids of composite graphs and their factors under various well-known graph operations such as graph Joins, Cartesian products, Prism, and the Corona. For the join of two graphs G1 and G2, the weight sequence of the composite graph does not depend on the weight sequences of its factors; rather it depends on the incident pattern of the maximum cliques of G1 and G2. We also characterize the structure of the g-centroid under various cases. For the Cartesian product of G1 and G2 and the prism of a graph, we establish the relationship between the g-centroid of a composite graph and its factors. Our results will facilitate the academic community to focus on the factor graphs while designing an approximate algorithm for a composite graph.