Motivation The crux of molecular property prediction is to generate meaningful representations of the molecules. One promising route is to exploit the molecular graph structure through Graph Neural Networks (GNNs). Both atoms and bonds significantly affect the chemical properties of a molecule, so an expressive model ought to exploit both node (atom) and edge (bond) information simultaneously. Inspired by this observation, we explore the multi-view modeling with graph neural network (MVGNN) to form a novel paralleled framework which considers both atoms and bonds equally important when learning molecular representations. In specific, one view is atom-central and the other view is bond-central, then the two views are circulated via specifically designed components to enable more accurate predictions. To further enhance the expressive power of MVGNN, we propose a cross-dependent message passing scheme to enhance information communication of different views. The overall framework is termed as CD-MVGNN. Results We theoretically justify the expressiveness of the proposed model in terms of distinguishing non-isomorphism graphs. Extensive experiments demonstrate that CD-MVGNN achieves remarkably superior performance over the state-of-the-art models on various challenging benchmarks. Meanwhile, visualization results of the node importance are consistent with prior knowledge, which confirms the interpretability power of CD-MVGNN. Availability The code and data underlying this work are available in GitHub at https://github.com/uta-smile/CD-MVGNN. Supplementary information Supplementary data are available at Bioinformatics online.

In chest computed tomography (CT) scans, pulmonary vessel suppression can make pulmonary nodules more evident, and therefore may increase the detectability of early lung cancer. The purpose of this study was to develop a computer-aided detection (CAD) system with a vessel suppression function and to verify the effectiveness of the vessel suppression on the performance of the pulmonary nodule CAD system. Methods: A CAD system with a vessel suppression function capable of suppressing vessels and detecting nodules was developed. First, a convolutional neural network (CNN)-based pulmonary vessel suppression technique was employed to remove the vessels from lungs while preserving the nodules. Then, a CNN-based pulmonary nodule detector was utilized to sequentially generate nodule candidates and reduce false positives (FPs). The performance levels of CAD systems with and without the vessel suppression function were compared using 888 three-dimensional chest CT scans from the Lung Nodule Analysis 2016 (LUNA16) dataset. The pulmonary nodule detection results were quantitatively evaluated using the average sensitivity at seven predefined FP rates: 0.125, 0.25, 0.5, 1, 2, 4, and 8 FPs per scan. Results: The developed pulmonary nodule CAD system improved the average sensitivity to 0.977 from 0.950 owing to the addition of the vessel suppression function. Conclusions: The vessel suppression function considerably improved the performance of the CAD system for pulmonary nodule detection. In practice, it would be embedded in CAD systems to assist radiologists in detecting pulmonary nodules in chest CT scans.

No abstract

No abstract

No abstract