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 GNN (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 AND IMPLEMENTATION: 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.

Exploring GUIs of Android apps plays a key role in many important scenarios such as functional testing (e.g., finding crash errors), security analysis (e.g., identifying malicious behav-iors) and competitive analysis (e.g., storyboarding app features). To automate GUI exploration, existing techniques often try to visit as many GUI pages as possible via specific strategies, e.g., random (like Monkey) or heuristic (like Stoat, A3E). However, their effectiveness is still unclear and much under-explored. To this end, we conducted the first study in this paper to understand and characterize their limitations by carefully analyzing the coverage reports from a set of real-world, open-source apps. Through this study, we identified three key limitations due to the lack of dependency knowledge during exploration, i.e., widget-page dependency, widget-widget dependency and system-event dependency. To overcome them, we introduce dependency-informed exploration, an automated approach that leverages static dependency analysis to effectively improve GUI exploration performance. Given an app, our approach first constructs a GUI page transition model that captures the dependencies between GUI widgets, and then guides GUI exploration during a depth-first traversal. We realized our approach as a tool named Gesda, and evaluated it on 70 open-source Android apps. The results show Gesda outperforms existing state-of-the-art GUI exploration techniques, i.e., Monkey and Stoat. Additionally, Gesda uncovers 4 previously unknown crashes in 4 apps as a by-product of GUI exploration due to the benefit of dependency knowledge, while Monkey and Stoat have not discovered them.

How to obtain informative representations of molecules is a crucial prerequisite in AI-driven drug design and discovery. Recent researches abstract molecules as graphs and employ Graph Neural Networks (GNNs) for molecular representation learning. Nevertheless, two issues impede the usage of GNNs in real scenarios: (1) insufficient labeled molecules for supervised training; (2) poor generalization capability to new-synthesized molecules. To address them both, we propose a novel framework, GROVER, which stands for Graph Representation frOm self-superVised mEssage passing tRansformer. With carefully designed self-supervised tasks in node-, edge- and graph-level, GROVER can learn rich structural and semantic information of molecules from enormous unlabelled molecular data. Rather, to encode such complex information, GROVER integrates Message Passing Networks into the Transformer-style architecture to deliver a class of more expressive encoders of molecules. The flexibility of GROVER allows it to be trained efficiently on large-scale molecular dataset without requiring any supervision, thus being immunized to the two issues mentioned above. We pre-train GROVER with 100 million parameters on 10 million unlabelled molecules---the biggest GNN and the largest training dataset in molecular representation learning. We then leverage the pre-trained GROVER for molecular property prediction followed by task-specific fine-tuning, where we observe a huge improvement (more than 6% on average) from current state-of-the-art methods on 11 challenging benchmarks. The insights we gained are that well-designed self-supervision losses and largely-expressive pre-trained models enjoy the significant potential on performance boosting.