Graph Neural Networks: Taxonomy, Advances, and Trends

Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks. Up to now, there have been several surveys on this topic. However, they usually lay emphasis on different angles so that the readers cannot see a panorama of the graph neural networks. This survey aims to overcome this limitation and provide a systematic and comprehensive review on the graph neural networks. First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 327 relevant literatures to show the panorama of the graph neural networks. All of them are classified into the corresponding categories. In order to drive the graph neural networks into a new stage, we summarize four future research directions so as to overcome the challenges faced. It is expected that more and more scholars can understand and exploit the graph neural networks and use them in their research community.

Two-dimensional satellite image compression using compressive sensing

Compressive sensing is receiving a lot of attention from the image processing research community as a promising technique for image recovery from very few samples. The modality of compressive sensing technique is very useful in the applications where it is not feasible to acquire many samples. It is also prominently useful in satellite imaging applications since it drastically reduces the number of input samples thereby reducing the storage and communication bandwidth required to store and transmit the data into the ground station. In this paper, an interior point-based method is used to recover the entire satellite image from compressive sensing samples. The compression results obtained are compared with the compression results from conventional satellite image compression algorithms. The results demonstrate the increase in reconstruction accuracy as well as higher compression rate in case of compressive sensing-based compression technique.

The relationship between Fear of COVID-19 and Loneliness among Yemeni students in China

The current research aims to identify the level of fear of Covid-19 and loneliness among Yemeni students in China, and to determine the relationship between them and whether there are differences in the responses of the research sample according to gender. The research adopted the descriptive approach, and the questionnaire was used as a tool for collecting data from the research sample. The research community consisted of Yemeni students in China who were enrolled in the 2021 academic year, the sample is (301) male and female students who were selected using a simple random sampling method. The results showed that the level of fear of Covid-19 and the degree of loneliness were high. There is a positive relationship between fear of COVID-19 and loneliness. There are differences in fear of Covid-19 according to the gender variable in favor of males, and differences in loneliness in favor of females.

Effectiveness of a parent-mediated intervention for toddlers with autism spectrum disorder: Evidence from a large community implementation

Recent efforts have focused on developing and evaluating early intervention for toddlers with probable or emerging autism spectrum disorder. Parent-mediated approaches have gained traction, with mounting evidence of efficacy, but a research-to-practice gap exists, and community effectiveness remains to be firmly established. We report outcomes of a parent-mediated toddler intervention delivered through a research-community partnership, using a community-partnered participatory framework. Data were available for 179 of 183 toddler-parent dyads receiving Social ABCs parent coaching (mean toddler age: 25.18 months; range, 14–34 months). Of these, 89.4% completed the 12-week program and 70.6% returned for 3-month follow-up assessment. Parents attained implementation fidelity exceeding 75%, and toddlers made gains on proximal and distal measures of social communication. Parent fidelity was associated with toddlers’ responsivity at week 12, and responsivity predicted later language gains and reduced autism spectrum disorder symptoms. The roles of child, family, and system factors are discussed. Community delivery of an evidence-based parent-mediated intervention for toddlers with autism spectrum disorder is feasible and effective. Given resource efficiencies associated with parent-mediated approaches, findings bolster current efforts to promote earlier and more widespread access to intervention at the first signs of developmental concern. Lay abstract In an effort to increase access to intervention as early as possible for toddlers with autism spectrum disorder or signs thereof, many researchers have developed interventions that can be delivered by parents in their own homes. These parent-mediated approaches have gained a lot of research attention in recent years and have been found to be helpful in terms of parent and toddler learning. Several studies have used a rigorous research design (a randomized controlled trial) to show that parent-mediated intervention can work under ideal well-controlled conditions. To build on this evidence, we also need to examine whether parent-mediated interventions can be taught well through community service providers and delivered in more “real-world” conditions. This study used a research-community partnership to provide a parent-mediated intervention (called the Social ABCs) to 179 families (mean toddler age was 25 months; ranging from 14 to 34 months). Almost 90% of the families completed the 12-week program and 70% returned for a follow-up assessment 3 months later. Analyses showed that parents learned the strategies that were designed to help them support their toddlers’ development. Also, toddlers made gains in their language, communication, and social skills. Importantly, parents’ use of the strategies was related to toddlers’ skill gains, suggesting that the use of the strategies made a difference for the toddlers. Findings support the use of parent-mediated intervention in this very young age group and suggest that such intervention approaches should be made available for community delivery.

Understanding Rhinovirus Circulation and Impact on Illness

Rhinoviruses (RVs) have been reported as one of the main viral causes for severe respiratory illnesses that may require hospitalization, competing with the burden of other respiratory viruses such as influenza and RSV in terms of severity, economic cost, and resource utilization. With three species and 169 subtypes, RV presents the greatest diversity within the Enterovirus genus, and despite the efforts of the research community to identify clinically relevant subtypes to target therapeutic strategies, the role of species and subtype in the clinical outcomes of RV infection remains unclear. This review aims to collect and organize data relevant to RV illness in order to find patterns and links with species and/or subtype, with a specific focus on species and subtype diversity in clinical studies typing of respiratory samples.

Bridges and Barriers: An Exploration of Engagements of the Research Community with the OpenStreetMap Community

The academic community frequently engages with OpenStreetMap (OSM) as a data source and research subject, acknowledging its complex and contextual nature. However, existing literature rarely considers the position of academic research in relation to the OSM community. In this paper we explore the extent and nature of engagement between the academic research community and the larger communities in OSM. An analysis of OSM-related publications from 2016 to 2019 and seven interviews conducted with members of one research group engaged in OSM-related research are described. The literature analysis seeks to uncover general engagement patterns while the interviews are used to identify possible causal structures explaining how these patterns may emerge within the context of a specific research group. Results indicate that academic papers generally show few signs of engagement and adopt data-oriented perspectives on the OSM project and product. The interviews expose that more complex perspectives and deeper engagement exist within the research group to which the interviewees belong, e.g., engaging in OSM mapping and direct interactions based on specific points-of-contact in the OSM community. Several conclusions and recommendations emerge, most notably: that every engagement with OSM includes an interpretive act which must be acknowledged and that the academic community should act to triangulate its interpretation of the data and OSM community by diversifying their engagement. This could be achieved through channels such as more direct interactions and inviting members of the OSM community to participate in the design and evaluation of research projects and programmes.

GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks

The tremendous success of graphical neural networks (GNNs) has already had a major impact on systems biology research. For example, GNNs are currently used for drug target recognition in protein-drug interaction networks as well as cancer gene discovery and more. Important aspects whose practical relevance is often underestimated are comprehensibility, interpretability, and explainability. In this work, we present a graph-based deep learning framework for disease subnetwork detection via explainable GNNs. In our framework, each patient is represented by the topology of a protein-protein network (PPI), and the nodes are enriched by molecular multimodal data, such as gene expression and DNA methylation. Therefore, our novel modification of the GNNexplainer for model-wide explanations can detect potential disease subnetworks, which is of high practical relevance. The proposed methods are implemented in the GNN-SubNet Python program, which we have made freely available on our GitHub for the international research community (https://github.com/pievos101/GNN-SubNet).

Betting on Bets

The AI Bookie column documents highlights from AI Bets, an online forum for the creation of adjudicatable predictions about the future of AI. Since the column’s inception 3 years ago, only a few scientific bets have been collected, despite universal approval around the idea of scientific betting. We hope to widen our reach with an additional first batch of seed bets that are of broad interest to the research community including AI bias, fifth sentence prediction, emotion regu-lation, big models, and fake news. For detailed guidelines and to place bets, visit sciencebets.org.

SorghumBase: a web-based portal for sorghum genetic information and community advancement

Main conclusion SorghumBase provides a community portal that integrates genetic, genomic, and breeding resources for sorghum germplasm improvement. Abstract Public research and development in agriculture rely on proper data and resource sharing within stakeholder communities. For plant breeders, agronomists, molecular biologists, geneticists, and bioinformaticians, centralizing desirable data into a user-friendly hub for crop systems is essential for successful collaborations and breakthroughs in germplasm development. Here, we present the SorghumBase web portal (https://www.sorghumbase.org), a resource for the sorghum research community. SorghumBase hosts a wide range of sorghum genomic information in a modular framework, built with open-source software, to provide a sustainable platform. This initial release of SorghumBase includes: (1) five sorghum reference genome assemblies in a pan-genome browser; (2) genetic variant information for natural diversity panels and ethyl methanesulfonate (EMS)-induced mutant populations; (3) search interface and integrated views of various data types; (4) links supporting interconnectivity with other repositories including genebank, QTL, and gene expression databases; and (5) a content management system to support access to community news and training materials. SorghumBase offers sorghum investigators improved data collation and access that will facilitate the growth of a robust research community to support genomics-assisted breeding.