Explainable drug repurposing via path based knowledge graph completion.

Drug repurposing aims to find new therapeutic applications for existing drugs in the pharmaceutical market, leading to significant savings in time and cost. The use of artificial intelligence and knowledge graphs to propose repurposing candidates facilitates the process, as large amounts of data can be processed. However, it is important to pay attention to the explainability needed to validate the predictions. We propose a general architecture to understand several explainable methods for graph completion based on knowledge graphs and design our own architecture for drug repurposing. We present XG4Repo (eXplainable Graphs for Repurposing), a framework that takes advantage of the connectivity of any biomedical knowledge graph to link compounds to the diseases they can treat. Our method allows methapaths of different types and lengths, which are automatically generated and optimised based on data. XG4Repo focuses on providing meaningful explanations to the predictions, which are based on paths from compounds to diseases. These paths include nodes such as genes, pathways, side effects, or anatomies, so they provide information about the targets and other characteristics of the biomedical mechanism that link compounds and diseases. Paths make predictions interpretable for experts who can validate them and use them in further research on drug repurposing. We also describe three use cases where we analyse new uses for Epirubicin, Paclitaxel, and Predinisone and present the paths that support the predictions.

Lightweight dense video captioning with cross-modal attention and knowledge-enhanced unbiased scene graph.

Dense video captioning (DVC) aims at generating description for each scene in a video. Despite attractive progress for this task, previous works usually only concentrate on exploiting visual features while neglecting audio information in the video, resulting in inaccurate scene event location. In this article, we propose a novel DVC model named CMCR, which is mainly composed of a cross-modal processing (CM) module and a commonsense reasoning (CR) module. CM utilizes a cross-modal attention mechanism to encode data in different modalities. An event refactoring algorithm is proposed to deal with inaccurate event localization caused by overlapping events. Besides, a shared encoder is utilized to reduce model redundancy. CR optimizes the logic of generated captions with both heterogeneous prior knowledge and entities' association reasoning achieved by building a knowledge-enhanced unbiased scene graph. Extensive experiments are conducted on ActivityNet Captions dataset, the results demonstrate that our model achieves better performance than state-of-the-art methods. To better understand the performance achieved by CMCR, we also apply ablation experiments to analyze the contributions of different modules.

Heterogeneous knowledge spillover channels in universities and green technology innovation in local firms: Stimulating quantity or quality?

Sluggish status of green technology development has stimulated research into new incentives and pathways. Beyond the traditional regulatory-push and demand-pull approaches, we reposition the strength of the technology push. Based on the innovation diffusion theory, a multidimensional path model of knowledge spillover in universities is constructed, and the impact of heterogeneous knowledge spillover channels on green innovation activities of local firms is discussed. We find that R&D collaboration has a significant effect on local firms' quality but not the quantity of green innovation. Contrarily, patent citations and technology transfer have unequal positive effects on the quantity of green innovation of local firms, while there is no evidence that they can also improve the quality of green innovation. Despite regional disparities, strict environmental regulations are pushing companies to cite university patents in some regions. The university knowledge stock has largely contributed to both quantitative and qualitative advances in subsequent green innovation in local firms. Our conclusions provide a precise and objective evaluation of the impact mechanism of multiple knowledge spillover channels in universities on firms' green innovation, as well as a reference for the selection of the form of industry-university-research collaboration.

POKR: Building a Computable Heterogeneous Knowledge Resource for Precision Oncology.

Precision oncology is expected to improve selection of targeted therapies, tailored to individual patients and ultimately improve cancer patients' outcomes. Several cancer genetics knowledge databases have been successfully developed for such purposes, including CIViC and OncoKB, with active community-based curations and scoring of genetic-treatment evidences. Although many studies were conducted based on each knowledge base respectively, the integrative analysis across both knowledge bases remains largely unexplored. Thus, there exists an urgent need for a heterogeneous precision oncology knowledge resource with computational power to support drug repurposing discovery in a timely manner, especially for life-threatening cancer. In this pilot study, we built a heterogeneous precision oncology knowledge resource (POKR) by integrating CIViC and OncoKB, in order to incorporate unique information contained in each knowledge base and make associations amongst biomedical entities (e.g., gene, drug, disease) computable and measurable via training POKR graph embeddings. All the relevant codes, database dump files, and pre-trained POKR embeddings can be accessed through the following URL: https://github.com/shenfc/POKR.

Modeling students' performance using graph convolutional networks.

Many models were recently proposed to classify students, relying on a large amount of pre-labeled data to verify their classification effectiveness. However, those models lack to accurately classify students into various behavioral patterns, employing nominal class labels, rather than ordinal ones. Meanwhile, such models cannot analyze high-dimensional learning behaviors among learners according to students' interaction with course videos. Since online learning data are huge, the main challenges associated with data are insufficient labeling and classification using nominal class labels. In this study, we proposed a model based on Graph Convolutional Network, as a semi-supervised classification task to classify students' engagement in various behavioral patterns. First, we proposed a label function to label datasets instead of manual labeling, in which input and output data are labeled for classification to provide a learning foundation for future data processing. Accordingly, we hypothesized four behavioral patterns, namely ("High-engagement", "Normal-engagement", "At-risk", and "Potential-At-risk") based on students' engagement with course videos and their performance on the assessments/quizzes conducted after. Then, we built a heterogeneous knowledge graph representing learners, course videos as entities, and capturing semantic relationships among students according to shared knowledge concepts in videos. Our model intrinsically works for heterogeneous knowledge graphs as a semi-supervised node classification task. It was evaluated on a real-world dataset across multiple settings to achieve a better predictive classification model. Experiment results showed that the proposed model can predict with an accuracy of 84% and an f1-score of 78% compared to baseline approaches.

HPO2Vec+: Leveraging heterogeneous knowledge resources to enrich node embeddings for the Human Phenotype Ontology.

BACKGROUND: In precision medicine, deep phenotyping is defined as the precise and comprehensive analysis of phenotypic abnormalities, aiming to acquire a better understanding of the natural history of a disease and its genotype-phenotype associations. Detecting phenotypic relevance is an important task when translating precision medicine into clinical practice, especially for patient stratification tasks based on deep phenotyping. In our previous work, we developed node embeddings for the Human Phenotype Ontology (HPO) to assist in phenotypic relevance measurement incorporating distributed semantic representations. However, the derived HPO embeddings hold only distributed representations for IS-A relationships among nodes, hampering the ability to fully explore the graph. METHODS: In this study, we developed a framework, HPO2Vec+, to enrich the produced HPO embeddings with heterogeneous knowledge resources (i.e., DECIPHER, OMIM, and Orphanet) for detecting phenotypic relevance. Specifically, we parsed disease-phenotype associations contained in these three resources to enrich non-inheritance relationships among phenotypic nodes in the HPO. To generate node embeddings for the HPO, node2vec was applied to perform node sampling on the enriched HPO graphs based on random walk followed by feature learning over the sampled nodes to generate enriched node embeddings. Four HPO embeddings were generated based on different graph structures, which we hereafter label as HPOEmb-Original, HPOEmb-DECIPHER, HPOEmb-OMIM, and HPOEmb-Orphanet. We evaluated the derived embeddings quantitatively through an HPO link prediction task with four edge embeddings operations and six machine learning algorithms. The resulting best embeddings were then evaluated for patient stratification of 10 rare diseases using electronic health records (EHR) collected at Mayo Clinic. We assessed our framework qualitatively by visualizing phenotypic clusters and conducting a use case study on primary hyperoxaluria (PH), a rare disease, on the task of inferring relevant phenotypes given 22 annotated PH related phenotypes. RESULTS: The quantitative link prediction task shows that HPOEmb-Orphanet achieved an optimal AUROC of 0.92 and an average precision of 0.94. In addition, HPOEmb-Orphanet achieved an optimal F1 score of 0.86. The quantitative patient similarity measurement task indicates that HPOEmb-Orphanet achieved the highest average detection rate for similar patients over 10 rare diseases and performed better than other similarity measures implemented by an existing tool, HPOSim, especially for pairwise patients with fewer shared common phenotypes. The qualitative evaluation shows that the enriched HPO embeddings are generally able to detect relationships among nodes with fine granularity and HPOEmb-Orphanet is particularly good at associating phenotypes across different disease systems. For the use case of detecting relevant phenotypic characterizations for given PH related phenotypes, HPOEmb-Orphanet outperformed the other three HPO embeddings by achieving the highest average P@5 of 0.81 and the highest P@10 of 0.79. Compared to seven conventional similarity measurements provided by HPOSim, HPOEmb-Orphanet is able to detect more relevant phenotypic pairs, especially for pairs not in inheritance relationships. CONCLUSION: We drew the following conclusions based on the evaluation results. First, with additional non-inheritance edges, enriched HPO embeddings can detect more associations between fine granularity phenotypic nodes regardless of their topological structures in the HPO graph. Second, HPOEmb-Orphanet not only can achieve the optimal performance through link prediction and patient stratification based on phenotypic similarity, but is also able to detect relevant phenotypes closer to domain expert's judgments than other embeddings and conventional similarity measurements. Third, incorporating heterogeneous knowledge resources do not necessarily result in better performance for detecting relevant phenotypes. From a clinical perspective, in our use case study, clinical-oriented knowledge resources (e.g., Orphanet) can achieve better performance in detecting relevant phenotypic characterizations compared to biomedical-oriented knowledge resources (e.g., DECIPHER and OMIM).