Scientists in disciplines such as neuroscience and bioinformatics are increasingly relying on science gateways for experimentation on voluminous data, as well as analysis and visualization in multiple perspectives. Though current science gateways provide easy access to computing resources, data sets and tools specific to the disciplines, scientists often use slow and tedious manual efforts to perform knowledge discovery to accomplish their research/education tasks. Recommender systems can provide expert guidance and can help them to navigate and discover relevant publications, tools, data sets, or even automate cloud resource configurations suitable for a given scientific task.To realize the potential of integration of recommenders in science gateways in order to spur research productivity, we present a novel "OnTimeRecommend" recommender system. The OnTimeRecommend comprises of several integrated recommender modules implemented as microservices that can be augmented to a science gateway in the form of a recommender-as-a-service. The guidance for use of the recommender modules in a science gateway is aided by a chatbot plug-in viz., Vidura Advisor. To validate our OnTimeRecommend, we integrate and show benefits for both novice and expert users in domain-specific knowledge discovery within two exemplar science gateways, one in neuroscience (CyNeuro) and the other in bioinformatics (KBCommons). K E Y W O R D Schatbot-guided user interface, knowledge discovery, microservices, recommender system, science gateway INTRODUCTIONRecent science and engineering research tasks are increasingly becoming data-intensive and thus relying on workflows to automate integration and analysis of voluminous data to test hypotheses. For example, research and training in neural science and engineering increasingly deal with diverse and voluminous multiparameter data, 1 posing unique challenges outlined in an NSF iNeuro report 2 as limited access to: multisomics data archives, 3 heterogeneous software 4 and computing resources (Neuroscience Gateway, 5 Amazon Web Services [AWS]), and multisite interdisciplinary expertise (e.g., engineering, biology and psychology). Existing distributed high-performance computing resources (HPC) and other cyberinfrastructure (CI) tools for data management support the related data analysis and visualization capabilities. However, to fully utilize such capabilities, neuroscientists (often with limited CI skills) are required to take valuable time away from the focus of knowledge discovery in neuroscience, in order to learn about how to use the various technologies.

No abstract

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI-COLUMBIA AT REQUEST OF AUTHOR.] Science gateways are web-portals that hide background complexities of underlying resources and expose easy-to-use capabilities of scientific applications to users in research and education.There is a growing need for next generation science gateways to keep up with advances in scientific tools, data sets and domain-specific user interface requirements. Specifically, the existing science gateways that can process pre-defined workflows and interface with a fixed cloud resource infrastructures need to be transformed to support: (a) extensible properties such as e.g., ability to easily integrate plug-ins (e.g. recommender systems, execution pipelines involving AI/ML/NLP algorithms), and (b) scalable infrastructures (e.g., ability to easily federated local and multi-cloud resources). In this MS Thesis, we address this extensibility and scalability problems in next-generation science gateways by proposing a "bring-your-own" plug-in management approach featuring web services and software design patterns borrowed from leading science gateways. We motivate the requirements for bring-your-own plug-ins management through a study of two exemplar science gateway use cases viz., "Mizzou Cyber Range" and "OnTimeRecommend Adviser". The Mizzou Cyber Range educational science gateway provides a safe and scalable playground to train next generation cyber security professionals to handle cyber-attacks using cloud-adoption within enterprise applications. The OnTimeRecommend Adviser features a variety of recommender modules to help novice/expert users with knowledge discovery through data sources such as e.g., publications, funding records, cloud templates and Jupyter notebooks. Based on the requirements, we create a general plug-in management approach that features application programming interfaces for creation of end-to-end application pipelines with diverse infrastructure, monitoring and user interface functions. In addition, we demonstrate a novel concept of micro service chaining that allows for seamless customization/integration of heterogeneous tools that are critical for knowledge discovery in research and education. Through usability testing, we show how our "bring-your-own" plug-in management approach improves the extensibility/scalability, and ultimately the sustainability of science gateways in data-intensive science as well as cyber security domain applications.