Search for: All records

IntroductionEffective monitoring of insect-pests is vital for safeguarding agricultural yields and ensuring food security. Recent advances in computer vision and machine learning have opened up significant possibilities of automated persistent monitoring of insect-pests through reliable detection and counting of insects in setups such as yellow sticky traps. However, this task is fraught with complexities, encompassing challenges such as, laborious dataset annotation, recognizing small insect-pests in low-resolution or distant images, and the intricate variations across insect-pests life stages and species classes. MethodsTo tackle these obstacles, this work investigates combining two solutions, Hierarchical Transfer Learning (HTL) and Slicing-Aided Hyper Inference (SAHI), along with applying a detection model. HTL pioneers a multi-step knowledge transfer paradigm, harnessing intermediary in-domain datasets to facilitate model adaptation. Moreover, slicing-aided hyper inference subdivides images into overlapping patches, conducting independent object detection on each patch before merging outcomes for precise, comprehensive results. ResultsThe outcomes underscore the substantial improvement achievable in detection results by integrating a diverse and expansive in-domain dataset within the HTL method, complemented by the utilization of SAHI. DiscussionWe also present a hardware and software infrastructure for deploying such models for real-life applications. Our results can assist researchers and practitioners looking for solutions for insect-pest detection and quantification on yellow sticky traps. 

Abstract Molecular Dynamics (MD) simulation of biomolecules provides important insights into conformational changes and dynamic behavior, revealing critical information about folding and interactions with other molecules. The collection of simulations stored in computers across the world holds immense potential to serve as training data for future Machine Learning models that will transform the prediction of structure, dynamics, drug interactions, and more. Ideally, there should exist an open access repository that enables scientists to submit and store their MD simulations of proteins and protein-drug interactions, and to find, retrieve, analyze, and visualize simulations produced by others. However, despite the ubiquity of MD simulation in structural biology, no such repository exists; as a result, simulations are instead stored in scattered locations without uniform metadata or access protocols. Here, we introduce MDRepo, a robust infrastructure that provides a relatively simple process for standardized community contribution of simulations, activates common downstream analyses on stored data, and enables search, retrieval, and visualization of contributed data. MDRepo is built on top of the open-source CyVerse research cyber-infrastructure, and is capable of storing petabytes of simulations, while providing high bandwidth upload and download capabilities and laying a foundation for cloud-based access to its stored data. 

BackgroundMolecular Dynamics (MD) simulation of biomolecules provides important insights into conformational changes and dynamic behavior, revealing critical information about folding and interactions with other molecules. This enables advances in drug discovery and the design of therapeutic interventions. The collection of simulations stored in computers across the world holds immense potential to serve as training data for future Machine Learning models that will transform the prediction of structure, dynamics, drug interactions, and more. A needIdeally, there should exist an open access repository that enables scientists to submit and store their MD simulations of proteins and protein-drug interactions, and to find, retrieve, analyze, and visualize simulations produced by others. However, despite the ubiquity of MD simulation in structural biology, no such repository exists; as a result, simulations are instead stored in scattered locations without uniform metadata or access protocols. A solutionHere, we introduce MDRepo, a robust infrastructure that supports a relatively simple process for standardized community contribution of simulations, activates common downstream analyses on stored data, and enables search, retrieval, and visualization of contributed data. MDRepo is built on top of the open-source CyVerse research cyberinfrastructure, and is capable of storing petabytes of simulations, while providing high bandwidth upload and download capabilities and laying a foundation for cloud-based access to its stored data. 

Modern science depends on computers, but not all scientists have access to the scale of computation they need. A digital divide separates scientists who accelerate their science using large cyberinfrastructure from those who do not, or who do not have access to the compute resources or learning opportunities to develop the skills needed. The exclusionary nature of the digital divide threatens equity and the future of innovation by leaving people out of the scientific process while over-amplifying the voices of a small group who have resources. However, there are potential solutions: recent advancements in public research cyberinfrastructure and resources developed during the open science revolution are providing tools that can help bridge this divide. These tools can enable access to fast and powerful computation with modest internet connections and personal computers. Here we contribute another resource for narrowing the digital divide: scalable virtual machines running on public cloud infrastructure. We describe the tools, infrastructure, and methods that enabled successful deployment of a reproducible and scalable cyberinfrastructure architecture for a collaborative data synthesis working group in February 2023. This platform enabled 45 scientists with varying data and compute skills to leverage 40,000 hours of compute time over a 4-day workshop. Our approach provides an open framework that can be replicated for educational and collaborative data synthesis experiences in any data- and compute-intensive discipline. 

Jetstream2 will be a category I production cloud resource that is part of the National Science Foundation’s Innovative HPC Program. The project’s aim is to accelerate science and engineering by providing “on-demand” programmable infrastructure built around a core system at Indiana University and four regional sites. Jetstream2 is an evolution of the Jetstream platform, which functions primarily as an Infrastructure-as-a-Service cloud. The lessons learned in cloud architecture, distributed storage, and container orchestration have inspired changes in both hardware and software for Jetstream2. These lessons have wide implications as institutions converge HPC and cloud technology while building on prior work when deploying their own cloud environments. Jetstream2’s next-generation hardware, robust open-source software, and enhanced virtualization will provide a significant platform to further cloud adoption within the US research and education communities.