An official website of the United States government
Abstract Effective research, education, and outreach efforts by theArabidopsis thalianacommunity, as well as other scientific communities that depend on Arabidopsis resources, depend vitally on easily available and publicly‐shared resources. These resources include reference genome sequence data and an ever‐increasing number of diverse data sets and data types.TAIR(The Arabidopsis Information Resource) and Araport (originally named the Arabidopsis Information Portal) are community informatics resources that provide tools, data, and applications to the more than 30,000 researchers worldwide that use in their work either Arabidopsis as a primary system of study or data derived from Arabidopsis. Four years after Araport's establishment, theIAICheld another workshop to evaluate the current status of Arabidopsis Informatics and chart a course for future research and development. The workshop focused on several challenges, including the need for reliable and current annotation, community‐defined common standards for data and metadata, and accessible and user‐friendly repositories/tools/methods for data integration and visualization. Solutions envisioned included (a) a centralized annotation authority to coalesce annotation from new groups, establish a consistent naming scheme, distribute this format regularly and frequently, and encourage and enforce its adoption. (b) Standards for data and metadata formats, which are essential, but challenging when comparing across diverse genotypes and in areas with less‐established standards (e.g., phenomics, metabolomics). Community‐established guidelines need to be developed. (c) A searchable, central repository for analysis and visualization tools. Improved versioning and user access would make tools more accessible. Workshop participants proposed a “one‐stop shop” website, an Arabidopsis “Super‐Portal” to link tools, data resources, programmatic standards, and best practice descriptions for each data type. This must have community buy‐in and participation in its establishment and development to encourage adoption.
more »
« less
PaleoRec: A sequential recommender system for the annotation of paleoclimate datasets
Abstract Studying past climate variability is fundamental to our understanding of current changes. In the era of Big Data, the value of paleoclimate information critically depends on our ability to analyze large volume of data, which itself hinges on standardization. Standardization also ensures that these datasets are more Findable, Accessible, Interoperable, and Reusable. Building upon efforts from the paleoclimate community to standardize the format, terminology, and reporting of paleoclimate data, this article describes PaleoRec, a recommender system for the annotation of such datasets. The goal is to assist scientists in the annotation task by reducing and ranking relevant entries in a drop-down menu. Scientists can either choose the best option for their metadata or enter the appropriate information manually. PaleoRec aims to reduce the time to science while ensuring adherence to community standards. PaleoRec is a type of sequential recommender system based on a recurrent neural network that takes into consideration the short-term interest of a user in a particular dataset. The model was developed using 1996 expert-annotated datasets, resulting in 6,512 sequences. The performance of the algorithm, as measured by the Hit Ratio, varies between 0.7 and 1.0. PaleoRec is currently deployed on a web interface used for the annotation of paleoclimate datasets using emerging community standards.
more »
« less
- PAR ID:
- 10337364
- Date Published:
- Journal Name:
- Environmental Data Science
- Volume:
- 1
- ISSN:
- 2634-4602
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)SARS-CoV-2 RNA detection in wastewater is being rapidly developed and adopted as a public health monitoring tool worldwide. With wastewater surveillance programs being implemented across many different scales and by many different stakeholders, it is critical that data collected and shared are accompanied by an appropriate minimal amount of meta-information to enable meaningful interpretation and use of this new information source and intercomparison across datasets. While some databases are being developed for specific surveillance programs locally, regionally, nationally, and internationally, common globally-adopted data standards have not yet been established within the research community. Establishing such standards will require national and international consensus on what meta-information should accompany SARS-CoV-2 wastewater measurements. To establish a recommendation on minimum information to accompany reporting of SARS-CoV-2 occurrence in wastewater for the research community, the United States National Science Foundation (NSF) Research Coordination Network on Wastewater Surveillance for SARS-CoV-2 hosted a workshop in February 2021 with participants from academia, government agencies, private companies, wastewater utilities, public health laboratories, and research institutes. This report presents the primary two outcomes of the workshop: (i) a recommendation on the set of minimum meta-information that is needed to confidently interpret wastewater SARS-CoV-2 data, and (ii) insights from workshop discussions on how to improve standardization of data reporting.more » « less
-
Recommender-as-a-Service with Chatbot Guided Domain-science Knowledge Discovery in a Science GatewayScientists 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, datasets 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).more » « less
-
While other areas of machine learning have seen more and more automation, designing a high-performing recommender system still requires a high level of human effort. Furthermore, recent work has shown that modern recommender system algorithms do not always improve over well-tuned baselines. A natural follow-up question is, "how do we choose the right algorithm for a new dataset and performance metric?" In this work, we start by giving the first large-scale study of recommender system approaches by comparing 24 algorithms and 100 sets of hyperparameters across 85 datasets and 315 metrics. We find that the best algorithms and hyperparameters are highly dependent on the dataset and performance metric. However, there is also a strong correlation between the performance of each algorithm and various meta-features of the datasets. Motivated by these findings, we create RecZilla, a meta-learning approach to recommender systems that uses a model to predict the best algorithm and hyperparameters for new, unseen datasets. By using far more meta-training data than prior work, RecZilla is able to substantially reduce the level of human involvement when faced with a new recommender system application. We not only release our code and pretrained RecZilla models, but also all of our raw experimental results, so that practitioners can train a RecZilla model for their desired performance metric: https://github.com/naszilla/reczilla.more » « less
-
Abstract The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other institutional video to reduce annotation effort, and enable automated tracking of underwater concepts when integrated with robotic vehicles. As FathomNet continues to grow and incorporate more labeled data from the community, we can accelerate the processing of visual data to achieve a healthy and sustainable global ocean.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1017/eds.2022.3
