Using association rule mining and ontologies to generate metadata recommendations from multiple biomedical databases

Abstract

Metadata—the machine-readable descriptions of the data—are increasingly seen as crucial for describing the vast array of biomedical datasets that are currently being deposited in public repositories. While most public repositories have firm requirements that metadata must accompany submitted datasets, the quality of those metadata is generally very poor. A key problem is that the typical metadata acquisition process is onerous and time consuming, with little interactive guidance or assistance provided to users. Secondary problems include the lack of validation and sparse use of standardized terms or ontologies when authoring metadata. There is a pressing need for improvements to the metadata acquisition process that will help users to enter metadata quickly and accurately. In this paper, we outline a recommendation system for metadata that aims to address this challenge. Our approach uses association rule mining to uncover hidden associations among metadata values and to represent them in the form of association rules. These rules are then used to present users with real-time recommendations when authoring metadata. The novelties of our method are that it is able to combine analyses of metadata from multiple repositories when generating recommendations and can enhance those recommendations by aligning them with ontology terms. We implemented our approach as a service integrated into the CEDAR Workbench metadata authoring platform, and evaluated it using metadata from two public biomedical repositories: US-based National Center for Biotechnology Information BioSample and European Bioinformatics Institute BioSamples. The results show that our approach is able to use analyses of previously entered metadata coupled with ontology-based mappings to present users with accurate recommendations when authoring metadata.

Understanding the Nature of Metadata: Systematic Review

“…Detailed machine-readable and actionable descriptions to enable data processing without human guidance [ 10 , 25 ]…”

“…As an example, matching can be understood in various ways. Metadata matches to instance data [ 8 ] or to semantic attributes [ 9 ] or other metadata [ 10 ]. The general understanding is ambiguous.…”

An open-source framework for neuroscience metadata management applied to digital reconstructions of neuronal morphology

“…7 Final dataset with reconstructions and all experimental groups added in the metadata portal or smart recommendation systems to further expedite and improve the critical bottleneck of database curation. Recently, machine learning algorithms have been successfully deployed for metadata extraction [27]. In particular, text mining tools, such as named entity recognition, can learn, identify, and label crucial elements of neuroscience documents like neuron names, brain regions, and experimental conditions [5,37] .…”

Strategic vision for improving human health at The Forefront of Genomics

“…Effective and efficient management of increasingly complex genomic datasets requires addressing challenges with these emerging approaches as well as innovations in the use of hardware, algorithms, software, standards, and platforms 40 . Current barriers include the lack of interoperable genomic data resources (which limits downstream access, integration, and analyses) and the absence of controlled and consistently adopted data and metadata vocabularies and ontologies 41,42 . User-friendly systems that capture metadata in a scalable, intelligent, and cost-effective manner and that allow for intuitive data visualizations are essential.…”