Abstract
The recent movement towards open data in the biomedical domain has generated a large number of datasets that are publicly accessible. The Big Data to Knowledge data indexing project, biomedical and healthCAre Data Discovery Index Ecosystem (bioCADDIE), has gathered these datasets in a one-stop portal aiming at facilitating their reuse for accelerating scientific advances. However, as the number of biomedical datasets stored and indexed increases, it becomes more and more challenging to retrieve the relevant datasets according to researchers’ queries. In this article, we propose an information retrieval (IR) system to tackle this problem and implement it for the bioCADDIE Dataset Retrieval Challenge. The system leverages the unstructured texts of each dataset including the title and description for the dataset, and utilizes a state-of-the-art IR model, medical named entity extraction techniques, query expansion with deep learning-based word embeddings and a re-ranking strategy to enhance the retrieval performance. In empirical experiments, we compared the proposed system with 11 baseline systems using the bioCADDIE Dataset Retrieval Challenge datasets. The experimental results show that the proposed system outperforms other systems in terms of inference Average Precision and inference normalized Discounted Cumulative Gain, implying that the proposed system is a viable option for biomedical dataset retrieval. Database URL: https://github.com/yanshanwang/biocaddie2016mayodata
Highlights
The recent movement towards open data in the biomedical domain has generated a large number of datasets that are publicly accessible [1,2,3]
We describe an information retrieval (IR) system for the bioCADDIE Dataset Retrieval Challenge and focus on using the unstructured textual data, ‘title’ and ‘description.’ The system utilizes a state-of-the-art IR model, medical named entity extraction techniques, query expansion with deep learning-based word embeddings and a re-ranking strategy to enhance the retrieval performance
We investigated the regulation of the size of Interleukin-2-producing CD4þ T-cell (IL-2p) pool using different IL-2-reporter mice
Summary
The recent movement towards open data in the biomedical domain has generated a large number of datasets that are publicly accessible [1,2,3]. It makes research transparent and reproducible, and allows for more collaborative and rapid progress and enables the development of new questions by revealing previously hidden patterns and connections across datasets [4]. As bioCADDIE has ingested and indexed >840 000 datasets from 23 different repositories across 10 different data types [8], it becomes more and more challenging to retrieve the datasets that meet the needs of the biomedical researchers
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have