LitSuggest: a web-based system for literature recommendation and curation using machine learning

Abstract

Searching and reading relevant literature is a routine practice in biomedical research. However, it is challenging for a user to design optimal search queries using all the keywords related to a given topic. As such, existing search systems such as PubMed often return suboptimal results. Several computational methods have been proposed as an effective alternative to keyword-based query methods for literature recommendation. However, those methods require specialized knowledge in machine learning and natural language processing, which can make them difficult for biologists to utilize. In this paper, we propose LitSuggest, a web server that provides an all-in-one literature recommendation and curation service to help biomedical researchers stay up to date with scientific literature. LitSuggest combines advanced machine learning techniques for suggesting relevant PubMed articles with high accuracy. In addition to innovative text-processing methods, LitSuggest offers multiple advantages over existing tools. First, LitSuggest allows users to curate, organize, and download classification results in a single interface. Second, users can easily fine-tune LitSuggest results by updating the training corpus. Third, results can be readily shared, enabling collaborative analysis and curation of scientific literature. Finally, LitSuggest provides an automated personalized weekly digest of newly published articles for each user's project. LitSuggest is publicly available at https://www.ncbi.nlm.nih.gov/research/litsuggest.

Graphical Abstract

LitSuggest suggests relevant PubMed articles with high accuracy, offers visualization and curation features, in addition to the possibility to download and share classification results.

Figure 1.

Overview of LitSuggest. LitSuggest trains ensemble learning models based on a set of example articles from users (1). The model is then used to rank and classify new publications (2). Classified publications can then be curated (3) and shared with other users. The curation interface displays the probability score (a) for each publication, publication content (b) such as title, abstract, type, keywords, journal, date, authors, links to external resources, and interface to annotate the publication with custom tags (c), a custom text note (d) and the date and user which made the latest changes (e).

Figure 2.

LitSuggest architecture.