Linked Discoveries™ is an experimental pilot resource developed by the National Library of Medicine (NLM) that helps users explore how articles with PubMed® abstracts connect to the surrounding literature. Linked Discoveries creates neighborhoods of related articles, highlights shared conditions, genes, and chemicals across the neighborhood, and surfaces context like NIH funding, citation relationships, retractions, and reviews.
The information displayed and available in Linked Discoveries comes from PubMed, including abstracts and reference data, along with related condition, gene, and chemical data linked from other NLM databases like Gene, MedGen, and PubChem®.
How does Linked Discoveries relate to PubMed’s Similar Articles?
Both Linked Discoveries and PubMed Similar Articles identify neighborhoods of related articles, but each is built for a different kind of task and does this in different ways.
PubMed Similar Articles generates a ranked list of related articles that can be combined with other PubMed searches for further refinement. For more information, refer to the Similar Articles section of the PubMed User Guide.
Linked Discoveries is a dynamic, interactive tool that lets users explore the research neighborhood itself to surface shared topics such as conditions, genes, and chemicals, along with contextual signals like citation relationships, retractions, and reviews. It uses an AI-informed approach to build neighborhoods of related articles. For more information, refer to the Linked Discoveries User Guide.
How can I access Linked Discoveries?
When looking at an abstract page in PubMed, you may see a “Linked Discoveries” button along the right-hand column on larger screens or below the title on smaller screens. Please note that this button is only available on abstract pages for articles that represent original research, reviews, and related evidence.
To explore a “neighborhood” of related articles for the PubMed record of interest (the “seed” article), click the Linked Discoveries button. A new browser tab will open and in Linked Discoveries, you will be able to:
- View your article of interest (the “seed”). Your seed article appears as the light blue node labeled “Seed” in the top left corner of the visualization. In the timeline view, a dotted blue line marks the publication year of the seed article.
- View related articles (the “neighborhood”). Each article in the neighborhood is represented by a node labeled with the first author and year of publication. The node color indicates the article type. See the key at the bottom of the visualization to identify article types.
- Filter the neighborhood by shared topics. Filter by condition, gene, or chemical to narrow the neighborhood to articles sharing those topics. You can select one or more topics to filter on and choose whether the neighborhood is narrowed to records tagged with any of the selected topics, or all the selected topics.
- View details for a selected node. By default, details for the seed article are shown in the article information card to the right of the graph or timeline. Click a different node to view its details instead. Filter the graph or timeline by clicking on the name of a specific condition, gene, or chemical on the information card. Click “View in table” to view the neighborhood in a structured table format.
- Build a new neighborhood from one of the nodes. Click “Set as seed article” to generate a new neighborhood from any of the nodes in the current visualization.
Your feedback will help guide our next steps!
Linked Discoveries is an experimental pilot resource still under active refinement, with ongoing exploration of new features and capabilities planned for future releases. We invite you to try Linked Discoveries, explore a topic of interest to you, and share your thoughts using the Feedback button on any Linked Discovery page. Your feedback will help us shape where this pilot goes next!
How can I learn more?
Consult the Linked Discoveries User Guide which provides helpful information as well as some tips on using the resource.
[Editor’s note: NCBI Insights published a more detailed blog post.]