A novel ontology-based biomedical search engine

When people search, they have questions in mind. GoPubMed allows to significantly faster find information needed through the use of background knowledge. GoPubMed:
  • retrieves PubMed abstracts for your search query,
  • detects terms from the Gene Ontology (GO) and Medical Subject Headings (MeSH) in the abstracts,
  • displays the subset of the GO and MeSH relevant to the keywords, and
  • allows you to browse the ontologies and display only papers containing specific GO and MeSH terms.

After performing a search, the resulting abstracts are annotated with your query keywords and GO and MeSH terms. The abstracts are grouped using the GO and MeSH terms, which appear in the text. Now the GO and MeSH hierarchies can be used to systematically explore the search results.

Note that only a subset of all GO and MeSH terms may be relevant to your query. This subset – more frequent terms - is presented on the left hand side. Sorting documents to a highly organised network facilitates the finding of relevant documents significantly.

The hierarchy of content shows the whole GO and MeSH ontologies. GO and MeSH serve as table of contents in order to structure the over 16 million articles of the MEDLINE data base.

About Gene Ontology (GO)
The GO provides a controlled vocabulary to describe gene and gene products in different organisms. GO is a knowledge network containing about 20.000 biological terms. It is built up as a directed acyclic graph starting from three basic areas namely

  • the molecular function of gene products,
  • their role in multi-step biological processes, and
  • their localization to cellular components.

GO terms are classified into only one of the three branches of the ontology. Although the ontology is presented as a tree, it is a network with cross links. So it is possible to navigate to a term of interest on different paths. Hence, a term of interest can be reached from quite different points of view.

About the Medical Subject Headings (MeSH)
MeSH is the controlled vocabulary thesaurus from National Library of Medicine's. It consists of sets of terms in a hierarchical structure that permits searching at various levels of specificity. At the most general level of the hierarchy are very broad headings such as "Anatomy" or "Diseases". More specific headings are found at more narrow levels.

There are more than 110,000 MeSH concepts in GoPubMed. There are also thousands of cross-references that assist in finding the most appropriate MeSH concept. So it is possible to navigate to a term of interest on different paths. Hence, a term of interest can be reached from quite different points of view. From the eleven levels of the MeSH hierarchy, GoPubMed uses the parts:

  • Anatomy,
  • Biological Sciences,
  • Chemicals and Drugs,
  • Diseases,
  • Health Care,
  • Natural Sciences,
  • Organisms,
  • Psychiatry and Psychology,
  • Techniques and Equipment, and
  • Technology, Industry, Agriculture

For further information, please visit:
http://www.gopubmed.com/

Most Popular Now

Stanford Medicine Study Suggests Physici…

Artificial intelligence-powered chatbots are getting pretty good at diagnosing some diseases, even when they are complex. But how do chatbots do when guiding treatment and care after the diagnosis? For...

OmicsFootPrint: Mayo Clinic's AI To…

Mayo Clinic researchers have pioneered an artificial intelligence (AI) tool, called OmicsFootPrint, that helps convert vast amounts of complex biological data into two-dimensional circular images. The details of the tool...

Testing AI with AI: Ensuring Effective A…

Using a pioneering artificial intelligence platform, Flinders University researchers have assessed whether a cardiac AI tool recently trialled in South Australian hospitals actually has the potential to assist doctors and...

Adults don't Trust Health Care to U…

A study finds that 65.8% of adults surveyed had low trust in their health care system to use artificial intelligence responsibly and 57.7% had low trust in their health care...

AI Unlocks Genetic Clues to Personalize …

A groundbreaking study led by USC Assistant Professor of Computer Science Ruishan Liu has uncovered how specific genetic mutations influence cancer treatment outcomes - insights that could help doctors tailor...

The 10 Year Health Plan: What do We Need…

Opinion Article by Piyush Mahapatra, Consultant Orthopaedic Surgeon and Chief Innovation Officer at Open Medical. There is a new ten-year plan for the NHS. It will "focus efforts on preventing, as...

Deep Learning to Increase Accessibility…

Coronary artery disease is the leading cause of death globally. One of the most common tools used to diagnose and monitor heart disease, myocardial perfusion imaging (MPI) by single photon...

People's Trust in AI Systems to Mak…

Psychologists warn that AI's perceived lack of human experience and genuine understanding may limit its acceptance to make higher-stakes moral decisions. Artificial moral advisors (AMAs) are systems based on artificial...

DMEA 2025 - Innovations, Insights and Ne…

8 - 10 April 2025, Berlin, Germany. Less than 50 days to go before DMEA 2025 opens its doors: Europe's leading event for digital health will once again bring together experts...

Relationship Between Sleep and Nutrition…

Diet and sleep, which are essential for human survival, are interrelated. However, recently, various services and mobile applications have been introduced for the self-management of health, allowing users to record...

New AI Tool Mimics Radiologist Gaze to R…

Artificial intelligence (AI) can scan a chest X-ray and diagnose if an abnormality is fluid in the lungs, an enlarged heart or cancer. But being right is not enough, said...

AI Model can Read ECGs to Identify Femal…

A new AI model can flag female patients who are at higher risk of heart disease based on an electrocardiogram (ECG). The researchers say the algorithm, designed specifically for female patients...