Related Experiment Video
Updated: Feb 13, 2026
10:53
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
Published on: January 3, 2017
10.4K
A global network of biomedical relationships derived from text
Bethany Percha1,2, Russ B Altman3,4,5
1Biomedical Informatics Training Program, Stanford University, Stanford, CA, USA.
Bioinformatics (Oxford, England)
|March 1, 2018
Summary
This study extracts and categorizes biomedical interactions from millions of research articles. It creates a large network of labeled relationships between chemicals, genes, and diseases to aid research.
Area of Science:
- Biomedical Informatics
- Computational Biology
- Text Mining
Background:
- Biomedical knowledge, including chemical, gene, and phenotype interactions, is dispersed across millions of research articles.
- Understanding these interactions is crucial for deciphering complex biological mechanisms, such as drug efficacy and individual drug responses.
Purpose of the Study:
- To develop a scalable method for identifying and classifying relationship types between biomedical entities (chemicals, genes, diseases) described in natural language.
- To map unstructured text descriptions of interactions onto structured, semantically-defined categories or 'themes'.
Main Methods:
- Utilized NCBI's PubTator annotations to identify biomedical entities in Medline abstracts.
- Employed the Stanford dependency parser to extract dependency paths connecting entity pairs within sentences.
- Applied an ensemble biclustering algorithm (EBC) combined with hierarchical clustering to group dependency paths into semantically coherent themes.
- Validated theme assignments against six established human-curated biomedical databases (DrugBank, Reactome, SIDER, TTD, OMIM, PharmGKB).
Main Results:
- Identified numerous themes for chemical-gene, chemical-disease, gene-disease, and gene-gene relationships.
- Thematic enrichments largely corresponded to known relationships in curated databases.
- Constructed a comprehensive network with millions of thematically-labeled interaction edges derived from single sentences in the literature.
Conclusions:
- Developed a novel computational approach to systematically categorize biomedical interactions from unstructured text.
- The generated network provides a valuable, large-scale resource for exploring and understanding complex biomedical relationships.
- The findings facilitate more efficient curation and discovery of knowledge within the biomedical research community.
Related Concept Videos
01:50Global Climate Change
29.1K
Throughout its ~4.5 billion year history, the Earth has experienced periods of warming and cooling. However, the current drastic increase in global temperatures is well outside of the Earth’s cyclic norms, and evidence for human-caused global climate change is compelling. Paleoclimatology, the study of ancient climate conditions, provides ample evidence for human-caused global climate change by comparing recent conditions with those in the past.
29.1K
02:12Relationship Formation
46.3K
What do you think is the single most influential factor in determining with whom you become friends and whom you form romantic relationships? You might be surprised to learn that the answer is simple: the people with whom you have the most contact. This most important factor is proximity. You are more likely to be friends with people you have regular contact with. For example, there are decades of research that shows that you are more likely to become friends with people who live in your dorm,...
46.3K
02:26Protein Networks
4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
01:28Ending Relationships
205
The dissolution of intimate relationships presents complex emotional and psychological challenges, particularly when emotional bonds are strong, the relationship is long-standing, and perceived alternatives are limited. This distress often intensifies in romantic breakups, where the initiator may experience greater turmoil than the rejected partner. Contributing factors include residual attachment, guilt over causing pain, and uncertainty about how to manage the situation. The stress is further...
205
02:18Network Covalent Solids
16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
01:14Pharmacokinetic–Pharmacodynamic Relationship: Duration of Dose-Effect Relationship
9
For drugs producing a quantal response, onset occurs when plasma concentration reaches a minimum effective level (Cmin). The drug's action duration depends on how long the plasma concentration remains above Cmin.Two primary factors influence this duration: dose size and the rate of drug removal from the action site. Both depend on the drug's redistribution to poorly perfused tissues and elimination processes. A larger dose promotes rapid onset and prolongs the effect's duration.Consider a...
9