Related Experiment Video
Updated: Jul 14, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
Gene ontology annotation by density and gravitation models
Wen-Juan Hou1, Kevin Hsin-Yih Lin, Hsin-Hsi Chen
1Department of Computer Science and Information Engineering, National Taiwan University, No.1, Sec.4, Roosevelt Road, Taipei, Taiwan 106. wjhou@nlg.csie.ntu.edu.tw
Automating gene ontology (GO) annotation is crucial. This study introduces a novel approach using biomedical documents to identify relevant papers for curators, improving the efficiency of gene annotation.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- The Gene Ontology (GO) provides standardized vocabularies for gene product annotation across databases.
- Manual GO annotation of genes from lengthy biomedical literature is time-consuming and labor-intensive.
- Efficient and automated methods for GO annotation are essential for biological research.
Purpose of the Study:
- To develop and evaluate a novel approach for GO annotation that utilizes full-text biomedical documents.
- To improve the efficiency of directing relevant papers to human curators for GO annotation.
- To explore computational methods for enhancing the accuracy and speed of gene-to-GO term assignment.
Main Methods:
- A GO annotation system was developed that analyzes full-text biomedical documents.
- The system explores word density and gravitation relationships between genes and GO terms.
- Multiple density and gravitation models were constructed and evaluated.
Main Results:
- The proposed approach effectively directs curators to more relevant papers for GO annotation.
- Analysis of word density and gravitation relationships aids in identifying gene-GO term associations.
- Evaluation using various criteria demonstrates the efficacy of the developed models.
Conclusions:
- The developed GO annotation approach offers a promising method for accelerating the annotation process.
- Utilizing full-text documents and exploring word relationships can significantly aid curators.
- This work contributes to more efficient and potentially automated gene ontology annotation.
Related Concept Videos
Genome Annotation and Assembly
Density
Protein Networks
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,...
Protein Networks
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,...
Molecular Models
Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...