Related Experiment Video
Updated: Jun 26, 2026
07:41
Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
SciMiner: web-based literature mining tool for target identification and functional enrichment analysis
Junguk Hur1, Adam D Schuyler, David J States
1Bioinformatics Program, University of Michigan, Ann Arbor, MI 48109, USA. juhur@umich.edu
Bioinformatics (Oxford, England)
|February 4, 2009
Summary
SciMiner is a tool for identifying genes and proteins from scientific literature. It uses context-specific analysis and functional enrichment to efficiently retrieve and summarize biological information.
Area of Science:
- Bioinformatics
- Computational Biology
- Literature Mining
Background:
- SciMiner is a web-based tool for literature mining and functional analysis.
- It processes MEDLINE abstracts and full texts for gene and protein identification.
- A server version is available for download, allowing institutional journal subscription access.
Purpose of the Study:
- To develop and evaluate SciMiner, a tool for identifying genes and proteins from biomedical literature.
- To provide functional enrichment analyses for retrieved targets, including Gene Ontology (GO) terms, Medical Subject Headings (MeSH) terms, pathways, and protein-protein interaction networks.
- To offer an efficient platform for retrieving and summarizing biological information from user-defined corpora.
Main Methods:
- SciMiner accepts free text queries (PubMed Entrez search) or PubMed identifiers.
- It employs regular expression patterns and curated dictionaries of gene symbols and names.
- Ambiguous acronyms are resolved using a scoring scheme based on co-occurrence with description terms and optional user-defined filters.
- Functional enrichment analyses compare identified targets against other searches or the complete HGNC gene set.
Main Results:
- SciMiner achieved 87.1% recall, 71.3% precision, and 75.8% F-measure in gene/protein name identification, evaluated against the BioCreAtIvE v2 Gene Normalization Task.
- The tool successfully identifies genes, proteins, GO terms, MeSH terms, pathways, and protein-protein interaction networks.
- Demonstrates efficient retrieval and summarization of biological information.
Conclusions:
- SciMiner provides an efficient platform for literature mining and functional analysis.
- Its context-specific analysis and functional enrichment capabilities aid in identifying relevant biological targets.
- The tool facilitates the retrieval and summarization of rich biological information from scientific literature.
