.png){kind=icon}
Return
Target discovery from data mining approaches
.png){kind=icon}
PRE
AI
DOI：10.1016/j.drudis.2008.12.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Data mining of available biomedical data and information has greatly boosted target discovery in the 'omics' era. Target discovery is the key step in the biomarker and drug discovery pipeline to diagnose and fight human diseases. In biomedical science, the 'target' is a broad concept ranging from molecular entities (such as genes, proteins and miRNAs) to biological phenomena (such as molecular functions, pathways and phenotypes). Within the context of biomedical science, data mining refers to a bioinformatics approach that combines biological concepts with computer tools or statistical methods that are mainly used to discover, select and prioritize targets. In response to the huge demand of data mining for target discovery in the 'omics' era, this review explicates various data mining approaches and their applications to target discovery with emphasis on text and microarray data analysis. Two emerging data mining approaches, chemogenomic data mining and proteomic data mining, are briefly introduced. Also discussed are the limitations of various data mining approaches found in the level of database integration, the quality of data annotation, sample heterogeneity and the performance of analytical and mining tools. Tentative strategies of integrating different data sources for target discovery, such as integrated text mining with high-throughput data analysis and integrated mining with pathway databases, are introduced.
Keywords:
DRUG DISCOVERY
MICROARRAY DATA
CANCER BIOMARKERS
PROTEOMIC DATA
TEXT
BIOINFORMATICS
NETWORK
INFORMATION
BIOLOGY
MARKERS
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.5
Papers:
6.4K
Citations:
2.3W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more