Poster: Analysis of gene ranking algorithms with extraction of relevant biomedical concepts from PubMed publications

Author

Kocbek, Simon ; Setre, R. ; Stiglic, Gregor ; Kim, Jin-Dong ; Pernek, Igor ; Tsuruoka, Yoshimasa ; Kokol, Peter ; Ananiadou, Sophia ; Tsujii, Jun Ichi

Author_Institution

Fac. of Health Sci., Univ. of Maribor, Maribor, Slovenia

fYear

2011

fDate

3-5 Feb. 2011

Firstpage

249

Lastpage

249

Abstract

AGRA (Analysis of Gene Ranking Algorithms) was proposed, a novel method where biologists and other experts with low or no previous computer knowledge can compare different FS methods with help of evidence mined from PubMed publications. To achieve this, AGRA uses the FACTA + system which is an online text search engine for MEDLINE abstracts and it helps users browse biomedical concepts (e.g. genes/proteins, diseases, symptoms, drugs, enzymes and chemical compounds) which co-occur in the documents retrieved by a search query. The system was tested with seven different gene ranking algorithms. The AGRA method was compared to overlaps calculated from feature selection based rankings.

Keywords

genetics; genomics; medical computing; query formulation; AGRA; FACTA; MEDLINE abstracts; PubMed; analysis of gene ranking algorithms; biomedical concepts; feature selection; gene ranking algorithms; search query; Algorithm design and analysis; Bioinformatics; Biomedical measurements; Computers; Diseases; Search engines; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Advances in Bio and Medical Sciences (ICCABS), 2011 IEEE 1st International Conference on

Conference_Location

Orlando, FL

Print_ISBN

978-1-61284-851-8

Type

conf

DOI

10.1109/ICCABS.2011.5729902

Filename

5729902