Abstract | ||
---|---|---|
The ability of stem cells holds great potential for drug discovery and cell replacement therapy. To realize this potential, effective high content screening for drug candidates is required. Analysis of images from high content screening typically requires DNA staining to identify cell nuclei to do cell segmentation before feature extraction and classification. However, DNA staining has negative effects on cell growth, and segmentation algorithms err when compound treatments cause nuclear or cell swelling/shrinkage. In this paper, we introduced a novel Information Distance Classification (IDC) method, requiring no segmentation or feature extraction; hence no DNA staining is needed. In classifying 480 candidate compounds that may be used to stimulate stem cell differentiation, the proposed IDC method was demonstrated to achieve a 3% higher F1 score than conventional analysis. As far as we know, this is the first work to apply information distance in high content screening. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33460-3_23 | ECML/PKDD (1) |
Keywords | Field | DocType |
classifying stem cell differentiation,information distance,stem cell,feature extraction,cell segmentation,cell nucleus,high content screening,dna staining,stem cell differentiation,cell replacement therapy,cell growth,effective high content screening | F1 score,Stem cell,Pattern recognition,Segmentation,Computer science,Information distance,Cell growth,Feature extraction,Cellular differentiation,Artificial intelligence,High-content screening,Bioinformatics | Conference |
Citations | PageRank | References |
0 | 0.34 | 18 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xianglilan Zhang | 1 | 3 | 1.74 |
Hong-nan Wang | 2 | 9 | 2.05 |
Tony J. Collins | 3 | 0 | 0.68 |
Zhigang Luo | 4 | 828 | 47.92 |
Ming Li | 5 | 5595 | 829.00 |