Two-stage clustering analysis to detect pattern change of biomarker expression between experimental conditions
- 주제(키워드) two-stage , pattern clustering , biomarker expression , intervention study , cross-over design
- 주제(기타) Mathematical & Computational Biology
- 설명문(일반) [Huh, Iksoo] Seoul Natl Univ, Coll Nursing, Seoul 03080, South Korea; [Huh, Iksoo] Seoul Natl Univ, Res Inst Nursing Sci, Seoul 03080, South Korea; [Choi, Sunghoon; Park, Taesung] Seoul Natl Univ, Dept Stat, Seoul 08826, South Korea; [Kim, Youjin; Park, Soo-Yeon; Kwon, Oran] Ewha Womans Univ, Dept Nutr Sci & Food Management, Seoul 03760, South Korea
- 등재 SCIE, SCOPUS
- 발행기관 INDERSCIENCE ENTERPRISES LTD
- 발행년도 2020
- URI http://www.dcollection.net/handler/ewha/000000172414
- 본문언어 영어
- Published As https://dx.doi.org/10.1504/IJDMB.2020.108701
초록/요약
In a crossover design, individuals usually undergo all experimental conditions, and the measurements of biomarkers are repeatedly observed at serial time points for each experimental condition. To analyse time-dependent changing patterns of biomarkers, clustering algorithms are commonly used across time points to group together subjects having similar changing patterns. Among the clustering methods, hierarchical- and K-means clustering have been popularly used. However, since they are originally unsupervised approaches, they do not identify different changing patterns between experimental conditions. Therefore, we propose a new two-stage clustering method focusing on changing patterns. The first stage is to eliminate non-informative biomarkers using Euclidean distances, and the second stage is to allocate the remaining biomarkers to predefined patterns using a correlation-based distance. We demonstrate the advantages of our proposed method by simulation and real data analysis.
more