@inproceedings{4c3db1cfb9424dbfbca220e1ce27b250,
title = "Data integration in multi-dimensional data sets: Informational asymmetry in the valid correlation of subdivided samples",
abstract = "Background: Flow cytometry is the only currently available high throughput technology that can measure multiple physical and molecular characteristics of individual cells. It is common in flow cytometry to measure a relatively large number of characteristics or features by performing separate experiments on subdivided samples. Correlating data from multiple experiments using certain shared features (e.g. cell size) could provide useful information on the combination pattern of the not shared features. Such correlation, however, are not always reliable. Methods: We developed a method to assess the correlation reliability by estimating the percentage of cells that can be unambiguously correlated between two samples. This method was evaluated using 81 pairs of subdivided samples of microspheres (artificial cells) with known molecular characteristics. Results: Strong correlation (R=0.85) was found between the estimated and actual percentage of unambiguous correlation. Conclusion: The correlation reliability we developed can be used to support data integration of experiments on subdivided samples.",
author = "Zeng, {Qing T.} and Pratt, {Juan Pablo} and Jane Pak and Kim, {Eun Young} and Dino Ravnic and Harold Huss and Mentzer, {Steven J.}",
year = "2006",
doi = "10.1007/11946465_38",
language = "English (US)",
isbn = "3540680632",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "423--432",
booktitle = "Biological and Medical Data Analysis - 7th International Symposium, ISBMDA 2006, Proceedings",
address = "Germany",
note = "7th International Symposium on Biological and Medical Data Analysis, ISBMDA 2006 ; Conference date: 07-12-2006 Through 08-12-2006",
}