Abstract
A gene-expression microarray datum is modeled as an exponential expression signal (log-normal distribution) and additive noise. Variance-stabilizing transformation based on this model is useful for improving the uniformity of variance, which is often assumed for conventional statistical analysis methods. However, the existing method of estimating transformation parameters may not be perfect because of poor management of outliers. By employing an information normalization technique, we have developed an improved parameter estimation method, which enables statistically more straightforward outlier exclusion and works well even in the case of small sample size. Validation of this method with experimental data has suggested that it is superior to the conventional method.
| Original language | English |
|---|---|
| Pages (from-to) | 669-679 |
| Number of pages | 11 |
| Journal | Journal of Bioinformatics and Computational Biology |
| Volume | 2 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 2004 Dec |
| Externally published | Yes |
Fingerprint
Keywords
- Gene-expression microarray data
- Information normalization
- Variance stabilization
ASJC Scopus subject areas
- Medicine(all)
- Cell Biology
Cite this
Improved parameter estimation for variance-stabilizing transformation of gene-expression microarray data. / Inoue, Masato; Nishimura, Shin Ichi; Hori, Gen; Nakahara, Hiroyuki; Saito, Michiko; Yoshihara, Yoshihiro; Amari, Shun Ichi.
In: Journal of Bioinformatics and Computational Biology, Vol. 2, No. 4, 12.2004, p. 669-679.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Improved parameter estimation for variance-stabilizing transformation of gene-expression microarray data
AU - Inoue, Masato
AU - Nishimura, Shin Ichi
AU - Hori, Gen
AU - Nakahara, Hiroyuki
AU - Saito, Michiko
AU - Yoshihara, Yoshihiro
AU - Amari, Shun Ichi
PY - 2004/12
Y1 - 2004/12
N2 - A gene-expression microarray datum is modeled as an exponential expression signal (log-normal distribution) and additive noise. Variance-stabilizing transformation based on this model is useful for improving the uniformity of variance, which is often assumed for conventional statistical analysis methods. However, the existing method of estimating transformation parameters may not be perfect because of poor management of outliers. By employing an information normalization technique, we have developed an improved parameter estimation method, which enables statistically more straightforward outlier exclusion and works well even in the case of small sample size. Validation of this method with experimental data has suggested that it is superior to the conventional method.
AB - A gene-expression microarray datum is modeled as an exponential expression signal (log-normal distribution) and additive noise. Variance-stabilizing transformation based on this model is useful for improving the uniformity of variance, which is often assumed for conventional statistical analysis methods. However, the existing method of estimating transformation parameters may not be perfect because of poor management of outliers. By employing an information normalization technique, we have developed an improved parameter estimation method, which enables statistically more straightforward outlier exclusion and works well even in the case of small sample size. Validation of this method with experimental data has suggested that it is superior to the conventional method.
KW - Gene-expression microarray data
KW - Information normalization
KW - Variance stabilization
UR - http://www.scopus.com/inward/record.url?scp=10944244154&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=10944244154&partnerID=8YFLogxK
U2 - 10.1142/S0219720004000806
DO - 10.1142/S0219720004000806
M3 - Article
VL - 2
SP - 669
EP - 679
JO - Journal of Bioinformatics and Computational Biology
JF - Journal of Bioinformatics and Computational Biology
SN - 0219-7200
IS - 4
ER -