S a signal rather than a noise. 3. Legend of Figure 2. "The data is..." should
PubMed ID:https://www.ncbi.nlm.nih.gov/pubmed/15957913 be "The data are... ". 4. p.7. There is no reference of Figures A, B in the main text. Also indicate in the legend of Figure 3 what is in Figure 3E. 5. p.8. In the legend of Figure 4 what the symbols in the outer-panel represent? What do the lines represent? It is better to use different notation (A, B) to avoid confusion in the main text of the second paragraph of p. 9. 6. p.9 What is "alpha" in Equation (4)? 7. p.9 line -9. You may include two specific patterns of dependence of two genes, namely, type A dependence of Klevanov, Jordan and
5-Difluoro-2-nitroaniline Carbamic acid Yakovlev (2006), and hidden regulator dependence of Lim, Kim and Kim (2011). 8. p.15 line -13. "euclidean Kernel" should be "Euclidean kernel" (9) 9. p.15 line -10. "a either" should be "either". 10. p.15 line -8. Author may want to include Tsai and Chen (2009) for
2-Bromo-1,3-difluoro-4-nitrobenzene another reference of Hotelling's T-square statistic. 11. p.17. line 15, What are "A" and "B"?
PubMed ID:https://www.ncbi.nlm.nih.gov/pubmed/23410069 12. p. 18 line 2. Better to include Lauritzen (1996) as a reference of IPS algorithm.Emmert-Streib et al. Biology Direct 2012, 7:44 http://www.biology-direct.com/content/7/1/Page 21 of13. p. 22. It would be more beneficial for the read to move the last paragraph of p. 22 (extended to p. 23) to Introduction section. References Efron B. (2007a). Correlation and large-scale simultaneous
signifance testing, J. Amer. Statist. Assoc. 102:93-103. Efron B. (2007b). Size, power and false discovery rates, Annals of Statist. 35:1351-1377. Fan J, Feng Y, Wu Y. (2009). Network exploration via the adaptive lasso and SCAD penalties. Ann. Statist. 3:521-541. Friedman J, Hastie T, Tibshirani R. (2008). Sparse inverse covariance estimation with the graphical lasso. Biostatistics 9:432441. Lauritzen SL. (1996), Graphical models, Oxford: Clarendon Press. Lim J, Kim J, Kim BS (2011). An alternative model of type A dependence in a gene set of correlated genews, Statist. Appl. Genet. Mol. Biol. Vol. 9, Article 12. Kiiver H, de Hoog F. (2012). Fitting very large Gaussian graphical models. Comp. Statist. Data Anal. 56:2626-2636. Klebanov L, Jordan C, Yakovlev A. (2006). A new type of stochastic dependence revealed in gene expression data, Statist. Appl. Genet. Mol. Biol. Vol. 5, Article 7.. Tsai CA, Chen J. (2009). Multivariate analysis of variance test for gene set analysis, Bioinformatics, 25:897-903. Witten DM, Friedman JH, Simon N. (2011). New insights and faster computation for the graphical lasso. J. Comp. Graph. Stat. 20:892-900. Zou H. (2006). The adaptive lasso and its oracle properties. J. Amer. Statist. Assoc. 101:1418-1429.Reply:8. p.40. Reference 109: Author was duplicated at the end. The location and the publisher were
1-(4-Bromo-2-pyridyl)piperazine missing. 9. p.41. Reference 117. The article title is missing. 10. p.41. Reference 118: The location of the publisher is missing. 11. p.41. Reference 133. The journal title should be consistent with Reference 27.Reply:All comments have been addressed and we revised the main text correspondingly. Thank you for your suggestions and comments.Referee 3: Dr. Joel BaderWe revised our text correspondingly and addressed all your suggestions. We would like to point out that the major goal of our review is not a full coverage of statistical details but to provide sufficient information for the reader to acquire a basic understanding of major principles and assumptions that underly the methods. The problem is that if too many detail are presented the paper would turn quickly in.