Noi/NOTES/2012-4-6
Jump to navigation
Jump to search
- Link to calendar: [[1]]
Regression analysis of UCLA SZ data set[edit]
- Continued from http://genome-tech.ucsd.edu/LabNotes/index.php/Noi/NOTES/2012-4-1 and after getting comments from Dr. Zhang during lab meeting (2012_04_04)
- From the list of CpG sites from regression analysis. I performed PCA analysis again by adding the GA samples from Kang Zhang's lab as control (only the 73 good quality samples).
- Note: I will add more information about analysis and PCA analysis result after removing CpG sites with less confident.
A=read.table("UCLA-GA_age_t2.5_methylMatrix.txt", header=TRUE,row.names=1) B=na.omit(A) B$STDEV=NULL B$min_RD=NULL B$mean_RD=NULL str(B) 'data.frame': 1120 obs. of 169 variables: pca_sites <- prcomp(B, scale=TRUE) summary(pca_sites) Importance of components: PC1 PC2 PC3 PC4 PC5 PC6 PC7 Proportion of Variance 0.672 0.0344 0.0117 0.00694 0.00625 0.00558 0.00461 write.table(file="age_pca_sites.orig.rotations", pca_sites$rotation) pca1 <- prcomp(t(B), scale=TRUE) summary(pca1) Importance of components: PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 Proportion of Variance 0.118 0.0535 0.0246 0.0198 0.0165 0.0153 0.0137 0.013 File:UCLA-GA age t2.5 p.png
A=read.table("UCLA-GA_disease_t2.5_methylMatrix.txt",header=TRUE,row.names=1) B=na.omit(A) B$STDEV=NULL B$min_RD=NULL B$mean_RD=NULL str(B) 'data.frame': 98 obs. of 169 variables: pca_sites <- prcomp(B, scale=TRUE) summary(pca_sites) Importance of components: PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 Proportion of Variance 0.669 0.0290 0.0219 0.0183 0.0165 0.0133 0.0107 0.0097 write.table(file="disease_pca_sites.orig.rotations", pca_sites$rotation) pca1 <- prcomp(t(B), scale=TRUE) summary(pca1) Importance of components: PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 Proportion of Variance 0.0722 0.0409 0.0384 0.0314 0.0302 0.0269 0.0246 0.0237 write.table(file="disease_pca_indiv.orig.x", pca1$x) File:UCLA-GA disease t2.5 p.png A=read.table("UCLA-GA_sex_t2.5_methylMatrix.txt",header=TRUE,row.names=1) B=na.omit(A) B$STDEV=NULL B$min_RD=NULL B$mean_RD=NULL str(B) 'data.frame': 887 obs. of 169 variables: pca_sites <- prcomp(B, scale=TRUE) summary(pca_sites) Importance of components: PC1 PC2 PC3 PC4 PC5 PC6 PC7 Proportion of Variance 0.631 0.0226 0.0185 0.0117 0.0111 0.00943 0.00844 write.table(file="sex_pca_sites.orig.rotations", pca_sites$rotation) pca1 <- prcomp(t(B), scale=TRUE) summary(pca1) Importance of components: PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 Proportion of Variance 0.0958 0.0378 0.0309 0.0236 0.0231 0.0201 0.0168 0.0158 File:UCLA-GA sex t2.5 p.png