Entering edit mode

13 months ago

ishackm
•
60

Hi all,

I hope you're well

I have the following the dataset:

```
QE1_Jo_Exp1_AOCS1_R QE1_Jo_Exp1_G33 QE1_Jo_Exp1_G33_R QE1_Jo_Exp1_G164
1 1027.9600 1434.3834 1774.4618 892.7630
2 1075.0975 1692.0633 1014.8056 537.9152
3 1031.2545 1377.9725 1181.1430 3983.6936
4 3257.5661 3433.5130 3644.4593 933.2016
5 535.0528 839.5253 523.3276 3708.1248
6 6259.4604 23886.0483 9353.2122 29776.4997
```

I used the following script to carry out PCA analysis:

```
a <- myPr
rv <- rowVars(as.matrix(a))
select <- order(rv, decreasing = TRUE)[seq_len(min(ntop = 12596, length(rv)))]
pca1 <- prcomp(t(a[select, ]))
scores <- data.frame(pca1$x[,1:ncol(pca1$rotation)])
scores.df <- data.frame(colnames(a), pca1$x[,1:ncol(pca1$rotation)])
pca1
summary(pca1)
```

The result is:

```
> summary(pca1)
Importance of components:
PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8 PC9 PC10 PC11
Standard deviation 5.441e+05 1.097e+05 6.167e+04 1.720e+04 1.293e+04 9.306e+03 8.535e+03 7.128e+03 4.357e+03 3.526e+03 2.666e+03
Proportion of Variance 9.470e-01 3.853e-02 1.217e-02 9.500e-04 5.300e-04 2.800e-04 2.300e-04 1.600e-04 6.000e-05 4.000e-05 2.000e-05
Cumulative Proportion 9.470e-01 9.855e-01 9.977e-01 9.987e-01 9.992e-01 9.995e-01 9.997e-01 9.999e-01 9.999e-01 1.000e+00 1.000e+00
PC12 PC13 PC14 PC15 PC16 PC17 PC18 PC19 PC20 PC21 PC22
Standard deviation 2.349e+03 1.851e-06 2.318e-07 2.279e-07 2.25e-07 2.173e-07 2.151e-07 2.148e-07 2.081e-07 2.065e-07 2.002e-07
Proportion of Variance 2.000e-05 0.000e+00 0.000e+00 0.000e+00 0.00e+00 0.000e+00 0.000e+00 0.000e+00 0.000e+00 0.000e+00 0.000e+00
Cumulative Proportion 1.000e+00 1.000e+00 1.000e+00 1.000e+00 1.00e+00 1.000e+00 1.000e+00 1.000e+00 1.000e+00 1.000e+00 1.000e+00
PC23 PC24
Standard deviation 1.942e-07 4.214e-11
Proportion of Variance 0.000e+00 0.000e+00
Cumulative Proportion 1.000e+00 1.000e+00
```

But when I do:

```
biplot(pca1)
```

I get the following

the current PCA plot

the desired PCA plot

This is my first time doing a PCA plot so any help will be greatly appreciated.

Many Thanks,

Ishack

Please see How to add images to a Biostars post to add your images properly. You need

the direct link to the image, not the link to the webpage that has the image embedded (which is what you have used here)Are your plots from the same dataset? How do you know that such a plot is possible with your dataset? They're both PC1 vs PC2 plots, maybe the nature of your data prevents the plot from being like #2?

Hi RamRS,

Thank you for your quick response

the second plot is from a different dataset but I would like to have the first dataset to have a plot similar to the second PCA plot, please

Check @Kevin's PCAtools package: PCA plot from read count matrix from RNA-Seq While this refers to RNAseq the principle should be the same.

Hi genomax, thanks for the link

I have created the following plot from this code:

The new PCA plot

is Dim 1 and Dim 2 same as PCA 1 and PCA 2?

As genomax says, you can just use my code from my other thread: PCA plot from read count matrix from RNA-Seq

Also PCAtools (https://bioconductor.org/packages/release/bioc/html/PCAtools.html) can be used - this was just released with Bioconductor 3.9