Assignment: Your task is to use Rmarkdown to write a short report, readable by a technically literate person. The code you used should not be visible in the final report (unless you have a good reason to show it).
Please submit both the Rmd file and the resulting html or pdf file. You can work with other members of class, but I expect each of you to construct and run all of the scripts yourself.
We have gene expression data for 15,847 genes in 84 threespine stickleback fish in an experiment, summarized in this figure:
The data files are:
CVvsGF_RNAseq_CPM.tsv - expression data: rows are genes; columns are fish The expression data are normalized (so units are in copies per million).
CVvsGF_RNAseq_Metadata.tsv - metadata about the fish
Your goal is to perform a PCA on these data to discover major sources of expression variation. In particular, which of the variables in the metadata are most strongly associated with overall differences in variation (e.g., sex? population? treatment?) How many genes contribute to this pattern? What do you think is leading to this pattern? In particular, to show this you should make a plot with one point for each of the 84 fish on the principal axes you find, colored by the grouping variable. Spoiler alert: if you normalize and/or transform the data appropriately, the two populations will separate cleanly in the plot of PC1 and PC2. You should find this normalization/transformation.