The getOutputForPCNOutliers takes which principal component you want to view and a list of labeling names which you want to see included in the report. These labelings need to be ones that have row labels, such as created by labeling.labelRows from the start of the tutorial.
pcaginsu.getOutputForPCNOutliers(1, ['cho_clustering', 'em', 'names'])
The result of that command should contain the same information as the following table.
PC-1 10 High/Low | PC-1 Value | em | cho_clustering | names |
high | 7.66496608144 | 4 | M | WSC4 |
high | 4.17705992859 | 4 | M | YOL019W |
high | 3.87001547533 | 4 | M | HOF1 |
high | 3.84837129339 | 5 | Early G1 | SUR1 |
high | 3.35847421047 | 4 | M | BUB3 |
high | 3.34419451262 | 4 | M | CDC5 |
high | 3.34037443779 | 4 | M | YML034W |
high | 3.27043501501 | 4 | M | COT1 |
high | 2.82125356759 | 4 | M | HDR1 |
high | 2.80269836671 | 4 | G2 | YIL158W |
low | -3.26930983481 | 2 | Late G1 | HO |
low | -3.39173779979 | 2 | Late G1 | RNR1 |
low | -3.44848612811 | 2 | Late G1 | YLR183C |
low | -3.56081559301 | 2 | Late G1 | CDC54 |
low | -3.59901879069 | 2 | Late G1 | YOR144C |
low | -3.60057680134 | 2 | Late G1 | HST3 |
low | -3.64414373489 | 2 | Late G1 | TOF1 |
low | -3.79017028645 | 2 | Late G1 | SPH1 |
low | -3.86578252915 | 2 | Late G1 | YPL264C |
low | -3.93550058084 | 2 | Late G1 | HHO1 |
Interestingly it appears that principal component one helps to differentiate between M phase and the Late G1 phase of the cell cycle.
We do provide a convenience function for saving the output of the getOutput commands, pcaGinsu.write2DStringArrayToFile, this function takes the result of the getOutput command, a file name, and an optional delimiter (which defaults to tab).
outliers = pcaginsu.getOutputForPCNOutliers(1, ['cho_clustering', 'em', 'names']) pcaGinsu.write2DStringArrayToFile(outliers, 'pca-outliers-1.txt')
Brandon King 2005-07-29