2 <head><title>Principal Component Analysis</title></head>
\r
4 <p><strong>Principal Component Analysis</strong></p>
\r
5 <p>This calculation creates a spatial representation of the
\r
6 similarities within a selected group, or all of the sequences in
\r
7 an alignment. After the calculation finishes, a 3D viewer displays the
\r
8 set of sequences as points in 'similarity space', and similar
\r
9 sequences tend to lie near each other in the space.</p>
\r
10 <p>Note: The calculation is computationally expensive, and may fail for very large sets of sequences -
\r
11 usually because the JVM has run out of memory. The next release of
\r
12 Jalview release will execute this calculation through a web service.</p>
\r
13 <p>Principal components analysis is a technique for examining the
\r
14 structure of complex data sets. The components are a set of dimensions
\r
15 formed from the measured values in the data set, and the principle
\r
16 component is the one with the greatest magnitude, or length. The
\r
17 sets of measurements that differ the most should lie at either end of
\r
18 this principle axis, and the other axes correspond to less extreme
\r
19 patterns of variation in the data set.
\r
22 <p>In this case, the components are generated by an eigenvector
\r
23 decomposition of the matrix formed from the sum of BLOSUM scores at
\r
24 each aligned position between each pair of sequences. The basic method
\r
25 is described in the paper by G. Casari, C. Sander and
\r
26 A. Valencia. Structural Biology volume 2, no. 2, February 1995 (<a
\r
27 href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=7749921">pubmed</a>)
\r
28 and implemented at the SeqSpace server at the EBI.
\r
31 <p><strong>The PCA Viewer</strong></p>
\r
32 <p>This is an interactive display of the sequences positioned within
\r
33 the similarity space. The colour of each sequence point is the same
\r
34 as the sequence group colours, white if no colour has been
\r
35 defined for the sequence, and green if the sequence is part of a
\r
36 the currently selected group.
\r
38 <p>The 3d view can be rotated by dragging the mouse with the
\r
39 <strong>left mouse button</strong> pressed. The view can also be
\r
40 zoomed in and out with the up and down <strong>arrow
\r
42 <p>A tool tip gives the sequence ID corresponding to a point in the
\r
43 space, and clicking a point toggles the selection of the
\r
44 corresponding sequence in the alignment window. Rectangular region
\r
45 based selection is also possible, by holding the 'S' key whilst
\r
46 left-clicking and dragging the mouse over the display.
\r
48 <p>Initially, the display shows the first three components of the
\r
49 similarity space, but any eigenvector can be used by changing the selected
\r
50 dimension for the x, y, or z axis through each ones menu located
\r
51 below the 3d display.
\r