1 / 31

Principal Component Analysis & Multidimensional scaling

Principal Component Analysis & Multidimensional scaling. Problem: Too much data!. Pat1 Pat2 Pat3 Pat4 Pat5 Pat6 Pat7 Pat8 Pat9 209619_at 7758 4705 5342 7443 8747 4933 7950 5031 5293 7546 32541_at 280 387 392 238 385 329 337 163 225 288

vita
Download Presentation

Principal Component Analysis & Multidimensional scaling

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Principal Component Analysis& Multidimensional scaling

  2. Problem: Too much data! Pat1 Pat2 Pat3 Pat4 Pat5 Pat6 Pat7 Pat8 Pat9 209619_at 7758 4705 5342 7443 8747 4933 7950 5031 5293 7546 32541_at 280 387 392 238 385 329 337 163 225 288 206398_s_at 1050 835 1268 1723 1377 804 1846 1180 252 1512 219281_at 391 593 298 265 491 517 334 387 285 507 207857_at 1425 977 2027 1184 939 814 658 593 659 1318 211338_at 37 27 28 38 33 16 36 23 31 30 213539_at 124 197 454 116 162 113 97 97 160 149 221497_x_at 120 86 175 99 115 80 83 119 66 113 213958_at 179 225 449 174 185 203 186 185 157 215 210835_s_at 203 144 197 314 250 353 173 285 325 215 209199_s_at 758 1234 833 1449 769 1110 987 638 1133 1326 217979_at 570 563 972 796 869 494 673 1013 665 1568 201015_s_at 533 343 325 270 691 460 563 321 261 331 203332_s_at 649 354 494 554 710 455 748 392 418 505 204670_x_at 5577 3216 5323 4423 5771 3374 4328 3515 2072 3061 208788_at 648 327 1057 746 541 270 361 774 590 679 210784_x_at 142 151 144 173 148 145 131 146 147 119 204319_s_at 298 172 200 298 196 104 144 110 150 341 205049_s_at 3294 1351 2080 2066 3726 1396 2244 2142 1248 1974 202114_at 833 674 733 1298 862 371 886 501 734 1409 213792_s_at 646 375 370 436 738 497 546 406 376 442 203932_at 1977 1016 2436 1856 1917 822 1189 1092 623 2190 203963_at 97 63 77 136 85 74 91 61 66 92 203978_at 315 279 221 260 227 222 232 141 123 319 203753_at 1468 1105 381 1154 980 1419 1253 554 1045 481 204891_s_at 78 71 152 74 127 57 66 153 70 108 209365_s_at 472 519 365 349 756 528 637 828 720 273 209604_s_at 772 74 130 216 108 311 80 235 177 191 211005_at 49 58 129 70 56 77 61 61 75 72 219686_at 694 342 345 502 960 403 535 513 258 386 38521_at 775 604 305 563 542 543 725 587 406 906 217853_at 367 168 107 160 287 264 273 113 89 363 217028_at 4926 2667 3542 5163 4683 3281 4822 3978 2702 3977

  3. Dimensional Reduction and feature selection • Reduction of dimensions • Principle Component Analysis (PCA) • Feature selection (gene selection) • Significant genes: t-test • Selection of a limited number of genes

  4. Principal Component Analysis (PCA) • Used for visualization of complex data • Developed to capture as much of the variation in data as possible • Generic features of principal components • summary variables • linear combinations of the original variables • uncorrelated with each other • capture as much of the original variance as possible

  5. Principal components • principal component (PC1) • the direction along which there is greatest variation • principal component (PC2) • the direction with maximum variation left in data, orthogonal to the direction (i.e. vector) of PC1 • principal component (PC3) • the direction with maximal variation left in data, orthogonal to the plane of PC1 and PC2 • (Rarely used) • etc...

  6. Example: 3 dimensions => 2 dimensions

  7. PCA - example

  8. PCA on all GenesLeukemia data, precursor B and T • Plot of 34 patients, 8973 dimensions (genes) reduced to 2

  9. Variance retained, variance lost

  10. Student t-test can be used to filter out differential expresse genes • Compares the means ( & ) of two data sets • tells us if they can be assumed to be equal • Can be used to identify significant genes • i.e. those that change their expression a lot!

  11. PCA on 100 top significant genes According to a Student’s t-test • Plot of 34 patients, 100 dimensions (genes) reduced to 2

  12. Multidimensional Scaling Procedures • Similar in spirit to PCA but it takes a dissimilarity as input

  13. Multidimensional Scaling Procedures The purpose of multidimensional scaling (MDS) is to map the distances between points in a high dimensional space into a lower dimensional space without too much loss of information.

  14. Math • MDS seeks values z_1,...,z_N in R^k to minimize the so-called stress function • This is known as least squares or classical multidimensional scaling. A gradient descent algorithm is used to minimize S. • A non-metric form of MDS is Sammons (1996) non-linear mapping. • Here the following stress function is being minimized:

  15. We use MDS to visualize the dissimilarities between objects. We use MDS to visualize the dissimilarities between objects. The procedures are very exploratory and their interpretations are as much art as they are science.

  16. Examples • The “points” that are represented in multidimensional space can be just about anything. • These objects might be people, in which case MDS can identify clusters of people who are “close” versus “distant” in some real or psychological sense.

  17. Multidimensional Scaling Procedures • As long as the “distance” between the objects can be assessed in some fashion, MDS can be used to find the lowest dimensional space that still adequately captures the distances between objects. • Once the number of dimensions is identified, a further challenge is identifying the meaning of those dimensions.

  18. Multidimensional Scaling Procedures • Basic data representation in MDS is a dissimilarity matrix that shows the distance between every possible pair of objects. • The goal of MDS is to faithfully represent these distances with the lowest possible dimensional space.

  19. Multidimensional Scaling Procedures • The mathematics behind MDS can be daunting to understand. • Two types: classical (metric) multidimensional scaling and non-metric scaling. • Example: Distances between cities on the globe

  20. Multidimensional Scaling Procedures • This table lists the distances between European cities. A multidimensional scaling of these data should be able to recover the two dimensions (North-South x East-West) that we know must underlie the spatial relations among the cities.

  21. Multidimensional Scaling Procedures • MDS begins by restricting the dimension of the space and then seeking an arrangement of the objects in that restricted space that minimizes the difference between the distances in that space compared to the actual distances.

  22. Multidimensional Scaling Procedures • Appropriate number of dimensions are identified… • Objects can be plotted in the multidimensional space… • Determine what objects cluster together and why they might cluster together. The latter issue concerns the meaning of the dimensions and often requires additional information.

  23. Multidimensional Scaling Procedures • In the cities data, the meaning is quite clear. • The dimensions refer to the North-South x East-West surface area across which the cities are dispersed. • We would expect MDS to faithfully recreate the map relations among the cities.

  24. Multidimensional Scaling Procedures This arrangement provides the best fit for a one-dimensional model. How good is the fit? We use a statistic called “stress” to judge the goodness-of-fit.

  25. Smaller stress values indicate better fit. Some rules of thumb for degree of fit are:

  26. The stress for the one-dimensional model of the cities data is .31, clearly a poor fit. The poor fit can also be seen in a plot of the actual distances versus the distances in the one-dimensional model, known as a Shepard plot. In a good fitting model, the points will lie along a line, sloping upward to the right, showing a one-to-one correspondence between distances in the model space and actual distances. Clearly not evident here.

  27. A two-dimensional model fits very well. The stress value is also quite small (.00902) indicating an exceptional fit. Of course, this is no great surprise for these data.

  28. Not any room for a three-dimensional model to improve matters. The stress is .00918, indicating that a third dimension does not help at all.

  29. Multidimensional Scaling Procedures Dimension 2 Dimension 1

  30. Multidimensional Scaling Procedures Dimension 3 Dimension 1

  31. MDS Example: Clusters among Prostate Samples

More Related