Presentation is loading. Please wait.

Presentation is loading. Please wait.

Dimension reduction : PCA and Clustering by Agnieszka S. Juncker

Similar presentations


Presentation on theme: "Dimension reduction : PCA and Clustering by Agnieszka S. Juncker"— Presentation transcript:

1 Dimension reduction : PCA and Clustering by Agnieszka S. Juncker
Part of the slides is adapted from Chris Workman

2 Advanced Data Analysis
The DNA Array Analysis Pipeline Question Experimental Design Array design Probe design Sample Preparation Hybridization Buy Chip/Array Image analysis Normalization Expression Index Calculation Comparable Gene Expression Data Statistical Analysis Fit to Model (time series) Advanced Data Analysis Clustering PCA Classification Promoter Analysis Meta analysis Survival analysis Regulatory Network

3 Motivation: Multidimensional data
Pat1 Pat2 Pat3 Pat4 Pat5 Pat6 Pat7 Pat8 Pat9 209619_at 32541_at 206398_s_at 219281_at 207857_at 211338_at 213539_at 221497_x_at 213958_at 210835_s_at 209199_s_at 217979_at 201015_s_at 203332_s_at 204670_x_at 208788_at 210784_x_at 204319_s_at 205049_s_at 202114_at 213792_s_at 203932_at 203963_at 203978_at 203753_at 204891_s_at 209365_s_at 209604_s_at 211005_at 219686_at 38521_at 217853_at 217028_at 201137_s_at 202284_s_at 201999_s_at 221737_at 205456_at 201540_at 219371_s_at 205297_s_at 208650_s_at 210031_at 203675_at 205255_x_at 202598_at 201022_s_at 218205_s_at 207820_at 202207_at

4 Dimension reduction methods
Principal component analysis (PCA) Cluster analysis Multidimensional scaling Correspondance analysis Singular value decomposition

5 Principal Component Analysis (PCA)
used for visualization of complex data developed to capture as much of the variation in data as possible

6 Principal components 1. principal component (PC1)
the direction along which there is greatest variation 2. principal component (PC2) the direction with maximum variation left in data, orthogonal to the 1. PC

7 Principal components General about principal components
summary variables linear combinations of the original variables uncorrelated with each other capture as much of the original variance as possible

8 Principal components

9 PCA - example

10 PCA on all Genes Leukemia data, precursor B and T
Plot of 34 patients, dimension of 8973 genes reduced to 2

11 PCA of genes (Leukemia data)
Plot of 8973 genes, dimension of 34 patients reduced to 2

12 Principal components - Variance

13 Clustering methods Hierarchical Partitioning agglomerative (buttom-up)
eg. UPGMA divisive (top-down) Partitioning eg. K-means clustering

14 Hierarchical clustering
Representation of all pairwise distances Parameters: none (distance measure) Results: in one large cluster hierarchical tree (dendrogram) Deterministic

15 Hierarchical clustering – UPGMA Algorithm
Assign each item to its own cluster Join the nearest clusters Reestimate the distance between clusters Repeat for 1 to n

16 Hierarchical clustering

17 Hierarchical clustering
Data with clustering order and distances Dendrogram representation

18 Leukemia data - clustering of patients

19 Leukemia data - clustering of patients on top 100 significant genes

20 Leukemia data - clustering of genes

21 K-means clustering Partition data into K clusters
Parameter: Number of clusters (K) must be chosen Randomilized initialization: different clusters each time

22 K-means - Algorithm Assign each item a class in 1 to K (randomly)
For each class 1 to K Calculate the centroid (one of the K-means) Calculate distance from centroid to each item Assign each item to the nearest centroid Repeat until no items are re-assigned (convergence)

23 K-mean clustering, K=3

24 K-mean clustering, K=3

25 K-mean clustering, K=3

26 K-means clustering of Leukemia data

27 Self Organizing Maps (SOM)
Partitioning method (similar to the K-means method) Clusters are organized in a two-dimensional grid Size of grid is specified (eg. 2x2 or 3x3) SOM algoritm finds the optimal organization of data in the grid

28 SOM - example

29 Comparison of clustering methods
Hierarchical clustering Distances between all variables Timeconsuming with a large number of gene Advantage to cluster on selected genes K-means clustering Faster algorithm Does only show relations between all variables SOM more advanced algorithm

30 Distance measures Euclidian distance Vector angle distance
Pearsons distance

31 Comparison of distance measures

32 Summary Dimension reduction important to visualize data Methods:
Principal Component Analysis Clustering Hierarchical K-means Self organizing maps (distance measure important)

33 Next: Exercises in PCA and clustering
Coffee break Next: Exercises in PCA and clustering


Download ppt "Dimension reduction : PCA and Clustering by Agnieszka S. Juncker"

Similar presentations


Ads by Google