biology driven clustering of microarray data
play

Biology-Driven Clustering of Microarray Data Applications to the - PowerPoint PPT Presentation

Dec 11, 2023 •408 likes •670 views

Biology-Driven Clustering of Microarray Data Applications to the NCI60 Data Set K.R. Coombes, K.A. Baggerly, D.N. Stivers, J. Wang, D. Gold, H.G. Sung, and S.J. Lee Introduction Microarray data is more than a large, unstructured matrix.

  1. Biology-Driven Clustering of Microarray Data Applications to the NCI60 Data Set K.R. Coombes, K.A. Baggerly, D.N. Stivers, J. Wang, D. Gold, H.G. Sung, and S.J. Lee

  2. Introduction • Microarray data is more than a large, unstructured matrix. – We already know many genes important for studying cancer through their involvement in specific biological processes – We also know that reproducible chromosomal abnormalities play an important role in cancer • Need analytical methods that use biological information early

  3. Methods • First, updated the annotations of the genes on the microarray • Performed separate analyses – using genes on individual chromosomes – using genes involved in different biological processes • Developed ways to assess how well each set of genes classified samples

  4. Quality of Annotations • Problem: – I.M.A.G.E. clone IDs and GenBank accession numbers are archival – UniGene clusters, gene names, descriptions, functions, etc., are changeable • Solution: – Download latest UniGene (build 137) and LocusLink to update annotations

  5. How many genes on the array have good annotations? Number Current UniGene of Spots Status 294 None (control spots) 128 Only 3’ – unknown to UniGene 1379 Only 3’ – known to UniGene 1 Only 5’ – unknown Only trust the 6 Only 5’ – known 7478 spots where 399 Both – unknown the UniGene 763 Both – 3’ known, 5’ unknown 291 Both – 3’ unknown, 5’ known clusters match. 646 Both known, but disagree 6093 Both known, and agree

  6. Where are the genes located? 6 (Observed - Expected) / SD 4 2 0 -2 -4 chi^2 = 148.8 p < 10^(-10) -6 X Y 5 10 15 20 Chromosome

  7. How do we determine the functions of genes? • UniGene -> LocusLink -> GeneOntology • GeneOntology is a structured, hierarchical vocabulary to describe gene functions in three broad areas: – biological process (why) – molecular function (what) – cellular component (where)

  8. What kinds of genes are on the microarray? Function Ann. Spots Function Ann. Spots Oncogenesis 140 180 Cell shape and size 78 101 Apoptosis 128 138 Protein traffic 157 188 Physiological proc. 180 210 Transport 146 136 Perc. of ext. stimuli 238 150 Cell proliferation 197 249 Ectoderm devel. 129 152 Stress response 599 372 Mesoderm devel. 92 102 Radiation response 147 136 Cell adhesion 111 140 Cell cycle 494 283 Cell-cell signaling 137 166 Nucleic acid met. 695 595 Signal transduction 222 228 Protein metabolism 471 567 Intracell sig cascade 110 110 Lipid metabolism 146 156 Cell motility 120 153 Carbohydrate met. 103 97 Cell organization 98 118 Energy pathways 88 98

  9. Data Preprocessing • Remove spots with poor annotations and spots with median intensity below the 97th percentile of empty spots. • Normalize each array so median log ratio between channels is one • Center each gene so mean log ratio across experiments is zero • Use (1-correlation)/2 as distance metric

  10. How well does a set of genes distinguish types of cancer? • Three methods for assessment: – Qualitative (PCA, MDS) – Quantitative (PCA + ANOVA) – Semi-quantitative (Grading Dendrograms)

  11. Multidimensional Scaling B 0.3 B M M 0.2 M M M R coordinate 2 S M B 0.1 B M L S B N N L N N S S C L S N 0.0 S N C L N B C L L C M B C B -0.1 N C R C R R O P O O R N R P R O OO R -0.2 -0.1 0.0 0.1 0.2 coordinate 1

  12. PCANOVA

  13. How good is a dendrogram? • A = cluster contains all colon.hcc2998 colon.km12 and only one kind of colon.colo205 colon.hct15 colon.sw620 colon.ht29 colon.hct116 cancer breast.t47d breast.mcf7 leukemia.hl60 leukemia.k562 leukemia.ccrfcem leukemia.molt4 • B = all, with extras leukemia.rpmi8226 leukemia.srcl7019 melanoma.uacc62 melanoma.skmel28 melanoma.skmel5 melanoma.uacc577 • C = all except one melanoma.malme3m melanoma.skmel2 breast.mdan breast.mdamb435 melanoma.m14 breast.unknown ovarian.8 • D = all except one, with nsclc.hop62 nsclc.h226 breast.bt549 cns.u251 cns.snb19 extras cns.snb75 cns.sf295 cns.sf268 breast.hs578t cns.sf539 renal.sn12c • E = all except two breast.mdamb231 nsclc.hop92 nsclc.a549 nsclc.ekvx nsclc.h322 nsclc.h522 • F = all except two, with nsclc.h23 nsclc.h460 prostate.du145 ovarian.5 ovarian.skov3 ovarian.igrov1 extras ovarian.3 ovarian.4 renal.tk10 renal.achn renal.uo31 renal.786o renal.rxf393 Cancer B C L M N O P R S renal.caki1 renal.a498 prostate.pc3 melanoma.loximvi 0.6 0.4 0.2 0.0 Score A A D F D C B

  14. Can cancers be distinguished by genes on one chromosome? ch B C L M N O P R S ch B C L M N O P R S 1 B A D F D B 13 D E 2 E C D D E D E 14 A A F 3 C E D E F 15 C B C F C 4 E E E E 16 5 A A D F E 17 A A D F E E 6 C A D E E D 18 E D 7 E A D E C E 19 D D 8 E C D 20 E C 9 B C C E E E 21 10 D E 22 A E E 11 E C C D X B A D E D 12 B C C E E E

  15. Heterogeneity of different types of cancer • Some cancers (colon, leukemia) are fairly easy to distinguish from others • Some (breast, lung) are so heterogeneous as to be almost impossible to distinguish • Some chromosomes (1, 2, 6, 7, 9, 12, 17) can distinguish many cancers. • Some (16, 21) are essentially random

  16. Chromosome 2 colon.sw620 0.8 colon.hct15 colon.hcc2998 colon.km12 colon.colo205 0.6 nsclc.a549 nsclc.h322 colon.hct116 nsclc.ekvx breast.t47d 0.4 breast.mcf7 nsclc.h522 nsclc.h23 leukemia.hl60 leukemia.k562 0.2 leukemia.ccrfcem leukemia.molt4 leukemia.rpmi8226 leukemia.srcl7019 0.0 prostate.pc3 ovarian.4 ovarian.3 ovarian.skov3 ovarian.igrov1 ovarian.5 breast.unknown ovarian.8 nsclc.hop62 prostate.du145 renal.786o renal.tk10 renal.a498 renal.rxf393 renal.achn renal.uo31 renal.caki1 nsclc.h226 melanoma.uacc62 melanoma.skmel5 melanoma.malme3m melanoma.uacc577 melanoma.skmel2 melanoma.skmel28 melanoma.m14 breast.mdan breast.mdamb435 nsclc.hop92 breast.mdamb231 colon.ht29 breast.hs578t breast.bt549 cns.sf539 melanoma.loximvi cns.snb75 cns.sf295 renal.sn12c cns.sf268 cns.u251 cns.snb19 nsclc.h460 0.6 0.4 0.2 0.0

  17. Chromosome 16 cns.sf539 0.8 breast.bt549 nsclc.h522 nsclc.h23 cns.sf268 breast.hs578t 0.6 renal.sn12c breast.mdamb231 nsclc.hop92 cns.sf295 0.4 leukemia.rpmi8226 leukemia.k562 prostate.pc3 melanoma.loximvi ovarian.4 0.2 ovarian.5 ovarian.3 nsclc.a549 nsclc.h322 0.0 nsclc.ekvx cns.u251 melanoma.malme3m melanoma.m14 breast.mdan breast.mdamb435 melanoma.uacc62 melanoma.skmel28 melanoma.skmel5 melanoma.uacc577 renal.uo31 nsclc.hop62 melanoma.skmel2 cns.snb75 cns.snb19 renal.a498 renal.rxf393 renal.achn renal.caki1 renal.786o renal.tk10 breast.unknown ovarian.8 ovarian.skov3 nsclc.h226 nsclc.h460 breast.mcf7 ovarian.igrov1 colon.hct116 prostate.du145 breast.t47d leukemia.ccrfcem leukemia.molt4 leukemia.hl60 colon.sw620 colon.colo205 colon.hcc2998 colon.km12 colon.hct15 leukemia.srcl7019 colon.ht29 0.6 0.4 0.2 0.0

  18. Can cancers be distinguished by genes of one function? • Table for functional categories looks a lot like the table for chromosomes • Some biological process categories (signal transduction, cell proliferation, cell cycle, protein metabolism) can distinguish many types of cancer • Others (apoptosis, energy pathways) cannot

  19. cell surface receptor linked signal transduction nsclc.h23 0.8 colon.ht29 leukemia.rpmi8226 leukemia.k562 leukemia.hl60 0.6 colon.sw620 leukemia.ccrfcem leukemia.molt4 ovarian.igrov1 leukemia.srcl7019 0.4 ovarian.3 colon.hct116 breast.t47d colon.hcc2998 0.2 colon.hct15 colon.colo205 colon.km12 melanoma.malme3m melanoma.skmel2 0.0 melanoma.uacc577 breast.mdan breast.mdamb435 melanoma.skmel28 melanoma.m14 melanoma.uacc62 melanoma.skmel5 cns.sf295 breast.mcf7 nsclc.h522 nsclc.h460 ovarian.5 nsclc.hop62 prostate.pc3 cns.snb75 ovarian.skov3 renal.a498 renal.caki1 renal.uo31 renal.achn renal.786o renal.rxf393 renal.tk10 nsclc.hop92 ovarian.4 nsclc.h226 breast.bt549 nsclc.ekvx nsclc.h322 nsclc.a549 prostate.du145 melanoma.loximvi breast.unknown ovarian.8 renal.sn12c cns.sf268 breast.mdamb231 cns.sf539 breast.hs578t cns.u251 cns.snb19 0.6 0.4 0.2 0.0

  20. protein metabolism and modification cns.sf268 0.8 breast.bt549 nsclc.hop92 cns.u251 cns.snb19 cns.sf295 0.6 cns.snb75 nsclc.hop62 breast.hs578t cns.sf539 0.4 nsclc.h226 melanoma.loximvi melanoma.uacc62 melanoma.skmel28 0.2 melanoma.malme3m melanoma.skmel5 melanoma.skmel2 melanoma.uacc577 nsclc.h460 0.0 nsclc.h23 nsclc.a549 nsclc.ekvx nsclc.h322 breast.t47d breast.mcf7 prostate.du145 breast.unknown ovarian.8 ovarian.3 ovarian.igrov1 ovarian.5 ovarian.skov3 prostate.pc3 ovarian.4 renal.uo31 renal.caki1 renal.tk10 renal.achn renal.786o renal.rxf393 renal.a498 colon.colo205 colon.ht29 colon.sw620 colon.hcc2998 colon.hct15 colon.km12 colon.hct116 leukemia.ccrfcem leukemia.molt4 leukemia.rpmi8226 leukemia.hl60 leukemia.k562 renal.sn12c breast.mdamb231 nsclc.h522 breast.mdan breast.mdamb435 melanoma.m14 leukemia.srcl7019 0.2 0.0 0.6 0.4

Recommend

Data-driven Clustering via Parameterized Lloyds Families Travis Dick Joint work with

Data-driven Clustering via Parameterized Lloyds Families Travis Dick Joint work with

Data-driven Clustering via Parameterized Lloyds Families Travis Dick Joint work with Maria-Florina Balcan and Colin White Carnegie Mellon University NeurIPS 2018 Data-driven Clustering Data-driven Clustering Clustering aims to divide a

675 views • 53 slides
Order Restricted Clustering for Dose- Response Microarray Data Adetayo Kasim Interuniversity

Order Restricted Clustering for Dose- Response Microarray Data Adetayo Kasim Interuniversity

Order Restricted Clustering for Dose- Response Microarray Data Adetayo Kasim Interuniversity Institute for Biostatistics and Statistical Bioinformatics Universiteit Hasselt &amp; Katholieke Universiteit Leuven Joint work with: Dan Lin , Ziv

436 views • 22 slides
Data Mining in Bioinformatics Day 7: Clustering in Bioinformatics Clustering Gene Expression Data

Data Mining in Bioinformatics Day 7: Clustering in Bioinformatics Clustering Gene Expression Data

Data Mining in Bioinformatics Day 7: Clustering in Bioinformatics Clustering Gene Expression Data Chlo-Agathe Azencott &amp; Karsten Borgwardt February 18 to March 1, 2013 Machine Learning &amp; Computational Biology Research Group Max

538 views • 51 slides
1 Biology Fundamentals - Expression Microarrays Transcriptome: Genes Proteome: Proteins Swiss

1 Biology Fundamentals - Expression Microarrays Transcriptome: Genes Proteome: Proteins Swiss

Differential gene expression General Introduction Swiss Institute of Bioinformatics - LF 11.2010 Overview (1) Reminder of biology n Major steps in microarray analysis n Microarray preparation design, clone/probe selection RNA

741 views • 28 slides
Data Mining in Bioinformatics Day 8: Clustering in Bioinformatics Clustering Gene Expression Data

Data Mining in Bioinformatics Day 8: Clustering in Bioinformatics Clustering Gene Expression Data

Data Mining in Bioinformatics Day 8: Clustering in Bioinformatics Clustering Gene Expression Data Chlo-Agathe Azencott &amp; Karsten Borgwardt February 10 to February 21, 2014 Machine Learning &amp; Computational Biology Research Group Max

522 views • 50 slides
Microarray Data Analysis of Adenocarcinoma Patients Survival Using ADC and K-Medians

Microarray Data Analysis of Adenocarcinoma Patients Survival Using ADC and K-Medians

Microarray Data Analysis of Adenocarcinoma Patients Survival Using ADC and K-Medians Clustering Wenting Zhou, Weichen Wu, Nathan Palmer, Emily Mower, Noah Daniels, Lenore Cowen, Anselm Blumer Tufts University http://camda.cs.tufts.edu

809 views • 37 slides
Graph Clustering Graph Clustering What is clustering? What is clustering? Finding patterns

Graph Clustering Graph Clustering What is clustering? What is clustering? Finding patterns

Graph Clustering Graph Clustering What is clustering? What is clustering? Finding patterns in data, or grouping similar groups of data-points together into clusters . Clustering algorithms for numeric data: Lloyds K-means, EM

688 views • 19 slides
A segmentation-clustering problem for the analysis of array CGH data F. Picard, S. Robin, E.

A segmentation-clustering problem for the analysis of array CGH data F. Picard, S. Robin, E.

A segmentation-clustering problem for the analysis of array CGH data F. Picard, S. Robin, E. Lebarbier, J-J. Daudin UMR INA-PG / INRA, Paris Bio-Info-Math Workshop, Tehran, April 2005 Microarray CGH technology - Known effects of big size

388 views • 24 slides
Introduction to Microarray Data Analysis and Gene Networks Lecture 5 Alvis Brazma European

Introduction to Microarray Data Analysis and Gene Networks Lecture 5 Alvis Brazma European

Introduction to Microarray Data Analysis and Gene Networks Lecture 5 Alvis Brazma European Bioinformatics Institute Lecture 5 Clustering Hierarchical K-means A few minutes about representing experimental designs

558 views • 21 slides
Capturing Best Practice for Microarray Gene Expression Data Analysis Gregory Piatetsky-Shapiro

Capturing Best Practice for Microarray Gene Expression Data Analysis Gregory Piatetsky-Shapiro

Capturing Best Practice for Microarray Gene Expression Data Analysis Gregory Piatetsky-Shapiro Tom Khabaza Sridhar Ramaswamy Presented briefly by Joey Mudd What is Microarray Data? Microarray devices obtain RNA expression levels from

579 views • 11 slides
Data Mining in Bioinformatics Day 2: Clustering Karsten Borgwardt February 21 to March 4, 2011

Data Mining in Bioinformatics Day 2: Clustering Karsten Borgwardt February 21 to March 4, 2011

Data Mining in Bioinformatics Day 2: Clustering Karsten Borgwardt February 21 to March 4, 2011 Machine Learning &amp; Computational Biology Research Group MPIs Tbingen .: Data Mining in Bioinformatics, Page 1 What is clustering? Clustering

612 views • 27 slides
Gene expression analysis Roadmap Microarray technology: how it work Applications: what

Gene expression analysis Roadmap Microarray technology: how it work Applications: what

Gene expression analysis Roadmap Microarray technology: how it work Applications: what can we do with it Preprocessing: Image processing Data normalization Classification Clustering Biclustering 1 Gene

438 views • 14 slides
Model-based clustering and data transformations of gene expression data Walter L. Ruzzo

Model-based clustering and data transformations of gene expression data Walter L. Ruzzo

Model-based clustering and data transformations of gene expression data Walter L. Ruzzo University of Washington UW CSE Computational Biology Group Overview Motivation Model-based clustering Validation Summary and

539 views • 34 slides
Clustering Clustering What? Given some input data, partition the data in multiple groups

Clustering Clustering What? Given some input data, partition the data in multiple groups

Clustering Clustering What? Given some input data, partition the data in multiple groups Why? Approximate large/infinite/continuous set of objects with finite set of representatives Eg. Vector quantization, codebook learning,

846 views • 68 slides
Recent development in microarray data analysis Guan-Hua Huang Institute of Statistics National

Recent development in microarray data analysis Guan-Hua Huang Institute of Statistics National

Recent development in microarray data analysis Guan-Hua Huang Institute of Statistics National Chiao Tung University Gene expression microarray The overwhelming majority of results rely on measures of relative expression -- genes are

605 views • 12 slides
Chapter 7: Clustering (Unsupervised Data Organization) 7.1 Hierarchical Clustering 7.2 Flat

Chapter 7: Clustering (Unsupervised Data Organization) 7.1 Hierarchical Clustering 7.2 Flat

Chapter 7: Clustering (Unsupervised Data Organization) 7.1 Hierarchical Clustering 7.2 Flat Clustering 7.3 Embedding into Vector Space for Visualization 7.4 Applications Clustering: unsupervised grouping (partitioning) of objects into

763 views • 49 slides
Graph Clustering Why graph clustering is useful? Distance matrices are graphs as useful as

Graph Clustering Why graph clustering is useful? Distance matrices are graphs as useful as

Graph Clustering Why graph clustering is useful? Distance matrices are graphs as useful as any other clustering Identification of communities in social networks Webpage clustering for better data management of web data Outline

607 views • 41 slides
k -means clustering Method to automatically separate data sets into distinct groups. Clustering

k -means clustering Method to automatically separate data sets into distinct groups. Clustering

k -means clustering Method to automatically separate data sets into distinct groups. Clustering example Clustering example k -means clustering algorithm 1. Start with k randomly chosen means 2. Color data points by the shortest distance to any

1.56k views • 19 slides
Data Mining in Bioinformatics Day 7: Clustering in Bioinformatics Karsten Borgwardt February 21

Data Mining in Bioinformatics Day 7: Clustering in Bioinformatics Karsten Borgwardt February 21

Data Mining in Bioinformatics Day 7: Clustering in Bioinformatics Karsten Borgwardt February 21 to March 4, 2011 Machine Learning &amp; Computational Biology Research Group MPIs Tbingen Karsten Borgwardt: Data Mining in Bioinformatics, Page

618 views • 24 slides
Bi-clustering and co-clustering Going further in cluster analysis and classifjcation: publics ou

Bi-clustering and co-clustering Going further in cluster analysis and classifjcation: publics ou

HAL Id: hal-01810380 manant des tablissements denseignement et de Summer School on Clustering, Data Analysis and Visualization of Complex Data, May 2018, Catania, Going further in cluster analysis and classifjcation: Bi-clustering and

1.23k views • 67 slides
Clustering A Categorization of Major Clustering Methods Partitioning Methods

Clustering A Categorization of Major Clustering Methods Partitioning Methods

Clustering What is Clustering? Types of Data in Cluster Analysis Clustering A Categorization of Major Clustering Methods Partitioning Methods Hierarchical Methods 1 2 What is Clustering? What is Clustering? Typical

647 views • 18 slides
12. Clustering Chlo-Agathe Azencot Centre for Computatjonal Biology, Mines ParisTech

12. Clustering Chlo-Agathe Azencot Centre for Computatjonal Biology, Mines ParisTech

Foundatjons of Machine Learning CentraleSuplec Fall 2017 12. Clustering Chlo-Agathe Azencot Centre for Computatjonal Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr Learning objectjves Explain what clustering

856 views • 67 slides
Clustering Lecture notes Clustering is Exploratory, unsupervised method Data in cluster is

Clustering Lecture notes Clustering is Exploratory, unsupervised method Data in cluster is

Clustering Lecture notes Clustering is Exploratory, unsupervised method Data in cluster is similar to each other, and dissimilar to other cluster data Finding structure in data Hard vs. Soft/Fuzzy vs. Exclusive Understanding and/or summarise

400 views • 26 slides
1 Data-dr Data-driven philosophy n philosophy Data-dr Data-driven: push n: push 7 8

1 Data-dr Data-driven philosophy n philosophy Data-dr Data-driven: push n: push 7 8

What What is is a a senso sensor network? network? 2 Tiny, untethered nodes with severe resource constraints Sensors, e.g., light, moisture, Tiny CPU and memory Da Data ta-Driven Pr -Driven Proc ocessing essing

177 views • 7 slides

More recommend