Identification of differentially Overview of our method expressed - - PowerPoint PPT Presentation

1

Learning to Classify Cancer from Gene Expressions and Clinical Data

Application: Classifiaton of Gastric Cancer

• Tumors from 17 patients with gastric carcinoma was

collected for surgically resected stomachs

– 5 female (aged 45-80, median 70) – 11 male (aged 49-93, median 73)

• 6 clinical parameters:
• cDNA microarrays were printed with 2504 genes
• Each gene was printed in duplicate on the arrays.

Sample Classes Distribution Laurén's histological classification Diffus or Intestinal 8 - Diffus, 9 - Intestinal Localization of tumor Cardia or Non-cardia 4 - Cardia, 13 - Non-cardia Lymph node metastasis Yes or No 10 - Yes, 7 - No Penetration of the stomach wall Yes or No 13 - Yes, 4 - No Remote metastasis Yes or No 3 - Yes, 10 - No Serum gastrin High or Normal 5 - High, 9 - Normal

Overview of our method

• Filtering of low intensity spots
• Normalization
• Averaging of duplicate spots
• Selection of significantly differentially expressed genes
• Discretization
• Rule learning by Rough Sets methods
• Prediction
• Evaluation with leave-one-out cross-validation

Notice that the problem is under-defined: 2500 attributes for 17 objects!

Identification of differentially expressed genes

• Differentially expressed genes can be identified

with hypothesis testing

• A two class problem (Y or N):

– H0: RatioY = RatioN v.s. H1: RatioY ¹ RatioN

• The distribution can be estimated with

bootstrapping to avoid assuming normality of the

• bservations

2

Gene selection

Gene selection with bootstraping for Lymph Node Metastasis:

H0: RatioLNM = RatioNot LNM v.s. H1: RatioLNM ≠ RatioNot LNM

Cluster(Hs.) Name Symbol Mean P-val boot-t Hs.291 glutamyl aminopeptidase (aminopeptidase A) ENPEP 0.727 0.142 Hs.823 hepsin (transmembrane protease, serine 1) HPN 0.542 0.1238 Hs.74861 activated RNA polymerase II transcription cofactor 4 PC4 0.839 0.1602 Hs.60478 ESTs, Moderately similar to S47073 finger protein HZF2 <Hs.60478> 0.6935 0.1414 0.001 Hs.284266 hypothetical protein MGC8471 MGC8471 0.4589 0.1013 0.001 Hs.96 phorbol-12-myristate-13-acetate-induced protein 1 PMAIP1 0.7117 0.1662 0.002 Hs.2025 transforming growth factor, beta 3 TGFB3 0.5842 0.1585 0.002 Hs.83469 nuclear factor (erythroid-derived 2)-like 1 NFE2L1 0.8419 0.1812 0.002 Hs.181046 dual specificity phosphatase 3 (vaccinia virus phosphatDUSP3 0.4843 0.0943 0.002 Hs.331 general transcription factor IIIC, polypeptide 1 GTF3C1 0.2834 0.0864 0.003 Hs.635 calcium channel, voltage-dependent, beta 1 subunit CACNB1 0.5364 0.122 0.003 Hs.1066 small nuclear ribonucleoprotein polypeptide E SNRPE 0.4673 0.1015 0.003 Hs.1098 DKFZp434J1813 protein DKFZP434J1813 0.5033 0.126 0.003 Hs.104481 Nck, Ash and phospholipase C binding protein NAP4 0.6001 0.1276 0.003 Hs.118825 mitogen-activated protein kinase kinase 6 MAP2K6 0.2853 0.0754 0.003 Hs.161 cadherin 2, type 1, N-cadherin (neuronal) CDH2 0.3771 0.1175 0.004 Hs.13063 transcription factor CA150 CA150 0.655 0.1831 0.004 Hs.124029 inositol polyphosphate-5-phosphatase, 40kD INPP5A 0.9106 0.2486 0.004 Hs.170980 KIAA0948 protein KIAA0948 0.683 0.1597 0.004 Hs.211614 chloride channel 6 CLCN6 0.4511 0.114 0.004

Classification

PMAIP1 ENPEP GTF3C1 CACNB1 HPN DKFZP434J1813 TGFB3 MGC8471 ... Class [*, 0.036) [*, -0.046) [*, -0.226) [-0.136, 0.290) [*, -0.288) [*, -0.044) [*, -0.152) [-0.016, 0.318) ... Y [0.036, 0.440) [0.380, *) [0.026, *) [0.290, *) [0.064, *) [0.292, *) [0.108, *) [0.318, *) ... Y [0.440, *) [0.380, *) [0.026, *) [-0.136, 0.290) [-0.288, 0.064) [0.292, *) [-0.152, 0.108) [0.318, *) ... Y [*, 0.036) [*, -0.046) [*, -0.226) [*, -0.136) [*, -0.288) [*, -0.044) [*, -0.152) [*, -0.016) ... N [0.440, *) [0.380, *) [*, -0.226) [0.290, *) [-0.288, 0.064) [-0.044, 0.292) [0.108, *) [0.318, *) ... Y [*, 0.036) [-0.046, 0.380) [-0.226, 0.026) [-0.136, 0.290) [0.064, *) [-0.044, 0.292) [0.108, *) [-0.016, 0.318) ... Y [0.036, 0.440) [*, -0.046) [*, -0.226) [-0.136, 0.290) [*, -0.288) [*, -0.044) [-0.152, 0.108) [-0.016, 0.318) ... N [0.440, *) [0.380, *) [-0.226, 0.026) [0.290, *) [0.064, *) [0.292, *) [0.108, *) [0.318, *) ... Y [0.036, 0.440) [*, -0.046) Undefined [*, -0.136) Undefined [*, -0.044) [*, -0.152) [*, -0.016) ... N Undefined [-0.046, 0.380) Undefined Undefined Undefined Undefined [*, -0.152) Undefined ... N [*, 0.036) [*, -0.046) [-0.226, 0.026) [*, -0.136) [-0.288, 0.064) [-0.044, 0.292) [0.108, *) [*, -0.016) ... N [0.440, *) [-0.046, 0.380) [0.026, *) [0.290, *) [-0.288, 0.064) [0.292, *) [*, -0.152) [0.318, *) ... Y [0.036, 0.440) [-0.046, 0.380) [*, -0.226) [*, -0.136) [*, -0.288) [-0.044, 0.292) [-0.152, 0.108) [*, -0.016) ... N [0.036, 0.440) [-0.046, 0.380) [-0.226, 0.026) [-0.136, 0.290) [-0.288, 0.064) [-0.044, 0.292) [-0.152, 0.108) [-0.016, 0.318) ... Y [0.440, *) [0.380, *) [0.026, *) [0.290, *) [0.064, *) [0.292, *) [-0.152, 0.108) [-0.016, 0.318) ... Y [0.036, 0.440) [-0.046, 0.380) [0.026, *) [-0.136, 0.290) [0.064, *) [-0.044, 0.292) [-0.152, 0.108) [-0.016, 0.318) ... Y [*, 0.036) [*, -0.046) [-0.226, 0.026) [*, -0.136) [*, -0.288) [*, -0.044) [*, -0.152) [*, -0.016) ... N

Decision system: Decision rules:

PMAIP1([*, 0.036)) AND PC4([-0.716, -0.073)) => Class(Y) PMAIP1([*, 0.036)) AND PC4([*, -0.716)) => Class(N) PMAIP1([0.036, 0.440)) AND PC4([*, -0.716)) => Class(N) TGFB3([*, -0.152)) AND MGC8471([-0.016, 0.318)) => Class(Y) TGFB3([0.108, *)) AND MGC8471([-0.016, 0.318)) => Class(Y) CLCN6([-0.209, 0.141)) AND MGC8471([-0.016, 0.318)) => Class(Y) CLCN6([*, -0.209)) AND MGC8471([-0.016, 0.318)) => Class(N)

Prediction Performance

Sample Reducer Discretation Max Genes Sig. lev. Accuracy Sens.

• Spec. AUC

Laurén's histological classification Dynamic Freq.bin (4) 10 0.01 16/17=0.941 1 0.86 0.93 Localization of tumor Dynamic Entropy 20 0.01 17/17=1 1 1 1 Lymph node metastasis Dynamic Freq.bin (3) 20 0.01 14/17=0.824 0.7 1 0.9 Penetration of the stomach wall Holte 1r Entropy 20 0.01 16/17=0.941 1 0.75 0.85 Remote metastasis Holte 1r Entropy 40 0.1 13/13=1 1 1 1 Serum gastrin Genetic Entropy 10 0.05 11/14=0.786 0.9 0.6 0.66

Sample Rules No. (avg) Rules No. (Range) Total no. of genes in all classifiers Laurén's histological classification 24.1 10-67 17 Localization of tumor 238.1 200-311 72 Lymph node metastasis 388.1 222-523 73 Penetration of the stomach wall 109.6 28-280 75 Remote metastasis 425.1 305-468 161 Serum gastrin 47.9 18-72 42

Validation from biomedical literature

Unkown Sample gastric cancer

• ther cancer

gastric cancer

• ther cancer

Connection Laurén's histological classification 1 2 Localization of tumor 2 3 22 Lymph node metastasis 1 2 1 26 Penetration of the stomach wall 4 1 1 17 Remote metastasis 3 2 47 Serum gastrin 1 1 18 Known connection to the parameter in Known Connection to

3

Genes occurring in the classifier for lymph node metastasis

Symbol Name Function No classifiers LNM Not LNM LOC51058 hypothetical protein unknown 17 x ISG15 interferon-stimulated protein, 15 kDa signal transduction 17 x Homo sapiens cDNA FLJ14959 fis, clone PLACE4000156unknown 16 x Homo sapiens, clone IMAGE:3948563 unknown 16 x DKFZP434J1813 DKFZp434J1813 protein unknown 16 x CACNB1 calcium channel, voltage-dependent, beta 1 subunit muscle contraction 15 x Homo sapiens, clone MGC:2492, mRNA, complete cds unknown 15 x NAP4 Nck, Ash and phospholipase C binding protein signal transduction 15 x PPP1CC protein phosphatase 1, catalytic subunit, gamma isoform cell division/prot synt 14 x ESTs, Mod similar to JC5238 galactosylceramide-like pro unknown 13 x HAT1 histone acetyltransferase 1 DNA packaging 13 x MGC8471 hypothetical protein MGC8471 unknown 13 x SEC4L GTP-binding prot homo to Sacc cerevisiae SEC4 signal transduction 12 x DUSP3 dual specificity phosphatase 3 signal transduction 11 x NOLA2 nucleolar protein family A, member 2 protein syntesis 11 x RAB11A RAB11A, member RAS oncogene family signal transduction 10 x Highest level

The classifiers at the best filtering level The classifiers at the best filtering level Lauren

Genetic reducer

4

Lauren

1R Classifier

Lauren

Dynamic reducer

Lymph node metastasis

Genetic reducer

Lymph node metastasis

1R Classifier

5

Comparison of the learning methods

using the best discretization method

Lauren

Conclusions

• Genes function in teams: Identification of individual,

significantly differentially expressed genes only is insufficient for classification

• Rough set learning identifies different groups of genes

for different objects

• RS learning outperforms both linear and quadratic linear

discriminant analysis

• Literature validation could not be completed; present

knowledge of cancer is scarce and fragmented

• RS supervised learning provides valuable hypotheses

about molecular functions of genes

• Combination of rough sets with feature selection

methods may be well suited for this task

• But: only 2,504 genes out of at least 30K genes were

used