Variable and feature selection have become the focus of much research in areas of application for which datasets with tens or hundreds of thousands of variables are available. These areas include text processing of internet documents, gene expression array analysis, and combinatorial chemistry. The objective of variable selection is three-fold: improving the prediction performance of the predictors, providing faster and more cost-effective predictors, and providing a better understanding of the underlying process that generated the data. The contributions of this special issue cover a wide range of aspects of such problems: providing a better definition of the objective function, feature construction, feature ranking, multivariate feature selection, efficient search methods, and feature validity assessment methods.

/pdf/an-introduction-to-variable-and-feature-selection-22eu49r0zd.pdf

An introduction to variable and feature selection

DNA micro-arrays now permit scientists to screen thousands of genes simultaneously and determine whether those genes are active, hyperactive or silent in normal or cancerous tissue. Because these new micro-array devices generate bewildering amounts of raw data, new analytical methods must be developed to sort out whether cancer tissues have distinctive signatures of gene expression over normal tissues or other types of cancer tissues.

In this paper, we address the problem of selection of a small subset of genes from broad patterns of gene expression data, recorded on DNA micro-arrays. Using available training examples from cancer and normal patients, we build a classifier suitable for genetic diagnosis, as well as drug discovery. Previous attempts to address this problem select genes with correlation techniques. We propose a new method of gene selection utilizing Support Vector Machine methods based on Recursive Feature Elimination (RFE). We demonstrate experimentally that the genes selected by our techniques yield better classification performance and are biologically relevant to cancer.

In contrast with the baseline method, our method eliminates gene redundancy automatically and yields better and more compact gene subsets. In patients with leukemia our method discovered 2 genes that yield zero leave-one-out error, while 64 genes are necessary for the baseline method to get the best result (one leave-one-out error). In the colon cancer database, using only 4 genes our method is 98% accurate, while the baseline method is only 86% accurate.

/pdf/gene-selection-for-cancer-classification-using-support-55rxvsb1p7.pdf

Gene Selection for Cancer Classification using Support Vector Machines

/pdf/learning-with-kernels-16eszacl48.pdf

Learning with kernels

MicroRNAs (miRNAs) are a class of small noncoding RNAs that control gene expression by targeting mRNAs and triggering either translation repression or RNA degradation Their aberrant expression may be involved in human diseases, including cancer Indeed, miRNA aberrant expression has been previously found in human chronic lymphocytic leukemias, where miRNA signatures were associated with specific clinicobiological features Here, we show that, compared with normal breast tissue, miRNAs are also aberrantly expressed in human breast cancer The overall miRNA expression could clearly separate normal versus cancer tissues, with the most significantly deregulated miRNAs being mir-125b, mir-145, mir-21, and mir-155 Results were confirmed by microarray and Northern blot analyses We could identify miRNAs whose expression was correlated with specific breast cancer biopathologic features, such as estrogen and progesterone receptor expression, tumor stage, vascular invasion, or proliferation index

MicroRNA gene expression deregulation in human breast cancer.

Support vector machines (SVMs) are becoming popular in a wide variety of biological applications. But, what exactly are SVMs and how do they work? And what are their most promising applications in the life sciences?

/pdf/what-is-a-support-vector-machine-u7ovdyjvgk.pdf

What is a support vector machine

Motivation: DNA microarray experiments generating thousands of gene expression measurements, are being used to gather information from tissue and cell samples regarding gene expression differences that will be useful in diagnosing disease. We have developed a new method to analyse this kind of data using support vector machines (SVMs). This analysis consists of both classification of the tissue samples, and an exploration of the data for mis-labeled or questionable tissue results. Results: We demonstrate the method in detail on samples consisting of ovarian cancer tissues, normal ovarian tissues, and other normal tissues. The dataset consists of expression experiment results for 97 802 cDNAs for each tissue. As a result of computational analysis, a tissue sample is discovered and confirmed to be wrongly labeled. Upon correction of this mistake and the removal of an outlier, perfect classification of tissues is achieved, but not with high confidence. We identify and analyse a subset of genes from the ovarian dataset whose expression is highly differentiated between the types of tissues. To show robustness of the SVM method, two previously published datasets from other types of tissues or cells are analysed. The results are comparable to those previously obtained. We show that other machine learning methods also perform comparably to the SVM on many of those datasets. Availability: The SVM software is available at http:// www. cs.columbia.edu/ ∼bgrundy/ svm.

/pdf/support-vector-machine-classification-and-validation-of-2p2be2xbdd.pdf

Support vector machine classification and validation of cancer tissue samples using microarray expression data

Comparative hybridization of an array of 21,500 ovarian cDNAs for the discovery of genes overexpressed in ovarian carcinomas.

http://depts.washington.edu/maizels9/downloads/pdf/Larson_Mol_Cell_2005.pdf

MRE11/RAD50 Cleaves DNA in the AID/UNG-Dependent Pathway of Immunoglobulin Gene Diversification

Homology-directed repair is a powerful mechanism for maintaining and altering genomic structure. We asked how chromatin structure contributes to the use of homologous sequences as donors for repair using the chicken B cell line DT40 as a model. In DT40, immunoglobulin genes undergo regulated sequence diversification by gene conversion templated by pseudogene donors. We found that the immunoglobulin Vλ pseudogene array is characterized by histone modifications associated with active chromatin. We directly demonstrated the importance of chromatin structure for gene conversion, using a regulatable experimental system in which the heterochromatin protein HP1 (Drosophila melanogaster Su[var]205), expressed as a fusion to Escherichia coli lactose repressor, is tethered to polymerized lactose operators integrated within the pseudo-Vλ donor array. Tethered HP1 diminished histone acetylation within the pseudo-Vλ array, and altered the outcome of Vλ diversification, so that nontemplated mutations rather than templated mutations predominated. Thus, chromatin structure regulates homology-directed repair. These results suggest that histone modifications may contribute to maintaining genomic stability by preventing recombination between repetitive sequences.

http://depts.washington.edu/maizels9/downloads/pdf/Cummings_plos_bio_2007.pdf

Chromatin Structure Regulates Gene Conversion

Background
Deamination of cytosine to produce uracil is a common and potentially mutagenic lesion in genomic DNA. U•G mismatches occur spontaneously throughout the genome, where they are repaired by factors associated with the base excision repair pathway. U•G mismatches are also the initiating lesion in immunoglobulin gene diversification, where they undergo mutagenic processing by redundant pathways, one dependent upon uracil excision and the other upon mismatch recognition by MutSα. While UNG is well known to initiate repair of uracil in DNA, the ability of MutSα to direct correction of this base has not been directly demonstrated.

http://depts.washington.edu/maizels9/downloads/pdf/1471-2199-9-94.pdf

David W. Bednarski

Papers

Support vector machine classification and validation of cancer tissue samples using microarray expression data

Comparative hybridization of an array of 21,500 ovarian cDNAs for the discovery of genes overexpressed in ovarian carcinomas.

MRE11/RAD50 Cleaves DNA in the AID/UNG-Dependent Pathway of Immunoglobulin Gene Diversification

Chromatin Structure Regulates Gene Conversion

High-fidelity correction of genomic uracil by human mismatch repair activities