ScoreGenes

Summary

ScoreGenes is a data analysis toolkit designed for large sets of gene expressions over various experiments. ScoreGenes includes methods for evaluating data sets, discovering informative genes that are differentially expressed across the classes, classifying the experiments using supervised learning algorithms, and clustering the genes using semi-supervised learning method. This toolkit efficiently handles large data sets.

Main Features

Version 1.0 (December, 2002)

Scores informative genes according to various statistical tests: TNoM, Info, t-Test, fold-change and more.
Evaluate data set by estimating the abundance of informative genes.
Supervised classification with the following algorithms: Adaboost, Naive Bayes, Gaussian Naive Bayes.
Semi-supervised clustering of the genes, using the learning method PCluster.
Cross validation ability: LOOCV and K-fold.
Platforms: Windows, and Linux.
Enables visualization using TreeView, or GeneXPress.
More detailed information and instructions

Development Team

Nir Friedman, Computer Science & Engineering, Hebrew University, Jerusalem.

Naftali Kaminski, University of Pittsburgh Medical Center.

Yoseph Barash, Computer Science & Engineering, Hebrew University, Jerusalem.

Noa Shefi, Computer Science & Engineering, Hebrew University, Jerusalem.

Gali Niv, Computer Science & Engineering, Hebrew University, Jerusalem.

Omri Peleg, Computer Science & Engineering, Hebrew University, Jerusalem.

Publications

Methods Papers

Comparative analysis of algorithms for signal quantitation from oligonucleotide microarrays by Y. Barash, E. Dehan, M. Krupsky, W. Franklin, M. Geraci, N.Friedman and N. Kaminski.
Bioinformatics, 20:839-4, 2004.

Practical Approaches to Analyzing Results of Microarray Experiments by N. Friedman and N. Kaminski.
American Journal of Respiratory and Cell Molecular Biology, 27:125-132, 2002. PDF.

Overabundance Analysis and Class Discovery in Gene Expression Data by A.Ben-Dor, N. Friedman and Z. Yakhini.
Technical Report 2002-50, School of Computer Science & Engineering, Hebrew University , 2002; PostScript, PDF.

Scoring genes for relevance by A. Ben-Dor, N. Friedman, & Z. Yakhini
Technical Report 2000-38, School of Computer Science & Engineering, Hebrew University , 2000; PDF

Tissue Classification with Gene Expression Profiles by A.Ben-Dor, L. Bruhn, N. Friedman I. Nachman, M. Schummer, and Z. Yakhini.
Journal of Computational Biology, 7:559--584, 2000. PostScript, PDF.

Applicative works

Peripheral blood mononuclear cell gene expression profiles identify emergent post-traumatic stress disorder among trauma survivors by R. Segman, N. Shefi, T. Goltser-Dubner, N. Friedman, N. Kaminski and A. Shalev
Molecular Psychiatry, 2005.

Stress-related genomic responses during the course of heat acclimation and its association with ischemic-reperfusion cross-tolerance by M. Horowitz, L. Eli-Berchoer, I. Wapinski, N. Friedman and E. Kodesh.
Journal of Applied Physiology, 97:1496-507, 2004.

Blood transcriptional signatures of multiple sclerosis: Unique gene expression of disease activity by A. Achiron, M. Gurevich, N. Friedman N. Kaminski, and M. Mandel.
Annals of Neurology, 55:410-7, 2004.

Human and porcine early kidney precursors as a new source for transplantation. by Dekel B, Burakova T, Arditti FD, Reich-Zeliger S, Milstein O, Aviel-Ronen S, Rechavi G, Friedman N, Kaminski N, Passwell JH and Reisner Y.
Nat Med. 2002 Jan;9:53-60.

Gene expression analysis reveals matrilysin as a key regulator of pulmonary fibrosis in mice and humans. by Zuo F, Kaminski N, Eugui E, Allard J, Yakhini Z, Ben-Dor A, Lollini L, Morris D, Kim Y, DeLustro B, Sheppard D, Pardo A, Selman M, and Heller RA.
Proc Natl Acad Sci U S A, 2002 Apr 30;99(9):6292-7 PDF.

Availability

The package is available here for academic research only under the LESSER GENERAL PUBLIC LICENSE
For further questions please contact scoregenes@cs.huji.ac.il