| Web site and design © 2008 by G6G Consulting Group. All Rights Reserved. Most product content has been taken directly from manufacturer's web sites; other product content is assembled by G6G Consulting Group. G6G welcomes any corrections and/or comments. |
Category Genomics>Gene Expression Analysis/Profiling/Tools Abstract IBM Genes@Work is a pattern discovery and classification system for gene expression data. It was designed to provide a rich set of tools for the analysis of gene expression data. Unique to Genes@Work is the search of "patterns" over a particular set of DNA microarray samples. A pattern is a collection of genes with similar expression levels over a subset of experiments. Each microarray is known a priori to belong to either one of two "phenotypes" under study. One of these phenotypes is used as a "control" phenotype, and the other phenotype will be termed the "target". The patterns are searched over the target phenotype. Patterns can be further applied to selecting relevant genes and building predictive models. Genes@Work provides an integrated set of tools for exploring and building predictive model hypothesis by using supervised learning techniques such as Support Vector Machines (SVM). Genes@Work features include: 1) Two types of input data - data can be formatted in either one of two tab separated formats (Affymetrix or Complimentary DNA). And, two different files are required for processing, one with the gene expression data and another describing the target phenotypes. 2) Visualizing gene array data - gene expression data can be visualized through a variety of color plots, scatter plots, pattern plots and hierarchical clustering dendrograms. 3) Advanced data preprocessing features include extensive scaling, filtering and feature selection. Expression data may be pre-processed before running the pattern discovery portion of the system. The pre- processing may enhance the ability to find a signal in the data. For example, filtering could be used to ignore genes that are Not present as judged by the Affymetrix call. Alternatively, filtering could be used to ignore genes that show insignificant change in expression across samples. Additionally, data can be scaled by taking logarithms above a given threshold. Scaling options include: Apply cutoff threshold, Apply loge transformation and Apply normalization/scaling to average. Filtering options include: % Present Calls less than, Standard deviation, by threshold; Standard deviation, by number of genes; Import feature list from file, etc. Feature selection options include: Fold ratio, by number of genes; Fold ratio, by threshold; USE-Fold filter for Affymetrix data, SNR (Signal to Noise Ratio), by number of genes; SNR, by threshold; etc. 4) Advanced Pattern Discovery parameters include: a) Phenotype - indicates the group of microarray samples over which patterns are searched, b) Delta - indicates the maximum deviation in normalized expression units for a gene to be included in a pattern, c) Min Support - indicates a search strategy for patterns, d) Max Pattern Count - indicates a search strategy for patterns alternative to Min Support, e) Threshold - sets whether a pattern is reported in relation to how often such a pattern should occur by random chance, f) Genes - indicates the minimum number of genes the reported patterns must contain, g) Independent Patterns - when this option is enabled, the program lists only the maximal patterns that are Not conditionally dependent with each other, etc. 5) Genes@Work supports hierarchical clustering for use in combination with pattern discovery or as an independent tool. 6) Genes@Work advanced graphical Classification sub-system allows you to classify based on patterns, generate predictive hypothesis and apply them to previously unseen data. Its Learning Machine options includes the following learning algorithms - Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), Pattern Discovery based classification (PD) and an experimental hybrid between PD and SVM (PD/SVM), and more.
Manufacturer Home office; see web site for international locations.
P.O. Box 218, Yorktown Heights, N.Y. 10598, USA IBM Corporation 1 New Orchard Road Armonk, New York 10504-1722 1-800-IBM-4YOU (1-800-426-4968) Technical Support: 1-800-IBM-SERV (1-800-426-7378) Manufacturer's Web Site www.research.ibm. com/FunGen/FGDownloads.htm Price Contact manufacturer G6G Product Number 20004 G6G Manufacturer Number 101280 |
| The G6G Directory of Omics and Intelligent Software |
|
|