MDCS – Microarray Data Classification Server

MDCS

:: DESCRIPTION

The MDCS provides maximal margin Linear Programming method (Antonov et al., 2004) for classification of tumor samples based on microarray data. This procedure detects groups of genes and constructs models (features) that strongly correlate with particular tumor types. The detected features include genes whose functional relations are changed for particular cancer types.

::DEVELOPER

MDCS Team

:: SCREENSHOTS

N/A

:: REQUIREMENTS

:: DOWNLOAD

 MDCS

:: MORE INFORMATION

Citation:

Antonov, A.V., Tetko, I.V, Prokopenko, V.V., Kosykh,D. & Mewes, H.W.
Web Portal for Classification of Expression Data using Maximal Margin Linear Programming,
Bioinformatics, 2004, 20, 3284-5.

 

R-SVM 2.0 – Recursive Sample Classification and Gene Selection with SVM

R-SVM 2.0

:: DESCRIPTION

R-SVM is a SVM-based method for doing supervised pattern recognition(classification) with microarray gene expression data.  The method uses SVM for both classification and for selecting a subset of relevant genes according to their relative contribution in the classification.  This process is done recursively so that a series of gene subsets and classification models can be obtained in a recursive manner, at different levels of gene selection.  The performance of the classification can be evaluated either on an independent test data set or by cross validation on the same data set.  R-SVM also includes an option for permutation experiments to assess the  significance of the performance.

::DEVELOPER

the Wong Lab

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux

:: DOWNLOAD

 R-SVM

:: MORE INFORMATION

Citation

ZHANG, X.G., LU, X., (Joint First Author) XU, X.Q., LEUNG, H.E., WONG, W.H. and LIU, J.S. (2006)
RSVM: A SVM based Strategy for Recursive Feature Selection and Sample Classification with Proteomics Mass-Spectrometry Data.
BMC Bioinformatics, 7:197

Q5 – Classification of Complete Mass Spectra of a Complex Protein Mixture

Q5

:: DESCRIPTION

Q5 is a closed-form, exact solution to the problem of classification of complete mass spectra of a complex protein mixture. Q5 employs a probabilistic classification algorithm built upon a dimension-reduced linear discriminant analysis. Our solution is computationally efficient; it is non-iterative and computes the optimal linear discriminant using closed-form equations. The optimal discriminant is computed and verified for datasets of complete, complex SELDI spectra of human blood serum. Replicate experiments of different training/testing splits of each dataset are employed to verify robustness of the algorithm. The probabilistic classification method achieves excellent performance. We achieve sensitivity, specificity, and positive predictive values above 97% on three ovarian cancer datasets and one prostate cancer dataset. The Q5 method outperforms previous full-spectrum complex sample spectral classification techniques, and can provide clues as to the molecular identities of differentially-expressed proteins and peptides.

::DEVELOPER

Donald Lab at Duke University

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Windows / Linux / MacOSX
  • Matlab

:: DOWNLOAD

Q5

:: MORE INFORMATION

Citation

Probabilistic Disease Classification of Expression-Dependent Proteomic Data from Mass Spectrometry of Human Serum
Ryan H. Lilien, Hany Farid and Bruce R. Donald
Journal of Computational Biology, 2003; 10(6): 925-946.

MICE 1.4 – Mouse Information & Classification Entity

MICE 1.4

:: DESCRIPTION

MICE (Mouse Information and Classification Entity) is a program aimed at facilitating the monitoring of animals in their facility. It consists of a virtual facility in which scientists can perform all the tasks done in the real world (i.e., receiving animals, breeding, etc…). Each animal is recorded with all associated information (birth date, cage number, ID number, tail analysis number, parents, genetic status, genetic background and more), allowing for reliable tracking. Animals can be identified, grouped, sorted, moved…, according to any parameter of interest to the scientist, including associated comments. Crossings are automatically processed by the program, which determines the new genetic background, generation number, cage location and due date.

MICE reminds the user when births are expected, and entering the newborn animals only requires a few clicks (of the mouse!). The genealogy of each animal can be determined in two different ways, including a visual tree from which each ancestor’s information can be retrieved.

::DEVELOPER

P. Pognonec

:: SCREENSHOTS

:: REQUIREMENTS

  • Windows / Mac OsX

:: DOWNLOAD

MICE for Win ; for Mac

:: MORE INFORMATION

Citation:

MICE, a program to track and monitor animals in animal facilities. BMC Genetics 2001 Mar;2(1):4

Any comment and/or proposal concerning this application is welcome! Please contact P. Pognonec for additional information.