Tools for data analysis

SigHunt: Horizontal Gene Transfer Finder Optimized for Eukaryotic Genomes

Authors

Kamil S. Jaroň, Jiří Moravec, Natália Martínková

Citation

Jaroň, K. S,, Moravec, J, Martínková, N. SigHunt: Horizontal gene transfer finder optimized for eukaryotic genomes [online]. 2013. Available from: http://www.iba.muni.cz/index-en.php?pg=research--data-analysis-tools--sighunt

Description

SigHunt analyses genomic signature of a DNA sequence and outputs the score DIAS. It consists of several tools:

Main tools

  • SigHunter -- batch program written in C that reads a fasta file and outputs genomic signature for specified, sequential windows of the DNA sequence.
  • SigHunt.r -- R functions that analyse genomic signatures provided by SigHunter

Additional tools

  • Discriminator -- R script for finding the most informative tetranucleotides with the TES
  • slaver.r -- R script written for easy manipulation of a large number of sequences

Source code

Data Analysis Tool for the Estimation of the Current Survival Measures

Authors

Eva Janoušová, Tomáš Pavlík, Richard Hůlek, Jiří Mayer, Ladislav Dušek

Description

This portal makes current survival measures for outcome assessment in chronic myeloid leukaemia (CML) patients available online. You can analyze your data in three simple steps and get summary tables and publication-quality figures. The calculations are based on a methodology recently published in international peer-reviewed journals.

Website

DBM Toolbox for Neuroimage Data

Author

Daniel Schwarz

Citation

Schwarz, D. DBM Toolbox for Neuroimage Data, version 1.1 [online]. 2012. Available from: http://www.iba.muni.cz/neuroimaging

Description

DBM Toolbox provides algorithms for deformable image registration of 3-D magnetic resonance brain images. The algorithms were implemented as functions and scripts in MATLAB® environment. Some of the functions, which provide computationally intensive tasks, have been compiled into *.mexw64 files for 64 bit Windows operation systems.

The toolbox was developed within the frame of the grant project Modern pattern recognition methods for image data analysis in neuropsychiatric research, supported by the Internal Grant Agency of the Czech Ministry of Health (project no. NS10347).

Documentation Source code

Recognition Toolbox for Neuroimage Data

Author

Eva Janoušová

Citation

Janoušová, E.. Recognition Toolbox for Neuroimage Data, version 1.0 [online]. 2012. Available from: http://www.iba.muni.cz/neuroimaging

Description

Recognition Toolbox provides algorithms for reduction and classification of two-dimensional (2-D) or three-dimensional (3-D) medical image data acquired with diverse medical imaging techniques. The algorithms were implemented as functions in MATLAB® environment.

The toolbox was developed within the frame of the grant project Modern pattern recognition methods for image data analysis in neuropsychiatric research, supported by the Internal Grant Agency of the Czech Ministry of Health (project no. NS10347).

Documentation Source code

Penalised Reduction & Classification Toolbox

Author

Eva Janoušová

Citation

Janoušová, E.. Penalised Reduction & Classification Toolbox, version 1.0 [online]. 2016 . Available from: http://www.iba.muni.cz/index-en.php?pg=research--data-analysis-tools--plda

Description

Penalised Reduction & Classification Toolbox provides algorithms for reduction and classification of various types of data, such as genetic data, two-dimensional (2-D) face image data or three-dimensional (3-D) brain image data. The algorithms were implemented as functions in MATLAB® environment. Nowadays, the toolbox enables reduction of data by selecting most discriminative features using penalised linear discriminant analysis (pLDA) with resampling, penalised linear regression (pLR) with resampling, and t-test or feature extraction using intersubject principal component analysis (isPCA). The reduced data are then classified into two groups using linear discriminant analysis (LDA) or linear support vector machines (SVM). Classification performance of methods acquired by leave-one-out cross-validation can be compared using the McNemar’s test.

Acknowledgement

The toolbox was developed within the frame of the grant project Advanced Methods for Recognition of MR brain images for Computer Aided Diagnosis of Neuropsychiatric Disorders, supported by the Internal Grant Agency of the Czech Ministry of Health (project no. NT 13359-4).

Documentation Source code

Feature Extraction & Classification Toolbox

Author

Radomír Kůs

Citation

Kůs, R. FEATbox (Feature Extraction & clAssification Toolbox), version 1.0 [on-line]. 2016. Available from: http://www.iba.muni.cz/index-en.php?pg=research--data-analysis-tools--featbox

Description

FEATbox (Feature Extraction & clAssification Toolbox) is an outcome of attempts to compare feature extraction and selection methods for schizophrenia classification based on magnetic resonance images (MRI) of brains. Thus, the primary focus of the toolbox are various feature extraction techniques, extracting features from 3-D images given in NIfTI format. Namely, Mann-Whitney testing is implemented as a representative of univariate approaches with contrast to multivariate methods such as intersubject PCA (isPCA), the K-SVD algorithm, and pattern-based morphometry (PBM). The extracted features can be either examined more thoroughly or passed to a subsequent leave-one-out cross-validated (LOOCV) linear support vector machine (SVM) classification. Also, several classification measures are implemented in the toolbox for assessing and comparing classification performance of different classification schemes.

Documentation Source code

Toolbox for Brain Image Recognition Using Artificial Neural Networks

Author

Roman Vyškovský

Citation

Vyškovský, R.: Toolbox for brain image recognition using artificial neural networks, version 1.0 [on-line]. 2016. Available from: http://www.iba.muni.cz/index-en.php?pg=research--data-analysis-tools--annbrainrecog_toolbox

Description

This toolbox is focused on brain image classification using artificial neural networks. The functions implemented in MATLAB® were created during experimentation aiming at the design of a classification scheme able to detect first-episode schizophrenia from brain MRI data. The experiments resulted in two classification schemes. The first one uses single classifiers based on artificial neural networks (ANN) and the second scheme takes advantage of Random Subspace Ensemble Multi-layer Perceptron (RSE-MLP).

Documentation Source code