targetedRetrieval 120705 – Targeted Retrieval of Gene Expression Measurements Using Regulatory Models

targetedRetrieval 120705

:: DESCRIPTION

targetedRetrieval is a model for the regulation of specific genes from a data repository and exploit it to construct a similarity metric for an information retrieval task.

::DEVELOPER

Probabilistic Machine Learning

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows /MacOsX
  • R package

:: DOWNLOAD

  targetedRetrieval

:: MORE INFORMATION

Citation

Elisabeth Georgii, Jarkko Salojärvi, Mikael Brosché, Jaakko Kangasjärvi, and Samuel Kaski.
Targeted retrieval of gene expression measurements using regulatory models.
Bioinformatics (2012) 28 (18): 2349-2356.

Eyediagram – Visualization Probabilistic Decompositions

Eyediagram

:: DESCRIPTION

The eyediagram visualization can be used to illustrate associations between entities, as found by probabilistic component models, such as topic models.

::DEVELOPER

Probabilistic Machine Learning

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows /MacOsX
  • R package

:: DOWNLOAD

 Eyediagram

:: MORE INFORMATION

Citation

Probabilistic retrieval and visualization of biologically relevant microarray experiments
José Caldas, Nils Gehlenborg, Ali Faisal, Alvis Brazma and Samuel Kaski
Bioinformatics (2009) 25 (12): i145-i153.

gseaLda – Probabilistic Retrieval and Visualization of Biologically Relevant Microarray Experiments

gseaLda

:: DESCRIPTION

gseaLda is a r package for probabilistic retrieval and visualization of biologically relevant microarray experiments

::DEVELOPER

Probabilistic Machine Learning

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows /MacOsX
  • R package

:: DOWNLOAD

 gseaLda

:: MORE INFORMATION

Citation

Probabilistic retrieval and visualization of biologically relevant microarray experiments
José Caldas, Nils Gehlenborg, Ali Faisal, Alvis Brazma and Samuel Kaski
Bioinformatics (2009) 25 (12): i145-i153.

LIGAP 20130505 – Identify Condition/Lineage Specific Time-course Profiles

LIGAP 20130505

:: DESCRIPTION

LIGAP allows integrative analysis and visualization of multiple lineages over whole time-course profiles.

::DEVELOPER

Computational systems biology group

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows / MacOsX
  • Matlab

:: DOWNLOAD

 LIGAP

:: MORE INFORMATION

Citation

BMC Genomics. 2012 Oct 30;13:572. doi: 10.1186/1471-2164-13-572.
An integrative computational systems biology approach identifies differentially regulated dynamic transcriptome signatures which drive the initiation of human T helper cell differentiation.
Aijö T, Edelman SM, Lönnberg T, Larjo A, Kallionpää H, Tuomela S, Engström E, Lahesmaa R, Lähdesmäki H.

Treebic 1.11 – Hierarchical Generative Biclustering for MicroRNA Expression Analysis

Treebic 1.11

:: DESCRIPTION

Treebic is a Software package for hierarchical biclustering.

::DEVELOPER

Probabilistic Machine Learning

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows /MacOsX
  • R package

:: DOWNLOAD

 Treebic

:: MORE INFORMATION

Citation

J. Caldas and S. Kaski.
Hierarchical generative biclustering for microRNA expression analysis.
J. Caldas and S. Kaski. Journal of Computational Biology, 18(3):251-261, 2011

GFAsparse 1.0.3 – Elementwise Sparse Group Factor Analysis

GFAsparse 1.0.3

:: DESCRIPTION

GFAsparse implements the Bayesian Group Factor Analysis with element wise prior inducing sparsity.

::DEVELOPER

Probabilistic Machine Learning

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Windows / Linux / MacOS
  • R

:: DOWNLOAD

 GFAsparse

:: MORE INFORMATION

Citation

Identification of structural features in chemicals associated with cancer drug response: a systematic data-driven analysis.
Khan SA, Virtanen S, Kallioniemi OP, Wennerberg K, Poso A, Kaski S.
Bioinformatics. 2014 Sep 1;30(17):i497-i504. doi: 10.1093/bioinformatics/btu456.

BinDNase – Predicting TF-DNA Interaction Sites using DNase-seq data

BinDNase

:: DESCRIPTION

BinDNase is a discriminative approach for transcription factor binding prediction using DNase I hypersensitivity data

::DEVELOPER

Computational systems biology group

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows / MacOsX
  • R

:: DOWNLOAD

 BinDNase

:: MORE INFORMATION

Citation

BinDNase: A discriminatory approach for transcription factor binding prediction using DNase I hypersensitivity data.
Kähärä J, Lähdesmäki H.
Bioinformatics. 2015 May 7. pii: btv294.

DyNB 20150501 – Analyze RNA-seq Time Series data

DyNB 20150501

:: DESCRIPTION

DyNB is novel statistical methodology for analyzing time-course RNA-seq data.

::DEVELOPER

Computational systems biology group

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows / MacOsX
  • Matlab

:: DOWNLOAD

 DyNB

:: MORE INFORMATION

Citation

Bioinformatics. 2014 Jun 15;30(12):i113-20. doi: 10.1093/bioinformatics/btu274.
Methods for time series analysis of RNA-seq data with application to human Th17 cell differentiation.
Äijö T, Butty V, Chen Z, Salo V, Tripathi S, Burge CB, Lahesmaa R, Lähdesmäki H.

MixChIP – Cell Type Specific Protein-DNA Binding analysis

MixChIP

:: DESCRIPTION

MixChIP is a probabilistic method for identifying cell type specific TF binding sites from heterogeneous chromatin immunoprecipitation sequencing (ChIP-seq) data.

::DEVELOPER

Computational systems biology group

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux / Windows / MacOsX
  • R

:: DOWNLOAD

 MixChIP

:: MORE INFORMATION

Citation

MixChIP: a probabilistic method for cell type specific protein-DNA binding analysis.
Rautio S, Lähdesmäki H.
BMC Bioinformatics. 2015 Dec 24;16(1):413. doi: 10.1186/s12859-015-0834-3.

peakANOVA – Stronger Findings from Mass Spectral data through Multi-peak Modeling

peakANOVA

:: DESCRIPTION

peakANOVA is a hierarchical Bayesian model for inferring differences between groups of samples more accurately in metabolomic studies, where the observed compounds are collinear.

::DEVELOPER

Probabilistic Machine Learning

:: SCREENSHOTS

N/a

:: REQUIREMENTS

  • Windows/Linux/MacOsX
  • Java/ R

:: DOWNLOAD

 peakANOVA

:: MORE INFORMATION

Citation

Stronger findings for metabolomics through Bayesian modeling of multiple peaks and compound correlations.
Suvitaival T, Rogers S, Kaski S.
Bioinformatics. 2014 Sep 1;30(17):i461-7. doi: 10.1093/bioinformatics/btu455