Megaclust: an innovative high throughput data mining approach to identify patterns in large datasets without a-priori knowledge

• Unité de recherche: INNOSUISSE
• Numéro de projet: 13198.1;8 PFFLE-LS
• Titre du projet anglais: Megaclust :an innovative high throughput data mining approach to identify patterns in large datasets without a-priori knowledge

Description succincte (Anglais)

Megaclust :an innovative high throughput data mining approach to identify patterns in large datasets without a-priori knowledge

Description succincte (Français)

Megaclust: an innovative high throughput data mining approach to identify patterns in large datasets without a-priori knowledge

Résumé des résultats (Abstract) (Anglais)

One emerging challenge of the digital era is the ability to cope with an ever increasing amount of data and identifying within it recurrent patterns, without preconceived knowledge about its structure. MegaClust is a toolbox that has been created over the last years at the Swiss Institute of Bioinformatics (SIB) and has been applied successfully to identify patterns in biological data obtained from high throughput platforms. This project intends to further develop and transform our research technology into a marketable product by providing a domain specific application of MegaClust for the automated analysis of flow cytometry data (FACS) for the pharma/biotech and Contracting Research Organizations (CROs) involved in the characterization and stratifications of drug responses in clinical trials.

Résumé des résultats (Abstract) (Français)

One emerging challenge of the digital era is the ability to cope with an ever increasing amount of data and identifying within it recurrent patterns, without preconceived knowledge about its structure. MegaClust is a toolbox that has been created over the last years at the Swiss Institute of Bioinformatics (SIB) and has been applied successfully to identify patterns in biological data obtained from high throughput platforms. This project intends to further develop and transform our research technology into a marketable product by providing a domain specific application of MegaClust for the automated analysis of flow cytometry data (FACS) for the pharma/biotech and Contracting Research Organizations (CROs) involved in the characterization and stratifications of drug responses in clinical trials.