Shannon Seminar Room (a105) Place du Levant 3, Maxwell Building, 1st floor -- Wednesday, 17 September 2014 at 10:00 (45 min.)
{
"name":"Spectral clustering techniques for biological data",
"description":"Earlier biological studies have shown a strong correlation between the structure of the nucleolus of a cell and the potential diseases affecting this cell. The biologist have generated a database by annihilating some specific genes of the cells and they have visually observed different conformations of the nucleolus. They are interested in grouping (clustering) the cells based on the conformation of their nucleolus. During this presentation, the spectral clustering techniques will be presented and applied on the biological data. After an image analysis processing, each cell is represented by a characteristics' vector. Those vectors are used to build a similarity matrix. The spectral graph theory is then performed to cluster the data. Results on both artificial and real data will be discuss.",
"startDate":"2014-09-17",
"endDate":"2014-09-17",
"startTime":"10:00",
"endTime":"10:45",
"location":"Shannon Seminar Room (a105) Place du Levant 3, Maxwell Building, 1st floor",
"label":"Add to my Calendar",
"options":[
"Apple",
"Google",
"iCal",
"Microsoft365",
"MicrosoftTeams",
"Outlook.com"
],
"timeZone":"Europe/Berlin",
"trigger":"click",
"inline":true,
"listStyle":"modal",
"iCalFileName":"Seminar-Reminder"
}
Earlier biological studies have shown a strong correlation between the structure of the nucleolus of a cell and the potential diseases affecting this cell. The biologist have generated a database by annihilating some specific genes of the cells and they have visually observed different conformations of the nucleolus. They are interested in grouping (clustering) the cells based on the conformation of their nucleolus. During this presentation, the spectral clustering techniques will be presented and applied on the biological data. After an image analysis processing, each cell is represented by a characteristics' vector. Those vectors are used to build a similarity matrix. The spectral graph theory is then performed to cluster the data. Results on both artificial and real data will be discuss.
