Difference between revisions of "Team:Marburg/Collaborations"

Line 145: Line 145:
 
                   an automated pipeline to streamline laboratory practices in ways that haven’t been possible before.
 
                   an automated pipeline to streamline laboratory practices in ways that haven’t been possible before.
 
                 </p>
 
                 </p>
                <br>
+
                 <p>
                 <p> For the software we decided to use an artificial intelligence (AI). Artificial intelligences
+
                  For the software we decided to use an artificial intelligence (AI). Artificial intelligences however
                   however rely on
+
                   rely on huge data sets to learn their specific task to perfection. In our case, we chose pictures of
                  huge data sets to learn their specific task to perfection. In our case, we chose pictures of
+
                   agar plates with colonies of E. coli as a suitable training set. Our experiments resulted in a big
                   agar plates with
+
                  amount of agar plates but it was clear to us pretty quickly that we could never reach a big enough
                  colonies of E. coli as a suitable training set. Our experiments resulted in a big amount of agar
+
                  data set just by making photos of our own plates to get an AI with an adequate performance. To achieve
                  plates but it
+
                  this goal, we launched the Colony picture collaboration. We asked other iGEM Teams if they could
                  was clear to us pretty quickly that we could never reach a big enough data set just by making
+
                  provide us pictures of their agar plates with E. coli colonies with which we can then train the robot.
                  photos of our own
+
                  In order to do that we published a script on how to take the ictures. We made the script as precise as
                  plates to get an AI with an adequate performance. To achieve this goal, we launched the Colony
+
                  possible to make sure that the data set was as consistent as possible.
                  picture
+
                  collaboration. We asked other iGEM Teams if they could provide us pictures of their agar plates
+
                  with E. coli
+
                  colonies with which we can then train the robot. In order to do that we published a script on
+
                  how to take the
+
                  pictures. We made the script as precise as possible to make sure that the data set was as
+
                  consistent as
+
                  possible.
+
 
                 </p>
 
                 </p>
 
                 <br> <br> <br> <br>
 
                 <br> <br> <br> <br>

Revision as of 20:06, 21 October 2019

C O L L A B O R A T I O N S


Through this iGEM year we interacted with so many iGEM Teams all around the world. It was a pleasure working with all the different teams and learn from each other. We got so many impressions about other projects and hope we could help with our collaborations. A huge Thank you for every team collaboration!


C O L O N Y
P I C T U R E S


In our colony picking collaboration we asked other iGEM teams to supply us with data for our picking algorithm. Thanks to this group effort we could build our colony picking unit.

T H EAG O L D E NAG A T E

C O L L A B O R A T I O N


B E R L I N / D E L F T


U CAD A V I S


U F L O R I D A


I N T E R A C T I O N S

W I T H

O T H E RAT E A M S


M E E T U P S