Difference between revisions of "Team:Marburg/Collaborations"

Line 131: Line 131:
 
               <section class="section">
 
               <section class="section">
 
                 <h2 class="subtitle">The Colony picture Collaboration</h2>
 
                 <h2 class="subtitle">The Colony picture Collaboration</h2>
                 <div style="display: flex; flex-direction: row;">
+
                 <figure Style="float:left; margin-right: 25px;">
                  <figure Style="float:left; margin-right: 25px;">
+
                  <img style="height: 65ex; width: 50ex"
                    <img style="height: 65ex; width: 50ex"
+
                    src=https://static.igem.org/mediawiki/2019/5/5e/T--marburg--colony_picking_2.jpeg
                      src=https://static.igem.org/mediawiki/2019/5/5e/T--marburg--colony_picking_2.jpeg
+
                    alt="Bild von Roboter Platzhalter">
                      alt="Bild von Roboter Platzhalter">
+
                  <figcaption>
                    <figcaption>
+
                    Figure 1: Pipetting Robot (OT-2) colony picking set up.
                      Figure 1: Pipetting Robot (OT-2) colony picking set up.
+
                  </figcaption>
                    </figcaption>
+
                </figure>
                  </figure>
+
                <p style="margin-bottom: 25px;">
                  <div>
+
                  Many repetitive tasks in the lab cost time such as pipetting or picking colonies from agar plates and
                    <p style="margin-bottom: 25px;">
+
                  could technically be performed by robots. We used Opentrons OT-2 as a platform and designed hardware
                      Many repetitive tasks in the lab cost time such as pipetting or picking colonies from agar plates
+
                  modules and scripts to outsource these tasks. Thereby, we can now offer the Opentrons user community
                      and
+
                  an automated pipeline to streamline laboratory practices in ways that haven’t been possible before.
                      could technically be performed by robots. We used Opentrons OT-2 as a platform and designed
+
                </p>
                      hardware
+
                <p>
                      modules and scripts to outsource these tasks. Thereby, we can now offer the Opentrons user
+
                  For the software we decided to use an artificial intelligence (AI). Artificial intelligences however
                      community
+
                  rely on huge data sets to learn their specific task to perfection. In our case, we chose pictures of
                      an automated pipeline to streamline laboratory practices in ways that haven’t been possible
+
                  agar plates with colonies of E. coli as a suitable training set. Our experiments resulted in a big
                      before.
+
                  amount of agar plates but it was clear to us pretty quickly that we could never reach a big enough
                    </p>
+
                  data set just by making photos of our own plates to get an AI with an adequate performance. To achieve
                    <p>
+
                  this goal, we launched the Colony picture collaboration. We asked other iGEM Teams if they could
                      For the software we decided to use an artificial intelligence (AI). Artificial intelligences
+
                  provide us pictures of their agar plates with E. coli colonies with which we can then train the robot.
                      however
+
                  In order to do that we published a script on how to take the ictures. We made the script as precise as
                      rely on huge data sets to learn their specific task to perfection. In our case, we chose pictures
+
                  possible to make sure that the data set was as consistent as possible.
                      of
+
                </p>
                      agar plates with colonies of E. coli as a suitable training set. Our experiments resulted in a big
+
                      amount of agar plates but it was clear to us pretty quickly that we could never reach a big enough
+
                      data set just by making photos of our own plates to get an AI with an adequate performance. To
+
                      achieve
+
                      this goal, we launched the Colony 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 ictures. We made the script as
+
                      precise as
+
                      possible to make sure that the data set was as consistent as possible.
+
                    </p>
+
                  </div>
+
                </div>
+
 
                 <figure Style="text-align:center">
 
                 <figure Style="text-align:center">
 
                   <img style="height: 50ex; width: 75ex"
 
                   <img style="height: 50ex; width: 75ex"
Line 180: Line 167:
 
                   Following this, we built a website so they could label the colonies on their images online.
 
                   Following this, we built a website so they could label the colonies on their images online.
 
                 </p>
 
                 </p>
                <br>
 
 
                 <figure Style="text-align:center">
 
                 <figure Style="text-align:center">
 
                   <img style="height: 50ex; width: 80ex"
 
                   <img style="height: 50ex; width: 80ex"
Line 189: Line 175:
 
                   </figcaption>
 
                   </figcaption>
 
                 </figure>
 
                 </figure>
                <br>
+
                 <p>
                 <p> In total 250 colony pictures were added to our data set, vastly increasing the performance of
+
                  In total 250 colony pictures were added to our data set, vastly increasing the performance of our AI
                  our AI in
+
                   in detecting colonies. As an incentive to participate in this collaboration we gave away prizes to the
                   detecting colonies.
+
                  teams that sent us their pictures, they received a small surprise, an E. coli plushie. The three teams
                  As an incentive to participate in this collaboration we gave away prizes to the teams that sent
+
                  that sent us the most pictures got an engraved trophy out of glass thanks to our sponsor of this
                  us their
+
                  collaboration, Doulix.
                  pictures, they received a small surprise, an E. coli plushie. The three teams that sent us the
+
                  most pictures got
+
                  an engraved trophy out of glass thanks to our sponsor of this collaboration, Doulix.
+
                </p>
+
 
                 </p>
 
                 </p>
 
               </section>
 
               </section>

Revision as of 20:10, 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