Karthikdevan (Talk | contribs) |
Karthikdevan (Talk | contribs) |
||
Line 11: | Line 11: | ||
<h2>Team IISc-Bangalore: A Machine Learning Algorithm for Cell Counting</h2> | <h2>Team IISc-Bangalore: A Machine Learning Algorithm for Cell Counting</h2> | ||
Team IISc worked towards developing a machine learning algorithm to count cells in a hemocytometer.<br> | Team IISc worked towards developing a machine learning algorithm to count cells in a hemocytometer.<br> | ||
− | The objective of the collaboration was to provide the IISc Team with sufficient data on the growth curve characteristics of <i>Saccharomyces cerevisiae</i> to enable them to train their machine learning algorithm. | + | The objective of the collaboration was to provide the IISc Team with sufficient data on the growth curve characteristics of <i>Saccharomyces cerevisiae</i> to enable them to train their machine learning algorithm. Optical Density(OD) measurements to monitor the growth curve becomes unreliable due to the large sizes of yeast cells (which distorts the linear correlation between OD and biomass), it was necessary to measure the cell count of yeast cultures. Haemocytometry is the most common method used to monitor the growth rate and biomass of yeast cultures. This process is very time-consuming and involves tedious labour in counting cells for each measurement. Our team performed two growth curves each spanning 16 hours and the images were generated which were to be used by their algorithm to analyze. Using Haemocytometry, a manual cell count of the yeast cell samples at each timepoint was performed and this data along with their corresponding images were submitted. |
Read more at <a href="https://2017.igem.org/Team:IISc-Bangalore/Collaborations#haemocytometry">Team IISc-Bangalore's wiki</a> | Read more at <a href="https://2017.igem.org/Team:IISc-Bangalore/Collaborations#haemocytometry">Team IISc-Bangalore's wiki</a> |
Latest revision as of 02:48, 31 October 2017
Collaborations
Team IISc-Bangalore: A Machine Learning Algorithm for Cell Counting
Team IISc worked towards developing a machine learning algorithm to count cells in a hemocytometer.The objective of the collaboration was to provide the IISc Team with sufficient data on the growth curve characteristics of Saccharomyces cerevisiae to enable them to train their machine learning algorithm. Optical Density(OD) measurements to monitor the growth curve becomes unreliable due to the large sizes of yeast cells (which distorts the linear correlation between OD and biomass), it was necessary to measure the cell count of yeast cultures. Haemocytometry is the most common method used to monitor the growth rate and biomass of yeast cultures. This process is very time-consuming and involves tedious labour in counting cells for each measurement. Our team performed two growth curves each spanning 16 hours and the images were generated which were to be used by their algorithm to analyze. Using Haemocytometry, a manual cell count of the yeast cell samples at each timepoint was performed and this data along with their corresponding images were submitted. Read more at Team IISc-Bangalore's wiki
ChassiDex: Feedback and data contribution by Team INSA-UPS France
Team INSA-UPS_France has worked with 3 diverse organisms for their project and we are very grateful to them for filling up the data for Komagataella Pichia pastoris SMD1168H and Vibrio harveyi JMH626 in our database, ChassiDex. They also provided us feedback on the user experience. They said:"Every important informations are required so I found it well-made. Our team would have definitely liked having this tool when we started this project."
Read their side of the story at Team INSA-UPS_France's wiki