Machine learning can help identify cell shapes asociated with complex cell behaviors

Wolfgang Losert (IPST/Physics) et al. published an article, “The social shape of sperm: using an integrative machine-learning approach to examine sperm ultrastructure and collective motility”, in the September 22 edition of Proceedings of The Royal Society B.

In their study, the researchers used machine learning to identify characteristics of shape and proportion that are associated with certain swimming behaviors in the sperm of several species of mice.  Sperm are typically solitary swimmers, but in some species, they aggregate and swim as a group.  Their findings advance our understanding of how even subtle variation in sperm design can drive differences in sperm function and performance.

"This work highlights the importance of data analytics experts and subject matter experts working together to break down barriers between fields and push the boundaries of knowledge," said Losert.