Neurotransmitter classification from electron microscopy images at synaptic sites in Drosophila melanogaster. (https://pubmed.ncbi.nlm.nih.gov/38729112/)

These scientists used a special type of microscope to look at the connections between nerve cells in the brain of a fruit fly. They wanted to know if these connections were like a gas pedal (excitatory) or a brake (inhibitory) for the nerve cells. To figure this out, they trained a computer program called an artificial neural network to predict which type of connection it was by looking at pictures taken by the microscope.

The computer program was able to predict with 87% accuracy for individual connections, 94% for whole nerve cells, and 91% for different types of nerve cells in the fruit fly brain. By studying these pictures, the scientists found small but important differences between the different types of connections. They also discovered that nerve cells that grow together tend to use the same type of connection that works quickly.

The scientists hope that by sharing their predictions with other researchers, it will help them come up with new ideas about how the brain of a fruit fly works.

Eckstein N., Bates AS., Champion A., Du M., Yin Y., Schlegel P., Lu AK., Rymer T., Finley-May S., Paterson T., Parekh R., Dorkenwald S., Matsliah A., Yu SC., McKellar C., Sterling A., Eichler K., Costa M., Seung S., Murthy M., Hartenstein V., Jefferis GSXE., Funke J. Neurotransmitter classification from electron microscopy images at synaptic sites in Drosophila melanogaster. Cell. 2024 May 9;187(10):2574-2594.e23. doi: 10.1016/j.cell.2024.03.016.