Scientists Identify Brain Cells Linked to Depression for the First Time

Boston University researchers have developed PhysMAP, a machine learning tool that identifies specific brain cell types linked to psychiatric disorders using only electrical recordings from living brains, without requiring genetic engineering. The tool can distinguish neurons like parvalbumin-positive cells implicated in schizophrenia and somatostatin-positive cells linked to major depressive disorder by analyzing unique electrical signatures. Trained on seven public datasets using optotagging techniques, PhysMAP addresses circuitopathies—disorders stemming from dysfunctional interactions between specific cell types rather than overall brain activity. The technology could eventually work alongside clinical electrodes like Neuropixels to help doctors diagnose cellular causes of psychiatric symptoms and select more effective treatments, providing a roadmap for targeted, next-generation psychiatric therapies.

PhysMAP: A Machine Learning Tool for Identifying Neuron Types

• ▪PhysMAP separates the voices of individual cell types within a crowd of electrical noise by combining several complementary features of each type's electrical signature.
• ▪PhysMAP can identify cell types in living brains using only electrical recordings without requiring genetic engineering.
• ▪PhysMAP is a machine learning tool that can distinguish between different types of neurons based solely on their unique electrical signatures.
• ▪PhysMAP identifies specific neuron types like parvalbumin or somatostatin cells by combining multiple electrical signatures.
• ▪PhysMAP multimodal representations are better aligned with known transcriptomically-defined cell types than any single modality alone.

Applications to Psychiatric Disorders and Circuitopathies

• ▪Circuitopathies include human diseases such as schizophrenia, major depressive disorder, and some forms of epilepsy.
• ▪PhysMAP can identify somatostatin-positive cells implicated in major depressive disorder.
• ▪PhysMAP can identify parvalbumin-positive cells implicated in schizophrenia and Dravet syndrome.
• ▪PhysMAP can identify cells implicated in psychiatric disorders such as schizophrenia and major depressive disorder directly from in vivo recordings.

Methodology Using Open Data and Optotagging

• ▪PhysMAP was trained and validated using seven public datasets.
• ▪Optotagging is a technique that combines molecular engineering with optical tools to tie electrical activity to specific cell types.
• ▪The Boston University team used optotagging datasets to train PhysMAP to learn the unique electrical signatures of different cell types.
• ▪PhysMAP can be used to iteratively detect batch effects which confound classification.
• ▪Once learned, PhysMAP mapping can be applied to new datasets where optotagging was not available, enabling the simultaneous study of multiple cell types.
• ▪The Boston University research team used seven open datasets that contained both the electrical activity of single neurons and their cell type identities.

Clinical Potential and Future Therapeutic Applications

• ▪A previous version of PhysMAP called WaveMAP was deployed to identify cell types in the very first human recordings with Neuropixels.
• ▪PhysMAP allows scientists to study how specific neural circuits fail in real-time, providing a roadmap for targeted, next-generation psychiatric therapies.
• ▪Information about cell type dysfunction identified by PhysMAP can be used to inform the development of future therapeutic strategies.
• ▪Neuropixels is a type of high-density electrode now considered the standard in neuroscience.
• ▪Chandramouli Chandrasekaran is an assistant professor of anatomy & neurobiology and psychological and brain sciences at Boston University.

2 sources