Classifier Prediction

Cell Type Prediction

This feature allows you to predict and annotate a Patch-Seq defined cell type to a cell with specific electrophysiological features.
If you experience any issues in your current browser, please switch to Chrome (testet with Version 126.0.6478.127)
BPEs Cell Type Prediction Feature allows you to predict the classification of a given cell based on its electrophysiological properties. Therefore, please choose a csv-file where each row represents a single cell and columns represent specific features (e.g. Action Potential Amplitude in mV). Then click Upload CSV. Based on your uploaded data, automated name-matching from your feature names to the classifier features will be provided. If the names of the features are different, you can add manual mappings. Please be aware of the individual definitions of each feature that you can find listed here. Demo Data can be downloaded from here.
Please select a tissue type (only cortex is supported yet)

1. Upload CSV

Please upload a CSV file

2. Feature Mapping

3. Classification

Please be aware that the displayed results represent predictions and must be interpreted with caution. We are more than happy to individually discuss the data and results with you and would be very happy if you would share the data with us to improve the classifier performance. Please do not hesitate to reach out to david.zimmermann@i-med.ac.at.