by Liset M de la Prida

Our lab is now in Github, where you can find our codes and developments for open neuroscience. This includes:

• CNN-ripple: a 1D convolutional neural network (CNN) operating over high-density LFP recordings to detect hippocampal SWR both offline and online. It works with recordings from several types of probes (e.g. linear arrays, high-density probes, ultradense Neuropixels) (Navas-Olive, Amaducci et al. eLife 2022). You can access to the original code in Python. We also have another version for Matlab.
• CNN-ripple-plugin: which allows the use of CNN-ripple as a real-time detection tool as part of the Open Ephys platform.
• rippl-AI: an open toolbox of Artifical Intelligence (AI) resources for detection of hippocampal neurophysiological signals, in particular SWR. This toolbox offers multiple successful plug-and-play machine learning (ML) models from 5 different architectures (1D-CNN, 2D-CNN, LSTM, SVM and XGBoost) that are ready to use to detect SWRs in hippocampal recordings. Moreover, there is an additional package that allows easy re-training, so that models are updated to better detect particular features of your own recordings (Navas-Olive, Rubio et al., biorxiv).
• Topological-SWR: a pipeline of the topological analysis of sharp-wave ripples (SWR) as published in Sebastian et al., Nat Neu 2023.
• Structure Index (SI): a graph-based topological metric to quantify the amount of structure present at the distribution of a given feature over a point cloud in an arbitrary D-dimensional space (Sebastian, Esparza and de la Prida, biorxiv 2024).