SpikeInterface/spikeinterface

A Python-based module for creating flexible and robust spike sorting pipelines.

What it solves

SpikeInterface provides a unified Python framework for spike sorting, which is the process of identifying and separating individual neural action potentials (spikes) from extracellular electrophysiology recordings. It eliminates the need for researchers to manually switch between disparate, incompatible spike sorting tools and file formats.

How it works

It acts as a comprehensive interface that wraps existing spike sorting technologies and algorithms into a single codebase. It allows users to read and write various extracellular file formats, pre-process recordings, and run multiple popular sorters (such as Kilosort, MountainSort, and in-house tools like Lupin) through a consistent API. The framework also includes tools for post-processing, quality metric computation, benchmarking, and motion/drift correction.

Who it’s for

Neuroscientists and researchers working with extracellular electrophysiology data who need to process, sort, and curate neural spike data using various algorithms and tools.

Highlights

  • Unified API: Access multiple semi-automatic spike sorters and in-house algorithms from one place.
  • Containerized Execution: Run popular sorters via Docker or Singularity without needing local installation.
  • Comprehensive Pipeline: Covers the entire workflow from reading raw files and pre-processing to post-processing and curation.
  • Validation Tools: Includes quality metrics and benchmarking capabilities to validate sorting outputs.
  • Flexible Curation: Supports ML-based, metrics-based, and manual curation strategies.

Related

  • Project
    nipy/nipype

    A Python project that provides a uniform interface to various neuroimaging software packages, allowing researchers to create integrated and reproducible processing pipelines.

  • Project
    sktime/sktime

    A Python library providing a unified interface for time series analysis, including forecasting, classification, and anomaly detection, compatible with the scikit-learn ecosystem.

  • Project
    hyperactive-project/Hyperactive

    A unified Python interface for hyperparameter tuning and black-box optimization that separates optimization problems from algorithms across multiple backends.

  • Project
    huggingface/transformers

    A model-definition framework providing a unified API to access, train, and deploy state-of-the-art pretrained models across text, vision, audio, and multimodal domains.

  • Project
    fangwei123456/spikingjelly

    SpikingJelly is a PyTorch‑based library for building, training, and deploying spiking neural networks, offering multiple performance back‑ends, large‑scale training tools, neuromorphic dataset loaders, and export to hardware formats.