UnitRefine: A Community Toolbox for Automated Spike Sorting Curation

bioRxiv (Cold Spring Harbor Laboratory)

Abstract

Abstract High-density electrophysiology simultaneously captures the activity from hundreds of neurons, but isolating single-unit activity still relies on slow and subjective manual curation. As datasets keep increasing, this poses a major bottleneck in the field. We therefore developed UnitRefine, a classification toolbox that automates curation by training various machine-learning models directly on human expert annotations. Fully integrated in the SpikeInterface ecosystem, UnitRefine combines established and novel quality metrics, cascading classification and comprehensive hyperparameter search to provide optimized models for different applications. UnitRefine achieves human-level performance across diverse datasets, spanning species, probe types, and laboratories, including recordings from mice, rats, mole rats, primates, and human patients. Applied to a large brain-wide dataset, UnitRefine doubled single unit yield and improved behavioral decoding performance. A streamlined graphical interface allows models to be fine-tuned to new datasets and shared via the Hugging Face Hub, enabling broad adoption and community-driven improvement of automated curation workflows.

Authors 9

1. Anoushka Jain Aachen Systems Neurophysiology Department of Neurobiology

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Institute of Biological Information Processing (IBI-3), Forschungszentrum Jülich

   Systems Neurophysiology, Department of Neurobiology, RWTH Aachen University, Aachen, Germany

2. Chris Halcrow

   University of Edinburgh

   Affiliation as printed

   Centre for Brain Discovery Sciences, Hugh Robson Building, University of Edinburgh, UK

3. Alexander Kleinjohann

   Forschungszentrum Jülich

   Affiliation as printed

   Institute of Advanced Simulations (IAS-6), Forschungszentrum Jülich

4. Federico Spurio

   University of Bonn

   Affiliation as printed

   Institute of Computer Science, University of Bonn

5. Severin Graff Aachen Systems Neurophysiology Department of Neurobiology

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Institute of Biological Information Processing (IBI-3), Forschungszentrum Jülich

   Systems Neurophysiology, Department of Neurobiology, RWTH Aachen University, Aachen, Germany

6. Jüergen Gall

   University of Bonn · TU Dortmund University · Lamarr Institute for Machine Learning and Artificial Intelligence

   Affiliation as printed

   Institute of Computer Science, University of Bonn

   Lamarr Institute for Machine Learning and Artificial Intelligence, Technical University Dortmund

7. Alessio Paolo Buccino

   Allen Institute for Neural Dynamics

   Affiliation as printed

   Allen Institute for Neural Dynamics, Seattle, WA, USA

8. Matthias H. Hennig

   University of Edinburgh

   Affiliation as printed

   Institute for Adaptive and Neural Computation, School of Informatics, The University of Edinburgh, UK

9. Simon Musall corresponding Aachen Systems Neurophysiology Department of Neurobiology

   University of Bonn · Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Institute of Biological Information Processing (IBI-3), Forschungszentrum Jülich

   Institute of Experimental Epileptology and Cognition Research, University of Bonn, Bonn, Germany

   Systems Neurophysiology, Department of Neurobiology, RWTH Aachen University, Aachen, Germany