SQUID: interpreting sequence-based deep learning models for regulatory genomics

SQUID [1] (Surrogate Quantitative Interpretability for Deepnets) is a Python suite to interpret sequence-based deep learning models for regulatory genomics data with domain-specific surrogate models. To learn more about this approach, please see our manuscript:

[1]

Seitz E, McCandlish D, Kinney J, Koo P. Identifying cis-regulatory mechanisms from genomic deep neural networks using surrogate models. (2023).

SQUID is written for Python and is provided under an MIT open source license. The documentation provided here is meant to help users quickly get SQUID working for their own research needs. Please do not hesitate to contact us with any questions or suggestions for improvements. For technical assistance or to report bugs, please contact Evan Seitz (Email: seitz@cshl.edu). For more general correspondence, please contact Peter Koo (Email: koo@cshl.edu, Twitter: @pkoo562) or Justin Kinney (Email: jkinney@cshl.edu, Twitter: @jbkinney).

Table of Contents

• Installation Instructions
  • SQUID
  • MAVE-NN
  • Example
• Modeling Tutorials
• API Reference
  • squid

Links

• Koo Lab

• Kinney Lab

• Cold Spring Harbor Laboratory

Note

This guide is under developement.