Insights into the inner workings of transformer models for protein function prediction.

Journal: Bioinformatics (Oxford, England)
Published Date: Mar 4, 2024

Abstract

MOTIVATION: We explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extending the widely used XAI method of integrated gradients such that latent representations inside of transformer models, which were finetuned to Gene Ontology term and Enzyme Commission number prediction, can be inspected too.

Authors

  • Markus Wenzel
    Fraunhofer Heinrich Hertz Institute and Technische Universität Berlin, Berlin 10587, Germany.
  • Erik Grüner
    Department of Artificial Intelligence, Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institut, HHI, Einsteinufer 37, 10587 Berlin, Germany.
  • Nils Strodthoff
    Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany. Author to whom any correspondence should be addressed.

Keywords

External Resources

Popular Topics
Recent Journals