101. Insights into the inner workings of transformer models for protein function prediction.
- Author
-
Wenzel, Markus, Grüner, Erik, and Strodthoff, Nils
- Subjects
- *
TRANSFORMER models , *PROTEIN models , *NERVE tissue proteins , *AMINO acid sequence , *ARTIFICIAL intelligence , *ARTIFICIAL membranes , *SYNTHETIC biology - 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. Results The approach enabled us to identify amino acids in the sequences that the transformers pay particular attention to, and to show that these relevant sequence parts reflect expectations from biology and chemistry, both in the embedding layer and inside of the model, where we identified transformer heads with a statistically significant correspondence of attribution maps with ground truth sequence annotations (e.g. transmembrane regions, active sites) across many proteins. Availability and Implementation Source code can be accessed at https://github.com/markuswenzel/xai-proteins. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF