EvoSeq-ML: Advancing Data-Centric Machine Learning with Evolutionary-Informed Protein Sequence Representation and Generation
Mehrsa Mardikoraem, Nathaniel Pascual, Joelle N. Eaves, Shramana Chatterjee, Anton Mahama, Patrick Finneran, Robert P. Hausinger, Daniel Woldring
This paper evaluates an ancestral sequence reconstruction-informed data augmentation strategy for improving protein sequence generation and representation learning, showing improved thermostability in generated variants.
bioRxiv · Oct 2, 2024 · PreprintBioinformatics