Skip to main content
Advertisement
  • Loading metrics

PLoS Computational Biology Issue Image | Vol. 20(3) April 2024

A Combination of machine learning and structure-based protein design enables the prediction and engineering of post-translational modifications.

Post-translational modifications of proteins can have high impact on their structure, function, half-life, and many more. Considering the prediction and design of typical post-translational modifications such as N-linked or O-linked glycosylation during protein design is now possible through our integration of machine learning models in the Rosetta software suite. For N-linked glycosylation, we added structural features to the machine learning model to improve likelihood of glycan presence. Post-translational modifications can now actively be included or removed while designing the proteins sequence. Ertelt et al 2024

Image Credit: Moritz Ertelt

thumbnail
A Combination of machine learning and structure-based protein design enables the prediction and engineering of post-translational modifications.

Post-translational modifications of proteins can have high impact on their structure, function, half-life, and many more. Considering the prediction and design of typical post-translational modifications such as N-linked or O-linked glycosylation during protein design is now possible through our integration of machine learning models in the Rosetta software suite. For N-linked glycosylation, we added structural features to the machine learning model to improve likelihood of glycan presence. Post-translational modifications can now actively be included or removed while designing the proteins sequence. Ertelt et al 2024

Image Credit: Moritz Ertelt

https://doi.org/10.1371/image.pcbi.v20.i03.g001