Figures
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
Citation: (2024) PLoS Computational Biology Issue Image | Vol. 20(3) April 2024. PLoS Comput Biol 20(3): ev20.i03. https://doi.org/10.1371/image.pcbi.v20.i03
Published: April 1, 2024
Copyright: © 2024 . This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
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