ABodyBuilder3: improved and scalable antibody structure predictions.
| Autor: | Kenlay H; Exscientia, Oxford OX4 4GE, United Kingdom., Dreyer FA; Exscientia, Oxford OX4 4GE, United Kingdom., Cutting D; Exscientia, Oxford OX4 4GE, United Kingdom., Nissley D; Exscientia, Oxford OX4 4GE, United Kingdom., Deane CM; Exscientia, Oxford OX4 4GE, United Kingdom.; Department of Statistics, University of Oxford, Oxford OX1 3LB, United Kingdom. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Bioinformatics (Oxford, England) [Bioinformatics] 2024 Oct 01; Vol. 40 (10). |
| DOI: | 10.1093/bioinformatics/btae576 |
| Abstrakt: | Summary: In this article, we introduce ABodyBuilder3, an improved and scalable antibody structure prediction model based on ABodyBuilder2. We achieve a new state-of-the-art accuracy in the modelling of CDR loops by leveraging language model embeddings, and show how predicted structures can be further improved through careful relaxation strategies. Finally, we incorporate a predicted Local Distance Difference Test into the model output to allow for a more accurate estimation of uncertainties. Availability and Implementation: The software package is available at https://github.com/Exscientia/ABodyBuilder3 with model weights and data at https://zenodo.org/records/11354577. (© The Author(s) 2024. Published by Oxford University Press.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|