nanoFOLD : sequence design of nanobodies via inverse folding
Chomicz, D.; Janusz, B.; Wrobel, S.; Dudzic, P.; Polasa, A.; Martin, K.; Darnell, S.; Comeau, S. R.; Krawczyk, K.
Show abstract
Antibodies devoid of light chains are a promising class of biotherapeutics. Computational methods that address these molecules are crucially needed to accelerate the traditional, long and expensive experimental process of their discovery. Inverse folding, wherein one is tasked to predict a sequence given molecular coordinates, is an established method in scaffold-based protein design. Here we develop an inverse folding method speci[fi]c to nanobodies. We demonstrate its application in nanobody-engineering scenarios of enriching binders from next-generation sequencing experiments and novel binder design.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- AbDesign: Database of point mutants of antibodies with associated structures reveals poor generalization of binding predictions from machine learning models. 96%
- NAStructuralDB : Structural database to facilitate computational studies of molecular modeling and recognition of proteins with special focus on antibody-antigen interactions. 95%
- Prediction of Antibody Non-Specificity using Protein Language Models and Biophysical Parameters 95%
Similar papers in this journal
- ParaSurf: A Surface-Based Deep Learning Approach for Paratope-Antigen Interaction Prediction 96%
- Paragraph - Antibody paratope prediction using Graph Neural Networks with minimal feature vectors 95%
- Learning Context-aware Structural Representations to Predict Antigen and Antibody Binding Interfaces 95%
Similar papers in this journal
- Guiding a language-model based protein design method towards MHC Class-I immune-visibility profiles for vaccines and therapeutics 96%
- DoggifAI: a transformer based approach for antibodycaninisation 95%
- Structural pre-training improves physical accuracy of antibody structure prediction using deep learning. 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.