NanoNet: Rapid end-to-end nanobody modeling by deep learning at sub angstrom resolution
Cohen, T.; Halfon, M.; Schneidman-Duhovny, D.
Show abstract
Antibodies are a rapidly growing class of therapeutics. Recently, single domain camelid VHH antibodies, and their recognition nanobody domain (Nb) appeared as a cost-effective highly stable alternative to full-length antibodies. There is a growing need for high-throughput epitope mapping based on accurate structural modeling of the variable domains that share a common fold and differ in the Complementarity Determining Regions (CDRs). We develop a deep learning end-to-end model, NanoNet, that given a sequence directly produces the 3D coordinates of the C[a] atoms of the entire VH domain. For the Nb test set, NanoNet achieves 1.7[A] overall average RMSD and 3.0[A] average RMSD for the most variable CDR3 loops. The accuracy for antibody VH domains is even higher: overall average RMSD < 1[A] and 2.2[A] RMSD for CDR3. NanoNet runtimes allow generation of ~1M nanobody structures in less than an hour on a standard CPU computer enabling high-throughput structure modeling.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Deep learning assessment of nativeness and pairing likelihood for antibody and nanobody design with AbNatiV2 95%
- Tuning antibody stability and function by rational designs of framework mutations 95%
- AbDesign: Database of point mutants of antibodies with associated structures reveals poor generalization of binding predictions from machine learning models. 95%
Similar papers in this journal
- Predicting structures of large protein assemblies using combinatorial assembly algorithm and AlphaFold2 96%
- US-align: Universal Structure Alignments of Proteins, Nucleic Acids, and Macromolecular Complexes 95%
- Sliding Window INteraction Grammar (SWING): a generalized interaction language model for peptide and protein interactions 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.