Janusz, B. | Search bioRxiv

bioRxiv2024

nanoBERT: A deep learning model for gene agnostic navigation of the nanobody mutational space

Nanobodies are a subclass of immunoglobulins, whose binding site consists of only one peptide chain, bestowing favorable biophysical properties. Recently, the first nanobody therapy was approved, paving the way for further clinical applications of this antibody format. Further development of nanobody-based therapeutics could be streamlined by computational methods. One of such methods is infilling - positional prediction of biologically feasible mutations in nanobodies. Being able to identify possible positional substitutions based on sequence context, facilitates functional design of such molecules. Here we present nanoBERT, a nanobody-specific transformer to predict amino acids in a given position in a query sequence. We demonstrate the need to develop such machine-learning based protocol as opposed to gene-specific positional statistics since appropriate genetic reference is not available. We benchmark nanoBERT with respect to human-based language models and ESM-2, demonstrating the benefit for domain-specific language models. We also demonstrate the benefit of employing nanobody-specific predictions for fine-tuning on experimentally measured thermostability dataset. We hope that nanoBERT will help engineers in a range of predictive tasks for designing therapeutic nanobodies. Availabilityhttps://huggingface.co/NaturalAntibody/

bioinformatics↗

bioRxiv2022

Structural pre-training improves physical accuracy of antibody structure prediction using deep learning.

Protein folding problem obtained a practical solution recently, owing to advances in deep learning. There are classes of proteins though, such as antibodies, that are structurally unique, where the general solution still lacks. In particular, the prediction of the CDR-H3 loop, which is an instrumental part of an antibody in its antigen recognition abilities, remains a challenge. Antibody-specific deep learning frameworks were proposed to tackle this problem noting great progress, both on accuracy and speed fronts. Oftentimes though, the original networks produce physically implausible bond geometries that then need to undergo a time-consuming energy minimization process. Here we hypothesized that pre-training the network on a large, augmented set of models with correct physical geometries, rather than a small set of real antibody X-ray structures, would allow the network to learn better bond geometries. We show that fine-tuning such a pre-trained network on a task of shape prediction on real X-ray structures improves the number of correct peptide bond distances. We further demonstrate that pre-training allows the network to produce physically plausible shapes on an artificial set of CDR-H3s, showing the ability to generalize to the vast antibody sequence space. We hope that our strategy will benefit the development of deep learning antibody models that rapidly generate physically plausible geometries, without the burden of time-consuming energy minimization.

bioinformatics↗