Machine Learning-Guided Engineering of High-Affinity Cross-Reactive Antibodies with Minimal Mutations
Hugo, D.; Grindel, A.-L.; Thenier, F.; Pluchart, C.; Munch, M.; Oliveira, C.; Dubois, S.; Le Drezen, C.; Guerois, R.; Maillere, B.; Truillet, C.; Nozach, H.
Show abstract
Antibodies raised against human targets often fail to recognize their animal orthologs, limiting preclinical evaluation in relevant models. We developed a Deep Mutational Scanning (DMS)-coupled deep learning strategy to engineer potent cross-reactive antibodies with minimal sequence divergence. Starting from C4, a fully human anti-PD-L1 antibody with weak recognition of murine PD-L1, DMS identified substitutions that improved binding to both human and mouse antigens. Conventional recombination of beneficial mutations generated highly cross-reactive antibodies but required 13 to 15 substitutions. To reduce this mutational burden, a deep learning model trained on DMS-derived sequence-binding data was used to identify minimal mutation combinations predicted to retain high affinity. This approach yielded variants carrying only 4 to 5 substitutions, with in vitro and cellular binding properties comparable to highly mutated antibodies. Epitope mapping, structural modeling and in vivo assessment further confirmed that these engineered antibodies retained PD-1/PD-L1 blockade and demonstrated therapeutic activity in a mouse tumor model.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- AlphaBind, a Domain-Specific Model to Predict and Optimize Antibody-Antigen Binding Affinity 96%
- BioPhi: A platform for antibody design, humanization and humanness evaluation based on natural antibody repertoires and deep learning 96%
- Tuning antibody stability and function by rational designs of framework mutations 96%
Similar papers in this journal
- Sequence signatures of two IGHV3-53/3-66 public clonotypes to SARS-CoV-2 receptor binding domain 94%
- Machine Learning Optimization of Candidate Antibodies Yields Highly Diverse Sub-nanomolar Affinity Antibody Libraries 94%
- Engineered Immunogens to Elicit Antibodies Against Conserved Coronavirus Epitopes 94%
Similar papers in this journal
- Ultrapotent and Broad Neutralization of SARS-CoV-2 Variants by Modular, Tetravalent, Bi-paratopic Antibodies 94%
- Deep repertoire mining uncovers ultra-broad coronavirus neutralizing antibodies targeting multiple epitopes 93%
- A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding 93%
Similar papers in this journal
- Massively Multiplexed Affinity Characterization of Therapeutic Antibodies Against SARS-CoV-2 Variants 94%
- Protein language models enable prediction of polyreactivity of monospecific, bispecific, and heavy-chain-only antibodies 94%
- Broadly Reactive Anti-VHH Antibodies for Characterizing, Blocking, or Activating Nanobody-Based CAR-T Cells 93%
Similar papers in this journal
"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.