Computational Antibody Papers

Filter by tags
binding prediction
Filter by published year
2025
TitleKey points

  • 2025-03-21

    Nanobody engineering: computational modelling and design for biomedical and therapeutic applications

    • binding prediction
    • nanobodies
    • Review on computational methods applied to nanobodies.
    • The review covers databases, modeling and design methods.
    • Much room is given to conformational sampling with molecular dynamics
    • They highlight a special class of nanobodies, quench-bodies (Q-bodies) that can also detect small molecules alongside normal proteins.
    • The focus presented is chiefly on binder design, rather than fine-tuning other biophysical properties.

  • 2025-03-11

    AntiBinder: utilizing bidirectional attention and hybrid encoding for precise antibody–antigen interaction prediction

    • binding prediction
    • Using language models & structural predictions to predict antibody-antigen interactions.
    • AntiBinder integrates sequence and structural information using IgFold for antibodies and ESM-2 for antigens, employing specialized encoders to extract meaningful features before passing them through multiple Bidirectional Attention Blocks (BidAttBlock) and a classifier.
    • The model was trained and evaluated on four datasets: COVID-19 (Cov-AbDab), HIV (LANL database), BioMap, and MET. These datasets contain antigen–antibody interaction pairs across multiple species and applications, covering viruses like SARS-CoV-2 and HIV, plenty of antigenic variants in total.
    • AntiBinder was benchmarked against 11 state-of-the-art models, including AttABseq, DG-affinity, DeepAAI, and general protein–protein interaction (PPI) models. AntiBinder did better.
    • Authors test the generalizability but chiefly within antigenic species, such as different covid variants or HIV mutants.

  • 2025-02-20

    A comparison of antibody–antigen complex sequence-to-structure prediction methods and their systematic biases

    • binding prediction
    • Benchmark of antibody-antigen docking and co-folding methods.
    • Methods compared were AF2-multimer, RoseTTAfold, AbAdapt, SnugDock and ClusPro.
    • ClusPro was given either AlphaFold or AbodyBuilder2 models of an antibody - it performed better when given ABodyBuilder2 models.
    • AlphaFOld multimer performed the best overall - however the top pose being close to correct only 19% of the time.
    • It appears that the best models reproduce correct side-chain binding geometries from the PDB.

  • 2025-02-17

    DyAb: sequence-based antibody design and property prediction in a low-data regime

    • binding prediction
    • language models
    • Method to employ low-N data for biologic engineering.
    • Assuming we have a dataset of ~100 affinity data points, we can choose (100 choose 2) pairs where we know which one has a larger readout than the other (e.g. stronger affinity) giving combinatorially larger amount of data points to train on.
    • The architecture used is CNN on top of a language model.
    • Benchmarked on three internal campaigns, Il6, EGFR and an undisclosed target.

  • 2025-02-03

    De novo design of epitope-specific antibodies against soluble and multipass membrane proteins with high specificity, developability, and function

    • binding prediction
    • generative methods
    • Novel method to design antibodies in silico with experimental validation.
    • The actual computational method is not disclosed.
    • The computational method takes target sequence/structure and constraints where the antibody should bind. The structure and sequence are then produced.
    • Method can generate nanomolar grade binders.
    • The main interesting take-away is test-time compute. By feeding the answers of the model back to itself, it produces better binders and does not compromise on diversity of the designs.

  • 2025-01-21

    Antibody affinity engineering using antibody repertoire data and machine learning

    • binding prediction
    • ngs
    • Novel experimental/computational workflow that demonstrates how little data might be needed to develop antibody affinity predictors.
    • Mice were immunized with hen egg white lysozyme and via computational procedure of clustering with known binders 35 antibodies were characterized together with their affinities.
    • These 35 antibodies were used to train the methods: Gaussian Process (GP) models with Matern and RBF kernels, Kernel Ridge Regression (KRR), Random Forest (RF) and Linear Regression (used as a baseline).
    • Seed sequences were point or double-mutated and their affinity predicted using GP (that performed the best). Eight mutants predicted to span the whole range of affinities were selected for experimental testing and they had very good agreement with the predictions.