Computational Antibody Papers

Filter by tags
All
Filter by published year
All
TitleKey points
    • Authors describe how using a structure predictor one can re-design the binding site, to maintain binding.
    • They use a proprietary GaluxDesign method, the method achieves 1.4 Å Ca RMSD in predicting CDR-H3 loop structures, leveraging a unique scoring metric (G-pass rate) that assesses both confidence and structural consistency for antibody design.
    • The method outperforms AlphaFold 2.3, ABlooper, and ImmuneBuilder in predicting CDR-H3 loop structures, with significantly lower RMSD values (1.4 Å compared to 2.4-3.7 Å), particularly on a more challenging, time-separated dataset.
    • The binding propensity to HER2 was evaluated using a large mutant library and calculated via the G-pass rate, outperforming AlphaFold's PAE-based scoring. The model showed strong discrimination with an AUROC of 0.758, compared to 0.529 for AlphaFold. The novel loop is scored using their metric (G-pass rate) in complex with Her2.
    • Novel antibody sequences were designed by predicting six CDR loops in antibody-protein complexes, using GaluxDesign models. These designs were experimentally tested, achieving high success rates, including a 13.2% success rate for HER2 antibody designs using yeast display methods.
    • Authors demonstrate that using scores from DeepAb one can sort mutations in an antibody that improve affinity and a series of other properties.
    • The authors used the DeepAb structure prediction mode model to rank mutations based on their impact on structure prediction confidence, leading to the design of 200 novel anti-hen egg lysozyme (HEL) antibody variants.
    • Single-point mutations from a deep mutational scanning (DMS) dataset (Warszawski et al.) were combined into multi-mutation variants (up to 7 mutations), and these variants were selected based on DeepAb scores for experimental testing.
    • The designed variants were expressed and tested for thermostability, colloidal stability, and binding affinity to HEL.
    • Large percentage of the variants showed improved thermostability (91%) and affinity (94%), with 10% showing significant increases in binding affinity.
    • A subset of 27 high-performing variants was further tested for developability characteristics, including nonspecific binding, aggregation propensity, and self-association, ensuring their practical usability.
  • 2024-09-04

    p-IgGen: A Paired Antibody Generative Language Model

    • generative methods
    • language models
    • developability
    • Novel generative model for antibody sequences that supports Vh/Vl pairing and generation of developable sequences.
    • Three models were created, IgGen (unpaired model), p-IgGen (unpaired fine-tuned on pairs) and developable p-IgGen (paired fine-tuned on developable sequences).
    • They used ca. 250m unpaired sequences and 1.8m paired sequences for training.
    • The model is based on GPT-2 but with rotary position embedding.
    • Developable sequences were defined as structural models of the 1.8m that had good TAP metrics (900,000 in total).
    • The model is much smaller than many of the models out there, (17m params), so it is more lightweight in training and application.
    • The model performs better on immunogenicity prediction than other models but worse on expression prediction.
    • Novel CDR-H3 structure prediction method, ComMat based on ensemble sampling.
    • Rather than generating a single structure, the method generates several solutions that are then all informing the next iteration.
    • The method was integrated into the structure module of AlphaFold2.
    • Crucially, with the introduction of the second prediction into the ‘community’, the predictions become better. However these quickly plateau, showing the limits of the approach.
    • The method does not produce better results than ABodyBuilder2 and EquiFold.
  • 2024-09-04

    Adapting protein language models for structure-conditioned design

    • language models
    • binding prediction
    • protein prediction
    • Novel language model incorporating structural information, with demonstrated experimental ability to improve design of therapeutic antibodies.
    • The new language model, ProseLM, builds upon Progen family of models from the same authors.
    • Structural information in the form of structural adapter layers after language model layers, encoding backbone and associated functional annotations.
    • Models with more parameters achieve much better perplexity. There is also some improvement by adding tangential context information such as ligands etc.
    • They trained an antibody-specific version of ProseLM, only on SABDAB data and it does much better on sequence recovery even than the larger models.
    • They use the model to propose mutations for Nivolumab ad Secukinumab, with mutations both in CDRs and Frameworks. THey used structures from the PDB as the basis for designs.
    • They found better binders, however if CDRs were re-designed the overall success rate of maintaining binding was lower (25% for Nivolumab) than when frameworks were redesigned (92%).
    • Novel humanization protocol employing language models and large-scale repertoire data.
    • Human OAS and germline sequences are embedded using ESM2.
    • K-nearest neighbors algorithm is then used to introduce mutations into the ESM-2 embedded query sequence coming from closest functional neighbors in the ESM2-embedded OAS+germlinse space.
    • Results of humanized abs are validated experimentally via ELISA.
    • Authors demonstrate that using inverse folding, one can affinity mature antibodies, confirmed experimentally.
    • Authors employ ESM-IF as the inverse folding algorithm.
    • They take two existing antibodies, bebletovimab and BD55-5840, both instrumental in COVID-19.
    • They introduce all possible single point mutations to the Vh and Vl regions (about 4300). They pick the best perplexity for experimental characterization.
    • The best perplexity ones have many framework mutations (bebletovimab 10/14 and BD55 5840 3/6). There was only one mutation to CDR-H3 in Bebletovimab.
    • Inverse folding mother achieves much better performance when antigen is used as well.
    • Authors introduce AntPack - software for rapid numbering of antibody sequences, germline identification and humanization.
    • Authors use a mixture model (so not ML!) on millions of sequences from NGS.
    • The sequences are pre-numbered to standardize them and then assigned to clusters which offer explainability on germline assignment and residue probability at a given position.
    • The method is very fast in comparison to HMM-based approaches such as ANARCI.
    • Method is available via https://github.com/Wang-lab-UCSD/AntPack
  • 2024-08-28

    AntiBARTy Diffusion for Property Guided Antibody Design

    • language models
    • generative methods
    • developability
    • Novel language model AntiBARTy with demonstration of how to use it to diffuse novel antibodies with favorable solubility properties.
    • The core model is a BART-based transformer, with 16m parameters.
    • It was firstly trained on all human heavy and light chains from OAS (254m heavies and 342m lights <- yes, more lights). This was followed by fine tuning on the higher quality paired data from OAS.
    • The diffusion model was based on U-net (CNN used for segmentation of medical images), totaling 3m parameters.
    • They define low and high solubility classes as predicted by protein-sol on paired OAS, with roughly 20k samples for each class.
    • Overall, one can sample from multivariate to get a vector in Antibarty latent space and use it to get an antibody sequence that is either high or low protein-sol predicted solubility.
    • Proposal for modeling antibodies using language, that is more fit-for purpose than current approaches.
    • It is plausible to represent antibodies/proteins as language to draw from existing trove of research on natural language.
    • Current approaches of porting the models from natural language to proteins/antibodies verbatim, might not release their full potential because of not focusing on key differences between natural language and proteins.
    • Authors propose a more fit for purpose formalization, where quite an important part is better token definition and associating them with function. For instance do not simply use amino acids or k-mers but have something more complex such as C*U and RA*, associated with hydrophobicity, binding zinc fingers or similar.