Computational Antibody Papers
Filter by tags
structure prediction
Filter by published year
All
TitleKey points
2026-10-09
Becoming the bull: Structural insights and engineering strategies for ultralong CDR-H3 paratopes from cattle
- experimental techniques
- structure prediction
- Study of the bovine ultra long CDR-H3s.
- Cattle produce unique immunoglobulins featuring ultralong CDR-H3 (uCDR-H3) loops that project a modular, disulfide-rich "knob" paratope from a conserved stalk, enabling access to recessed or cryptic epitopes and enabling reformatting into diverse therapeutic architectures.
- Generated through restricted VDJ gene usage (IGHV1-7, IGHD8-2, and IGHJ2-4), cysteine-rich somatic hypermutation, and diverse intra-knob disulfide pairing topologies, uCDR-H3 regions achieve extensive structural diversity while relying on highly conserved V30 lambda light chains to provide framework stability and favorable biophysical traits.
- Because antigen binding depends exclusively on the 4-6 kDa knob mini-domain, paratopes isolated via display technologies can be engineered into common light chain bispecific antibodies, loop-grafted Fc-knob variants, Knobbodies, framework-inserted Fabs/VHHs, artificial coiled-coil arrays, or autonomous solid-phase synthesized peptides.
- While uCDR-H3 constructs exhibit favorable developability traits like high thermal stability and limited aggregation across broad pH ranges, translational challenges remain regarding potential non-human immunogenicity, sequence-dependent self-association tendencies, and structural instability when minimal knobs lack terminal spatial constraints.
2026-09-29
Fast retrieval of structurally similar antibodies from large sequence databases with AbSLang
- structure prediction
- annotation/numbering
- Contrastive-learned sequence embeddings that predict antibody complementarity-determining region (CDR) structural similarity (RMSD) without explicit 3D structure generation, enabling ultra-fast structural retrieval across multi-million sequence databases.
- AbSlang is trained on SAbDab structure pairs- it predicts CDR RMSD with mean absolute errors (MAE = 0.42--0.56A) comparable to state-of-the-art 3D structure predictors like AlphaFold3 and ABodyBuilder3, while outperforming sequence-identity baselines.
- Using a twin neural network with 8 FlashAttention transformer encoder layers, AbSLang projects protein language model embeddings (IgT5 for paired VH/VL; ESM-C for single-domain VH/VHH) into 512-dimensional vectors trained against dynamic time warping (DTW) loop alignments.
- Integrated with FAISS product quantization, AbSLang-search queries 2.5 million paired sequences in 7 seconds using an 879 MB index (compared to 18 minutes and 508 GB of storage for ABodyBuilder3 PDB files) and searches 10 million heavy chains in 1.22 seconds.
- AbSLang-search matches explicit structure prediction workflows in identifying structurally similar antibodies (top-20 neighbor overlap of 13.60/20 vs. 14.40/20), enabling scalable mining of structurally convergent antibodies across distinct genetic lineages.
- AbSlang was not benchmarked against the likes of Foldseek.
2026-09-21
Federated Training Dramatically Improves the Accuracy of Protein-Ligand Co-folding on Private Pharma Structures
- structure prediction
- Five major pharmaceutical companies collaboratively fine-tuned the OpenFold3 model across ~20,000 private structures using federated learning, ensuring sensitive data and IP never left their secure environments.
- The resulting model (AISB-1-Fed) significantly outperformed public baseline models, increasing high-quality interface predictions from 35.6% to 52.1% and correct ligand poses from 28.9% to 46.8%.
- Public databases typically lack dense, drug-relevant medicinal-chemistry series. By pooling private data, the initiative effectively tripled the high-quality protein-ligand data available for training.
- Although explicitly trained to improve protein-ligand co-folding (small molecule binding), the model also yielded a substantial, unexpected improvement in protein-protein interface (PPI) prediction quality.
- Evaluated ten co-folding protocols on a benchmark of 412 human monomeric antigen complexes
- They demonstrate that recent architectures like Protenix v2 (52% top-1 success on post-cutoff Fv complexes) substantially outperform earlier methods like AlphaFold-Multimer (20%) and Protenix v0.5, which serves as the open-source AlphaFold3 reproduction baseline.
- Modeling accuracy scaled inversely with CDR-H3 loop length. Short loops (<11 residues) were predicted accurately across all methods (0.4–0.7 Å Calpha RMSD), whereas long loops (>16 residues) remained challenging but showed distinct improvement in Protenix v2 (median 2.67 Å RMSD vs. 3.22–3.88 Å in older methods).
- CDR-H3 accuracy was identified as the primary structural feature distinguishing successful complex predictions DockQ \ge 0.49 from failures, demonstrating a strong inverse correlation with overall DockQ scores (Spearman rho = -0.74) and high metric discrimination (AUROC = 0.91).
- Prediction failures in unconstrained models were dominated by sampling limitations (failure to generate native-like poses) rather than ipTM ranking failures; providing idealized epitope constraints or increasing seed depth successfully rescued many of these failures by guiding the search space.
2026-08-21
Benchmarking Antibody Modeling Tools across Structure Prediction, Docking, and Paratope–Epitope Interface Analysis
- structure prediction
- Benchmarking of some structural prediction methods on antibody-related tasks.
- Benchmarked five computational tools across two core tasks: AlphaFold3 (AF3), ImmuneBuilder (ABodyBuilder2/ABB2), and IgFold for antibody variable fragment (Fv) structure prediction, as well as AF3, dyMEAN, and GRAMM for antigen–antibody complex structure prediction and docking.
- Tools were tested on 50 non-redundant humanized antibody–antigen Fab complexes from the Protein Data Bank (PDB), filtered for resolution < 3.0Å and released after December 19, 2023, to eliminate training data overlap.
- All Fv predictors achieved high backbone accuracy (mean TM-score > 0.97), but AF3 demonstrated statistically significant advantages in global Fv geometry and hypervariable CDR-H3 loop modeling (median CDR-H3 RMSD of 0.86 Å, compared to 1.34 Å for ABB2 and 1.52 Å for IgFold). In complex prediction, AF3 substantially outperformed dyMEAN and GRAMM, generating reliable docking poses for 46% of complexes, whereas classical rigid-body docking (GRAMM) and epitope-guided modeling (dyMEAN) almost completely failed.
- Paratope and epitope residue recovery is strictly dependent on initial docking accuracy. When docking succeeds, AF3 reliably identifies interface residues (F1 score ~ 0.85/0.87), salt bridges (84% recall), and non-bonded contacts (75% recall).
2026-08-21
High-accuracy structural modeling of antibody-antigen complexes
- binding prediction
- structure prediction
- Novel method, DeepAAAssembly, to model antibody antigen complexes, beating AF3.
- DeepAAAssembly introduces a hybrid framework that pairs deep learning inter-chain distance predictions with flexible Monte Carlo sampling, overcoming the lack of strong co-evolutionary signals in antibody-antigen interfaces.
- The pipeline feeds Voronoi tessellation contact geometry, AntiBERTy embeddings, and a Triangular Awareness module into a multi-column CNN, creating continuous multi-peak distance energy landscapes to guide both global orientation sampling and local CDR loop refinement.
- Evaluated on Docking Benchmark 5.5, it surpassed AF3 with a 12.9% higher average DockQ score on best-generated models (0.454 vs. 0.402) and boosted the overall modeling success rate (DockQ > 0.23) from 47.8% to 56.7%.
- Demonstrates strong generalization on CASP15/16 blind targets by successfully correcting severe initial orientation errors, elevating previously failed structural predictions into acceptable, physically plausible models
2026-07-13
Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine
- structure prediction
- Novel structural co-folding method that rivals AF3 architectures whilst being completely open sourced.
- OpenDDE replaces direct coordinate regression with atomic latent reasoning over granular structural tokens and scales the standard Pairformer hidden dimension from 128 to 384, expanding parameter capacity.
- The model implements a differentiable shape-complementarity objective to physically fit interfaces and naturally unifies structure prediction and de novo design inside a single conditional diffusion framework via masking.
- The model uses a 4-stage precision-breadth-precision data distribution to master geometry , consuming ~414k GPU-hours handled efficiently via Fold-CP context parallelism.
- The model sets state-of-the-art antibody-antigen success rates (e.g., 70.0% on FoldBench-AB and 66.4% on 2026ARK-AB) , easily outperforming Protenix-v1 (beating/equalling AF3!), and climbs to nearly 90% oracle accuracy when scaled with test-time seeds.
- Very fast antibody modeling, FlashABB, with applications to developability screening.
- FlashABB accurately performs sota antibody antibody structure prediction in just 5 ms, making it faster than protein language models can even generate sequence embeddings, by completely discarding traditional pair representations in favor of an inner-product-based, linear-memory "Flashpoint Attention" (FPA) algorithm.
- Featuring roughly 7.2 million parameters trained on 8,395 SAbDab structures, the model is strictly forced to run on float32 precision to avoid the catastrophic numerical cancellation errors that heavily degrade 16-bit float implementations during distance calculations.
- Eliminating the structural compute bottleneck allows developers to scale downstream analysis to millions of sequences; using the variant tool FlashTAP, teams can filter out liability flags and predict therapeutic developability metrics for 100 antibodies per second.
- Having said that, CDR-H3 is still sota - so in the region of 2.5A, but it gets there way faster.
2026-06-23
AbCVista: a deep learning framework for predicting antibody conformational ensembles
- structure prediction
- Deep learning framework designed to predict both highly accurate single antibody structures and biologically realistic 3D conformational ensembles.
- It combines a fast, antibody-specific sequence alignment tool (Abalign) with an optimized OpenFold engine, utilizing a novel "split-and-intersect" cross-chain clustering strategy to properly model heavy-light chain coordination without chain-segregation bias.
- In static benchmarks, it outperforms top-tier models like AlphaFold3 and IgFold, especially on the notoriously difficult hypervariable CDR-H3 loop, while cutting down structure inference time to roughly 2 minutes per antibody.
- Validated against extensive Molecular Dynamics (MD) simulations, its generated ensembles accurately capture true biological flexibility rather than random sampling noise, which significantly improves downstream therapeutic evaluations like antibody aggregation and developability mapping.
2026-05-29
ABRefine: An Accurate Antibody Structure Refinement Method by Equivariant Graph Transformer with Rigid Body Constraint
- structure prediction
- An end-to-end structural refinement method specifically developed for antibodies and nanobodies.
- Curates structures from SAbDab to train a pure equivariant graph transformer (not a standard EGNN) that directly predicts 3D coordinate shift vectors for all backbone atoms (N, Ca, C, O).
- Benchmarked against five baseline methods, achieving an average Ca RMSD improvement typically on the order of 0.01 Å to 0.05 Å - which essentially is raising questions of statistical significance (as the error bars are order of 1.0A at least).