Computational Antibody Papers
Filter by tags
All
Filter by published year
All
TitleKey points
2026-09-11
Antibody maturation increases rigidity in protein-contacting regions and flexibility at glycan interfaces
- molecular dynamics
- MD simulation study showing that paratopes rigidify upon maturation.
- Through over 8.5 milliseconds of molecular dynamics simulations across seven antibody lineages, the authors demonstrate that affinity maturation selectively tunes paratope dynamics by rigidifying protein-contacting regions while enhancing flexibility at glycan-contacting interfaces.
- Global antibody flexibility displays no uniform trend across lineages. Intermediate antibodies often exhibit non-monotonic dynamic changes, localized conformational entropy is specifically adapted depending on the target antigen interface.
- Variable region dynamics remain largely consistent regardless of whether the constant region is present or whether light chain isotypes (Kappa vs. Lambda) are swapped, proving that computational costs for all-atom simulations can be cut by at least half by simulating variable regions alone without sacrificing accuracy.
2026-09-11
SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
- protein design
- non-antibody stuff
- Novel algorithm for sequence-structure co-design - SimpleDesign.
- SimpleDesign introduces a single-stage framework for joint protein sequence and structure co-design that operates directly in data space, eliminating the need for complex structure tokenizers or multi-stage training.
- It pairs discrete masked sequence recovery trained via cross-entropy with continuous C_alpha coordinate denoising trained via velocity-matching MSE, implemented using standard Transformer or Mixture-of-Transformer backbones.
- On benchmarks spanning 100–500 amino acids, SimpleDesign matches or exceeds the sequence-structure consistency and structural diversity of complex tokenized protein language models such as ESM3 and DPLM2.
- Compared to specialized geometric flow and diffusion models, it produces substantially higher-quality sequences with significantly lower ProGen2 perplexity and higher predicted foldability (pLDDT).
2026-09-11
Review: application and opportunities for machine learning and artificial intelligence in preclinical immunogenicity risk assessment
- developability
- Review recounting insights from an EMBL-EBI workshop on how AI/ML are applied alongside in vitro assays and Quantitative Systems Pharmacology (QSP) to evaluate and mitigate preclinical immunogenicity risks for biotherapeutics.
- Advanced in silico tools (such as NetMHCIIpan 4.3, Graph-pMHC, and HLAIIPred) accurately predict HLA Class II peptide presentation using mass-spectrometry immunopeptidomics data, though predicting T-cell receptor (TCR) binding for unseen epitopes and B-cell epitopes remains a bottleneck.
- Pharmaceutical workflows integrate computational screening early in candidate selection to guide deimmunization, while QSP "middle-out" modeling combines computational predictions with empirical assay data to simulate clinical anti-drug antibody (ADA) formation and pharmacokinetic impacts.
- The risk assessment framework is expanding beyond standard monoclonal antibodies to address unique immunological challenges in complex modalities, including AAV viral vectors, CAR-T cell therapies, and CRISPR-Cas9 gene editing components.
- Future improvements in clinical ADA prediction rely on overcoming data fragmentation, assay non-standardization, and small dataset sizes, with collaborative initiatives like federated learning offering a path forward.
2026-09-11
RFOptimization: Guiding Design Optimization with All-Atom Structure Prediction
- protein design
- RFOptimization - a training-free framework that converts initial 3D biomolecular designs into high-confidence candidates by interleaving RoseTTAFold3 gradient-guided MCMC sequence search with Boltz and MPNN inverse-folding cycling.
- The tool requires an initial 3D complex (PDB or mmCIF) as an input seed and yields a complete trajectory of optimized candidate sequences, predicted structures, and confidence metrics within 1–10 GPU minutes.
- Benchmarked across general mini-protein binders, cyclic peptides, small-molecule biosensors, and catalytic enzymes, the pipeline uses customizable residue masks that allow users to target specific regions (such as interface residues or antibody CDR loops) while keeping functional motifs fixed.
- Without wet-lab testing, performance was evaluated strictly in silico, achieving up to a 4.4x improvement in held-out AlphaFold3 refolding pass rates and outperforming existing baselines under a 3-model consensus filter (AF3, RF3, Boltz) at ~26 GPU-minutes per passing design.
2026-09-04
Benchmarking AI Agents on Experimentally Grounded Decisions in Therapeutic Antibody Discovery
- agents
- Benchmarking agents on making decisions on experimental workflows in biologics discovery.
- TxBench-Antibody Discovery benchmarks AI agents on 100 decision-focused evaluations derived from public experimental data across 10 biologics competencies, ranging from target selection and binding kinetics to cellular pharmacology and candidate de-risking.
- The benchmark evaluated 20 model-harness configurations, combining LLMs (e.g., Opus 5, Grok 4.6, Gemini 3.7 Flash, GPT-5.6) with execution scaffolds like Claude Code across 6,000 total runs using autonomous, deterministically graded workflows.
- Frontier agents remain unreliable decision-makers, with the top configuration (Opus 5 with Claude Code) achieving only a 53.0% pass rate, while additional cost, token usage, or tool activity failed to consistently improve accuracy.
- 82.3% of agent failures stemmed from flawed scientific judgment and biological context misinterpretation rather than computational execution errors (17.7%), with model rankings fluctuating significantly depending on the specific biological discipline.
2026-09-04
Antibody framework engineering enables augmented cytokine receptor signaling capacities of bispecific single domain antibody-based IL-21 mimetics
- nanobodies
- protein design
- Discovery and engineering of bispecific single-domain antibody (sdAb)-based IL-21 mimetics (surrogate agonists) that target the IL-21R and IL-2Rgamma receptor subunits to activate downstream STAT3 signaling and induce Granzyme B expression in immune cells.
- ColabFold (AlphaFold2) was used to model complex structures of IL-21R and IL-2Rgamma bound to VHH paratopes, generating structural hypotheses on how distinct epitope bins and paratope orientations dictate productive receptor signaling geometry.
- ProteinMPNN was applied to perform structure-based framework engineering by aligning VHH backbones to established VH dimer templates (PDB 7LU9 and 7L6M), yielding novel mutation sets (dsdAb(3)–(5)) designed to induce noncovalent VHH:VHH intramolecular dimerization.
- Candidate designs were assembled onto antibody scaffolds and energy-minimized using Molecular Operating Environment (MOE), followed by binding interface evaluation and selection using PRODIGY.
- The computationally engineered framework mutations enforced spatial rigidity and proximity between paratopes, successfully converting weak or inactive bispecific formats into highly potent cytokine mimetics without altering individual antigen-binding affinities.
2026-09-04
De novo designed single-domain antibodies protect against lethal cobra venom neurotoxicity in vivo
- nanobodies
- protein design
- End-to-end framework using generative deep learning to design de novo single-domain antibodies against the snake neurotoxin alpha-cobratoxin, leading to the experimental validation of low-nanomolar binders that achieved 100% in vivo survival in mice.
- Conducted a head-to-head in silico comparison of three vhh-capable generative design tools (Germinal, RFantibody, and BoltzGen) across three structural scaffolds (9GCN, 7XL0, and 3EAK), fixing CDR loop lengths and targeting five specific epitope hotspot residues (D27, R33, K35, R36, and V37).
- Evaluated complex predictions using AlphaFold3 (AF3) interface predicted TM-scores iptm combined with a target-aligned vhh structural self-consistency filter RMSD < 6Å), where Germinal generated a substantially higher fraction of passing candidates (46/300) than RFantibody (6/900) or BoltzGen (12/900).
- Profiling against SAbDab, OAS, and INDI antibody databases demonstrated that Germinal generated more novel CDR3 sequences and broader loop conformation sampling, which significantly narrowed the compute-time required per successful candidate despite Germinal's higher raw GPU runtime per design.
- Scaled the Germinal pipeline to ~8,000 trajectories using multi-stage filtering (including pDockQ2, PAE, spatial aggregation propensity, and AF3 re-prediction) to select candidates for experimental testing, finding retrospectively that AF3 ipSAE_min ranked true binders more effectively than standard ipTM
- Novel dataset of 160 VHH-Fc profiled across 10 biophysical assays.
- They demonstrated that tabular neural networks (TabICLv2, TabPFN v2.5) trained solely on 559 IgG heavy chains outperform intra-format VHH-Fc models in zero-shot predictions, showing that training data scale outweighs structural divergence between scaffolds.
- Surface-driven properties transfer with high accuracy, heparin binding (rho=.82), hydrophobicity (HIC, rho=.63), and self-association (AC-SINS, rho=0.62), whereas thermostability (Tm2, rho=0.16) remains scaffold-dependent and requires direct measurement.
- Augmenting models with simple surface property inputs (HIC and HAC) boosts prediction accuracy for complex liabilities like polyreactivity (PR-CHO, rho = 0.40 to 0.51).
- 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.
- Training specificity models across several domains.
- Models were trained strictly on public 1D sequence data (amino acids, DNA/RNA nucleotides, and chemical SMILES) across six biological domains, requiring no 3D structural information.
- Base sequence encoders were kept frozen while small 5–7 million parameter projection heads were trained in under an hour per fold on a single GPU using thermodynamic contrastive learning.
- Development was driven entirely via natural-language prompts by a domain expert with zero coding experience, with all numerical claims verified by an independent AI auditor.
- Top-1 target retrieval accuracy reached up to 98.0% from pools of 512 candidates, successfully generalizing to unseen rare HLA alleles and non-canonical binding targets that rule-based tools miss.
- Used as re-ranking filters alongside existing computational workflows, the models dramatically boosted precision, such as raising CRISPR off-target prediction precision from 33.2% to 94.0%.