Computational Antibody Papers
Filter by tags
protein design
Filter by published year
All
TitleKey points
2026-10-20
Multi-objective Amortized CDRH3 Sequence Sampling Diversifies Promising Antibody Candidates
- protein design
- Novel CDR-H3 redesign algorithm improving sequence design sampling quality.
- By framing antibody CDRH3 redesign as a preference-conditioned multi-objective Generative Flow Network (MOGFN) task, the authors show that fine-tuning an autoregressive protein language model across 14 heterogeneous rewards generates approximately 10x more distinct, acceptable candidates at 50% sequence identity than standard inverse-folding baselines across 45 held-out antibody complexes.
- The generative policy uses AMPLIFY-AR, a new 350M-parameter autoregressive span-in-filling model trained in fill-in-the-middle (FIM) format that evaluates sequence log-probabilities in a single forward pass, providing a 10.7x throughput speedup over masked pseudo-likelihood baselines. Conditioned on the native framework backbone and target preference vectors via cross-attention, the policy is optimized using a trajectory balance objective with a centered-residual VarGrad estimator and a log-cosh loss to amortize sampling along the Pareto frontier.
- Evaluated across a five-stage filtering funnel incorporating ABodyBuilder3, Chai-1, spatial aggregation propensity (SAP), and Rosetta/FoldX, GFN candidates consistently achieve lower aggregation propensity and higher sample diversity (measured by Vendi scores) among post-filter survivors. While dedicated inverse-folding models (ProteinMPNN and ESM-IF) achieve superior median Rosetta binding scores (−14.52 and −13.07 REU vs. −9.73 to −8.88 REU for GFN models), the MOGFN approach successfully discovers broader, functionally plausible sequence spaces outside standard structure-based solutions.
- Novel epitope-specific antibody design method.
- TiDE-Ab is a conditional SE(3) flow-matching framework for de novo epitope-specific antibody design that utilizes dynamic guidance scheduling to discover global binding poses from scratch while generating structurally valid, clash-free CDR conformations.
- Operating on unpaired antigen and antibody scaffold structures without pre-aligned frames, the model introduces Time-Dependent Classifier-Free Guidance (TD-CFG), applying strong epitope conditioning early to establish global pose orientation, followed by cosine annealing and early truncation to permit undisturbed local CDR refinement.
- Across 55 non-redundant benchmark target complexes, TiDE-Ab demonstrated state-of-the-art performance by achieving higher epitope recall than RFantibody (0.935 vs. 0.878) while eliminating over 95% of steric clashes (8.14 vs. 168.20 clashes per complex).
- In therapeutic case studies on TGF-β and IL-17A, TiDE-Ab reliably generated candidates reproducing both isoform-selective and cross-reactive clinical binding profiles using realistic partial-epitope inputs, whereas baseline diffusion models consistently failed to yield viable structures.
2026-09-21
TorchCraft: Unified binder design by inverting an all-atom structure predictor
- protein design
- Novel protein design algorithm - TorchCraft.
- TorchCraft addresses antibody design through framework-conditioned VHH (nanobody) design, where CDR regions (CDR1, CDR2, and CDR3) are optimized while keeping a selected antibody framework sequence fixed.
- To enforce antibody-specific sequence preferences, the framework incorporates a CDR-restricted IgLM language-model objective that uses the fixed framework and surrounding CDRs as infilling context to guide CDR optimization toward natural antibody distributions.
- Experimental wet-lab campaigns validated raw TorchCraft VHH designs without post hoc sequence redesign against four targets (BHRF1, EFNA5, PDGFR beta, and S100A4), yielding measured apparent dissociation constants (K_D) ranging from 24.3 nM to 354 nM.
- In computational benchmarks across 15 targets and five distinct nanobody frameworks (5JDS, 7EOW, 7XLO, 8COH, and 8Z8V), TorchCraft achieved high computational pass rates using a joint criterion evaluating AF3-derived interface confidence (TorchScore) and an ESM2-150M perplexity expression threshold
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
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
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
2026-08-28
OpenGerminal: an open-source implementation of the Germinal antibody design pipeline
- protein design
- generative methods
- A restriction free reproduction of the antibody design workflow germinal
- Replaces proprietary dependencies (PyRosetta, IgLM) with an open-source toolchain (OpenMM, AbLang1, sc-rs) and fixes multi-chain bugs, enabling unrestricted academic and commercial deployment.
- Demonstrates that AbLang1-guided hallucination significantly increases initial cofolding pass rates (e.g., 33.7% vs. 18.6% for PD-L1) with equal or higher structural confidence, at the cost of a ~1.5x increase in per-trajectory compute time.
- Uses hard-coded placeholder values for three energy metrics which degrades ensemble selection and disables the interface hydrogen-bond filter and lacks wet-lab experimental validation of the generated binders.
2026-06-24
BoltzProt-1: Towards Efficient De Novo Binder Design with Good Developability
- protein design
- binding prediction
- Novel de novo protein binder design pipeline from Boltz that pairs an optimized candidate generation engine with BoltzPPI, a novel, interaction-aware scoring model built to rank designs based on binding confidence rather than just geometric plausibility.
- To train BoltzPPI, the authors created a set of positive labels (PDB and patent complexes) and negative labels (synthetic non-interacting protein pairs co-localized via Boltz-2). This input pool (token, pair, distance, and mask features) is processed through a Pairformer stack using specific optimization tricks (co-trained focal loss, multi-view representation dropping, and Gaussian noise injection) to predict a binary binding-confidence score.
- Significantly improves experimental VHH design performance, boosting the confirmed-binder hit rate from 3.3% to 8.0% on novel targets and successfully discovering screening hits for 7 out of 10 benchmark targets from the Chai-2 dataset.
- Yields highly manufacturable binders, with 58% of its confirmed candidates passing a comprehensive panel of strict biophysical filters (such as thermal stability, purity, and low aggregation Propensity), outperforming both BoltzGen (40%) and clinical-stage VHH controls (21%).
- Generates structurally distinct binders whose CDR loops remain highly distinct from any known entries in the SAbDab database, with the entire pipeline made available to researchers via the Boltz API and Lab platforms.
- Case study of JAM-2, a generative biomolecular design model that engineered drug-like VHH antibodies against five distinct peptide-MHC class I (pMHC-I) targets across two HLA alleles using only target amino acid sequences as input.
- When reformatted into bispecific T-cell engagers (TCEs) without experimental optimization, the designs mediated potent, sub-nanomolar T-cell activation and successfully directed primary human T cells to kill target-presenting cells.
- Binders achieved stringent selectivity, showing a minimum 216-fold preference for NY-ESO-1 over highly similar human self-peptides and safely discriminating mutant KRAS variants (G12V and G12C) from wild-type sequences. A cryo-EM structure verified this atomic accuracy with a whole-complex Ca RMSD of 0.93 Å.
- Bypassing the need for downstream engineering, 78% of the designed antibodies passed five core industry-standard biophysical developability criteria, exhibiting strong expression titers, favorable monomericity, thermal stability, and low polyreactivity