Computational Antibody Papers

Filter by tags
generative methods
Filter by published year
2026
TitleKey points

  • 2026-10-09

    MIMOSA: Guiding De Novo Antibody Design with Natural Interaction Fingerprints

    • generative methods
    • Novel de novo antibody design framework (not new model), based on mimicking the binding partner of the target.
    • Authors introduce MIMOSA (MIMic-Oriented Structural Antibody generation), an inference-time, model-agnostic framework that guides diffusion-based de novo antibody design by steering CDR backbones toward known target-partner interaction fingerprints, achieving 20–26% experimental hit rates and single-digit nanomolar binders on targets where unconstrained generative models fail.
    • The framework applies a differentiable "mimic potential" during diffusion to dynamically steer CDR backbone coordinates, followed by optional sequence-fixing during inverse folding to preserve essential hotspot chemistry. It flexibly accommodates both contiguous single-loop motifs using a sliding-window search and spatially dispersed multi-CDR hotspots via Hungarian per-residue assignment without requiring model retraining.
    • Validated using RFAntibody and BoltzGen backbones across three targets (KEAP1, uPA, and IL-8), MIMOSA successfully generated nanobody binders reaching affinities down to 4.1 nM for IL-8 and 37 nM for KEAP1. The method focused search space without collapsing diversity, maintaining high CDR sequence variation (53–61% CDR differences between designs) across multiple framework scaffolds and loop lengths.
    • Experimental evaluation revealed that mimic fidelity complements standard folding confidence metrics (ipSAE), providing a critical selection signal on targets like IL-8 where folding confidence alone cannot differentiate binders from non-binders.

  • 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.