Computational Antibody Papers

Filter by tags
non-antibody stuff
Filter by published year
2026
TitleKey points

  • 2026-05-22

    Fast and Ultra-Capable Protein Design: Advancing the Frontier Through Atomistic SE(3)-Equivariance with Genie 3

    • protein design
    • non-antibody stuff
    • Novel protein design model, revisiting the SE(3)architecture.
    • Genie 3 is an all-atom, SE(3)-equivariant structure diffusion model that treats proteins as branched polymers to capture sidechain details, utilizing a Latent Transformer with bidirectional layer updates and an Invariant Point Attention structural decoder.
    • The authors did not test the model on therapeutic formats such as antibodies or nanobodies; instead, they focused entirely on generating generic de novo protein binders, unconditional monomers, and functional motif scaffolds.
    • The method was computationally benchmarked using self-consistency pipelines (ProteinMPNN/ESMFold), MotifBench for functional sites, and a strict AF2M+ binder interface metric, alongside real-world experimental validation that yielded a 12.5% hit rate against the Nipah virus Glycoprotein G

  • 2026-02-05

    Multiple protein structure alignment at scale with FoldMason

    • non-antibody stuff
    • structure prediction
    • Protocol for ultra fast protein structure alignment.
    • FoldMason represents protein structures as 1D sequences using a structural alphabet (3Di+AA), which allows it to perform multiple alignments using fast string comparison algorithms and a parallelized progressive alignment following a minimum spanning tree.
    • It operates two to three orders of magnitude faster than traditional structure-based methods, achieving a 722x speedup over tools like MUSTANG and scaling to align 10,000 structures in a fraction of the time required by competitors for just 100.
    • It matches the accuracy of gold-standard structure aligners and exceeds sequence-based tools, particularly in aligning distantly related proteins or flexible structures that global superposition-based methods struggle to handle.
    • It is used for large-scale structural analysis of massive databases like AlphaFoldDB, building structure-based phylogenies for proteins that have diverged past the "twilight zone" of sequence similarity, and providing interactive web-based visualizations of complex MSTAs

  • 2026-02-05

    Biophysically Grounded Deep Learning Improves Protein–Protein ΔΔG Prediction

    • binding prediction
    • non-antibody stuff
    • Method addressing binding prediction strength training on low data noisy dataset.
    • The researchers address the issue that the field's standard benchmark, SKEMPI2, has significant hidden data leakage where different protein complexes share over 99% sequence identity, leading to inflated performance estimates in models that simply memorize these patterns. Problem raised by many, addressed by hardly any.
    • ProtBFF injects five interpretable physical priors, Interface, Burial, Dihedral, SASA, and lDDT, directly into residue embeddings using cross-embedding attention to prioritize the most structurally relevant parts of a protein.
    • By evaluating models on stricter, homology-based sequence clusters (60% similarity), the authors proved that ProtBFF allows general-purpose models like ESM to match or outperform specialized state-of-the-art predictors, even in data-limited "few-shot" scenarios.

  • 2026-02-05

    Iterative Epitope Expansion Enables Structure-Guided de novo Design of IgE-Binding Miniproteins Targeting the FcεRI Interface

    • non-antibody stuff
    • protein design
    • Describing a protocol to design mini-binders for a multi domain not that well characterized target using Latent-X1 and to lesser extent Chai.
    • The protocol used Latent-X1 to generate de novo sequences and initial poses, which were then refolded using Chai-1 to ensure the designs were structurally consistent and plausible.
    • The final rank was determined by the equation score = 2.0 * Binder PTM - 0.1 * min-iPAE - 0.1 * complex RMSD. This formula prioritized high global confidence (PTM) while penalizing designs where the Latent-X1 pose and Chai-1 refolded structure disagreed (iPAE and RMSD).
    • To handle the complex, multidomain IgE interface, they first designed binders against a smaller, stable seed on the epsilon3 domain before iteratively expanding the interface toward the full receptor-binding site.
    • Out of hundreds of generated designs, fewer than 80 candidates across two rounds were selected for wet-lab testing, resulting in a 6% hit rate and the identification of three specific IgE-binding miniproteins