Monoclonal and Polyclonal Antibodies Research

ConformAb designs antibody sequences that maintain CDR canonical conformations, improving binding affinity without target-specific data.

This study evaluates IgG depletion in pigtail macaques using Rozanoliximab and Imlifidase, finding that Imlifidase causes more rapid and effective depletion than Rozanoliximab.

This paper presents an AI-driven computational strategy to predict affinity-enhancing mutations for anti-B7-H3 nanobodies, aiming to accelerate high-affinity nanobody development.

HyperBind2 improves antibody discovery through multi-shot learning, achieving higher accuracy with iterative lab-AI feedback cycles and reducing experimental burden.

This paper evaluates two bispecific CD20xCD40 antibodies, showing they modulate multiple immune cell types and achieve deep immunomodulation without safety issues.

The paper develops a computational platform to stabilize human VH domains for creating multispecific biologics with conditional activity.

This paper evaluates a novel Fc-optimized antibody drug conjugate targeting CD7, showing potent anti-leukemia activity in preclinical T-ALL models.

This paper shows that BLOSUM similarity scores correlate with antibody binding affinity, suggesting generative models implicitly learn evolutionary priors.

This study assesses the effects of deglycosylation on the stability and function of an anti-cocaine mAb using DSF and fluorescence labeling.

This study uses deep learning to design anti-VEGF nanobodies with improved affinity and stability through structure-guided mutational modeling and a sequence-based melting temperature predictor.

This paper introduces peleke-1, a suite of protein language models fine-tuned for generating targeted antibody sequences from antigen inputs.

This paper describes a method to discover protein-small molecule hybrids using pharmacophore-driven antibody discovery on yeast, showing that screening outcomes are pharmacophore-dependent.

The paper curates a database of therapeutic antibodies linked to clinical trial outcomes, identifies poor performance of existing tools in predicting immunogenicity, and highlights the need for systems immunology approaches.

This paper presents an AI framework to design common light chains for bispecific antibodies, reducing experimental screening and enabling production-ready antibodies for 7 out of 10 targets.

Property Enhancer optimizes antibody properties using a data-efficient framework, achieving significant affinity gains in both in silico and in vitro tests.

This paper introduces a yeast mating-based platform for generating ultra-large antibody libraries and demonstrates its ability to discover high-affinity binders.

This study designs factorizable antibody libraries using neural networks, finding they outperform random and enumerated libraries in pMHC binding.

The paper reports cryo-EM structures of avian IgA and compares them to mammalian IgA, revealing structural differences that may affect mucosal immune responses.

Germinal is a generative pipeline that designs functional antibodies with nanomolar binding affinities using minimal experimental testing.

This study shows that rabbit kappa light chain allotypes affect chimeric antibody expression and function, with K1-b9 maintaining robust performance due to a stable disulfide bond.

IgGM is a generative model for antibody design that produces high-affinity antibodies through tasks like structure prediction and affinity maturation, validated on multiple antigens.

This paper improves the affinity and potency of a monoclonal antibody against Shigella flexneri 3a O-antigen using phage display and whole-cell panning, showing enhanced antibacterial activity and broader serotype recognition.

The study uses a modified PISA assay to identify TNF as the antigen of infliximab among 8,000 proteins in activated monocytes, demonstrating its utility for antibody-antigen interaction analysis.

The paper identifies engineered Fc variants in therapeutic antibodies and fusion proteins using the IMGT/FcVariantsExplorer tool and integrates the findings into IMGT/mAb-DB.

The paper develops an in silico-in vitro workflow to generate high-affinity antibodies targeting the KRAS(G12D)-MHC I complex, achieving nanomolar affinity and specific T cell activation.

This paper develops a deep learning framework to generate light chains from heavy chains using unpaired antibody sequences, revealing maturation-linked pairing patterns.

This paper describes an experimental pipeline for generating human monoclonal antibodies against bacterial pathogens using synthetic glycan fragments, identifying functional antibodies against Staphylococcus aureus and Streptococcus pyogenes.

This paper shows that using the Leap-In transposon platform improves predictability in developing bispecific antibody-producing cell lines by enabling stable pools with predictable productivity and heterodimer fractions.

The paper introduces TNP, a computational tool for predicting nanobody developability, calibrated with clinical-stage sequences and experimental data.

This paper introduces a reinforcement learning framework for antibody sequence design that improves biophysical properties using infilling models and online learning strategies.