Monoclonal and Polyclonal Antibodies Research

This study characterizes porcine antibodies using sequence and structural data, identifying unique features that may affect CDR-H3 properties and humanization potential.

The paper introduces a dataset of VHH-Fc antibodies and shows that IgG-trained models outperform VHH-Fc-specific models in predicting developability properties.

This paper demonstrates that fusion-protein architecture determines site selectivity in proximity-directed enzymatic modification of antibodies, enabling site-specific functionalization.

This study humanizes and engineers infliximab to improve its potency and developability, identifying LW2Y as a lead candidate with enhanced pH-dependent properties.

The paper develops a workflow combining immune yeast Fab display with focused humanization to identify binding-positive humanized anti-Aβ antibodies in a single sorting round.

This study uses molecular dynamics simulations to show how oligomannose Fc glycans alter CD16a binding by changing energetic interactions and conformational dynamics.

This study identifies a shark-derived VNAR that binds a hidden epitope on FAP, revealing structural insights for multiepitope targeting strategies.

AbPACER prioritizes high-affinity scFv clones from phage-display NGS data using parent-aware features and neural ranking, outperforming existing methods in recovery of known clones.

AbSLang-search efficiently retrieves structurally similar antibodies from large sequence databases using a contrastive learning model for CDR RMSD prediction.

The paper screens nanobodies to find an intrabody that inhibits ITCH E3 ubiquitin ligase activity in human cells using in vitro and intracellular assays.

This study uses molecular dynamics simulations to compare the effects of N-glycosylation on IgG2 and IgG4 antibodies, showing subclass-dependent impacts on flexibility and antigen binding.

This paper introduces InterAb and InterAb-Opt, computational frameworks that predict and optimize broadly neutralizing antibodies using all-atom modeling and pre-trained language models, showing significant improvements in binding affinity and neutralization activity.

This paper develops a supramolecular ADC conjugation method that improves drug loading and efficacy in pancreatic cancer compared to cysteine-conjugated analogs.

This paper designs functional multibodies using AI, demonstrating their therapeutic potential with high affinity and specificity across multiple targets.

This paper uses a machine learning model to generate new anti-PD-1 antibodies with improved potency, validated through molecular dynamics simulations and experimental testing.

The paper introduces a method to measure and reconstruct intact IgG repertoires, preserving molecular connectivity between Fab and Fc domains.

This paper redesigns an Fc-binding peptide to enable multivalent antibody assembly without altering the IgG scaffold, showing enhanced stability and functional utility.

AINN-Express predicts VHH antibody expression using only sequence data, achieving high ROC-AUC scores in both known and new programs without requiring structural data or task-specific training.

This paper develops sensitive ELISAs to quantify J-chain-containing IgA and IgM, revealing that 10% of circulating IgA is polymeric and enabling high-throughput analysis of polymeric IgA responses.

The paper engineers high-affinity cross-reactive antibodies with minimal mutations using deep learning and deep mutational scanning.

The paper designs structurally diverse antibody repertoires with drug-like properties using a computational method called CADAbRe, demonstrating their utility in binding to challenging targets.

The paper describes a computational workflow for designing NAZ-mAb variants targeting p95HER2, showing improved expression yields but weaker binding affinities compared to the parent antibody.

This paper benchmarks PTIm-mAb, an AI-driven antibody design platform, against eleven FDA-approved bispecific antibodies, showing improvements in developability metrics without compromising other factors.

This study characterizes FCRL5 as a low-affinity IgG-Fc receptor with distinct binding properties, showing preference for afucosylated IgG and identifying key residues for interaction.

This paper develops a single-domain antibody specific for M1-linked ubiquitin chains, enabling their detection and analysis across multiple applications.

This paper engineers an improved IgG-degrading enzyme, IdeSM33, showing enhanced activity and IgG depletion in vivo, with therapeutic potential for autoimmune diseases and gene therapy.

This study investigates how core fucosylation affects IgG1-FcCD16a binding through molecular dynamics simulations, revealing structural and dynamic changes that reduce ADCC.

The paper develops a synapse-based ODE model for immune cell engagers that shows trimer per synapse invariance across effector-to-tumor ratios, improving mechanistic understanding of bispecific antibody function.

BoltzProt-1 improves nanobody design for protein targets by increasing hit rates and developability compared to existing methods.