AI Developments for T and B Cell Receptor Modeling and Therapeutic Design

2026/01/23 by Linhui Xie, Aurelien Pelissier, Yanjun Shao +1 · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · #q-bio.BM

paper · pdf

arxiv published 2026/01/23 · arxiv updated 2026/01/28

Abstract

Artificial intelligence (AI) is accelerating progress in modeling T and B cell receptors by enabling predictive and generative frameworks grounded in sequence data and immune context. This chapter surveys recent advances in the use of protein language models, machine learning, and multimodal integration for immune receptor modeling. We highlight emerging strategies to leverage single-cell and repertoire-scale datasets, and optimize immune receptor candidates for therapeutic design. These developments point toward a new generation of data-efficient, generalizable, and clinically relevant models that better capture the diversity and complexity of adaptive immunity.

Citations

• Democratizing Protein Language Model Training, Sharing and Collaboration
• Tokenizing Loops of Antibodies
• The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies
• T cell receptor cross-reactivity prediction improved by a comprehensive mutational scan database
• AbRank: A Benchmark Dataset and Metric-Learning Framework for Antibody-Antigen Affinity Ranking
• AbBiBench: A Benchmark for Antibody Binding Affinity Maturation and Design
• Learning the language of protein-protein interactions
• PLM-interact: extending protein language models to predict protein-protein interactions
• BetterBodies: Reinforcement Learning guided Diffusion for Antibody Sequence Design
• TCR-GPT: Integrating Autoregressive Model and Reinforcement Learning for T-Cell Receptor Repertoires Generation
• AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
• AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions
• Contrastive learning of T cell receptor representations
• Improving Antibody Design with Force-Guided Sampling in Diffusion Models
• Accurate structure prediction of biomolecular interactions with AlphaFold 3
• Large scale paired antibody language models
• Atomically accurate de novo design of antibodies with RFdiffusion
• ANTIPASTI: interpretable prediction of antibody binding affinity exploiting Normal Modes and Deep Learning
• Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design
• Improving antibody language models with native pairing
• De novo design of protein structure and function with RFdiffusion
• Large language models generate functional protein sequences across diverse families
• Evolutionary-scale prediction of atomic-level protein structure with a language model
• Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
• Flow Matching for Generative Modeling
• Deciphering antibody affinity maturation with language models and weakly supervised learning
• ProteinBERT: a universal deep-learning model of protein sequence and function
• Denoising Diffusion Probabilistic Models
• NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data
• Integer Discrete Flows and Lossless Compression
• Learning protein sequence embeddings using information from structure
• BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model
• Conditioning by adaptive sampling for robust design
• Computational strategies for dissecting the high-dimensional complexity of adaptive immune repertoires
• Graph Attention Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• A Survey on Transfer Learning
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Discussions

• Linhui Xie, Aurelien Pelissier, Yanjun Shao, Mar'ia Rodriguez Martinez: AI Developments for T and B Cell Receptor Modeling and Therapeutic Design https://arxiv.org/abs/2601.17138 https://arxiv.org/pdf [bsky, 0 points, 0 comments]

Related

• Predicting adaptive immune receptor specificities by machine learning is a data generation problem
• Learning immune receptor representations with protein language models
• Learning the principles of T cell antigen discernment
• Physicochemically Informed Dual-Conditioned Generative Model of T-Cell Receptor Variable Regions for Cellular Therapy
• AI driven B-cell Immunotherapy Design