Deep generative models for T cell receptor protein sequences

Probabilistic models of adaptive immune repertoire sequence distributions can be used to infer the expansion of immune cells in response to stimulus, differentiate genetic from environmental factors that determine repertoire sharing, and evaluate the suitability of various target immune sequences for stimulation via vaccination. Classically, these models are defined in terms of a probabilistic V(D)J recombination model which is sometimes combined with a selection model. In this paper we take a different approach, fitting variational autoencoder (VAE) models parameterized by deep neural networks to T cell receptor (TCR) repertoires. We show that simple VAE models can perform accurate cohort frequency estimation, learn the rules of VDJ recombination, and generalize well to unseen sequences. Further, we demonstrate that VAE-like models can distinguish between real sequences and sequences generated according to a recombination-selection model, and that many characteristics of VAE-generated sequences are similar to those of real sequences.

• Publication year

  2019

• Venue

  eLife

• Publication date

  2019-09-05

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.7554/eLife.46935PMID 31487240PMCID 6728137
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• AUTO-ENCODING VARIATIONAL BAYES

  2020cited by this paper
• sumrep: A Summary Statistic Framework for Immune Receptor Repertoire Comparison and Model Validation

  2019cited by this paper
• Toward machine-guided design of proteins

  2018cited by this paper
• Predicting the spectrum of TCR repertoire sharing with a data‐driven model of recombination

  2018cited by this paper
• OLGA: fast computation of generation probabilities of B- and T-cell receptor amino acid sequences and motifs

  2018cited by this paper
• A Diverse Lipid Antigen–Specific TCR Repertoire Is Clonally Expanded during Active Tuberculosis

  2018cited by this paper
• Memory CD4+ T cell receptor repertoire data mining as a tool for identifying cytomegalovirus serostatus

  2018cited by this paper
• Hyperspherical Variational Auto-Encoders

  2018cited by this paper
• Precise tracking of vaccine-responding T cell clones reveals convergent and personalized response in identical twins

  2018cited by this paper
• Deep generative models of genetic variation capture the effects of mutations

  2018cited by this paper
• Detecting T cell receptors involved in immune responses from single repertoire snapshots

  2018influential reference
• Exploring the pre-immune landscape of antigen-specific T cells

  2018cited by this paper
• Immunosequencing identifies signatures of cytomegalovirus exposure history and HLA-mediated effects on the T cell repertoire

  2017cited by this paper
• ggplot2 - Elegant Graphics for Data Analysis (2nd Edition)

  2017cited by this paper
• Reproducibility and Reuse of Adaptive Immune Receptor Repertoire Data

  2017cited by this paper
• Adaptive Immune Receptor Repertoire Community recommendations for sharing immune-repertoire sequencing data

  2017cited by this paper
• High-throughput immune repertoire analysis with IGoR

  2017cited by this paper
• Method for identification of condition-associated public antigen receptor sequences

  2017cited by this paper
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)

  2017cited by this paper
• Do GANs actually learn the distribution? An empirical study

  2017cited by this paper
• Variational auto-encoding of protein sequences

  2017cited by this paper
• Jupyter Notebooks - a publishing format for reproducible computational workflows

  2016cited by this paper
• Ladder Variational Autoencoders

  2016cited by this paper
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

  2016cited by this paper
• beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

  2016cited by this paper
• Change-O: a toolkit for analyzing large-scale B cell immunoglobulin repertoire sequencing data

  2015cited by this paper
• High-throughput pairing of T cell receptor α and β sequences

  2015cited by this paper
• Streamlined Plot Theme and Plot Annotations for 'ggplot2'

  2015cited by this paper
• Quantifying selection in immune receptor repertoires

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Sequence analysis of T-cell repertoires in health and disease

  2013cited by this paper
• Nestly - a Framework for Running Software with Nested Parameter Choices and Aggregating Results

  2013cited by this paper
• Estimating the ratio of CD4+ to CD8+ T cells using high-throughput sequence data.

  2013cited by this paper
• Statistical inference of the generation probability of T-cell receptors from sequence repertoires

  2012cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• Recombination centres and the orchestration of V(D)J recombination

  2011cited by this paper
• Data Structures for Statistical Computing in Python

  2010cited by this paper
• Biopython: freely available Python tools for computational molecular biology and bioinformatics

  2009cited by this paper
• The mechanism and regulation of chromosomal V(D)J recombination.

  2002cited by this paper

• Attribution assignment for deep-generative sequence models enables interpretability analysis using positive-only data

  2025cites this paper
• Enhancing sequence alignment of adaptive immune receptors through multi-task deep learning

  2025cites this paper
• Spatiotemporal Single-Cell Analysis Reveals T Cell Clonal Dynamics and Phenotypic Plasticity in Human Graft-versus-Host Disease

  2025cites this paper
• Revolutionizing oncology: the role of Artificial Intelligence (AI) as an antibody design, and optimization tools

  2025cites this paper
• Self-Contemplating In-Context Learning Enhances T Cell Receptor Generation for Novel Epitopes

  2025cites this paper
• Conditional generation of real antigen-specific T cell receptor sequences

  2025cites this paper
• Self-supervised learning of T cell receptor sequences exposes core properties for T cell membership

  2024cites this paper
• Principles and therapeutic applications of adaptive immunity.

  2024cites this paper
• Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody–Antigen Interactions

  2024cites this paper
• T cell receptor signaling and cell immunotherapy

  2024cites this paper
• Adaptive immune receptor repertoire analysis

  2024cites this paper
• Reading the repertoire: Progress in adaptive immune receptor analysis using machine learning.

  2024cites this paper
• Identification, characterization, and design of plant genome sequences using deep learning.

  2024cites this paper
• Bulk T cell repertoire sequencing (TCR-Seq) is a powerful technology for understanding inflammation-mediated diseases.

  2024cites this paper
• TCR-GPT: Integrating Autoregressive Model and Reinforcement Learning for T-Cell Receptor Repertoires Generation

  2024cites this paper
• GRIP: Graph Representation of Immune Repertoire Using Graph Neural Network and Transformer

  2023cites this paper
• Machine learning analysis of the T cell receptor repertoire identifies sequence features of self-reactivity.

  2023cites this paper
• Modeling of Immune Sequences from COVID-19 Infected Human Blood Samples with Variational Autoencoders

  2023cites this paper
• Simulation of adaptive immune receptors and repertoires with complex immune information to guide the development and benchmarking of AIRR machine learning

  2023cites this paper
• Generative models for protein sequence modeling: recent advances and future directions

  2023cites this paper
• Weakly supervised identification and generation of adaptive immune receptor sequences associated with immune disease status

  2023cites this paper
• Deep unsupervised learning methods for the identification and characterization of TCR specificity to Sars-Cov-2

  2023influential citation
• A transfer-learning approach to predict antigen immunogenicity and T-cell receptor specificity

  2023cites this paper
• A Kernelized Stein Discrepancy for Biological Sequences

  2023cites this paper
• Designing meaningful continuous representations of T cell receptor sequences with deep generative models

  2023influential citation
• Quantitative Annotations of T-Cell Repertoire Specificity

  2023cites this paper
• Machine learning analysis of the T cell receptor repertoire identifies sequence features that predict self-reactivity

  2023cites this paper
• Machine Learning Approaches to TCR Repertoire Analysis

  2022cites this paper
• Prediction of designer-recombinases for DNA editing with generative deep learning

  2022cites this paper
• Comparative Study of Repertoire Classification Methods Reveals Data Efficiency of k -mer Feature Extraction

  2022cites this paper
• Access to ground truth at unconstrained size makes simulated data as indispensable as experimental data for bioinformatics methods development and benchmarking

  2022cites this paper
• Deep autoregressive generative models capture the intrinsics embedded in T-cell receptor repertoires

  2022cites this paper
• Comparing T cell receptor repertoires using optimal transport

  2022cites this paper
• Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

  2021cites this paper
• Deep generative models create new and diverse protein structures

  2021cites this paper
• Function-guided protein design by deep manifold sampling

  2021cites this paper
• MotifBoost: k-mer based data-efficient immune repertoire classification method

  2021cites this paper
• Modeling and predicting the overlap of B- and T-cell receptor repertoires in healthy and SARS-CoV-2 infected individuals

  2021cites this paper
• Integrating T-cell receptor and transcriptome for large-scale single-cell immune profiling analysis

  2021cites this paper
• Immune2vec: Embedding B/T Cell Receptor Sequences in ℝN Using Natural Language Processing

  2021cites this paper
• Conditional generative modeling for de novo protein design with hierarchical functions

  2021cites this paper
• Echidna: integrated simulations of single-cell immune receptor repertoires and transcriptomes

  2021cites this paper
• In silico proof of principle of machine learning-based antibody design at unconstrained scale

  2021cites this paper
• A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity

  2021cites this paper
• Individualized VDJ recombination predisposes the available Ig sequence space

  2021cites this paper
• Recent advances in de novo protein design: Principles, methods, and applications

  2021cites this paper
• The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires

  2021cites this paper
• Creating artificial human genomes using generative neural networks

  2021cites this paper
• Convergent selection in antibody repertoires is revealed by deep learning

  2020cites this paper
• Learning the Ising Model with Generative Neural Networks

  2020cites this paper
• Probing T-cell response by sequence-based probabilistic modeling

  2020cites this paper
• Mining adaptive immune receptor repertoires for biological and clinical information using machine learning

  2020cites this paper
• Design of proteins presenting discontinuous functional sites using deep learning

  2020cites this paper
• Deep generative selection models of T and B cell receptor repertoires with soNNia

  2020cites this paper
• Application of deep learning in genomics

  2020cites this paper
• Immune Literacy: Reading, Writing, and Editing Adaptive Immunity

  2020cites this paper
• De novo protein design by deep network hallucination

  2020cites this paper
• An evolution-based model for designing chorismate mutase enzymes

  2020cites this paper
• Methods for sequence and structural analysis of B and T cell receptor repertoires

  2020cites this paper
• Deep Learning in Protein Structural Modeling and Design

  2020cites this paper
• Generative models of T-cell receptor sequences.

  2020influential citation
• Macromolecular modeling and design in Rosetta: recent methods and frameworks

  2020cites this paper
• Evolution-based design of chorismate mutase enzymes

  2020cites this paper
• On generative models of T-cell receptor sequences

  2019cites this paper
• Deep learning for mining protein data

  2019cites this paper
• Selected before selection: A case for inherent antigen bias in the T cell receptor repertoire.

  2019cites this paper
• Creating Artificial Human Genomes Using Generative Models

  2019cites this paper
• TCRGenesis: Generation of SIINFEKL-specific T-cell receptor sequences using autoregressive Transformer

  year unknowncites this paper
• Conditional Generation of Antigen Specific T-cell Receptor Sequences

  year unknowncites this paper