1
|
Yadav S, Vora DS, Sundar D, Dhanjal JK. TCR-ESM: Employing protein language embeddings to predict TCR-peptide-MHC binding. Comput Struct Biotechnol J 2024; 23:165-173. [PMID: 38146434 PMCID: PMC10749252 DOI: 10.1016/j.csbj.2023.11.037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2023] [Revised: 11/19/2023] [Accepted: 11/20/2023] [Indexed: 12/27/2023] Open
Abstract
Cognate target identification for T-cell receptors (TCRs) is a significant barrier in T-cell therapy development, which may be overcome by accurately predicting TCR interaction with peptide-bound major histocompatibility complex (pMHC). In this study, we have employed peptide embeddings learned from a large protein language model- Evolutionary Scale Modeling (ESM), to predict TCR-pMHC binding. The TCR-ESM model presented outperforms existing predictors. The complementarity-determining region 3 (CDR3) of the hypervariable TCR is located at the center of the paratope and plays a crucial role in peptide recognition. TCR-ESM trained on paired TCR data with both CDR3α and CDR3β chain information performs significantly better than those trained on data with only CDR3β, suggesting that both TCR chains contribute to specificity, the relative importance however depends on the specific peptide-MHC targeted. The study illuminates the importance of MHC information in TCR-peptide binding which remained inconclusive so far and was thought dependent on the dataset characteristics. TCR-ESM outperforms existing approaches on external datasets, suggesting generalizability. Overall, the potential of deep learning for predicting TCR-pMHC interactions and improving the understanding of factors driving TCR specificity are highlighted. The prediction model is available at http://tcresm.dhanjal-lab.iiitd.edu.in/ as an online tool.
Collapse
Affiliation(s)
- Shashank Yadav
- Department of Biomedical Engineering, University of Arizona, Tucson 85721, AZ, USA
| | - Dhvani Sandip Vora
- Department of Biochemical Engineering and Biotechnology, Indian Institute of Technology Delhi, New Delhi 110016, India
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, New Delhi 110020, India
| | - Durai Sundar
- Department of Biochemical Engineering and Biotechnology, Indian Institute of Technology Delhi, New Delhi 110016, India
| | - Jaspreet Kaur Dhanjal
- Department of Computational Biology, Indraprastha Institute of Information Technology, Delhi, New Delhi 110020, India
| |
Collapse
|
2
|
Kim HY, Kim S, Park WY, Kim D. TSpred: a robust prediction framework for TCR-epitope interactions using paired chain TCR sequence data. Bioinformatics 2024; 40:btae472. [PMID: 39052940 PMCID: PMC11297499 DOI: 10.1093/bioinformatics/btae472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 06/11/2024] [Accepted: 07/25/2024] [Indexed: 07/27/2024] Open
Abstract
MOTIVATION Prediction of T-cell receptor (TCR)-epitope interactions is important for many applications in biomedical research, such as cancer immunotherapy and vaccine design. The prediction of TCR-epitope interactions remains challenging especially for novel epitopes, due to the scarcity of available data. RESULTS We propose TSpred, a new deep learning approach for the pan-specific prediction of TCR binding specificity based on paired chain TCR data. We develop a robust model that generalizes well to unseen epitopes by combining the predictive power of CNN and the attention mechanism. In particular, we design a reciprocal attention mechanism which focuses on extracting the patterns underlying TCR-epitope interactions. Upon a comprehensive evaluation of our model, we find that TSpred achieves state-of-the-art performances in both seen and unseen epitope specificity prediction tasks. Also, compared to other predictors, TSpred is more robust to bias related to peptide imbalance in the dataset. In addition, the reciprocal attention component of our model allows for model interpretability by capturing structurally important binding regions. Results indicate that TSpred is a robust and reliable method for the task of TCR-epitope binding prediction. AVAILABILITY AND IMPLEMENTATION Source code is available at https://github.com/ha01994/TSpred.
Collapse
Affiliation(s)
- Ha Young Kim
- Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, South Korea
| | | | - Woong-Yang Park
- GENINUS Inc., Seoul 05836, South Korea
- Samsung Genome Institute, Samsung Medical Center, Seoul 06351, South Korea
- Department of Molecular Cell Biology, Sungkyunkwan University School of Medicine, Suwon 16419, South Korea
| | - Dongsup Kim
- Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, South Korea
| |
Collapse
|
3
|
Ehrlich R, Glynn E, Singh M, Ghersi D. Computational Methods for Predicting Key Interactions in T Cell-Mediated Adaptive Immunity. Annu Rev Biomed Data Sci 2024; 7:295-316. [PMID: 38748864 DOI: 10.1146/annurev-biodatasci-102423-122741] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/25/2024]
Abstract
The adaptive immune system recognizes pathogen- and cancer-specific features and is endowed with memory, enabling it to respond quickly and efficiently to repeated encounters with the same antigens. T cells play a central role in the adaptive immune system by directly targeting intracellular pathogens and helping to activate B cells to secrete antibodies. Several fundamental protein interactions-including those between major histocompatibility complex (MHC) proteins and antigen-derived peptides as well as between T cell receptors and peptide-MHC complexes-underlie the ability of T cells to recognize antigens with great precision. Computational approaches to predict these interactions are increasingly being used for medically relevant applications, including vaccine design and prediction of patient response to cancer immunotherapies. We provide computational researchers with an accessible introduction to the adaptive immune system, review computational approaches to predict the key protein interactions underlying T cell-mediated adaptive immunity, and highlight remaining challenges.
Collapse
Affiliation(s)
- Ryan Ehrlich
- School of Interdisciplinary Informatics, University of Nebraska, Omaha, Nebraska, USA;
| | - Eric Glynn
- Lewis-Sigler Institute, Princeton University, Princeton, New Jersey, USA
| | - Mona Singh
- Department of Computer Science, Princeton University, Princeton, New Jersey, USA;
- Lewis-Sigler Institute, Princeton University, Princeton, New Jersey, USA
| | - Dario Ghersi
- School of Interdisciplinary Informatics, University of Nebraska, Omaha, Nebraska, USA;
| |
Collapse
|
4
|
Hao Q, Long Y, Yang Y, Deng Y, Ding Z, Yang L, Shu Y, Xu H. Development and Clinical Applications of Therapeutic Cancer Vaccines with Individualized and Shared Neoantigens. Vaccines (Basel) 2024; 12:717. [PMID: 39066355 PMCID: PMC11281709 DOI: 10.3390/vaccines12070717] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2024] [Revised: 06/18/2024] [Accepted: 06/24/2024] [Indexed: 07/28/2024] Open
Abstract
Neoantigens, presented as peptides on the surfaces of cancer cells, have recently been proposed as optimal targets for immunotherapy in clinical practice. The promising outcomes of neoantigen-based cancer vaccines have inspired enthusiasm for their broader clinical applications. However, the individualized tumor-specific antigens (TSA) entail considerable costs and time due to the variable immunogenicity and response rates of these neoantigens-based vaccines, influenced by factors such as neoantigen response, vaccine types, and combination therapy. Given the crucial role of neoantigen efficacy, a number of bioinformatics algorithms and pipelines have been developed to improve the accuracy rate of prediction through considering a series of factors involving in HLA-peptide-TCR complex formation, including peptide presentation, HLA-peptide affinity, and TCR recognition. On the other hand, shared neoantigens, originating from driver mutations at hot mutation spots (e.g., KRASG12D), offer a promising and ideal target for the development of therapeutic cancer vaccines. A series of clinical practices have established the efficacy of these vaccines in patients with distinct HLA haplotypes. Moreover, increasing evidence demonstrated that a combination of tumor associated antigens (TAAs) and neoantigens can also improve the prognosis, thus expand the repertoire of shared neoantigens for cancer vaccines. In this review, we provide an overview of the complex process involved in identifying personalized neoantigens, their clinical applications, advances in vaccine technology, and explore the therapeutic potential of shared neoantigen strategies.
Collapse
Affiliation(s)
- Qing Hao
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
| | - Yuhang Long
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
| | - Yi Yang
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
| | - Yiqi Deng
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
- Colorectal Cancer Center, Department of General Surgery, West China Hospital, Sichuan University, Chengdu 610041, China
| | - Zhenyu Ding
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
| | - Li Yang
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
| | - Yang Shu
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
- Gastric Cancer Center, Department of General Surgery, West China Hospital, Sichuan University, Chengdu 610041, China
- Institute of General Surgery, West China Hospital, Sichuan University, Chengdu 610041, China
| | - Heng Xu
- State Key Laboratory of Biotherapy and Cancer Center, Department of Biotherapy, West China Hospital, Sichuan University, Chengdu 610041, China; (Q.H.); (Y.L.); (Y.Y.); (Y.D.); (Z.D.); (L.Y.)
- Institute of General Surgery, West China Hospital, Sichuan University, Chengdu 610041, China
- Research Center of Clinical Laboratory Medicine, Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu 610041, China
| |
Collapse
|
5
|
Velez-Arce A, Huang K, Li MM, Lin X, Gao W, Fu T, Kellis M, Pentelute BL, Zitnik M. TDC-2: Multimodal Foundation for Therapeutic Science. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.06.12.598655. [PMID: 38948789 PMCID: PMC11212894 DOI: 10.1101/2024.06.12.598655] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/02/2024]
Abstract
Therapeutics Data Commons (tdcommons.ai) is an open science initiative with unified datasets, AI models, and benchmarks to support research across therapeutic modalities and drug discovery and development stages. The Commons 2.0 (TDC-2) is a comprehensive overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new multimodal tasks and model frameworks, and comprehensive benchmarks. TDC-2 introduces over 1,000 multimodal datasets spanning approximately 85 million cells, pre-calculated embeddings from 5 state-of-the-art single-cell models, and a biomedical knowledge graph. TDC-2 drastically expands the coverage of ML tasks across therapeutic pipelines and 10+ new modalities, spanning but not limited to single-cell gene expression data, clinical trial data, peptide sequence data, peptidomimetics protein-peptide interaction data regarding newly discovered ligands derived from AS-MS spectroscopy, novel 3D structural data for proteins, and cell-type-specific protein-protein interaction networks at single-cell resolution. TDC-2 introduces multimodal data access under an API-first design using the model-view-controller paradigm. TDC-2 introduces 7 novel ML tasks with fine-grained biological contexts: contextualized drug-target identification, single-cell chemical/genetic perturbation response prediction, protein-peptide binding affinity prediction task, and clinical trial outcome prediction task, which introduce antigen-processing-pathway-specific, cell-type-specific, peptide-specific, and patient-specific biological contexts. TDC-2 also releases benchmarks evaluating 15+ state-of-the-art models across 5+ new learning tasks evaluating models on diverse biological contexts and sampling approaches. Among these, TDC-2 provides the first benchmark for context-specific learning. TDC-2, to our knowledge, is also the first to introduce a protein-peptide binding interaction benchmark.
Collapse
|
6
|
Bulashevska A, Nacsa Z, Lang F, Braun M, Machyna M, Diken M, Childs L, König R. Artificial intelligence and neoantigens: paving the path for precision cancer immunotherapy. Front Immunol 2024; 15:1394003. [PMID: 38868767 PMCID: PMC11167095 DOI: 10.3389/fimmu.2024.1394003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/29/2024] [Accepted: 05/13/2024] [Indexed: 06/14/2024] Open
Abstract
Cancer immunotherapy has witnessed rapid advancement in recent years, with a particular focus on neoantigens as promising targets for personalized treatments. The convergence of immunogenomics, bioinformatics, and artificial intelligence (AI) has propelled the development of innovative neoantigen discovery tools and pipelines. These tools have revolutionized our ability to identify tumor-specific antigens, providing the foundation for precision cancer immunotherapy. AI-driven algorithms can process extensive amounts of data, identify patterns, and make predictions that were once challenging to achieve. However, the integration of AI comes with its own set of challenges, leaving space for further research. With particular focus on the computational approaches, in this article we have explored the current landscape of neoantigen prediction, the fundamental concepts behind, the challenges and their potential solutions providing a comprehensive overview of this rapidly evolving field.
Collapse
Affiliation(s)
- Alla Bulashevska
- Host-Pathogen-Interactions, Paul-Ehrlich-Institut, Langen, Germany
| | - Zsófia Nacsa
- Host-Pathogen-Interactions, Paul-Ehrlich-Institut, Langen, Germany
| | - Franziska Lang
- TRON - Translational Oncology at the University Medical Center of the Johannes Gutenberg University gGmbH, Mainz, Germany
| | - Markus Braun
- Host-Pathogen-Interactions, Paul-Ehrlich-Institut, Langen, Germany
| | - Martin Machyna
- Host-Pathogen-Interactions, Paul-Ehrlich-Institut, Langen, Germany
| | - Mustafa Diken
- TRON - Translational Oncology at the University Medical Center of the Johannes Gutenberg University gGmbH, Mainz, Germany
| | - Liam Childs
- Host-Pathogen-Interactions, Paul-Ehrlich-Institut, Langen, Germany
| | - Renate König
- Host-Pathogen-Interactions, Paul-Ehrlich-Institut, Langen, Germany
| |
Collapse
|
7
|
Jiang F, Guo Y, Ma H, Na S, Zhong W, Han Y, Wang T, Huang J. GTE: a graph learning framework for prediction of T-cell receptors and epitopes binding specificity. Brief Bioinform 2024; 25:bbae343. [PMID: 39007599 PMCID: PMC11247411 DOI: 10.1093/bib/bbae343] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 05/15/2024] [Accepted: 07/01/2024] [Indexed: 07/16/2024] Open
Abstract
The interaction between T-cell receptors (TCRs) and peptides (epitopes) presented by major histocompatibility complex molecules (MHC) is fundamental to the immune response. Accurate prediction of TCR-epitope interactions is crucial for advancing the understanding of various diseases and their prevention and treatment. Existing methods primarily rely on sequence-based approaches, overlooking the inherent topology structure of TCR-epitope interaction networks. In this study, we present $GTE$, a novel heterogeneous Graph neural network model based on inductive learning to capture the topological structure between TCRs and Epitopes. Furthermore, we address the challenge of constructing negative samples within the graph by proposing a dynamic edge update strategy, enhancing model learning with the nonbinding TCR-epitope pairs. Additionally, to overcome data imbalance, we adapt the Deep AUC Maximization strategy to the graph domain. Extensive experiments are conducted on four public datasets to demonstrate the superiority of exploring underlying topological structures in predicting TCR-epitope interactions, illustrating the benefits of delving into complex molecular networks. The implementation code and data are available at https://github.com/uta-smile/GTE.
Collapse
Affiliation(s)
- Feng Jiang
- Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States
| | - Yuzhi Guo
- Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States
| | - Hehuan Ma
- Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States
| | - Saiyang Na
- Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States
| | - Wenliang Zhong
- Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States
| | - Yi Han
- Public Health, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, TX 75390, United States
| | - Tao Wang
- Public Health, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, TX 75390, United States
| | - Junzhou Huang
- Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States
| |
Collapse
|
8
|
Leary AY, Scott D, Gupta NT, Waite JC, Skokos D, Atwal GS, Hawkins PG. Designing meaningful continuous representations of T cell receptor sequences with deep generative models. Nat Commun 2024; 15:4271. [PMID: 38769289 PMCID: PMC11106309 DOI: 10.1038/s41467-024-48198-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2023] [Accepted: 04/24/2024] [Indexed: 05/22/2024] Open
Abstract
T Cell Receptor (TCR) antigen binding underlies a key mechanism of the adaptive immune response yet the vast diversity of TCRs and the complexity of protein interactions limits our ability to build useful low dimensional representations of TCRs. To address the current limitations in TCR analysis we develop a capacity-controlled disentangling variational autoencoder trained using a dataset of approximately 100 million TCR sequences, that we name TCR-VALID. We design TCR-VALID such that the model representations are low-dimensional, continuous, disentangled, and sufficiently informative to provide high-quality TCR sequence de novo generation. We thoroughly quantify these properties of the representations, providing a framework for future protein representation learning in low dimensions. The continuity of TCR-VALID representations allows fast and accurate TCR clustering and is benchmarked against other state-of-the-art TCR clustering tools and pre-trained language models.
Collapse
Affiliation(s)
- Allen Y Leary
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA.
| | - Darius Scott
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA
| | - Namita T Gupta
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA
| | - Janelle C Waite
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA
| | - Dimitris Skokos
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA
| | - Gurinder S Atwal
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA
| | - Peter G Hawkins
- Regeneron Pharmaceuticals Inc., 777 Old Saw Mill River Road, Tarrytown, NY, 10591, USA.
| |
Collapse
|
9
|
Jiang M, Yu Z, Lan X. VitTCR: A deep learning method for peptide recognition prediction. iScience 2024; 27:109770. [PMID: 38711451 PMCID: PMC11070698 DOI: 10.1016/j.isci.2024.109770] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Revised: 01/21/2024] [Accepted: 04/15/2024] [Indexed: 05/08/2024] Open
Abstract
This study introduces VitTCR, a predictive model based on the vision transformer (ViT) architecture, aimed at identifying interactions between T cell receptors (TCRs) and peptides, crucial for developing cancer immunotherapies and vaccines. VitTCR converts TCR-peptide interactions into numerical AtchleyMaps using Atchley factors for prediction, achieving AUROC (0.6485) and AUPR (0.6295) values. Benchmark analysis indicates VitTCR's performance is comparable to other models, with further comparative studies suggested to understand its effectiveness in varied contexts. Additionally, integrating a positional bias weight matrix (PBWM), derived from amino acid contact probabilities in structurally resolved pMHC-TCR complexes, slightly improves VitTCR's accuracy. The model's predictions show weak yet statistically significant correlations with immunological factors like T cell clonal expansion and activation percentages, underscoring the biological relevance of VitTCR's predictive capabilities. VitTCR emerges as a valuable computational tool for predicting TCR-peptide interactions, offering insights for immunotherapy and vaccine development.
Collapse
Affiliation(s)
- Mengnan Jiang
- School of Medicine, Tsinghua University, Beijing 100084, China
| | - Zilan Yu
- School of Medicine, Tsinghua University, Beijing 100084, China
- Centre for Life Sciences, Tsinghua University, Beijing 100084, China
| | - Xun Lan
- School of Medicine, Tsinghua University, Beijing 100084, China
- Centre for Life Sciences, Tsinghua University, Beijing 100084, China
- Tsinghua-Peking Center for Life Sciences, MOE Key Laboratory of Tsinghua University, Beijing, China
- MOE Key Laboratory of Bioinformatics, Tsinghua University, Beijing 100084, China
| |
Collapse
|
10
|
Gao Y, Dong K, Gao Y, Jin X, Yang J, Yan G, Liu Q. Unified cross-modality integration and analysis of T cell receptors and T cell transcriptomes by low-resource-aware representation learning. CELL GENOMICS 2024; 4:100553. [PMID: 38688285 PMCID: PMC11099349 DOI: 10.1016/j.xgen.2024.100553] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/13/2023] [Revised: 03/09/2024] [Accepted: 04/06/2024] [Indexed: 05/02/2024]
Abstract
Single-cell RNA sequencing (scRNA-seq) and T cell receptor sequencing (TCR-seq) are pivotal for investigating T cell heterogeneity. Integrating these modalities, which is expected to uncover profound insights in immunology that might otherwise go unnoticed with a single modality, faces computational challenges due to the low-resource characteristics of the multimodal data. Herein, we present UniTCR, a novel low-resource-aware multimodal representation learning framework designed for the unified cross-modality integration, enabling comprehensive T cell analysis. By designing a dual-modality contrastive learning module and a single-modality preservation module to effectively embed each modality into a common latent space, UniTCR demonstrates versatility in connecting TCR sequences with T cell transcriptomes across various tasks, including single-modality analysis, modality gap analysis, epitope-TCR binding prediction, and TCR profile cross-modality generation, in a low-resource-aware way. Extensive evaluations conducted on multiple scRNA-seq/TCR-seq paired datasets showed the superior performance of UniTCR, exhibiting the ability of exploring the complexity of immune system.
Collapse
Affiliation(s)
- Yicheng Gao
- Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration (Tongji University), Ministry of Education, Tongji Hospital, School of Medicine, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; State Key Laboratory of Cardiology and Medical Innovation Center, Shanghai East Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China
| | - Kejing Dong
- Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration (Tongji University), Ministry of Education, Tongji Hospital, School of Medicine, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; State Key Laboratory of Cardiology and Medical Innovation Center, Shanghai East Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China
| | - Yuli Gao
- Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration (Tongji University), Ministry of Education, Tongji Hospital, School of Medicine, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; State Key Laboratory of Cardiology and Medical Innovation Center, Shanghai East Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China
| | - Xuan Jin
- Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration (Tongji University), Ministry of Education, Tongji Hospital, School of Medicine, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; State Key Laboratory of Cardiology and Medical Innovation Center, Shanghai East Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China
| | - Jingya Yang
- Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai 201804, China
| | - Gang Yan
- Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai 201804, China.
| | - Qi Liu
- Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration (Tongji University), Ministry of Education, Tongji Hospital, School of Medicine, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; State Key Laboratory of Cardiology and Medical Innovation Center, Shanghai East Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai 200092, China; Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai 201804, China; Research Institute of Intelligent Computing, Zhejiang Lab, Hangzhou 311121, China.
| |
Collapse
|
11
|
Liu Y, Zhou Y, Hu X, Le-Ge W, Wang H, Jiang T, Li J, Hu Y, Wang Y. DIRMC: a database of immunotherapy-related molecular characteristics. Database (Oxford) 2024; 2024:baae032. [PMID: 38713861 PMCID: PMC11184449 DOI: 10.1093/database/baae032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Revised: 03/02/2024] [Accepted: 03/29/2024] [Indexed: 05/09/2024]
Abstract
Cancer immunotherapy has brought about a revolutionary breakthrough in the field of cancer treatment. Immunotherapy has changed the treatment landscape for a variety of solid and hematologic malignancies. To assist researchers in efficiently uncovering valuable information related to cancer immunotherapy, we have presented a manually curated comprehensive database called DIRMC, which focuses on molecular features involved in cancer immunotherapy. All the content was collected manually from published literature, authoritative clinical trial data submitted by clinicians, some databases for drug target prediction such as DrugBank, and some experimentally confirmed high-throughput data sets for the characterization of immune-related molecular interactions in cancer, such as a curated database of T-cell receptor sequences with known antigen specificity (VDJdb), a pathology-associated TCR database (McPAS-TCR) et al. By constructing a fully connected functional network, ranging from cancer-related gene mutations to target genes to translated target proteins to protein regions or sites that may specifically affect protein function, we aim to comprehensively characterize molecular features related to cancer immunotherapy. We have developed the scoring criteria to assess the reliability of each MHC-peptide-T-cell receptor (TCR) interaction item to provide a reference for users. The database provides a user-friendly interface to browse and retrieve data by genes, target proteins, diseases and more. DIRMC also provides a download and submission page for researchers to access data of interest for further investigation or submit new interactions related to cancer immunotherapy targets. Furthermore, DIRMC provides a graphical interface to help users predict the binding affinity between their own peptide of interest and MHC or TCR. This database will provide researchers with a one-stop resource to understand cancer immunotherapy-related targets as well as data on MHC-peptide-TCR interactions. It aims to offer reliable molecular characteristics support for both the analysis of the current status of cancer immunotherapy and the development of new immunotherapy. DIRMC is available at http://www.dirmc.tech/. Database URL: http://www.dirmc.tech/.
Collapse
Affiliation(s)
- Yue Liu
- Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
| | - Yuhuan Zhou
- School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong 518055, China
| | - Xiumei Hu
- Beidahuang Industry Group General Hospital, Harbin 150001, China
| | - Wuri Le-Ge
- Department of Pain, Tongliao City Hospital, Tongliao 028000, China
| | - Haoyan Wang
- Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
| | - Tao Jiang
- Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
| | - Junyi Li
- School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong 518055, China
| | - Yang Hu
- Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
| | - Yadong Wang
- Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
| |
Collapse
|
12
|
Marrer-Berger E, Nicastri A, Augustin A, Kramar V, Liao H, Hanisch LJ, Carpy A, Weinzierl T, Durr E, Schaub N, Nudischer R, Ortiz-Franyuti D, Breous-Nystrom E, Stucki J, Hobi N, Raggi G, Cabon L, Lezan E, Umaña P, Woodhouse I, Bujotzek A, Klein C, Ternette N. The physiological interactome of TCR-like antibody therapeutics in human tissues. Nat Commun 2024; 15:3271. [PMID: 38627373 PMCID: PMC11021511 DOI: 10.1038/s41467-024-47062-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2022] [Accepted: 03/19/2024] [Indexed: 04/19/2024] Open
Abstract
Selective binding of TCR-like antibodies that target a single tumour-specific peptide antigen presented by human leukocyte antigens (HLA) is the absolute prerequisite for their therapeutic suitability and patient safety. To date, selectivity assessment has been limited to peptide library screening and predictive modeling. We developed an experimental platform to de novo identify interactomes of TCR-like antibodies directly in human tissues using mass spectrometry. As proof of concept, we confirm the target epitope of a MAGE-A4-specific TCR-like antibody. We further determine cross-reactive peptide sequences for ESK1, a TCR-like antibody with known off-target activity, in human liver tissue. We confirm off-target-induced T cell activation and ESK1-mediated liver spheroid killing. Off-target sequences feature an amino acid motif that allows a structural groove-coordination mimicking that of the target peptide, therefore allowing the interaction with the engager molecule. We conclude that our strategy offers an accurate, scalable route for evaluating the non-clinical safety profile of TCR-like antibody therapeutics prior to first-in-human clinical application.
Collapse
Affiliation(s)
- Estelle Marrer-Berger
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Annalisa Nicastri
- The Jenner Institute, Old Road Campus Research Building, Oxford, OX37DQ, UK
- Centre for Immuno-Oncology, Old Road Campus Research Building, Oxford, OX37DQ, UK
| | - Angelique Augustin
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Vesna Kramar
- Roche Innovation Center Zürich, 8952, Schlieren, Switzerland
| | - Hanqing Liao
- The Jenner Institute, Old Road Campus Research Building, Oxford, OX37DQ, UK
- Centre for Immuno-Oncology, Old Road Campus Research Building, Oxford, OX37DQ, UK
| | | | - Alejandro Carpy
- Roche Pharma Research & Early Development, Roche Innovation Center Munich, 82377, Penzberg, Germany
| | - Tina Weinzierl
- Roche Innovation Center Zürich, 8952, Schlieren, Switzerland
| | - Evelyne Durr
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Nathalie Schaub
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Ramona Nudischer
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Daniela Ortiz-Franyuti
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Ekaterina Breous-Nystrom
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Janick Stucki
- Alveolix AG, Swiss Organs-on-Chip Innovation, 3010, Bern, Switzerland
| | - Nina Hobi
- Alveolix AG, Swiss Organs-on-Chip Innovation, 3010, Bern, Switzerland
| | - Giulia Raggi
- Alveolix AG, Swiss Organs-on-Chip Innovation, 3010, Bern, Switzerland
| | - Lauriane Cabon
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Emmanuelle Lezan
- Roche Pharma Research & Early Development, Roche Innovation Center Basel, 4070, Basel, Switzerland
| | - Pablo Umaña
- Roche Innovation Center Zürich, 8952, Schlieren, Switzerland
| | - Isaac Woodhouse
- The Jenner Institute, Old Road Campus Research Building, Oxford, OX37DQ, UK
- Centre for Immuno-Oncology, Old Road Campus Research Building, Oxford, OX37DQ, UK
| | - Alexander Bujotzek
- Roche Pharma Research & Early Development, Roche Innovation Center Munich, 82377, Penzberg, Germany
| | - Christian Klein
- Roche Innovation Center Zürich, 8952, Schlieren, Switzerland.
| | - Nicola Ternette
- The Jenner Institute, Old Road Campus Research Building, Oxford, OX37DQ, UK.
- Centre for Immuno-Oncology, Old Road Campus Research Building, Oxford, OX37DQ, UK.
- Department of Pharmaceutical Sciences, University of Utrecht, 3584, CH, Utrecht, The Netherlands.
| |
Collapse
|
13
|
Croce G, Bobisse S, Moreno DL, Schmidt J, Guillame P, Harari A, Gfeller D. Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells. Nat Commun 2024; 15:3211. [PMID: 38615042 PMCID: PMC11016097 DOI: 10.1038/s41467-024-47461-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Accepted: 04/03/2024] [Indexed: 04/15/2024] Open
Abstract
T cells have the ability to eliminate infected and cancer cells and play an essential role in cancer immunotherapy. T cell activation is elicited by the binding of the T cell receptor (TCR) to epitopes displayed on MHC molecules, and the TCR specificity is determined by the sequence of its α and β chains. Here, we collect and curate a dataset of 17,715 αβTCRs interacting with dozens of class I and class II epitopes. We use this curated data to develop MixTCRpred, an epitope-specific TCR-epitope interaction predictor. MixTCRpred accurately predicts TCRs recognizing several viral and cancer epitopes. MixTCRpred further provides a useful quality control tool for multiplexed single-cell TCR sequencing assays of epitope-specific T cells and pinpoints a substantial fraction of putative contaminants in public databases. Analysis of epitope-specific dual α T cells demonstrates that MixTCRpred can identify α chains mediating epitope recognition. Applying MixTCRpred to TCR repertoires from COVID-19 patients reveals enrichment of clonotypes predicted to bind an immunodominant SARS-CoV-2 epitope. Overall, MixTCRpred provides a robust tool to predict TCRs interacting with specific epitopes and interpret TCR-sequencing data from both bulk and epitope-specific T cells.
Collapse
Affiliation(s)
- Giancarlo Croce
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University of Lausanne, Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
- Agora Cancer Research Centre, Lausanne, Switzerland
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland
| | - Sara Bobisse
- Agora Cancer Research Centre, Lausanne, Switzerland
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University Hospital of Lausanne, Lausanne, Switzerland
| | - Dana Léa Moreno
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University of Lausanne, Lausanne, Switzerland
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland
- Agora Cancer Research Centre, Lausanne, Switzerland
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland
| | - Julien Schmidt
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University of Lausanne, Lausanne, Switzerland
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University Hospital of Lausanne, Lausanne, Switzerland
| | - Philippe Guillame
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University Hospital of Lausanne, Lausanne, Switzerland
| | - Alexandre Harari
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University of Lausanne, Lausanne, Switzerland
- Agora Cancer Research Centre, Lausanne, Switzerland
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University Hospital of Lausanne, Lausanne, Switzerland
| | - David Gfeller
- Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University of Lausanne, Lausanne, Switzerland.
- Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland.
- Agora Cancer Research Centre, Lausanne, Switzerland.
- Swiss Cancer Center Leman (SCCL), Lausanne, Switzerland.
| |
Collapse
|
14
|
Shao W, Yao Y, Yang L, Li X, Ge T, Zheng Y, Zhu Q, Ge S, Gu X, Jia R, Song X, Zhuang A. Novel insights into TCR-T cell therapy in solid neoplasms: optimizing adoptive immunotherapy. Exp Hematol Oncol 2024; 13:37. [PMID: 38570883 PMCID: PMC10988985 DOI: 10.1186/s40164-024-00504-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 03/21/2024] [Indexed: 04/05/2024] Open
Abstract
Adoptive immunotherapy in the T cell landscape exhibits efficacy in cancer treatment. Over the past few decades, genetically modified T cells, particularly chimeric antigen receptor T cells, have enabled remarkable strides in the treatment of hematological malignancies. Besides, extensive exploration of multiple antigens for the treatment of solid tumors has led to clinical interest in the potential of T cells expressing the engineered T cell receptor (TCR). TCR-T cells possess the capacity to recognize intracellular antigen families and maintain the intrinsic properties of TCRs in terms of affinity to target epitopes and signal transduction. Recent research has provided critical insight into their capability and therapeutic targets for multiple refractory solid tumors, but also exposes some challenges for durable efficacy. In this review, we describe the screening and identification of available tumor antigens, and the acquisition and optimization of TCRs for TCR-T cell therapy. Furthermore, we summarize the complete flow from laboratory to clinical applications of TCR-T cells. Last, we emerge future prospects for improving therapeutic efficacy in cancer world with combination therapies or TCR-T derived products. In conclusion, this review depicts our current understanding of TCR-T cell therapy in solid neoplasms, and provides new perspectives for expanding its clinical applications and improving therapeutic efficacy.
Collapse
Affiliation(s)
- Weihuan Shao
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Yiran Yao
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Ludi Yang
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Xiaoran Li
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Tongxin Ge
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Yue Zheng
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Qiuyi Zhu
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Shengfang Ge
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Xiang Gu
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China
| | - Renbing Jia
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China.
| | - Xin Song
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China.
| | - Ai Zhuang
- Department of Ophthalmology, Ninth People's Hospital, Shanghai JiaoTong University School of Medicine, 639 Zhi Zao Ju Road, Shanghai Ninth People's Hospital, Shanghai, 200011, People's Republic of China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, 200011, People's Republic of China.
| |
Collapse
|
15
|
Ji H, Wang XX, Zhang Q, Zhang C, Zhang HM. Predicting TCR sequences for unseen antigen epitopes using structural and sequence features. Brief Bioinform 2024; 25:bbae210. [PMID: 38711371 PMCID: PMC11074592 DOI: 10.1093/bib/bbae210] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2024] [Revised: 04/04/2024] [Accepted: 04/22/2024] [Indexed: 05/08/2024] Open
Abstract
T-cell receptor (TCR) recognition of antigens is fundamental to the adaptive immune response. With the expansion of experimental techniques, a substantial database of matched TCR-antigen pairs has emerged, presenting opportunities for computational prediction models. However, accurately forecasting the binding affinities of unseen antigen-TCR pairs remains a major challenge. Here, we present convolutional-self-attention TCR (CATCR), a novel framework tailored to enhance the prediction of epitope and TCR interactions. Our approach utilizes convolutional neural networks to extract peptide features from residue contact matrices, as generated by OpenFold, and a transformer to encode segment-based coded sequences. We introduce CATCR-D, a discriminator that can assess binding by analyzing the structural and sequence features of epitopes and CDR3-β regions. Additionally, the framework comprises CATCR-G, a generative module designed for CDR3-β sequences, which applies the pretrained encoder to deduce epitope characteristics and a transformer decoder for predicting matching CDR3-β sequences. CATCR-D achieved an AUROC of 0.89 on previously unseen epitope-TCR pairs and outperformed four benchmark models by a margin of 17.4%. CATCR-G has demonstrated high precision, recall and F1 scores, surpassing 95% in bidirectional encoder representations from transformers score assessments. Our results indicate that CATCR is an effective tool for predicting unseen epitope-TCR interactions. Incorporating structural insights enhances our understanding of the general rules governing TCR-epitope recognition significantly. The ability to predict TCRs for novel epitopes using structural and sequence information is promising, and broadening the repository of experimental TCR-epitope data could further improve the precision of epitope-TCR binding predictions.
Collapse
MESH Headings
- Receptors, Antigen, T-Cell/chemistry
- Receptors, Antigen, T-Cell/immunology
- Receptors, Antigen, T-Cell/metabolism
- Receptors, Antigen, T-Cell/genetics
- Humans
- Epitopes/chemistry
- Epitopes/immunology
- Computational Biology/methods
- Neural Networks, Computer
- Epitopes, T-Lymphocyte/immunology
- Epitopes, T-Lymphocyte/chemistry
- Antigens/chemistry
- Antigens/immunology
- Amino Acid Sequence
Collapse
Affiliation(s)
- Hongchen Ji
- Department of Oncology of Xijing Hospital, Air Force Medical University, Xi’an, Shaanxi, China
| | - Xiang-Xu Wang
- Department of Oncology of Xijing Hospital, Air Force Medical University, Xi’an, Shaanxi, China
| | - Qiong Zhang
- Department of Oncology of Xijing Hospital, Air Force Medical University, Xi’an, Shaanxi, China
| | - Chengkai Zhang
- Department of Oncology of Xijing Hospital, Air Force Medical University, Xi’an, Shaanxi, China
| | - Hong-Mei Zhang
- Department of Oncology of Xijing Hospital, Air Force Medical University, Xi’an, Shaanxi, China
| |
Collapse
|
16
|
Xiong P, Liang A, Cai X, Xia T. APTAnet: an atom-level peptide-TCR interaction affinity prediction model. BIOPHYSICS REPORTS 2024; 10:1-14. [PMID: 38737473 PMCID: PMC11079603 DOI: 10.52601/bpr.2023.230037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2023] [Accepted: 01/26/2024] [Indexed: 05/14/2024] Open
Abstract
The prediction of affinity between TCRs and peptides is crucial for the further development of TIL (Tumor-Infiltrating Lymphocytes) immunotherapy. Inspired by the broader research of drug-protein interaction (DPI), we propose an atom-level peptide-TCR interaction (PTI) affinity prediction model APTAnet using natural language processing methods. APTAnet model achieved an average ROC-AUC and PR-AUC of 0.893 and 0.877, respectively, in ten-fold cross-validation on 25,675 pairs of PTI data. Furthermore, experimental results on an independent test set from the McPAS database showed that APTAnet outperformed the current mainstream models. Finally, through the validation on 11 cases of real tumor patient data, we found that the APTAnet model can effectively identify tumor peptides and screen tumor-specific TCRs.
Collapse
Affiliation(s)
- Peng Xiong
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
| | - Anyi Liang
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
| | - Xunhui Cai
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China
| | - Tian Xia
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
- Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China
| |
Collapse
|
17
|
Vecchio E, Rotundo S, Veneziano C, Abatino A, Aversa I, Gallo R, Giordano C, Serapide F, Fusco P, Viglietto G, Cuda G, Costanzo F, Russo A, Trecarichi EM, Torti C, Palmieri C. The spike-specific TCRβ repertoire shows distinct features in unvaccinated or vaccinated patients with SARS-CoV-2 infection. J Transl Med 2024; 22:33. [PMID: 38185632 PMCID: PMC10771664 DOI: 10.1186/s12967-024-04852-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Accepted: 01/02/2024] [Indexed: 01/09/2024] Open
Abstract
BACKGROUND The evolving variants of SARS-CoV-2 may escape immunity from prior infections or vaccinations. It's vital to understand how immunity adapts to these changes. Both infection and mRNA vaccination induce T cells that target the Spike protein. These T cells can recognize multiple variants, such as Delta and Omicron, even if neutralizing antibodies are weakened. However, the degree of recognition can vary among people, affecting vaccine efficacy. Previous studies demonstrated the capability of T-cell receptor (TCR) repertoire analysis to identify conserved and immunodominant peptides with cross-reactive potential among variant of concerns. However, there is a need to extend the analysis of the TCR repertoire to different clinical scenarios. The aim of this study was to examine the Spike-specific TCR repertoire profiles in natural infections and those with combined natural and vaccine immunity. METHODS A T-cell enrichment approach and bioinformatic tools were used to investigate the Spike-specific TCRβ repertoire in peripheral blood mononuclear cells of previously vaccinated (n = 8) or unvaccinated (n = 6) COVID-19 patients. RESULTS Diversity and clonality of the TCRβ repertoire showed no significant differences between vaccinated and unvaccinated groups. When comparing the TCRβ data to public databases, 692 unique TCRβ sequences linked to S epitopes were found in the vaccinated group and 670 in the unvaccinated group. TCRβ clonotypes related to spike regions S135-177, S264-276, S319-350, and S448-472 appear notably more prevalent in the vaccinated group. In contrast, the S673-699 epitope, believed to have super antigenic properties, is observed more frequently in the unvaccinated group. In-silico analyses suggest that mutations in epitopes, relative to the main SARS-CoV-2 variants of concern, don't hinder their cross-reactive recognition by associated TCRβ clonotypes. CONCLUSIONS Our findings reveal distinct TCRβ signatures in vaccinated and unvaccinated individuals with COVID-19. These differences might be associated with disease severity and could influence clinical outcomes. TRIAL REGISTRATION FESR/FSE 2014-2020 DDRC n. 585, Action 10.5.12, noCOVID19@UMG.
Collapse
Affiliation(s)
- Eleonora Vecchio
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
- Interdepartmental Centre of Services, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Salvatore Rotundo
- Department of Medical and Surgical Sciences, Chair of Infectious and Tropical Diseases, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Claudia Veneziano
- Interdepartmental Centre of Services, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Antonio Abatino
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
| | - Ilenia Aversa
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
| | - Raffaella Gallo
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
| | - Caterina Giordano
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
| | - Francesca Serapide
- Department of Medical and Surgical Sciences, Chair of Infectious and Tropical Diseases, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Paolo Fusco
- Department of Medical and Surgical Sciences, Chair of Infectious and Tropical Diseases, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Giuseppe Viglietto
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
| | - Giovanni Cuda
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
| | - Francesco Costanzo
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy
- Interdepartmental Centre of Services, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Alessandro Russo
- Department of Medical and Surgical Sciences, Chair of Infectious and Tropical Diseases, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Enrico Maria Trecarichi
- Department of Medical and Surgical Sciences, Chair of Infectious and Tropical Diseases, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Carlo Torti
- Department of Medical and Surgical Sciences, Chair of Infectious and Tropical Diseases, University "Magna Graecia", 88100, Catanzaro, Italy
| | - Camillo Palmieri
- Department of Experimental and Clinical Medicine, University "Magna Graecia", Viale Europa, 88100, Catanzaro, Italy.
| |
Collapse
|
18
|
Nenclares P, Larkeryd A, Manodoro F, Lee JY, Lalondrelle S, Gilbert DC, Punta M, O’Leary B, Rullan A, Sadanandam A, Chain B, Melcher A, Harrington KJ, Bhide SA. T-cell receptor determinants of response to chemoradiation in locally-advanced HPV16-driven malignancies. Front Oncol 2024; 13:1296948. [PMID: 38234396 PMCID: PMC10791873 DOI: 10.3389/fonc.2023.1296948] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Accepted: 11/28/2023] [Indexed: 01/19/2024] Open
Abstract
Background The effect of chemoradiation on the anti-cancer immune response is being increasingly acknowledged; however, its clinical implications in treatment responses are yet to be fully understood. Human papillomavirus (HPV)-driven malignancies express viral oncogenic proteins which may serve as tumor-specific antigens and represent ideal candidates for monitoring the peripheral T-cell receptor (TCR) changes secondary to chemoradiotherapy (CRT). Methods We performed intra-tumoral and pre- and post-treatment peripheral TCR sequencing in a cohort of patients with locally-advanced HPV16-positive cancers treated with CRT. An in silico computational pipeline was used to cluster TCR repertoire based on epitope-specificity and to predict affinity between these clusters and HPV16-derived epitopes. Results Intra-tumoral repertoire diversity, intra-tumoral and post-treatment peripheral CDR3β similarity clustering were predictive of response. In responders, CRT triggered an increase peripheral TCR clonality and clonal relatedness. Post-treatment expansion of baseline peripheral dominant TCRs was associated with response. Responders showed more baseline clustered structures of TCRs maintained post-treatment and displayed significantly more maintained clustered structures. When applying clustering by TCR-specificity methods, responders displayed a higher proportion of intra-tumoral TCRs predicted to recognise HPV16 peptides. Conclusions Baseline TCR characteristics and changes in the peripheral T-cell clones triggered by CRT are associated with treatment outcome. Maintenance and boosting of pre-existing clonotypes are key elements of an effective anti-cancer immune response driven by CRT, supporting a paradigm in which the immune system plays a central role in the success of CRT in current standard-of-care protocols.
Collapse
Affiliation(s)
- Pablo Nenclares
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
- Head and Neck Unit, The Royal Marsden Hospital, London, United Kingdom
| | - Adrian Larkeryd
- Bioinformatics Unit, The Centre for Translational Immunotherapy, The Institute of Cancer Research, London, United Kingdom
| | - Floriana Manodoro
- Genomics Facility, The Institute of Cancer Research, London, United Kingdom
| | - Jen Y. Lee
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
| | - Susan Lalondrelle
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
| | - Duncan C. Gilbert
- Sussex Cancer Centre, University Hospitals Sussex NHS Foundation Trust, Brighton, United Kingdom
| | - Marco Punta
- Unit of Immunogenetic, Leukemia Genomics and Immunobiology, IRCCS Ospedale San Raffaele, Milan, Italy
| | - Ben O’Leary
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
- Head and Neck Unit, The Royal Marsden Hospital, London, United Kingdom
| | - Antonio Rullan
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
- Head and Neck Unit, The Royal Marsden Hospital, London, United Kingdom
| | - Anguraj Sadanandam
- Systems and Precision Cancer Medicine Team, The Institute of Cancer Research, London, United Kingdom
| | - Benny Chain
- Division of Infection and Immunity, University College London, London, United Kingdom
| | - Alan Melcher
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
| | - Kevin J. Harrington
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
- Head and Neck Unit, The Royal Marsden Hospital, London, United Kingdom
| | - Shreerang A. Bhide
- Radiotherapy and Imaging Division, The Institute of Cancer Research, London, United Kingdom
- Head and Neck Unit, The Royal Marsden Hospital, London, United Kingdom
| |
Collapse
|
19
|
Chen J, Zhao B, Lin S, Sun H, Mao X, Wang M, Chu Y, Hong L, Wei D, Li M, Xiong Y. TEPCAM: Prediction of T-cell receptor-epitope binding specificity via interpretable deep learning. Protein Sci 2024; 33:e4841. [PMID: 37983648 PMCID: PMC10731497 DOI: 10.1002/pro.4841] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 10/11/2023] [Accepted: 11/16/2023] [Indexed: 11/22/2023]
Abstract
The recognition of T-cell receptor (TCR) on the surface of T cell to specific epitope presented by the major histocompatibility complex is the key to trigger the immune response. Identifying the binding rules of TCR-epitope pair is crucial for developing immunotherapies, including neoantigen vaccine and drugs. Accurate prediction of TCR-epitope binding specificity via deep learning remains challenging, especially in test cases which are unseen in the training set. Here, we propose TEPCAM (TCR-EPitope identification based on Cross-Attention and Multi-channel convolution), a deep learning model that incorporates self-attention, cross-attention mechanism, and multi-channel convolution to improve the generalizability and enhance the model interpretability. Experimental results demonstrate that our model outperformed several state-of-the-art models on two challenging tasks including a strictly split dataset and an external dataset. Furthermore, the model can learn some interaction patterns between TCR and epitope by extracting the interpretable matrix from cross-attention layer and mapping them to the three-dimensional structures. The source code and data are freely available at https://github.com/Chenjw99/TEPCAM.
Collapse
Affiliation(s)
- Junwei Chen
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
| | - Bowen Zhao
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
| | - Shenggeng Lin
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
| | - Heqi Sun
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
| | - Xueying Mao
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
| | - Meng Wang
- Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and EngineeringCentral South UniversityChangshaChina
| | - Yanyi Chu
- Department of PathologyStanford University School of MedicineStandfordCaliforniaUSA
| | - Liang Hong
- Institute of Natural Sciences, Shanghai Jiao Tong UniversityShanghaiChina
- Artificial Intelligence Biomedical Center, Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong UniversityShanghaiChina
| | - Dong‐Qing Wei
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
| | - Min Li
- Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and EngineeringCentral South UniversityChangshaChina
| | - Yi Xiong
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina
- Artificial Intelligence Biomedical Center, Zhangjiang Institute for Advanced Study, Shanghai Jiao Tong UniversityShanghaiChina
| |
Collapse
|
20
|
Koyama K, Hashimoto K, Nagao C, Mizuguchi K. Attention network for predicting T-cell receptor-peptide binding can associate attention with interpretable protein structural properties. FRONTIERS IN BIOINFORMATICS 2023; 3:1274599. [PMID: 38170146 PMCID: PMC10759225 DOI: 10.3389/fbinf.2023.1274599] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Accepted: 11/27/2023] [Indexed: 01/05/2024] Open
Abstract
Understanding how a T-cell receptor (TCR) recognizes its specific ligand peptide is crucial for gaining an insight into biological functions and disease mechanisms. Despite its importance, experimentally determining TCR-peptide-major histocompatibility complex (TCR-pMHC) interactions is expensive and time-consuming. To address this challenge, computational methods have been proposed, but they are typically evaluated by internal retrospective validation only, and few researchers have incorporated and tested an attention layer from language models into structural information. Therefore, in this study, we developed a machine learning model based on a modified version of Transformer, a source-target attention neural network, to predict the TCR-pMHC interaction solely from the amino acid sequences of the TCR complementarity-determining region (CDR) 3 and the peptide. This model achieved competitive performance on a benchmark dataset of the TCR-pMHC interaction, as well as on a truly new external dataset. Additionally, by analyzing the results of binding predictions, we associated the neural network weights with protein structural properties. By classifying the residues into large- and small-attention groups, we identified statistically significant properties associated with the largely attended residues such as hydrogen bonds within CDR3. The dataset that we created and the ability of our model to provide an interpretable prediction of TCR-peptide binding should increase our knowledge about molecular recognition and pave the way for designing new therapeutics.
Collapse
Affiliation(s)
- Kyohei Koyama
- Laboratory for Computational Biology, Institute for Protein Research, Osaka University, Osaka, Japan
- National Institutes of Biomedical Innovation, Health and Nutrition, Osaka, Japan
- Graduate School of Frontier Biosciences, Osaka University, Osaka, Japan
| | - Kosuke Hashimoto
- Laboratory for Computational Biology, Institute for Protein Research, Osaka University, Osaka, Japan
| | - Chioko Nagao
- Laboratory for Computational Biology, Institute for Protein Research, Osaka University, Osaka, Japan
| | - Kenji Mizuguchi
- Laboratory for Computational Biology, Institute for Protein Research, Osaka University, Osaka, Japan
- National Institutes of Biomedical Innovation, Health and Nutrition, Osaka, Japan
- Graduate School of Frontier Biosciences, Osaka University, Osaka, Japan
| |
Collapse
|
21
|
Han Y, Yang Y, Tian Y, Fattah FJ, von Itzstein MS, Hu Y, Zhang M, Kang X, Yang DM, Liu J, Xue Y, Liang C, Raman I, Zhu C, Xiao O, Dowell JE, Homsi J, Rashdan S, Yang S, Gwin ME, Hsiehchen D, Gloria-McCutchen Y, Pan K, Wu F, Gibbons D, Wang X, Yee C, Huang J, Reuben A, Cheng C, Zhang J, Gerber DE, Wang T. pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.12.01.569599. [PMID: 38105939 PMCID: PMC10723300 DOI: 10.1101/2023.12.01.569599] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/19/2023]
Abstract
Profiling the binding of T cell receptors (TCRs) of T cells to antigenic peptides presented by MHC proteins is one of the most important unsolved problems in modern immunology. Experimental methods to probe TCR-antigen interactions are slow, labor-intensive, costly, and yield moderate throughput. To address this problem, we developed pMTnet-omni, an Artificial Intelligence (AI) system based on hybrid protein sequence and structure information, to predict the pairing of TCRs of αβ T cells with peptide-MHC complexes (pMHCs). pMTnet-omni is capable of handling peptides presented by both class I and II pMHCs, and capable of handling both human and mouse TCR-pMHC pairs, through information sharing enabled this hybrid design. pMTnet-omni achieves a high overall Area Under the Curve of Receiver Operator Characteristics (AUROC) of 0.888, which surpasses competing tools by a large margin. We showed that pMTnet-omni can distinguish binding affinity of TCRs with similar sequences. Across a range of datasets from various biological contexts, pMTnet-omni characterized the longitudinal evolution and spatial heterogeneity of TCR-pMHC interactions and their functional impact. We successfully developed a biomarker based on pMTnet-omni for predicting immune-related adverse events of immune checkpoint inhibitor (ICI) treatment in a cohort of 57 ICI-treated patients. pMTnet-omni represents a major advance towards developing a clinically usable AI system for TCR-pMHC pairing prediction that can aid the design and implementation of TCR-based immunotherapeutics.
Collapse
|
22
|
Zhao M, Xu SX, Yang Y, Yuan M. GGNpTCR: A Generative Graph Structure Neural Network for Predicting Immunogenic Peptides for T-cell Immune Response. J Chem Inf Model 2023; 63:7557-7567. [PMID: 37990917 DOI: 10.1021/acs.jcim.3c01293] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2023]
Abstract
Identifying the interactions between T-cell receptor (TCRs) and human antigens is a crucial step in developing new vaccines, diagnostics, and immunotherapy. Current methods primarily focus on learning binding patterns from known TCR binding repertoires by using sequence information alone without considering the binding specificity of new antigens or exogenous peptides that have not appeared in the training set. Furthermore, the spatial structure of antigens plays a critical role in immune studies and immunotherapy, which should be addressed properly in the identification of interacting TCR-antigen pairs. In this study, we introduced a novel deep learning framework based on generative graph structures, GGNpTCR, for predicting interactions between TCR and peptides from sequence information. Results of real data analysis indicate that our model achieved excellent prediction for new antigens unseen in the training data set, making significant improvements compared to existing methods. We also applied the model to a large COVID-19 data set with no antigens in the training data set, and the improvement was also significant. Furthermore, through incorporation of additional supervised mechanisms, GGNpTCR demonstrated the ability to precisely forecast the locations of peptide-TCR interactions within 3D configurations. This enhancement substantially improved the model's interpretability. In summary, based on the performance on multiple data sets, GGNpTCR has made significant progress in terms of performance, universality, and interpretability.
Collapse
Affiliation(s)
- Minghua Zhao
- Department of Statistics and Finance, University of Science and Technology of China, Hefei 230026, China
| | - Steven X Xu
- Genmab US, Inc., Princeton, New Jersey 08540, United States
| | - Yaning Yang
- Department of Statistics and Finance, University of Science and Technology of China, Hefei 230026, China
| | - Min Yuan
- School of Public Health Administration, Anhui Medical University, Hefei 230032, China
| |
Collapse
|
23
|
Pang Z, Lu MM, Zhang Y, Gao Y, Bai JJ, Gu JY, Xie L, Wu WZ. Neoantigen-targeted TCR-engineered T cell immunotherapy: current advances and challenges. Biomark Res 2023; 11:104. [PMID: 38037114 PMCID: PMC10690996 DOI: 10.1186/s40364-023-00534-0] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Accepted: 10/22/2023] [Indexed: 12/02/2023] Open
Abstract
Adoptive cell therapy using T cell receptor-engineered T cells (TCR-T) is a promising approach for cancer therapy with an expectation of no significant side effects. In the human body, mature T cells are armed with an incredible diversity of T cell receptors (TCRs) that theoretically react to the variety of random mutations generated by tumor cells. The outcomes, however, of current clinical trials using TCR-T cell therapies are not very successful especially involving solid tumors. The therapy still faces numerous challenges in the efficient screening of tumor-specific antigens and their cognate TCRs. In this review, we first introduce TCR structure-based antigen recognition and signaling, then describe recent advances in neoantigens and their specific TCR screening technologies, and finally summarize ongoing clinical trials of TCR-T therapies against neoantigens. More importantly, we also present the current challenges of TCR-T cell-based immunotherapies, e.g., the safety of viral vectors, the mismatch of T cell receptor, the impediment of suppressive tumor microenvironment. Finally, we highlight new insights and directions for personalized TCR-T therapy.
Collapse
Affiliation(s)
- Zhi Pang
- Liver Cancer Institute, Key Laboratory of Carcinogenesis and Cancer Invasion, Ministry of Education, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
- Clinical Center for Biotherapy, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
| | - Man-Man Lu
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, 200237, China
| | - Yu Zhang
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, 200237, China
| | - Yuan Gao
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, 200237, China
| | - Jin-Jin Bai
- Liver Cancer Institute, Key Laboratory of Carcinogenesis and Cancer Invasion, Ministry of Education, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
- Clinical Center for Biotherapy, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
| | - Jian-Ying Gu
- Clinical Center for Biotherapy, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
| | - Lu Xie
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, 200237, China.
| | - Wei-Zhong Wu
- Liver Cancer Institute, Key Laboratory of Carcinogenesis and Cancer Invasion, Ministry of Education, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
- Clinical Center for Biotherapy, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
| |
Collapse
|
24
|
Korpela D, Jokinen E, Dumitrescu A, Huuhtanen J, Mustjoki S, Lähdesmäki H. EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings. Bioinformatics 2023; 39:btad743. [PMID: 38070156 PMCID: PMC10963061 DOI: 10.1093/bioinformatics/btad743] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 11/20/2023] [Accepted: 12/07/2023] [Indexed: 12/21/2023] Open
Abstract
MOTIVATION T cells play an essential role in adaptive immune system to fight pathogens and cancer but may also give rise to autoimmune diseases. The recognition of a peptide-MHC (pMHC) complex by a T cell receptor (TCR) is required to elicit an immune response. Many machine learning models have been developed to predict the binding, but generalizing predictions to pMHCs outside the training data remains challenging. RESULTS We have developed a new machine learning model that utilizes information about the TCR from both α and β chains, epitope sequence, and MHC. Our method uses ProtBERT embeddings for the amino acid sequences of both chains and the epitope, as well as convolution and multi-head attention architectures. We show the importance of each input feature as well as the benefit of including epitopes with only a few TCRs to the training data. We evaluate our model on existing databases and show that it compares favorably against other state-of-the-art models. AVAILABILITY AND IMPLEMENTATION https://github.com/DaniTheOrange/EPIC-TRACE.
Collapse
Affiliation(s)
- Dani Korpela
- Department of Computer Science, Aalto University, 02150 Espoo, Finland
| | - Emmi Jokinen
- Department of Computer Science, Aalto University, 02150 Espoo, Finland
- Translational Immunology Research Program, Department of Clinical Chemistry and Hematology, University of Helsinki, 00290 Helsinki, Finland
- Hematology Research Unit Helsinki, Helsinki University Hospital Comprehensive Cancer Center, 00290 Helsinki, Finland
| | | | - Jani Huuhtanen
- Translational Immunology Research Program, Department of Clinical Chemistry and Hematology, University of Helsinki, 00290 Helsinki, Finland
- Hematology Research Unit Helsinki, Helsinki University Hospital Comprehensive Cancer Center, 00290 Helsinki, Finland
| | - Satu Mustjoki
- Translational Immunology Research Program, Department of Clinical Chemistry and Hematology, University of Helsinki, 00290 Helsinki, Finland
- Hematology Research Unit Helsinki, Helsinki University Hospital Comprehensive Cancer Center, 00290 Helsinki, Finland
- iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland
| | - Harri Lähdesmäki
- Department of Computer Science, Aalto University, 02150 Espoo, Finland
| |
Collapse
|
25
|
Lee SB, Pan J, Xiong D, Palen K, Johnson B, Lubet RA, Shoemaker RH, Green JE, Fernando RI, Sei S, You M, Wang Y. Striking efficacy of a vaccine targeting TOP2A for triple-negative breast cancer immunoprevention. NPJ Precis Oncol 2023; 7:108. [PMID: 37880313 PMCID: PMC10600249 DOI: 10.1038/s41698-023-00461-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Accepted: 09/29/2023] [Indexed: 10/27/2023] Open
Abstract
Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer that has a poor prognosis. TOP2A is a key enzyme in DNA replication and is a therapeutic target for breast and other cancers. TOP2A-specific Th1-promoting epitopes with optimal binding affinity to MHC II were identified using a combined scoring system. The multi-peptide TOP2A vaccine elicited a robust immunologic response in immunized mice, as demonstrated by the significant production of Th1 cytokines from immunized animals' splenocytes stimulated in vitro with TOP2A peptides. Anti-tumor efficacy of the TOP2A vaccine was demonstrated in a syngeneic TNBC mouse model, in which pre-graft preventive vaccination was associated with significantly decreased tumor growth as compared to adjuvant control. In a genetically engineered mouse (GEM) model of TNBC, vaccinated animals demonstrated a significant reduction in tumor incidence and average tumor volume compared to adjuvant control. Finally, we examined TCR sequences in CD4 tumor Infiltrating lymphocytes (TIL) from vaccinated mice and found that the TIL contained TCR sequences specific to the three vaccine peptides. These data indicate that our newly developed multi-peptide TOP2A vaccine is highly immunogenic, elicits TILs with vaccine specific TCRs, and is highly effective in preventing and intercepting TNBC development and progression in vivo.
Collapse
Affiliation(s)
- Sang Beom Lee
- Center for Cancer Prevention, Houston Methodist Cancer Center, Houston Methodist Research Institute, Weill Cornell College of Medicine, Houston, TX, USA
| | - Jing Pan
- Center for Cancer Prevention, Houston Methodist Cancer Center, Houston Methodist Research Institute, Weill Cornell College of Medicine, Houston, TX, USA
| | - Donghai Xiong
- Center for Cancer Prevention, Houston Methodist Cancer Center, Houston Methodist Research Institute, Weill Cornell College of Medicine, Houston, TX, USA
| | - Katie Palen
- Division of Hematology and Oncology, Department of Medicine, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Bryon Johnson
- Division of Hematology and Oncology, Department of Medicine, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Ronald A Lubet
- Chemopreventive Agent Development Research Group, Division of Cancer Prevention, National Cancer Institute, Bethesda, MD, USA
| | - Robert H Shoemaker
- Chemopreventive Agent Development Research Group, Division of Cancer Prevention, National Cancer Institute, Bethesda, MD, USA
| | - Jeffrey E Green
- Laboratory of Cancer Biology and Genetics, National Cancer Institute, NIH, Bethesda, MD, USA
| | - Romaine Ingrid Fernando
- Chemopreventive Agent Development Research Group, Division of Cancer Prevention, National Cancer Institute, Bethesda, MD, USA
| | - Shizuko Sei
- Chemopreventive Agent Development Research Group, Division of Cancer Prevention, National Cancer Institute, Bethesda, MD, USA
| | - Ming You
- Center for Cancer Prevention, Houston Methodist Cancer Center, Houston Methodist Research Institute, Weill Cornell College of Medicine, Houston, TX, USA.
| | - Yian Wang
- Center for Cancer Prevention, Houston Methodist Cancer Center, Houston Methodist Research Institute, Weill Cornell College of Medicine, Houston, TX, USA.
| |
Collapse
|
26
|
Bravi B, Di Gioacchino A, Fernandez-de-Cossio-Diaz J, Walczak AM, Mora T, Cocco S, Monasson R. A transfer-learning approach to predict antigen immunogenicity and T-cell receptor specificity. eLife 2023; 12:e85126. [PMID: 37681658 PMCID: PMC10522340 DOI: 10.7554/elife.85126] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 09/07/2023] [Indexed: 09/09/2023] Open
Abstract
Antigen immunogenicity and the specificity of binding of T-cell receptors to antigens are key properties underlying effective immune responses. Here we propose diffRBM, an approach based on transfer learning and Restricted Boltzmann Machines, to build sequence-based predictive models of these properties. DiffRBM is designed to learn the distinctive patterns in amino-acid composition that, on the one hand, underlie the antigen's probability of triggering a response, and on the other hand the T-cell receptor's ability to bind to a given antigen. We show that the patterns learnt by diffRBM allow us to predict putative contact sites of the antigen-receptor complex. We also discriminate immunogenic and non-immunogenic antigens, antigen-specific and generic receptors, reaching performances that compare favorably to existing sequence-based predictors of antigen immunogenicity and T-cell receptor specificity.
Collapse
Affiliation(s)
- Barbara Bravi
- Department of Mathematics, Imperial College LondonLondonUnited Kingdom
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| | - Andrea Di Gioacchino
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| | - Jorge Fernandez-de-Cossio-Diaz
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| | - Aleksandra M Walczak
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| | - Thierry Mora
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| | - Simona Cocco
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| | - Rémi Monasson
- Laboratoire de Physique de l’Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-CitéParisFrance
| |
Collapse
|
27
|
Ghoreyshi ZS, George JT. Quantitative approaches for decoding the specificity of the human T cell repertoire. Front Immunol 2023; 14:1228873. [PMID: 37781387 PMCID: PMC10539903 DOI: 10.3389/fimmu.2023.1228873] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 08/17/2023] [Indexed: 10/03/2023] Open
Abstract
T cell receptor (TCR)-peptide-major histocompatibility complex (pMHC) interactions play a vital role in initiating immune responses against pathogens, and the specificity of TCRpMHC interactions is crucial for developing optimized therapeutic strategies. The advent of high-throughput immunological and structural evaluation of TCR and pMHC has provided an abundance of data for computational approaches that aim to predict favorable TCR-pMHC interactions. Current models are constructed using information on protein sequence, structures, or a combination of both, and utilize a variety of statistical learning-based approaches for identifying the rules governing specificity. This review examines the current theoretical, computational, and deep learning approaches for identifying TCR-pMHC recognition pairs, placing emphasis on each method's mathematical approach, predictive performance, and limitations.
Collapse
Affiliation(s)
- Zahra S. Ghoreyshi
- Department of Biomedical Engineering, Texas A&M University, College Station, TX, United States
| | - Jason T. George
- Department of Biomedical Engineering, Texas A&M University, College Station, TX, United States
- Engineering Medicine Program, Texas A&M University, Houston, TX, United States
- Center for Theoretical Biological Physics, Rice University, Houston, TX, United States
| |
Collapse
|
28
|
Shcherbinin DS, Karnaukhov VK, Zvyagin IV, Chudakov DM, Shugay M. Large-scale template-based structural modeling of T-cell receptors with known antigen specificity reveals complementarity features. Front Immunol 2023; 14:1224969. [PMID: 37649481 PMCID: PMC10464843 DOI: 10.3389/fimmu.2023.1224969] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2023] [Accepted: 07/27/2023] [Indexed: 09/01/2023] Open
Abstract
Introduction T-cell receptor (TCR) recognition of foreign peptides presented by the major histocompatibility complex (MHC) initiates the adaptive immune response against pathogens. While a large number of TCR sequences specific to different antigenic peptides are known to date, the structural data describing the conformation and contacting residues for TCR-peptide-MHC complexes is relatively limited. In the present study we aim to extend and analyze the set of available structures by performing highly accurate template-based modeling of these complexes using TCR sequences with known specificity. Methods Identification of CDR3 sequences and their further clustering, based on available spatial structures, V- and J-genes of corresponding T-cell receptors, and epitopes, was performed using the VDJdb database. Modeling of the selected CDR3 loops was conducted using a stepwise introduction of single amino acid substitutions to the template PDB structures, followed by optimization of the TCR-peptide-MHC contacting interface using the Rosetta package applications. Statistical analysis and recursive feature elimination procedures were carried out on computed energy values and properties of contacting amino acid residues between CDR3 loops and peptides, using R. Results Using the set of 29 complex templates (including a template with SARS-CoV-2 antigen) and 732 specificity records, we built a database of 1585 model structures carrying substitutions in either TCRα or TCRβ chains with some models representing the result of different mutation pathways for the same final structure. This database allowed us to analyze features of amino acid contacts in TCR - peptide interfaces that govern antigen recognition preferences and interpret these interactions in terms of physicochemical properties of interacting residues. Conclusion Our results provide a methodology for creating high-quality TCR-peptide-MHC models for antigens of interest that can be utilized to predict TCR specificity.
Collapse
Affiliation(s)
- Dmitrii S. Shcherbinin
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia
- Laboratory of Structural Bioinformatics, Institute of Biomedical Chemistry, Moscow, Russia
| | - Vadim K. Karnaukhov
- Center of Life Sciences, Skolkovo Institute of Science and Technology, Moscow, Russia
| | - Ivan V. Zvyagin
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
| | - Dmitriy M. Chudakov
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia
- Center of Life Sciences, Skolkovo Institute of Science and Technology, Moscow, Russia
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
- Center of Molecular Medicine, Central European Institute of Technology (CEITEC), Masaryk University, Brno, Czechia
| | - Mikhail Shugay
- Institute of Translational Medicine, Center for Precision Genome Editing and Genetic Technologies for Biomedicine, Pirogov Russian National Research Medical University, Moscow, Russia
- Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry, Russian Academy of Sciences, Moscow, Russia
| |
Collapse
|
29
|
Zhao Y, He B, Xu F, Li C, Xu Z, Su X, He H, Huang Y, Rossjohn J, Song J, Yao J. DeepAIR: A deep learning framework for effective integration of sequence and 3D structure to enable adaptive immune receptor analysis. SCIENCE ADVANCES 2023; 9:eabo5128. [PMID: 37556545 PMCID: PMC10411891 DOI: 10.1126/sciadv.abo5128] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Accepted: 07/06/2023] [Indexed: 08/11/2023]
Abstract
Structural docking between the adaptive immune receptors (AIRs), including T cell receptors (TCRs) and B cell receptors (BCRs), and their cognate antigens are one of the most fundamental processes in adaptive immunity. However, current methods for predicting AIR-antigen binding largely rely on sequence-derived features of AIRs, omitting the structure features that are essential for binding affinity. In this study, we present a deep learning framework, termed DeepAIR, for the accurate prediction of AIR-antigen binding by integrating both sequence and structure features of AIRs. DeepAIR achieves a Pearson's correlation of 0.813 in predicting the binding affinity of TCR, and a median area under the receiver-operating characteristic curve (AUC) of 0.904 and 0.942 in predicting the binding reactivity of TCR and BCR, respectively. Meanwhile, using TCR and BCR repertoire, DeepAIR correctly identifies every patient with nasopharyngeal carcinoma and inflammatory bowel disease in test data. Thus, DeepAIR improves the AIR-antigen binding prediction that facilitates the study of adaptive immunity.
Collapse
Affiliation(s)
- Yu Zhao
- AI Lab, Tencent, Shenzhen, China
| | - Bing He
- AI Lab, Tencent, Shenzhen, China
| | - Fan Xu
- AI Lab, Tencent, Shenzhen, China
| | - Chen Li
- Biomedicine Discovery Institute and Monash Data Futures Institute, Monash University, Melbourne, VIC 3800, Australia
| | | | | | | | | | - Jamie Rossjohn
- Infection and Immunity Program and Department of Biochemistry and Molecular Biology, Biomedicine Discovery Institute, Monash University, Melbourne, VIC 3800, Australia
- Institute of Infection and Immunity, Cardiff University School of Medicine, Heath Park, Cardiff, UK
| | - Jiangning Song
- AI Lab, Tencent, Shenzhen, China
- Biomedicine Discovery Institute and Monash Data Futures Institute, Monash University, Melbourne, VIC 3800, Australia
| | | |
Collapse
|
30
|
Yang M, Huang ZA, Zhou W, Ji J, Zhang J, He S, Zhu Z. MIX-TPI: a flexible prediction framework for TCR-pMHC interactions based on multimodal representations. Bioinformatics 2023; 39:btad475. [PMID: 37527015 PMCID: PMC10423027 DOI: 10.1093/bioinformatics/btad475] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Revised: 07/05/2023] [Accepted: 07/29/2023] [Indexed: 08/03/2023] Open
Abstract
MOTIVATION The interactions between T-cell receptors (TCR) and peptide-major histocompatibility complex (pMHC) are essential for the adaptive immune system. However, identifying these interactions can be challenging due to the limited availability of experimental data, sequence data heterogeneity, and high experimental validation costs. RESULTS To address this issue, we develop a novel computational framework, named MIX-TPI, to predict TCR-pMHC interactions using amino acid sequences and physicochemical properties. Based on convolutional neural networks, MIX-TPI incorporates sequence-based and physicochemical-based extractors to refine the representations of TCR-pMHC interactions. Each modality is projected into modality-invariant and modality-specific representations to capture the uniformity and diversities between different features. A self-attention fusion layer is then adopted to form the classification module. Experimental results demonstrate the effectiveness of MIX-TPI in comparison with other state-of-the-art methods. MIX-TPI also shows good generalization capability on mutual exclusive evaluation datasets and a paired TCR dataset. AVAILABILITY AND IMPLEMENTATION The source code of MIX-TPI and the test data are available at: https://github.com/Wolverinerine/MIX-TPI.
Collapse
Affiliation(s)
- Minghao Yang
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
| | - Zhi-An Huang
- Research Office, City University of Hong Kong (Dongguan), Dongguan 523000, China
| | - Wei Zhou
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
| | - Junkai Ji
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
| | - Jun Zhang
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
| | - Shan He
- School of Computer Science, University of Birmingham, Birmingham B15 2TT, United Kingdom
| | - Zexuan Zhu
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
- National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen 518060, China
| |
Collapse
|
31
|
Hudson D, Fernandes RA, Basham M, Ogg G, Koohy H. Can we predict T cell specificity with digital biology and machine learning? Nat Rev Immunol 2023; 23:511-521. [PMID: 36755161 PMCID: PMC9908307 DOI: 10.1038/s41577-023-00835-3] [Citation(s) in RCA: 32] [Impact Index Per Article: 32.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 12/07/2022] [Indexed: 02/10/2023]
Abstract
Recent advances in machine learning and experimental biology have offered breakthrough solutions to problems such as protein structure prediction that were long thought to be intractable. However, despite the pivotal role of the T cell receptor (TCR) in orchestrating cellular immunity in health and disease, computational reconstruction of a reliable map from a TCR to its cognate antigens remains a holy grail of systems immunology. Current data sets are limited to a negligible fraction of the universe of possible TCR-ligand pairs, and performance of state-of-the-art predictive models wanes when applied beyond these known binders. In this Perspective article, we make the case for renewed and coordinated interdisciplinary effort to tackle the problem of predicting TCR-antigen specificity. We set out the general requirements of predictive models of antigen binding, highlight critical challenges and discuss how recent advances in digital biology such as single-cell technology and machine learning may provide possible solutions. Finally, we describe how predicting TCR specificity might contribute to our understanding of the broader puzzle of antigen immunogenicity.
Collapse
Affiliation(s)
- Dan Hudson
- MRC Human Immunology Unit, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK
- The Rosalind Franklin Institute, Didcot, UK
| | - Ricardo A Fernandes
- Chinese Academy of Medical Sciences Oxford Institute, University of Oxford, Oxford, UK
| | | | - Graham Ogg
- MRC Human Immunology Unit, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK
- Chinese Academy of Medical Sciences Oxford Institute, University of Oxford, Oxford, UK
| | - Hashem Koohy
- MRC Human Immunology Unit, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK.
- Centre for Computational Biology, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK.
| |
Collapse
|
32
|
Myronov A, Mazzocco G, Król P, Plewczynski D. BERTrand-peptide:TCR binding prediction using Bidirectional Encoder Representations from Transformers augmented with random TCR pairing. Bioinformatics 2023; 39:btad468. [PMID: 37535685 PMCID: PMC10444968 DOI: 10.1093/bioinformatics/btad468] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2023] [Revised: 06/28/2023] [Accepted: 08/01/2023] [Indexed: 08/05/2023] Open
Abstract
MOTIVATION The advent of T-cell receptor (TCR) sequencing experiments allowed for a significant increase in the amount of peptide:TCR binding data available and a number of machine-learning models appeared in recent years. High-quality prediction models for a fixed epitope sequence are feasible, provided enough known binding TCR sequences are available. However, their performance drops significantly for previously unseen peptides. RESULTS We prepare the dataset of known peptide:TCR binders and augment it with negative decoys created using healthy donors' T-cell repertoires. We employ deep learning methods commonly applied in Natural Language Processing to train part a peptide:TCR binding model with a degree of cross-peptide generalization (0.69 AUROC). We demonstrate that BERTrand outperforms the published methods when evaluated on peptide sequences not used during model training. AVAILABILITY AND IMPLEMENTATION The datasets and the code for model training are available at https://github.com/SFGLab/bertrand.
Collapse
Affiliation(s)
- Alexander Myronov
- Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
- Ardigen, Krakow, Poland
| | | | | | - Dariusz Plewczynski
- Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland
| |
Collapse
|
33
|
Zhang Y, Jian X, Xu L, Zhao J, Lu M, Lin Y, Xie L. iTCep: a deep learning framework for identification of T cell epitopes by harnessing fusion features. Front Genet 2023; 14:1141535. [PMID: 37229205 PMCID: PMC10203616 DOI: 10.3389/fgene.2023.1141535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Accepted: 04/20/2023] [Indexed: 05/27/2023] Open
Abstract
Neoantigens recognized by cytotoxic T cells are effective targets for tumor-specific immune responses for personalized cancer immunotherapy. Quite a few neoantigen identification pipelines and computational strategies have been developed to improve the accuracy of the peptide selection process. However, these methods mainly consider the neoantigen end and ignore the interaction between peptide-TCR and the preference of each residue in TCRs, resulting in the filtered peptides often fail to truly elicit an immune response. Here, we propose a novel encoding approach for peptide-TCR representation. Subsequently, a deep learning framework, namely iTCep, was developed to predict the interactions between peptides and TCRs using fusion features derived from a feature-level fusion strategy. The iTCep achieved high predictive performance with AUC up to 0.96 on the testing dataset and above 0.86 on independent datasets, presenting better prediction performance compared with other predictors. Our results provided strong evidence that model iTCep can be a reliable and robust method for predicting TCR binding specificities of given antigen peptides. One can access the iTCep through a user-friendly web server at http://biostatistics.online/iTCep/, which supports prediction modes of peptide-TCR pairs and peptide-only. A stand-alone software program for T cell epitope prediction is also available for convenient installing at https://github.com/kbvstmd/iTCep/.
Collapse
Affiliation(s)
- Yu Zhang
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
| | - Xingxing Jian
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
- Bioinformatics Center, National Clinical Research Centre for Geriatric Disorders, Department of Geriatrics, Xiangya Hospital, Central South University, Changsha, Hunan, China
| | - Linfeng Xu
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
- Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, Institute of Bio-Diversity Science, School of Life Sciences, Fudan University, Shanghai, China
| | - Jingjing Zhao
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
| | - Manman Lu
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
| | - Yong Lin
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
| | - Lu Xie
- Shanghai-MOST Key Laboratory of Health and Disease Genomics, Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
| |
Collapse
|
34
|
Wu J, Qi M, Zhang F, Zheng Y. TPBTE: A model based on convolutional Transformer for predicting the binding of TCR to epitope. Mol Immunol 2023; 157:30-41. [PMID: 36966551 DOI: 10.1016/j.molimm.2023.03.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2022] [Revised: 03/12/2023] [Accepted: 03/14/2023] [Indexed: 03/29/2023]
Abstract
T cell receptors (TCRs) selectively bind to antigens to fight pathogens with specific immunity. Current tools focus on the nature of amino acids within sequences and take less into account the nature of amino acids far apart and the relationship between sequences, leading to significant differences in the results from different datasets. We propose TPBTE, a model based on convolutional Transformer for Predicting the Binding of TCR to Epitope. It takes epitope sequences and the complementary decision region 3 (CDR3) sequences of TCRβ chain as inputs. And it uses a convolutional attention mechanism to learn amino acid representations between different positions of the sequences based on learning local features of the sequences. At the same time, it uses cross attention to learn the interaction information between TCR sequences and epitope sequences. A comprehensive evaluation of the TCR-epitope data shows that the average area under the curve of TPBTE outperforms the baseline model, and demonstrate an intentional performance. In addition, TPBTE can give the probability of binding TCR to epitopes, which can be used as the first step of epitope screening, narrowing the scope of epitope search and reducing the time of epitope search.
Collapse
|
35
|
Peng X, Lei Y, Feng P, Jia L, Ma J, Zhao D, Zeng J. Characterizing the interaction conformation between T-cell receptors and epitopes with deep learning. NAT MACH INTELL 2023. [DOI: 10.1038/s42256-023-00634-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/29/2023]
|
36
|
Frank ML, Lu K, Erdogan C, Han Y, Hu J, Wang T, Heymach JV, Zhang J, Reuben A. T-Cell Receptor Repertoire Sequencing in the Era of Cancer Immunotherapy. Clin Cancer Res 2023; 29:994-1008. [PMID: 36413126 PMCID: PMC10011887 DOI: 10.1158/1078-0432.ccr-22-2469] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2022] [Revised: 10/07/2022] [Accepted: 11/14/2022] [Indexed: 11/23/2022]
Abstract
T cells are integral components of the adaptive immune system, and their responses are mediated by unique T-cell receptors (TCR) that recognize specific antigens from a variety of biological contexts. As a result, analyzing the T-cell repertoire offers a better understanding of immune responses and of diseases like cancer. Next-generation sequencing technologies have greatly enabled the high-throughput analysis of the TCR repertoire. On the basis of our extensive experience in the field from the past decade, we provide an overview of TCR sequencing, from the initial library preparation steps to sequencing and analysis methods and finally to functional validation techniques. With regards to data analysis, we detail important TCR repertoire metrics and present several computational tools for predicting antigen specificity. Finally, we highlight important applications of TCR sequencing and repertoire analysis to understanding tumor biology and developing cancer immunotherapies.
Collapse
Affiliation(s)
- Meredith L Frank
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas.,The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, Texas
| | - Kaylene Lu
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas.,The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, Texas.,Department of Cancer Biology, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Can Erdogan
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas.,Rice University, Houston, Texas
| | - Yi Han
- Quantitative Biomedical Research Center, Peter O'Donnell Jr. School of Public Health, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Jian Hu
- The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, Texas.,Department of Cancer Biology, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Tao Wang
- Quantitative Biomedical Research Center, Peter O'Donnell Jr. School of Public Health, University of Texas Southwestern Medical Center, Dallas, Texas.,Center for the Genetics of Host Defense, University of Texas Southwestern Medical Center, Dallas, Texas
| | - John V Heymach
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas.,The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, Texas
| | - Jianjun Zhang
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas.,The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, Texas.,Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Alexandre Reuben
- Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas.,The University of Texas MD Anderson Cancer Center UT Health Houston Graduate School of Biomedical Sciences, Houston, Texas
| |
Collapse
|
37
|
Gao Y, Gao Y, Fan Y, Zhu C, Wei Z, Zhou C, Chuai G, Chen Q, Zhang H, Liu Q. Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition. NAT MACH INTELL 2023. [DOI: 10.1038/s42256-023-00619-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/08/2023]
|
38
|
Sanromán ÁF, Joshi K, Au L, Chain B, Turajlic S. TCR sequencing: applications in immuno-oncology research. IMMUNO-ONCOLOGY TECHNOLOGY 2023; 17:100373. [PMID: 36908996 PMCID: PMC9996383 DOI: 10.1016/j.iotech.2023.100373] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Abstract
•T-cell receptor (TCR) interaction with major histocompatibility complex-antigen complexes leads to antitumour responses.•TCR sequencing analysis allows characterisation of T cells that recognise tumour neoantigens.•T-cell clonal revival and clonal replacement potentially underpin immunotherapy responses.
Collapse
Affiliation(s)
- Á F Sanromán
- Cancer Dynamics Laboratory, The Francis Crick Institute, London, UK
| | - K Joshi
- Department of Medical Oncology, The Royal Marsden NHS Foundation Trust, London, UK.,Renal and Skin Unit, The Royal Marsden NHS Foundation Trust, London, UK
| | - L Au
- Cancer Dynamics Laboratory, The Francis Crick Institute, London, UK.,Department of Medical Oncology, Peter MacCallum Cancer Centre, Melbourne, Australia.,Cancer Immunology Program, Peter MacCallum Cancer Centre, Melbourne, Australia.,Sir Peter MacCallum Department of Oncology, The University of Melbourne, Australia
| | - B Chain
- Division of Infection and Immunity, University College London, London, UK.,Department of Computer Science, University College London, London, UK
| | - S Turajlic
- Renal and Skin Unit, The Royal Marsden NHS Foundation Trust, London, UK.,Melanoma and Kidney Cancer Team, The Institute of Cancer Research, London, UK
| |
Collapse
|
39
|
Vlachonikola E, Pechlivanis N, Karakatsoulis G, Sofou E, Gkoliou G, Jeromin S, Stavroyianni N, Ranghetti P, Scarfo L, Österholm C, Mansouri L, Notopoulou S, Siorenta A, Anagnostopoulos A, Ghia P, Haferlach C, Rosenquist R, Psomopoulos F, Kouvatsi A, Baliakas P, Stamatopoulos K, Chatzidimitriou A. T cell receptor gene repertoire profiles in subgroups of patients with chronic lymphocytic leukemia bearing distinct genomic aberrations. Front Oncol 2023; 13:1097942. [PMID: 36816924 PMCID: PMC9929157 DOI: 10.3389/fonc.2023.1097942] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Accepted: 01/17/2023] [Indexed: 02/05/2023] Open
Abstract
Background Microenvironmental interactions of the malignant clone with T cells are critical throughout the natural history of chronic lymphocytic leukemia (CLL). Indeed, clonal expansions of T cells and shared clonotypes exist between different CLL patients, strongly implying clonal selection by antigens. Moreover, immunogenic neoepitopes have been isolated from the clonotypic B cell receptor immunoglobulin sequences, offering a rationale for immunotherapeutic approaches. Here, we interrogated the T cell receptor (TR) gene repertoire of CLL patients with different genomic aberration profiles aiming to identify unique signatures that would point towards an additional source of immunogenic neoepitopes for T cells. Experimental design TR gene repertoire profiling using next generation sequencing in groups of patients with CLL carrying one of the following copy-number aberrations (CNAs): del(11q), del(17p), del(13q), trisomy 12, or gene mutations in TP53 or NOTCH1. Results Oligoclonal expansions were found in all patients with distinct recurrent genomic aberrations; these were more pronounced in cases bearing CNAs, particularly trisomy 12, rather than gene mutations. Shared clonotypes were found both within and across groups, which appeared to be CLL-biased based on extensive comparisons against TR databases from various entities. Moreover, in silico analysis identified TR clonotypes with high binding affinity to neoepitopes predicted to arise from TP53 and NOTCH1 mutations. Conclusions Distinct TR repertoire profiles were identified in groups of patients with CLL bearing different genomic aberrations, alluding to distinct selection processes. Abnormal protein expression and gene dosage effects associated with recurrent genomic aberrations likely represent a relevant source of CLL-specific selecting antigens.
Collapse
Affiliation(s)
- Elisavet Vlachonikola
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Department of Genetics, Development and Molecular Biology, School of Biology, Aristotle, University of Thessaloniki, Thessaloniki, Greece
| | - Nikolaos Pechlivanis
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Department of Genetics, Development and Molecular Biology, School of Biology, Aristotle, University of Thessaloniki, Thessaloniki, Greece
| | - Georgios Karakatsoulis
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Department of Mathematics, School of Sciences, University of Ioannina, Ioannina, Greece
| | - Electra Sofou
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Laboratory of Biological Chemistry, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Glykeria Gkoliou
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Department of Medicine, Democritus University of Thrace, Alexandroupolis, Greece
| | | | - Niki Stavroyianni
- Hematology Department and Hematopoietic Cell Transplantation (HCT) Unit, G. Papanicolaou Hospital, Thessaloniki, Greece
| | - Pamela Ranghetti
- Division of Experimental Oncology, Università Vita-Salute San Raffaele and Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Ospedale San Raffaele, Milan, Italy
| | - Lydia Scarfo
- Division of Experimental Oncology, Università Vita-Salute San Raffaele and Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Ospedale San Raffaele, Milan, Italy
| | - Cecilia Österholm
- Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden
| | - Larry Mansouri
- Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden
| | - Sofia Notopoulou
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece
| | - Alexandra Siorenta
- Immunology Department and National Tissue Typing Center, General Hospital of Athens “G. Gennimatas”, Athens, Greece
| | - Achilles Anagnostopoulos
- Hematology Department and Hematopoietic Cell Transplantation (HCT) Unit, G. Papanicolaou Hospital, Thessaloniki, Greece
| | - Paolo Ghia
- Division of Experimental Oncology, Università Vita-Salute San Raffaele and Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Ospedale San Raffaele, Milan, Italy
| | | | - Richard Rosenquist
- Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden,Clinical Genetics, Karolinska University Hospital, Solna, Sweden
| | - Fotis Psomopoulos
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece
| | - Anastasia Kouvatsi
- Department of Genetics, Development and Molecular Biology, School of Biology, Aristotle, University of Thessaloniki, Thessaloniki, Greece
| | - Panagiotis Baliakas
- Department of Immunology, Genetics and Pathology, Science for Life Laboratory, Uppsala University, Uppsala, Sweden
| | - Kostas Stamatopoulos
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden
| | - Anastasia Chatzidimitriou
- Institute of Applied Biosciences, Centre for Research and Technology Hellas, Thessaloniki, Greece,Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden,*Correspondence: Anastasia Chatzidimitriou,
| |
Collapse
|
40
|
Jian X, Zhang Y, Zhao J, Zhao Z, Lu M, Xie L. CoV2-TCR: A web server for screening TCR CDR3 from TCR immune repertoire of COVID-19 patients and their recognized SARS-CoV-2 epitopes. Comput Struct Biotechnol J 2023; 21:1362-1371. [PMID: 36741787 PMCID: PMC9882952 DOI: 10.1016/j.csbj.2023.01.038] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2022] [Revised: 01/08/2023] [Accepted: 01/26/2023] [Indexed: 01/30/2023] Open
Abstract
Although multiple vaccines have been developed and widely administered, several severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants have been reported to evade immune responses and spread diffusely. Here, 108 RNA-seq files from coronavirus disease 2019 (COVID-19) patients and healthy donors (HD) were downloaded to extract their TCR immune repertoire by MiXCR. Those extracted TCR repertoire were compared and it was found that disease progression was related negatively with diversity and positively with clonality. Specifically, greater proportions of high-abundance clonotypes were observed in active and severe COVID-19 samples, probably resulting from strong stimulation of SARS-CoV-2 epitopes and a continued immune response in host. To investigate the specific recognition between TCR CDR3 and SARS-CoV-2 epitopes, we constructed an accurate classifier CoV2-TCR with an AUC of 0.967 in an independent dataset, which outperformed several similar tools. Based on this model, we observed a huge range in the number of those TCR CDR3 recognizing those different peptides, including 28 MHC-I epitopes from SARS-CoV-2 and 22 immunogenic peptides from SARS-CoV-2 variants. Interestingly, their proportions of high-abundance, low-abundance and rare clonotypes were close for each peptide. To expand the potential application of this model, we established the webserver, CoV2-TCR, in which users can obtain those recognizing CDR3 sequences from the TCR repertoire of COVID-19 patients based on the 9-mer peptides containing mutation site(s) on the four main proteins of SARS-CoV-2 variants. Overall, this study provides preliminary screening for candidate antigen epitopes and the TCR CDR3 that recognizes them, and should be helpful for vaccine design on SARS-CoV-2 variants.
Collapse
Affiliation(s)
- Xingxing Jian
- Bioinformatics Center & National Clinical Research Centre for Geriatric Disorders & Department of Geriatrics, Xiangya Hospital, Central South University, Changsha, Hunan, China,Corresponding author.
| | - Yu Zhang
- Shanghai-MOST Key Laboratory of Health and Disease Genomics (Chinese National Human Genome Center at Shanghai), Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China,School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai, China
| | - Jingjing Zhao
- Shanghai-MOST Key Laboratory of Health and Disease Genomics (Chinese National Human Genome Center at Shanghai), Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China,College of Food Science and Technology, Shanghai Ocean University, Shanghai, China
| | - Zhuoming Zhao
- Shanghai-MOST Key Laboratory of Health and Disease Genomics (Chinese National Human Genome Center at Shanghai), Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China,College of Food Science and Technology, Shanghai Ocean University, Shanghai, China
| | - Manman Lu
- Shanghai-MOST Key Laboratory of Health and Disease Genomics (Chinese National Human Genome Center at Shanghai), Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China
| | - Lu Xie
- Bioinformatics Center & National Clinical Research Centre for Geriatric Disorders & Department of Geriatrics, Xiangya Hospital, Central South University, Changsha, Hunan, China,Shanghai-MOST Key Laboratory of Health and Disease Genomics (Chinese National Human Genome Center at Shanghai), Institute of Genome and Bioinformatics, Shanghai Institute for Biomedical and Pharmaceutical Technologies, Shanghai, China,Corresponding author at: Bioinformatics Center & National Clinical Research Centre for Geriatric Disorders & Department of Geriatrics, Xiangya Hospital, Central South University, Changsha, Hunan, China.
| |
Collapse
|
41
|
Akerman O, Isakov H, Levi R, Psevkin V, Louzoun Y. Counting is almost all you need. Front Immunol 2023; 13:1031011. [PMID: 36741395 PMCID: PMC9896581 DOI: 10.3389/fimmu.2022.1031011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2022] [Accepted: 12/27/2022] [Indexed: 01/21/2023] Open
Abstract
The immune memory repertoire encodes the history of present and past infections and immunological attributes of the individual. As such, multiple methods were proposed to use T-cell receptor (TCR) repertoires to detect disease history. We here show that the counting method outperforms two leading algorithms. We then show that the counting can be further improved using a novel attention model to weigh the different TCRs. The attention model is based on the projection of TCRs using a Variational AutoEncoder (VAE). Both counting and attention algorithms predict better than current leading algorithms whether the host had CMV and its HLA alleles. As an intermediate solution between the complex attention model and the very simple counting model, we propose a new Graph Convolutional Network approach that obtains the accuracy of the attention model and the simplicity of the counting model. The code for the models used in the paper is provided at: https://github.com/louzounlab/CountingIsAlmostAllYouNeed.
Collapse
Affiliation(s)
- Ofek Akerman
- Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel
- Department of Computer Science, Bar-Ilan University, Ramat Gan, Israel
| | - Haim Isakov
- Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel
| | - Reut Levi
- Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel
| | - Vladimir Psevkin
- Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel
| | - Yoram Louzoun
- Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel
| |
Collapse
|
42
|
Cai Y, Chen R, Gao S, Li W, Liu Y, Su G, Song M, Jiang M, Jiang C, Zhang X. Artificial intelligence applied in neoantigen identification facilitates personalized cancer immunotherapy. Front Oncol 2023; 12:1054231. [PMID: 36698417 PMCID: PMC9868469 DOI: 10.3389/fonc.2022.1054231] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Accepted: 12/16/2022] [Indexed: 01/10/2023] Open
Abstract
The field of cancer neoantigen investigation has developed swiftly in the past decade. Predicting novel and true neoantigens derived from large multi-omics data became difficult but critical challenges. The rise of Artificial Intelligence (AI) or Machine Learning (ML) in biomedicine application has brought benefits to strengthen the current computational pipeline for neoantigen prediction. ML algorithms offer powerful tools to recognize the multidimensional nature of the omics data and therefore extract the key neoantigen features enabling a successful discovery of new neoantigens. The present review aims to outline the significant technology progress of machine learning approaches, especially the newly deep learning tools and pipelines, that were recently applied in neoantigen prediction. In this review article, we summarize the current state-of-the-art tools developed to predict neoantigens. The standard workflow includes calling genetic variants in paired tumor and blood samples, and rating the binding affinity between mutated peptide, MHC (I and II) and T cell receptor (TCR), followed by characterizing the immunogenicity of tumor epitopes. More specifically, we highlight the outstanding feature extraction tools and multi-layer neural network architectures in typical ML models. It is noted that more integrated neoantigen-predicting pipelines are constructed with hybrid or combined ML algorithms instead of conventional machine learning models. In addition, the trends and challenges in further optimizing and integrating the existing pipelines are discussed.
Collapse
Affiliation(s)
- Yu Cai
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Rui Chen
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Shenghan Gao
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Wenqing Li
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Yuru Liu
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Guodong Su
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Mingming Song
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Mengju Jiang
- School of Medicine, Northwest University, Xi’an, Shaanxi, China
| | - Chao Jiang
- Department of Neurology, The Second Affiliated Hospital of Xi’an Medical University, Xi’an, Shaanxi, China,*Correspondence: Chao Jiang, ; Xi Zhang,
| | - Xi Zhang
- School of Medicine, Northwest University, Xi’an, Shaanxi, China,*Correspondence: Chao Jiang, ; Xi Zhang,
| |
Collapse
|
43
|
Lybaert L, Lefever S, Fant B, Smits E, De Geest B, Breckpot K, Dirix L, Feldman SA, van Criekinge W, Thielemans K, van der Burg SH, Ott PA, Bogaert C. Challenges in neoantigen-directed therapeutics. Cancer Cell 2023; 41:15-40. [PMID: 36368320 DOI: 10.1016/j.ccell.2022.10.013] [Citation(s) in RCA: 31] [Impact Index Per Article: 31.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/07/2022] [Revised: 08/19/2022] [Accepted: 10/11/2022] [Indexed: 11/11/2022]
Abstract
A fundamental prerequisite for the efficacy of cancer immunotherapy is the presence of functional, antigen-specific T cells within the tumor. Neoantigen-directed therapy is a promising strategy that aims at targeting the host's immune response against tumor-specific antigens, thereby eradicating cancer cells. Initial forays have been made in clinical environments utilizing vaccines and adoptive cell therapy; however, many challenges lie ahead. We provide an in-depth overview of the current state of the field with an emphasis on in silico neoantigen discovery and the clinical aspects that need to be addressed to unlock the full potential of this therapy.
Collapse
Affiliation(s)
| | | | | | - Evelien Smits
- Center for Oncological Research, University of Antwerp, 2610 Wilrijk, Belgium
| | - Bruno De Geest
- Department of Pharmaceutics, Ghent University, 9000 Ghent, Belgium
| | - Karine Breckpot
- Laboratory of Molecular and Cellular Therapy, Department of Biomedical Sciences, Vrije Universiteit Brussel, Brussels, Belgium
| | - Luc Dirix
- Translational Cancer Research Unit, Center for Oncological Research, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerp, Belgium
| | - Steven A Feldman
- Center for Cancer Cell Therapy, Stanford University School of Medicine, Stanford, CA, USA
| | - Wim van Criekinge
- Department of Data Analysis and Mathematical Modelling, Ghent University, Ghent, Belgium
| | - Kris Thielemans
- Laboratory of Molecular and Cellular Therapy, Department of Biomedical Sciences, Vrije Universiteit Brussel, Brussels, Belgium
| | - Sjoerd H van der Burg
- Medical Oncology, Oncode Institute, Leiden University Medical Center, Leiden, the Netherlands
| | - Patrick A Ott
- Department of Medical Oncology, Dana-Farber Cancer Institute and Harvard Medical School, Boston, MA, USA
| | | |
Collapse
|
44
|
Zhang L, Li H, Zhang Z, Wang J, Chen G, Chen D, Shi W, Jia G, Liu M. Hybrid gMLP model for interaction prediction of MHC-peptide and TCR. Front Genet 2023; 13:1092822. [PMID: 36685858 PMCID: PMC9845249 DOI: 10.3389/fgene.2022.1092822] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Accepted: 12/01/2022] [Indexed: 01/05/2023] Open
Abstract
Understanding the interaction of T-cell receptor (TCR) with major histocompatibility-peptide (MHC-peptide) complex is extremely important in human immunotherapy and vaccine development. However, due to the limited available data, the performance of existing models for predicting the interaction of T-cell receptors (TCR) with major histocompatibility-peptide complexes is still unsatisfactory. Deep learning models have been applied to prediction tasks in various fields and have achieved better results compared with other traditional models. In this study, we leverage the gMLP model combined with attention mechanism to predict the interaction of MHC-peptide and TCR. Experiments show that our model can predict TCR-peptide interactions accurately and can handle the problems caused by different TCR lengths. Moreover, we demonstrate that the models trained with paired CDR3β-chain and CDR3α-chain data are better than those trained with only CDR3β-chain or with CDR3α-chain data. We also demonstrate that the hybrid model has greater potential than the traditional convolutional neural network.
Collapse
Affiliation(s)
- Lichao Zhang
- School of Intelligent Manufacturing and Equipment, Shenzhen Institute of Information Technology, Shenzhen, China,*Correspondence: Lichao Zhang, ; Mingjun Liu,
| | - Haojin Li
- School of Software, Shandong University, Jinan, China
| | - Zhenjiu Zhang
- School of Intelligent Manufacturing and Equipment, Shenzhen Institute of Information Technology, Shenzhen, China
| | - Jinjin Wang
- School of Intelligent Manufacturing and Equipment, Shenzhen Institute of Information Technology, Shenzhen, China
| | | | | | - Wentao Shi
- School of Intelligent Manufacturing and Equipment, Shenzhen Institute of Information Technology, Shenzhen, China
| | - Gaozhi Jia
- School of Intelligent Manufacturing and Equipment, Shenzhen Institute of Information Technology, Shenzhen, China
| | - Mingjun Liu
- School of Intelligent Manufacturing and Equipment, Shenzhen Institute of Information Technology, Shenzhen, China,*Correspondence: Lichao Zhang, ; Mingjun Liu,
| |
Collapse
|
45
|
Deng L, Ly C, Abdollahi S, Zhao Y, Prinz I, Bonn S. Performance comparison of TCR-pMHC prediction tools reveals a strong data dependency. Front Immunol 2023; 14:1128326. [PMID: 37143667 PMCID: PMC10152969 DOI: 10.3389/fimmu.2023.1128326] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2022] [Accepted: 03/24/2023] [Indexed: 05/06/2023] Open
Abstract
The interaction of T-cell receptors with peptide-major histocompatibility complex molecules (TCR-pMHC) plays a crucial role in adaptive immune responses. Currently there are various models aiming at predicting TCR-pMHC binding, while a standard dataset and procedure to compare the performance of these approaches is still missing. In this work we provide a general method for data collection, preprocessing, splitting and generation of negative examples, as well as comprehensive datasets to compare TCR-pMHC prediction models. We collected, harmonized, and merged all the major publicly available TCR-pMHC binding data and compared the performance of five state-of-the-art deep learning models (TITAN, NetTCR-2.0, ERGO, DLpTCR and ImRex) using this data. Our performance evaluation focuses on two scenarios: 1) different splitting methods for generating training and testing data to assess model generalization and 2) different data versions that vary in size and peptide imbalance to assess model robustness. Our results indicate that the five contemporary models do not generalize to peptides that have not been in the training set. We can also show that model performance is strongly dependent on the data balance and size, which indicates a relatively low model robustness. These results suggest that TCR-pMHC binding prediction remains highly challenging and requires further high quality data and novel algorithmic approaches.
Collapse
Affiliation(s)
- Lihua Deng
- Institute of Systems Immunology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Cedric Ly
- Institut of Medical Systems Biology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Sina Abdollahi
- Institut of Medical Systems Biology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Yu Zhao
- Institut of Medical Systems Biology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Immo Prinz
- Institute of Systems Immunology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
- *Correspondence: Immo Prinz, ; Stefan Bonn,
| | - Stefan Bonn
- Institut of Medical Systems Biology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
- *Correspondence: Immo Prinz, ; Stefan Bonn,
| |
Collapse
|
46
|
Grazioli F, Machart P, Mösch A, Li K, Castorina LV, Pfeifer N, Min MR. Attentive Variational Information Bottleneck for TCR-peptide interaction prediction. Bioinformatics 2022; 39:6960920. [PMID: 36571499 PMCID: PMC9825246 DOI: 10.1093/bioinformatics/btac820] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2022] [Revised: 11/18/2022] [Accepted: 12/23/2022] [Indexed: 12/27/2022] Open
Abstract
MOTIVATION We present a multi-sequence generalization of Variational Information Bottleneck and call the resulting model Attentive Variational Information Bottleneck (AVIB). Our AVIB model leverages multi-head self-attention to implicitly approximate a posterior distribution over latent encodings conditioned on multiple input sequences. We apply AVIB to a fundamental immuno-oncology problem: predicting the interactions between T-cell receptors (TCRs) and peptides. RESULTS Experimental results on various datasets show that AVIB significantly outperforms state-of-the-art methods for TCR-peptide interaction prediction. Additionally, we show that the latent posterior distribution learned by AVIB is particularly effective for the unsupervised detection of out-of-distribution amino acid sequences. AVAILABILITY AND IMPLEMENTATION The code and the data used for this study are publicly available at: https://github.com/nec-research/vibtcr. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
| | - Pierre Machart
- Biomedical AI Group, NEC Laboratories Europe, Heidelberg 69115, Germany
| | - Anja Mösch
- Biomedical AI Group, NEC Laboratories Europe, Heidelberg 69115, Germany
| | - Kai Li
- Machine Learning Department, NEC Laboratories America, Princeton, NJ 08540, USA
| | | | - Nico Pfeifer
- Methods in Medical Informatics, Department of Computer Science, University of Tübingen, Tübingen 72076, Germany
| | | |
Collapse
|
47
|
Montemurro A, Jessen LE, Nielsen M. NetTCR-2.1: Lessons and guidance on how to develop models for TCR specificity predictions. Front Immunol 2022; 13:1055151. [PMID: 36561755 PMCID: PMC9763291 DOI: 10.3389/fimmu.2022.1055151] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2022] [Accepted: 11/22/2022] [Indexed: 12/12/2022] Open
Abstract
T cell receptors (TCR) define the specificity of T cells and are responsible for their interaction with peptide antigen targets presented in complex with major histocompatibility complex (MHC) molecules. Understanding the rules underlying this interaction hence forms the foundation for our understanding of basic adaptive immunology. Over the last decade, efforts have been dedicated to developing assays for high throughput identification of peptide-specific TCRs. Based on such data, several computational methods have been proposed for predicting the TCR-pMHC interaction. The general conclusion from these studies is that the prediction of TCR interactions with MHC-peptide complexes remains highly challenging. Several reasons form the basis for this including scarcity and quality of data, and ill-defined modeling objectives imposed by the high redundancy of the available data. In this work, we propose a framework for dealing with this redundancy, allowing us to address essential questions related to the modeling of TCR specificity including the use of peptide- versus pan-specific models, how to best define negative data, and the performance impact of integrating of CDR1 and 2 loops. Further, we illustrate how and why it is strongly recommended to include simple similarity-based modeling approaches when validating an improved predictive power of machine learning models, and that such validation should include a performance evaluation as a function of "distance" to the training data, to quantify the potential for generalization of the proposed model. The conclusion of the work is that, given current data, TCR specificity is best modeled using peptide-specific approaches, integrating information from all 6 CDR loops, and with negative data constructed from a combination of true and mislabeled negatives. Comparing such machine learning models to similarity-based approaches demonstrated an increased performance gain of the former as the "distance" to the training data was increased; thus demonstrating an improved generalization ability of the machine learning-based approaches. We believe these results demonstrate that the outlined modeling framework and proposed evaluation strategy form a solid basis for investigating the modeling of TCR specificities and that adhering to such a framework will allow for faster progress within the field. The final devolved model, NetTCR-2.1, is available at https://services.healthtech.dtu.dk/service.php?NetTCR-2.1.
Collapse
Affiliation(s)
- Alessandro Montemurro
- Department of Health Technology, Section for Bioinformatics, Technical University of Denmark, DTU, 2800 Kgs., Lyngby, Denmark
| | - Leon Eyrich Jessen
- Department of Health Technology, Section for Bioinformatics, Technical University of Denmark, DTU, 2800 Kgs., Lyngby, Denmark
| | - Morten Nielsen
- Department of Health Technology, Section for Bioinformatics, Technical University of Denmark, DTU, 2800 Kgs., Lyngby, Denmark,Instituto de Investigaciones Biotecnológicas, Universidad Nacional de San Martín, Buenos Aires, Argentina,*Correspondence: Morten Nielsen,
| |
Collapse
|
48
|
Robert PA, Akbar R, Frank R, Pavlović M, Widrich M, Snapkov I, Slabodkin A, Chernigovskaya M, Scheffer L, Smorodina E, Rawat P, Mehta BB, Vu MH, Mathisen IF, Prósz A, Abram K, Olar A, Miho E, Haug DTT, Lund-Johansen F, Hochreiter S, Haff IH, Klambauer G, Sandve GK, Greiff V. Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for antibody specificity prediction. NATURE COMPUTATIONAL SCIENCE 2022; 2:845-865. [PMID: 38177393 DOI: 10.1038/s43588-022-00372-4] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/16/2021] [Accepted: 11/09/2022] [Indexed: 01/06/2024]
Abstract
Machine learning (ML) is a key technology for accurate prediction of antibody-antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody-antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design.
Collapse
Affiliation(s)
- Philippe A Robert
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway.
| | - Rahmad Akbar
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | - Robert Frank
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | | | - Michael Widrich
- ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria
| | - Igor Snapkov
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | - Andrei Slabodkin
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | - Maria Chernigovskaya
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | | | - Eva Smorodina
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | - Puneet Rawat
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | - Brij Bhushan Mehta
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway
| | - Mai Ha Vu
- Department of Linguistics and Scandinavian Studies, University of Oslo, Oslo, Norway
| | | | - Aurél Prósz
- Danish Cancer Society Research Center, Translational Cancer Genomics, Copenhagen, Denmark
| | - Krzysztof Abram
- The Novo Nordisk Foundation Center for Biosustainability, Autoflow, DTU Biosustain and IT University of Copenhagen, Copenhagen, Denmark
| | - Alex Olar
- Department of Complex Systems in Physics, Eötvös Loránd University, Budapest, Hungary
| | - Enkelejda Miho
- Institute of Medical Engineering and Medical Informatics, School of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern Switzerland, Muttenz, Switzerland
- aiNET GmbH, Basel, Switzerland
- Swiss Institute of Bioinformatics, Lausanne, Switzerland
| | | | | | - Sepp Hochreiter
- ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria
- Institute of Advanced Research in Artificial Intelligence (IARAI), Vienna, Austria
| | | | - Günter Klambauer
- ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria
| | | | - Victor Greiff
- Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway.
| |
Collapse
|
49
|
Fang Y, Liu X, Liu H. Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity. Brief Bioinform 2022; 23:6696141. [PMID: 36094087 DOI: 10.1093/bib/bbac378] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 07/06/2022] [Accepted: 08/09/2022] [Indexed: 12/14/2022] Open
Abstract
MOTIVATION It has been proven that only a small fraction of the neoantigens presented by major histocompatibility complex (MHC) class I molecules on the cell surface can elicit T cells. This restriction can be attributed to the binding specificity of T cell receptor (TCR) and peptide-MHC complex (pMHC). Computational prediction of T cells binding to neoantigens is a challenging and unresolved task. RESULTS In this paper, we proposed an attention-aware contrastive learning model, ATMTCR, to infer the TCR-pMHC binding specificity. For each TCR sequence, we used a transformer encoder to transform it to latent representation, and then masked a percentage of amino acids guided by attention weights to generate its contrastive view. Compared to fully-supervised baseline model, we verified that contrastive learning-based pretraining on large-scale TCR sequences significantly improved the prediction performance of downstream tasks. Interestingly, masking a percentage of amino acids with low attention weights yielded best performance compared to other masking strategies. Comparison experiments on two independent datasets demonstrated our method achieved better performance than other existing algorithms. Moreover, we identified important amino acids and their positional preference through attention weights, which indicated the potential interpretability of our proposed model.
Collapse
Affiliation(s)
- Yiming Fang
- School of Computer Science and Technology, Nanjing Tech University, 211816, Nanjing, China
| | - Xuejun Liu
- School of Computer Science and Technology, Nanjing Tech University, 211816, Nanjing, China
| | - Hui Liu
- School of Computer Science and Technology, Nanjing Tech University, 211816, Nanjing, China
| |
Collapse
|
50
|
Grazioli F, Mösch A, Machart P, Li K, Alqassem I, O’Donnell TJ, Min MR. On TCR binding predictors failing to generalize to unseen peptides. Front Immunol 2022; 13:1014256. [PMID: 36341448 PMCID: PMC9634250 DOI: 10.3389/fimmu.2022.1014256] [Citation(s) in RCA: 21] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2022] [Accepted: 10/05/2022] [Indexed: 11/18/2022] Open
Abstract
Several recent studies investigate TCR-peptide/-pMHC binding prediction using machine learning or deep learning approaches. Many of these methods achieve impressive results on test sets, which include peptide sequences that are also included in the training set. In this work, we investigate how state-of-the-art deep learning models for TCR-peptide/-pMHC binding prediction generalize to unseen peptides. We create a dataset including positive samples from IEDB, VDJdb, McPAS-TCR, and the MIRA set, as well as negative samples from both randomization and 10X Genomics assays. We name this collection of samples TChard. We propose the hard split, a simple heuristic for training/test split, which ensures that test samples exclusively present peptides that do not belong to the training set. We investigate the effect of different training/test splitting techniques on the models’ test performance, as well as the effect of training and testing the models using mismatched negative samples generated randomly, in addition to the negative samples derived from assays. Our results show that modern deep learning methods fail to generalize to unseen peptides. We provide an explanation why this happens and verify our hypothesis on the TChard dataset. We then conclude that robust prediction of TCR recognition is still far for being solved.
Collapse
Affiliation(s)
- Filippo Grazioli
- Biomedical AI Group, NEC Laboratories Europe, Heidelberg, Germany
- *Correspondence: Filippo Grazioli, ; Martin Renqiang Min,
| | - Anja Mösch
- Biomedical AI Group, NEC Laboratories Europe, Heidelberg, Germany
| | - Pierre Machart
- Biomedical AI Group, NEC Laboratories Europe, Heidelberg, Germany
| | - Kai Li
- Machine Learning Department, NEC Laboratories America, Princeton, NJ, United States
| | - Israa Alqassem
- Biomedical AI Group, NEC Laboratories Europe, Heidelberg, Germany
| | - Timothy J. O’Donnell
- Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, United States
| | - Martin Renqiang Min
- Machine Learning Department, NEC Laboratories America, Princeton, NJ, United States
- *Correspondence: Filippo Grazioli, ; Martin Renqiang Min,
| |
Collapse
|