Feature selection enhances peptide binding predictions for TCR-specific interactions DOI Creative Commons
Hamid Teimouri,

Zahra S. Ghoreyshi,

Anatoly B. Kolomeisky

и другие.

Frontiers in Immunology, Год журнала: 2025, Номер 15

Опубликована: Янв. 23, 2025

Introduction T-cell receptors (TCRs) play a critical role in the immune response by recognizing specific ligand peptides presented major histocompatibility complex (MHC) molecules. Accurate prediction of peptide binding to TCRs is essential for advancing immunotherapy, vaccine design, and understanding mechanisms autoimmune disorders. Methods This study presents theoretical approach that explores impact feature selection techniques on enhancing predictive accuracy models tailored TCRs. To evaluate our across different TCR systems, we utilized dataset includes libraries tested against three distinct murine A broad range physicochemical properties, including amino acid composition, dipeptide tripeptide features, were integrated into machine learning-based framework identify key properties contributing affinity. Results Our analysis reveals leveraging optimized subsets not only simplifies model complexity but also enhances performance, enabling more precise identification interactions. The results method are consistent with findings from hybrid approaches utilize both sequence structural data as input well experimental data. Discussion highlights peptide-TCR interactions, providing quantitative tool uncovering molecular assisting design advanced targeted therapeutics.

Язык: Английский

Can we predict T cell specificity with digital biology and machine learning? DOI Open Access
D. R. Hudson, Ricardo A. Fernandes, Mark Basham

и другие.

Nature reviews. Immunology, Год журнала: 2023, Номер 23(8), С. 511 - 521

Опубликована: Фев. 8, 2023

Язык: Английский

Процитировано

120
TCRmodel2: high-resolution modeling of T cell receptor recognition using deep learning DOI Creative Commons
Rui Yin, Helder Veras Ribeiro Filho, Valerie C. L. Lin

и другие.

Nucleic Acids Research, Год журнала: 2023, Номер 51(W1), С. W569 - W576

Опубликована: Май 4, 2023

Abstract The cellular immune system, which is a critical component of human immunity, uses T cell receptors (TCRs) to recognize antigenic proteins in the form peptides presented by major histocompatibility complex (MHC) proteins. Accurate definition structural basis TCRs and their engagement peptide–MHCs can provide insights into normal aberrant help guide design vaccines immunotherapeutics. Given limited amount experimentally determined TCR–peptide–MHC structures vast within each individual as well targets, accurate computational modeling approaches are needed. Here, we report update our web server, TCRmodel, was originally developed model unbound from sequence, now complexes utilizing several adaptations AlphaFold. This method, named TCRmodel2, allows users submit sequences through an easy-to-use interface shows similar or greater accuracy than AlphaFold other methods based on benchmarking. It generate models 15 minutes, output provided with confidence scores integrated molecular viewer. TCRmodel2 available at https://tcrmodel.ibbr.umd.edu.

Язык: Английский

Процитировано

45
Development and use of machine learning algorithms in vaccine target selection DOI Creative Commons
Barbara Bravi

npj Vaccines, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 20, 2024

Computer-aided discovery of vaccine targets has become a cornerstone rational design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in design concerned with the identification B T cell epitopes correlates protection. provide examples ML models, as well types data predictions for which they are built. argue that interpretable potential to improve immunogens also tool scientific discovery, by helping elucidate molecular processes underlying vaccine-induced immune responses. outline limitations challenges terms availability method development need be addressed bridge gap between advances their translational application

Язык: Английский

Процитировано

34
TULIP: A transformer-based unsupervised language model for interacting peptides and T cell receptors that generalizes to unseen epitopes DOI Creative Commons
Barthelemy Meynard-Piganeau, Christoph Feinauer, Martin Weigt

и другие.

Proceedings of the National Academy of Sciences, Год журнала: 2024, Номер 121(24)

Опубликована: Июнь 5, 2024

The accurate prediction of binding between T cell receptors (TCR) and their cognate epitopes is key to understanding the adaptive immune response developing immunotherapies. Current methods face two significant limitations: shortage comprehensive high-quality data bias introduced by selection negative training commonly used in supervised learning approaches. We propose a method, Transformer-based Unsupervised Language model for Interacting Peptides (TULIP), that addresses both limitations leveraging incomplete unsupervised using transformer architecture language models. Our flexible integrates all possible sources, regardless quality or completeness. demonstrate existence sampling procedure previous approaches, emphasizing need an approach. TULIP recognizes specific TCRs epitope, performing well on unseen epitopes. outperforms state-of-the-art models offers promising direction development more TCR epitope recognition

Язык: Английский

Процитировано

17
Computational Methods in Immunology and Vaccinology: Design and Development of Antibodies and Immunogens DOI Creative Commons
Federica Guarra, Giorgio Colombo

Journal of Chemical Theory and Computation, Год журнала: 2023, Номер 19(16), С. 5315 - 5333

Опубликована: Авг. 1, 2023

The design of new biomolecules able to harness immune mechanisms for the treatment diseases is a prime challenge computational and simulative approaches. For instance, in recent years, antibodies have emerged as an important class therapeutics against spectrum pathologies. In cancer, immune-inspired approaches are witnessing surge thanks better understanding tumor-associated antigens their engagement or evasion from human system. Here, we provide summary main state-of-the-art that used antigens, parallel, review key methodologies epitope identification both B- T-cell mediated responses. A special focus devoted description structure- physics-based models, privileged over purely sequence-based We discuss implications novel methods engineering with tailored immunological properties possible therapeutic uses. Finally, highlight extraordinary challenges opportunities presented by integration emerging Artificial Intelligence technologies prediction epitopes, antibodies.

Язык: Английский

Процитировано

33
Accurate modeling of peptide-MHC structures with AlphaFold DOI
Victor Mikhaylov, Chad A. Brambley, Grant L. J. Keller

и другие.

Structure, Год журнала: 2023, Номер 32(2), С. 228 - 241.e4

Опубликована: Дек. 18, 2023

Язык: Английский

Процитировано

31
Can AlphaFold’s breakthrough in protein structure help decode the fundamental principles of adaptive cellular immunity? DOI
Benjamin McMaster, Christopher J. Thorpe, Graham S. Ogg

и другие.

Nature Methods, Год журнала: 2024, Номер 21(5), С. 766 - 776

Опубликована: Апрель 23, 2024

Язык: Английский

Процитировано

14
Adaptive immune receptor repertoire analysis DOI
Vanessa Mhanna, Habib Bashour, Khang Lê Quý

и другие.

Nature Reviews Methods Primers, Год журнала: 2024, Номер 4(1)

Опубликована: Янв. 25, 2024

Язык: Английский

Процитировано

12
RACER-m leverages structural features for sparse T cell specificity prediction DOI Creative Commons
Ailun Wang, Xingcheng Lin, Kevin Ng Chau

и другие.

Science Advances, Год журнала: 2024, Номер 10(20)

Опубликована: Май 15, 2024

Reliable prediction of T cell specificity against antigenic signatures is a formidable task, complicated by the immense diversity receptor and antigen sequence space resulting limited availability training sets for inferential models. Recent modeling efforts have demonstrated advantage incorporating structural information to overcome need extensive data, yet disentangling heterogeneous TCR-antigen interface accurately predict MHC-allele-restricted TCR-peptide interactions has remained challenging. Here, we present RACER-m, coarse-grained model leveraging key biophysical from publicly available crystal structures. Explicit inclusion content substantially reduces required number examples maintains reliable predictions TCR-recognition sensitivity across diverse biological contexts. Our capably identifies biophysically meaningful point-mutant peptides that affect binding affinity, distinguishing its ability in predicting TCR point-mutants alternative sequence-based methods. Its application broadly applicable studies involving both closely related structurally pairs.

Язык: Английский

Процитировано

10
Structure-based prediction of T cell receptor recognition of unseen epitopes using TCRen DOI
В. К. Карнаухов, Dmitrii S. Shcherbinin, Anton O. Chugunov

и другие.

Nature Computational Science, Год журнала: 2024, Номер 4(7), С. 510 - 521

Опубликована: Июль 10, 2024

Язык: Английский

Процитировано

9