Characterizing the interaction conformation between T-cell receptors and epitopes with deep learning

Peng, Xingang; Lei, Yipin; Feng, Peiyuan; Jia, Lemei; Ma, Jianzhu; Zhao, Dan; Zeng, Jianyang

doi:10.1038/s42256-023-00634-4

Cited by 17 publications

(15 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study provides a useful groundwork for our better understanding of the interaction conformation between T-cell receptors and epitopes. We plan to integrate multivariate prior biological and biomedical knowledge and design highly interpretable model architectures to develop advanced deep learning methods for predicting of T cell receptor-epitope binding specificity (Lu, et al, 2021; Peng, et al, 2023; Racle, et al, 2023) in future work.…”

Section: Discussionmentioning

confidence: 99%

Supervised contrastive learning enhances MHC-II peptide binding affinity prediction

Shen,

Liu,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

Accurate prediction of major histocompatibility complex (MHC)-peptide binding affinity could provide essential insights into cellular immune responses and guide the discovery of neoantigens and personalized immunotherapies. Nevertheless, the existing deep learning-based approaches for predicting MHC-II peptide interactions fall short of satisfactory performance and offer restricted model interpretability. In this study, we propose a novel deep neural network, termed ConBoTNet, to address the above issues by introducing the designed supervised contrastive learning and bottleneck transformer extractors. Specifically, the supervised contrastive learning pre-training enhances the model’s representative and generalizable capabilities on MHC-II peptides by pulling positive pairs closer and pushing negative pairs further in the feature space, while the bottleneck transformer module focuses on MHC-II peptide interactions to precisely identify binding cores and anchor positions in an unsupervised manner. Extensive experiments on benchmark datasets under 5-fold cross-validation, leave-one-molecule-out validation, independent testing, and binding core prediction settings highlighted the superiority of our proposed ConBoTNet over current state-of-the-art methods. Data distribution analysis in the latent feature space demonstrated that supervised contrastive learning can aggregate MHC-II-peptide samples with similar affinity labels and learn common features of similar affinity. Additionally, we interpreted the trained neural network by associating the attention weights with peptides and innovatively find both well-established and potential peptide motifs. This work not only introduces an innovative tool for accurately predicting MHC-II peptide affinity, but also provides new insights into a new paradigm for modeling essential biological interactions, advancing data-driven discovery in biomedicine.

show abstract

Section: Discussionmentioning

confidence: 99%

Supervised contrastive learning enhances MHC-II peptide binding affinity prediction

Shen,

Liu,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…VAEs in peptide-MHC binding optimization have great potential for advancing the design of vaccines and immunotherapies ( 103 ). One recent study, TCR–Epitope Interaction Modelling at Residue Level (TEIM-Res) ( 104 ), uses the sequences of TCRs and epitopes as inputs to predict pairwise residue distances and contact sites. An epitope feature vector generated by an AE is fed into an interaction extractor for global epitope information.…”

Section: Tcr-pmhc Specificity Prediction Methodsmentioning

confidence: 99%

Quantitative approaches for decoding the specificity of the human T cell repertoire

Ghoreyshi,

George

2023

Front. Immunol.

View full text Add to dashboard Cite

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.

show abstract

“…While traditional experimental techniques for studying PPIs, such as yeast two-hybrid screening 7 , co-immunoprecipitation 8 , pull-down assays 9 , and fluorescence resonance energy transfer (FRET) 10 , are effective, they often require extensive labor and substantial financial investment. To address these challenges, advancements in computational tools and artificial intelligence (AI) algorithms have transformed the study of PPIs 11 . These in-silico strategies leverage expansive datasets to predict PPIs, enabling interaction site prediction 12 , interaction type classification 9 , and binding affinity prediction 13 .…”

Section: Introductionmentioning

confidence: 99%

Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction

Yue,

Li,

Cheng

et al. 2024

Preprint

View full text Add to dashboard Cite

Structure-based machine learning algorithms have been utilized to predict the properties of protein-protein interaction (PPI) complexes, such as binding affinity, which is critical for understanding biological mechanisms and disease treatments. While most existing algorithms represent PPI complex graph structures at the atom-scale or residue-scale, these representations can be computationally expensive or may not sufficiently integrate finer chemical-plausible interaction details for improving predictions. Here, we introduce MCGLPPI, a novel geometric representation learning framework that combines graph neural networks (GNNs) with the MARTINI molecular coarse-grained (CG) model to predict overall PPI properties accurately and efficiently. This framework maps proteins onto a concise CG-scale complex graph, where nodes represent CG beads and edges encode chemically plausible interactions. The GNN-based encoder is tailored to extract high-quality representations from this graph, efficiently capturing the overall properties of the protein complex structure. Extensive experiments on three different downstream PPI property prediction tasks demonstrate that MCGLPPI achieves competitive performance compared with the counterparts at the atom- and residue-scale, but with only a third of the computational resource consumption. Furthermore, the CG-scale pre-training on protein domain-domain interaction structures enhances its predictive capabilities for PPI tasks. MCGLPPI offers an effective and efficient solution for PPI overall property predictions, serving as a promising tool for the large-scale analysis of biomolecular interactions.

show abstract

Characterizing the interaction conformation between T-cell receptors and epitopes with deep learning

Cited by 17 publications

References 55 publications

Supervised contrastive learning enhances MHC-II peptide binding affinity prediction

Supervised contrastive learning enhances MHC-II peptide binding affinity prediction

Quantitative approaches for decoding the specificity of the human T cell repertoire

Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction

Contact Info

Product

Resources

About