Current challenges for epitope-agnostic TCR interaction prediction and a new perspective derived from image classification

Moris, Pieter; Pauw, Joey De; Postovskaya, Anna; Gielis, Sofie; Neuter, Nicolas De; Bittremieux, Wout; Ogunjimi, Benson; Laukens, Kris; Meysman, Pieter

doi:10.1101/2019.12.18.880146

Cited by 11 publications

(11 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classification of TCRs specific for the ELAGIGILTV and ASNENMETM peptides showed an intermediate pattern. Overall, the classification of TCRs for different epitopes show very significant differences in performance (Figure 7B), as has been observed previously for other models (Moris et al, 2020). This also suggests that the overall performance as showed in Table 2 is somewhat misleading, as it will be skewed by the more abundant epitopes.…”

Section: Classifier Performance Varies Between Epitopessupporting

confidence: 80%

“…To evaluate the performance of the presented classifier compared to published classifiers in the field, we compared performance with ERGO (Springer et al, 2020) and ImRex (Moris et al, 2020) on the same validation sets. ERGO is available as a web tool (https://tcr.cs.biu.ac.il/), and the models trained on the VDJdb (Bagaev et al, 2020) were used for the benchmarking.…”

Section: Benchmarking Against Other Classifiersmentioning

confidence: 99%

See 1 more Smart Citation

Predicting T Cell Receptor Antigen Specificity From Structural Features Derived From Homology Models of Receptor-Peptide-Major Histocompatibility Complexes

2021

View full text Add to dashboard Cite

The physical interaction between the T cell receptor (TCR) and its cognate antigen causes T cells to activate and participate in the immune response. Understanding this physical interaction is important in predicting TCR binding to a target epitope, as well as potential cross-reactivity. Here, we propose a way of collecting informative features of the binding interface from homology models of T cell receptor-peptide-major histocompatibility complex (TCR-pMHC) complexes. The information collected from these structures is sufficient to discriminate binding from non-binding TCR-pMHC pairs in multiple independent datasets. The classifier is limited by the number of crystal structures available for the homology modelling and by the size of the training set. However, the classifier shows comparable performance to sequence-based classifiers requiring much larger training sets.

show abstract

Section: Classifier Performance Varies Between Epitopessupporting

confidence: 80%

Section: Benchmarking Against Other Classifiersmentioning

confidence: 99%

Predicting T Cell Receptor Antigen Specificity From Structural Features Derived From Homology Models of Receptor-Peptide-Major Histocompatibility Complexes

2021

View full text Add to dashboard Cite

show abstract

“…These learned motifs can then be used as part of a complex deep learning model to either describe the data in a new latent space or be used for a classification task. Furthermore, since the initial conception and presentation of this work, multiple groups have begun to recognize the value of deep learning and broader machine learning techniques in this endeavor to learn these sequence concepts of immune receptors [26][27][28][29][30] .…”

Section: Resultsmentioning

confidence: 99%

DeepTCR is a deep learning framework for revealing sequence concepts within T-cell repertoires

et al. 2021

View full text Add to dashboard Cite

Deep learning algorithms have been utilized to achieve enhanced performance in pattern-recognition tasks. The ability to learn complex patterns in data has tremendous implications in immunogenomics. T-cell receptor (TCR) sequencing assesses the diversity of the adaptive immune system and allows for modeling its sequence determinants of antigenicity. We present DeepTCR, a suite of unsupervised and supervised deep learning methods able to model highly complex TCR sequencing data by learning a joint representation of a TCR by its CDR3 sequences and V/D/J gene usage. We demonstrate the utility of deep learning to provide an improved ‘featurization’ of the TCR across multiple human and murine datasets, including improved classification of antigen-specific TCRs and extraction of antigen-specific TCRs from noisy single-cell RNA-Seq and T-cell culture-based assays. Our results highlight the flexibility and capacity for deep neural networks to extract meaningful information from complex immunogenomic data for both descriptive and predictive purposes.

show abstract

“…Bornholdt et al [23] cloned an extensive panel of mAbs targeting GP from peripheral B cells of a convalescent donor who survived the 2014 EBOV outbreak in Zaire [9,13]. The authors deposited the sequences of heavy-and light-chains of 349 mAbs in GenBank (accession numbers listed in S7 Table of their publication).…”

Section: Set Of Anti-ebov Absmentioning

confidence: 99%

“…Thus, machine learning (ML) approaches have already been used to analyze and classify information derived from cells expressing adaptive immune receptors [9]. Some of these ML applications include predicting peptide presentation by T cells [10][11][12][13], affinity of peptide binding to Major Histocompatibility Complex molecules [14,15], and binding affinity of neutralizing Abs [16]. Additionally, deep learning techniques have also been used in Ab paratope prediction [17].…”

Section: Introductionmentioning

confidence: 99%

Using the antibody-antigen binding interface to train image-based deep neural networks for antibody-epitope classification

2021

View full text Add to dashboard Cite

High-throughput B-cell sequencing has opened up new avenues for investigating complex mechanisms underlying our adaptive immune response. These technological advances drive data generation and the need to mine and analyze the information contained in these large datasets, in particular the identification of therapeutic antibodies (Abs) or those associated with disease exposure and protection. Here, we describe our efforts to use artificial intelligence (AI)-based image-analyses for prospective classification of Abs based solely on sequence information. We hypothesized that Abs recognizing the same part of an antigen share a limited set of features at the binding interface, and that the binding site regions of these Abs share share common structure and physicochemical property patterns that can serve as a “fingerprint” to recognize uncharacterized Abs. We combined large-scale sequence-based protein-structure predictions to generate ensembles of 3-D Ab models, reduced the Ab binding interface to a 2-D image (fingerprint), used pre-trained convolutional neural networks to extract features, and trained deep neural networks (DNNs) to classify Abs. We evaluated this approach using Ab sequences derived from human HIV and Ebola viral infections to differentiate between two Abs, Abs belonging to specific B-cell family lineages, and Abs with different epitope preferences. In addition, we explored a different type of DNN method to detect one class of Abs from a larger pool of Abs. Testing on Ab sets that had been kept aside during model training, we achieved average prediction accuracies ranging from 71–96% depending on the complexity of the classification task. The high level of accuracies reached during these classification tests suggests that the DNN models were able to learn a series of structural patterns shared by Abs belonging to the same class. The developed methodology provides a means to apply AI-based image recognition techniques to analyze high-throughput B-cell sequencing datasets (repertoires) for Ab classification.

show abstract

Current challenges for epitope-agnostic TCR interaction prediction and a new perspective derived from image classification

Abstract: T cell epitope prediction | T cell receptor | epitope specificity | immunoinformatics | convolutional neural network | deep learningCorrespondence: pieter.moris@uantwerpen.be

Cited by 11 publications

References 42 publications

Predicting T Cell Receptor Antigen Specificity From Structural Features Derived From Homology Models of Receptor-Peptide-Major Histocompatibility Complexes

Predicting T Cell Receptor Antigen Specificity From Structural Features Derived From Homology Models of Receptor-Peptide-Major Histocompatibility Complexes

DeepTCR is a deep learning framework for revealing sequence concepts within T-cell repertoires

Using the antibody-antigen binding interface to train image-based deep neural networks for antibody-epitope classification

Contact Info

Product

Resources

About