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

Abstract

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.

Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for real-world antibody specificity prediction

“…"Backwards" (B) is only allowed as the first move (otherwise, it would collide with the previous position). For instance, " (25,30,28), BSLDUSUSRS, RGAYYGSSYGA" or " (26,30,27), DLURSLDDUL, YYGSSYGAMDY" are two protein structures of the size "10 moves" or 11 AAs. In particular, an antigen is a multi-chain Ymir protein (structure and AA sequence), and the antibody is represented either as an 11 AAs sub-sequence of its CDRH3 (sequence only) or as with a 3D conformation as an Ymir protein (structure and AA sequence).…”

“…Machine learning (ML) represents an increasingly used approach for antibody-antigen binding prediction (3,10,18,(21)(22)(23)(24)(25)(26)(27)(28)(29)(30)(31)(32) given its capacity to infer the hidden nonlinear rules underlying high-complexity protein-protein interaction (30,(33)(34)(35)(36)(37)(38). Recent reports suggest that binding prediction based on antibody sequence or structure may be feasible as long as sufficiently large antigen(epitope)-specific antibody datasets become available (15,16,(39)(40)(41)(42)(43).…”

Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies

“…As such, it was possible to identify dissimilar antibody sequences that would bind the same epitope, a task that is usually very challenging. With a conceptually similar goal, Ripoll et al 160 computationally constructed 3D-models of epitope-specific antibody sequences to train image-based deep neural networks for antibody-epitope classification showing a potential route towards applying image recognition techniques to sequence-based datasets for antigen specificity discovery.…”

Application of Artificial Intelligence in COVID-19 Diagnosis and Therapeutics

“…Fast et al further expanded this method to identify T-cell epitopes for SARS-CoV-2 RBD [ 76 ]. Antibody-epitope classification using deep neural networks (DNNs) was reported using input two-dimensional images generated from a three-dimensional image projection created by the Rosetta antibody software [ 77 ]. The ML platform REDIAL-2020 estimates small compound activities in a broad range of SARS-CoV-2-related assays [ 78 ].…”