Deciphering the language of antibodies using self-supervised learning

An individual's B cell receptor (BCR) repertoire encodes information about past immune responses, and potential for future disease protection. Deciphering the information stored in BCR sequence datasets will transform our fundamental understanding of disease and enable discovery of novel diagnostics and antibody therapeutics. One of the grand challenges of BCR sequence analysis is the prediction of BCR properties from their amino acid sequence alone. Here we present an antibody-specific language model, AntiBERTa, which provides a contextualised representation of BCR sequences. Following pre-training, we show that AntiBERTa embeddings learn biologically relevant information, generalizable to a range of applications. As a case study, we demonstrate how AntiBERTa can be fine-tuned to predict paratope positions from an antibody sequence, outperforming public tools across multiple metrics. To our knowledge, AntiBERTa is the deepest protein family-specific language model, providing a rich representation of BCRs. AntiBERTa embeddings are primed for multiple downstream tasks and can improve our understanding of the language of antibodies.

AbDiver - A tool to explore the natural antibody landscape to aid therapeutic design

Motivation: Rational design of therapeutic antibodies can be improved by harnessing the natural sequence diversity of these molecules. Our understanding of the diversity of antibodies has recently been greatly facilitated through the deposition of hundreds of millions of human antibody sequences in next-generation sequencing (NGS) repositories. Contrasting a query therapeutic antibody sequence to naturally observed diversity in similar antibody sequences from NGS can provide a mutational road-map for antibody engineers designing biotherapeutics. Because of the sheer scale of the antibody NGS datasets, performing queries across them is computationally challenging. Results: To facilitate harnessing antibody NGS data, we developed AbDiver (http://naturalantibody.com/abdiver), a free portal allowing users to compare their query sequences to those observed in the natural repertoires. AbDiver offers three antibody-specific use-cases: 1) compare a query antibody to positional variability statistics precomputed from multiple independent studies 2) retrieve close full variable sequence matches to a query antibody and 3) retrieve CDR3 or clonotype matches to a query antibody. We applied our system to a set of 742 therapeutic antibodies, demonstrating that for each use-case our system can retrieve relevant results for most sequences. AbDiver facilitates the navigation of vast antibody mutation space for the purpose of rational therapeutic antibody de-sign and engineering. Availability: AbDiver is freely accessible at http://naturalantibody.com/abdiver

Machine Learning Detects Anti-DENV Signatures in Antibody Repertoire Sequences

Dengue infection is a global threat. As of today, there is no universal dengue fever treatment or vaccines unreservedly recommended by the World Health Organization. The investigation of the specific immune response to dengue virus would support antibody discovery as therapeutics for passive immunization and vaccine design. High-throughput sequencing enables the identification of the multitude of antibodies elicited in response to dengue infection at the sequence level. Artificial intelligence can mine the complex data generated and has the potential to uncover patterns in entire antibody repertoires and detect signatures distinctive of single virus-binding antibodies. However, these machine learning have not been harnessed to determine the immune response to dengue virus. In order to enable the application of machine learning, we have benchmarked existing methods for encoding biological and chemical knowledge as inputs and have investigated novel encoding techniques. We have applied different machine learning methods such as neural networks, random forests, and support vector machines and have investigated the parameter space to determine best performing algorithms for the detection and prediction of antibody patterns at the repertoire and antibody sequence levels in dengue-infected individuals. Our results show that immune response signatures to dengue are detectable both at the antibody repertoire and at the antibody sequence levels. By combining machine learning with phylogenies and network analysis, we generated novel sequences that present dengue-binding specific signatures. These results might aid further antibody discovery and support vaccine design.

A Sequence-based Antibody Paratope Prediction Model Through Combing Local-Global Information and Partner Features

Antibodies are proteins which play a vital role in the immune system by recognizing and neutralizing antigens. The region on the antibody binds to the antigens, also known as paratope, mediates antibody-antigen interaction with high affinity and specificity. And the accurate prediction of those regions from antibody sequence contributes to the design of therapeutic antibodies and remains challenging. However, the experimental methods are time-consuming and expensive. In this article, we propose a sequence-based method for antibody paratope prediction by combing the local and global features of antibody sequence and global features of partner antigen sequence. For extracting local features, we use Convolution Neural Networks(CNNs) and a sliding window approach on antibody sequence. For extracting global features, we use Attention-based Bidirectional Long Short-Term Memory(Att-BLSTM) networks on antibody sequence. For extracting partner features, we employ Att-BLSTM on the partner antigen sequence as well. And then, all features are combined to predict antibody paratope by fully-connected networks. The experiments show that our proposed method achieves superior performance over the state-of-the-art sequenced-based antibody paratope prediction methods on benchmark datasets.

Sequence and functional characterization of a public HIV-specific antibody clonotype

Public antibody clonotypes shared among multiple individuals have been identified for several pathogens. However, little is known about the limits of what constitutes a public clonotype. Here, we characterize the sequence and functional properties of antibodies from a public HIV-specific clonotype comprising sequences from 3 individuals. Our results showed that antigen specificity for the public antibodies was modulated by the VH, but not VL, germline gene. Non-native pairing of public heavy and light chains from different donors resulted in antibodies with consistent antigen specificity, suggesting functional complementation of sequences within the public antibody clonotype. The strength of antigen recognition appeared to be dependent on the specific antibody light chain used, but not on other sequence features such as germline or native-antibody sequence identity. Understanding the determinants of antibody clonotype "publicness" can provide insights into the fundamental rules of host-pathogen interactions at the population level, with implications for clonotype-specific vaccine development.

Robustification of RosettaAntibody and Rosetta SnugDock

In recent years, the observed antibody sequence space has grown exponentially due to advances in high-throughput sequencing of immune receptors. The rise in sequences has not been mirrored by a rise in structures, as experimental structure determination techniques have remained low-throughput. Computational modeling, however, has the potential to close the sequence–structure gap. To achieve this goal, computational methods must be robust, fast, easy to use, and accurate. Here we report on the latest advances made in RosettaAntibody and Rosetta SnugDock—methods for antibody structure prediction and antibody–antigen docking. We simplified the user interface, expanded and automated the template database, generalized the kinematics of antibody–antigen docking (which enabled modeling of single-domain antibodies) and incorporated new loop modeling techniques. To evaluate the effects of our updates on modeling accuracy, we developed rigorous tests under a new scientific benchmarking framework within Rosetta. Benchmarking revealed that more structurally similar templates could be identified in the updated database and that SnugDock broadened its applicability without losing accuracy. However, there are further advances to be made, including increasing the accuracy and speed of CDR-H3 loop modeling, before computational approaches can accurately model any antibody.