Antibody complementarity determining region design using high-capacity machine learning

Cmai: Predicting Antigen-Antibody Interactions from Massive Sequencing Data

The interaction between antigens and antibodies (B cell receptors, BCRs) is the key step underlying the function of the humoral immune system in various biological contexts. The capability to profile the landscape of antigen-binding affinity of a vast number of BCRs will provide a powerful tool to reveal novel insights at unprecedented levels and will yield powerful tools for translational development. However, current experimental approaches for profiling antibody-antigen interactions are costly and time-consuming, and can only achieve low-to-mid throughput. On the other hand, bioinformatics tools in the field of antibody informatics mostly focus on optimization of antibodies given known binding antigens, which is a very different research question and of limited scope. In this work, we developed an innovative Artificial Intelligence tool, Cmai, to address the prediction of the binding between antibodies and antigens that can be scaled to high-throughput sequencing data. Cmai achieved an AUROC of 0.91 in our validation cohort. We devised a biomarker metric based on the output from Cmai applied to high-throughput BCR sequencing data. We found that, during immune-related adverse events (irAEs) caused by immune-checkpoint inhibitor (ICI) treatment, the humoral immunity is preferentially responsive to intracellular antigens from the organs affected by the irAEs. In contrast, extracellular antigens on malignant tumor cells are inducing B cell infiltrations, and the infiltrating B cells have a greater tendency to co-localize with tumor cells expressing these antigens. We further found that the abundance of tumor antigen-targeting antibodies is predictive of ICI treatment response. Overall, Cmai and our biomarker approach filled in a gap that is not addressed by current antibody optimization works nor works such as AlphaFold3 that predict the structures of complexes of proteins that are known to bind.

Prospects for the computational humanization of antibodies and nanobodies

To be viable therapeutics, antibodies must be tolerated by the human immune system. Rational approaches to reduce the risk of unwanted immunogenicity involve maximizing the 'humanness' of the candidate drug. However, despite the emergence of new discovery technologies, many of which start from entirely human gene fragments, most antibody therapeutics continue to be derived from non-human sources with concomitant humanization to increase their human compatibility. Early experimental humanization strategies that focus on CDR loop grafting onto human frameworks have been critical to the dominance of this discovery route but do not consider the context of each antibody sequence, impacting their success rate. Other challenges include the simultaneous optimization of other drug-like properties alongside humanness and the humanization of fundamentally non-human modalities such as nanobodies. Significant efforts have been made to develop in silico methodologies able to address these issues, most recently incorporating machine learning techniques. Here, we outline these recent advancements in antibody and nanobody humanization, focusing on computational strategies that make use of the increasing volume of sequence and structural data available and the validation of these tools. We highlight that structural distinctions between antibodies and nanobodies make the application of antibody-focused in silico tools to nanobody humanization non-trivial. Furthermore, we discuss the effects of humanizing mutations on other essential drug-like properties such as binding affinity and developability, and methods that aim to tackle this multi-parameter optimization problem.

The rise of big data: deep sequencing-driven computational methods are transforming the landscape of synthetic antibody design

Synthetic antibodies (Abs) represent a category of artificial proteins capable of closely emulating the functions of natural Abs. Their in vitro production eliminates the need for an immunological response, streamlining the process of Ab discovery, engineering, and development. These artificially engineered Abs offer novel approaches to antigen recognition, paratope site manipulation, and biochemical/biophysical enhancements. As a result, synthetic Abs are fundamentally reshaping conventional methods of Ab production. This mirrors the revolution observed in molecular biology and genomics as a result of deep sequencing, which allows for the swift and cost-effective sequencing of DNA and RNA molecules at scale. Within this framework, deep sequencing has enabled the exploration of whole genomes and transcriptomes, including particular gene segments of interest. Notably, the fusion of synthetic Ab discovery with advanced deep sequencing technologies is redefining the current approaches to Ab design and development. Such combination offers opportunity to exhaustively explore Ab repertoires, fast-tracking the Ab discovery process, and enhancing synthetic Ab engineering. Moreover, advanced computational algorithms have the capacity to effectively mine big data, helping to identify Ab sequence patterns/features hidden within deep sequencing Ab datasets. In this context, these methods can be utilized to predict novel sequence features thereby enabling the successful generation of de novo Ab molecules. Hence, the merging of synthetic Ab design, deep sequencing technologies, and advanced computational models heralds a new chapter in Ab discovery, broadening our comprehension of immunology and streamlining the advancement of biological therapeutics.

Recent advances in generative biology for biotherapeutic discovery

Generative biology combines artificial intelligence (AI), advanced life sciences technologies, and automation to revolutionize the process of designing novel biomolecules with prescribed properties, giving drug discoverers the ability to escape the limitations of biology during the design of next-generation protein therapeutics. Significant hurdles remain, namely: (i) the inherently complex nature of drug discovery, (ii) the bewildering number of promising computational and experimental techniques that have emerged in the past several years, and (iii) the limited availability of relevant protein sequence-function data for drug-like molecules. There is a need to focus on computational methods that will be most practically effective for protein drug discovery and on building experimental platforms to generate the data most appropriate for these methods. Here, we discuss recent advances in computational and experimental life sciences that are most crucial for impacting the pace and success of protein drug discovery.

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

Machine learning for functional protein design

Recent breakthroughs in AI coupled with the rapid accumulation of protein sequence and structure data have radically transformed computational protein design. New methods promise to escape the constraints of natural and laboratory evolution, accelerating the generation of proteins for applications in biotechnology and medicine. To make sense of the exploding diversity of machine learning approaches, we introduce a unifying framework that classifies models on the basis of their use of three core data modalities: sequences, structures and functional labels. We discuss the new capabilities and outstanding challenges for the practical design of enzymes, antibodies, vaccines, nanomachines and more. We then highlight trends shaping the future of this field, from large-scale assays to more robust benchmarks, multimodal foundation models, enhanced sampling strategies and laboratory automation.

Advancing Antibody Engineering through Synthetic Evolution and Machine Learning

Abs are versatile molecules with the potential to achieve exceptional binding to target Ags, while also possessing biophysical properties suitable for therapeutic drug development. Protein display and directed evolution systems have transformed synthetic Ab discovery, engineering, and optimization, vastly expanding the number of Ab clones able to be experimentally screened for binding. Moreover, the burgeoning integration of high-throughput screening, deep sequencing, and machine learning has further augmented in vitro Ab optimization, promising to accelerate the design process and massively expand the Ab sequence space interrogated. In this Brief Review, we discuss the experimental and computational tools employed in synthetic Ab engineering and optimization. We also explore the therapeutic challenges posed by developing Abs for infectious diseases, and the prospects for leveraging machine learning-guided protein engineering to prospectively design Abs resistant to viral escape.

CD47Binder: Identify CD47 Binding Peptides by Combining Next-Generation Phage Display Data and Multiple Peptide Descriptors

CD47/SIRPα pathway is a new breakthrough in the field of tumor immunity after PD-1/PD-L1. While current monoclonal antibody therapies targeting CD47/SIRPα have demonstrated some anti-tumor effectiveness, there are several inherent limitations associated with these formulations. In the paper, we developed a predictive model that combines next-generation phage display (NGPD) and traditional machine learning methods to distinguish CD47 binding peptides. First, we utilized NGPD biopanning technology to screen CD47 binding peptides. Second, ten traditional machine learning methods based on multiple peptide descriptors and three deep learning methods were used to build computational models for identifying CD47 binding peptides. Finally, we proposed an integrated model based on support vector machine. During the five-fold cross-validation, the integrated predictor demonstrated specificity, accuracy, and sensitivity of 0.755, 0.764, and 0.772, respectively. Furthermore, an online bioinformatics tool called CD47Binder has been developed for the integrated predictor. This tool is readily accessible on http://i.uestc.edu.cn/CD47Binder/cgi-bin/CD47Binder.pl .

High-throughput analysis system of interaction kinetics for data-driven antibody design

Surface plasmon resonance (SPR) is widely used for antigen-antibody interaction kinetics analysis. However, it has not been used in the screening phase because of the low throughput of measurement and analysis. Herein, we proposed a high-throughput SPR analysis system named "BreviA" using the Brevibacillus expression system. Brevibacillus was transformed using a plasmid library containing various antibody sequences, and single colonies were cultured in 96-well plates. Sequence analysis was performed using bacterial cells, and recombinant antibodies secreted in the supernatant were immobilized on a sensor chip to analyze their interactions with antigens using high-throughput SPR. Using this system, the process from the transformation to 384 interaction analyses can be performed within a week. This system utility was tested using an interspecies specificity design of an anti-human programmed cell death protein 1 (PD-1) antibody. A plasmid library containing alanine and tyrosine mutants of all complementarity-determining region residues was generated. A high-throughput SPR analysis was performed against human and mouse PD-1, showing that the mutation in the specific region enhanced the affinity for mouse PD-1. Furthermore, deep mutational scanning of the region revealed two mutants with > 100-fold increased affinity for mouse PD-1, demonstrating the potential efficacy of antibody design using data-driven approach.

Deep learning in preclinical antibody drug discovery and development

Antibody drugs have become a key part of biotherapeutics. Patients suffering from various diseases have benefited from antibody therapies. However, its development process is rather long, expensive and risky. To speed up the process, reduce cost and improve success rate, artificial intelligence, especially deep learning methods, have been widely used in all aspects of preclinical antibody drug development, from library generation to hit identification, developability screening, lead selection and optimization. In this review, we systematically summarize antibody encodings, deep learning architectures and models used in preclinical antibody drug discovery and development. We also critically discuss challenges and opportunities, problems and possible solutions, current applications and future directions of deep learning in antibody drug development.

Accelerating antibody discovery and design with artificial intelligence: Recent advances and prospects

Therapeutic antibodies are the largest class of biotherapeutics and have been successful in treating human diseases. However, the design and discovery of antibody drugs remains challenging and time-consuming. Recently, artificial intelligence technology has had an incredible impact on antibody design and discovery, resulting in significant advances in antibody discovery, optimization, and developability. This review summarizes major machine learning (ML) methods and their applications for computational predictors of antibody structure and antigen interface/interaction, as well as the evaluation of antibody developability. Additionally, this review addresses the current status of ML-based therapeutic antibodies under preclinical and clinical phases. While many challenges remain, ML may offer a new therapeutic option for the future direction of fully computational antibody design.

AI/ML combined with next-generation sequencing of VHH immune repertoires enables the rapid identification of de novo humanized and sequence-optimized single domain antibodies: a prospective case study

Introduction: In this study, we demonstrate the feasibility of yeast surface display (YSD) and nextgeneration sequencing (NGS) in combination with artificial intelligence and machine learning methods (AI/ML) for the identification of de novo humanized single domain antibodies (sdAbs) with favorable early developability profiles. Methods: The display library was derived from a novel approach, in which VHH-based CDR3 regions obtained from a llama (Lama glama), immunized against NKp46, were grafted onto a humanized VHH backbone library that was diversified in CDR1 and CDR2. Following NGS analysis of sequence pools from two rounds of fluorescence-activated cell sorting we focused on four sequence clusters based on NGS frequency and enrichment analysis as well as in silico developability assessment. For each cluster, long short-term memory (LSTM) based deep generative models were trained and used for the in silico sampling of new sequences. Sequences were subjected to sequence- and structure-based in silico developability assessment to select a set of less than 10 sequences per cluster for production. Results: As demonstrated by binding kinetics and early developability assessment, this procedure represents a general strategy for the rapid and efficient design of potent and automatically humanized sdAb hits from screening selections with favorable early developability profiles.

Staying Ahead of the Game: How SARS-CoV-2 has Accelerated the Application of Machine Learning in Pandemic Management

In recent years, machine learning (ML) techniques have garnered considerable interest for their potential use in accelerating the rate of drug discovery. With the emergence of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, the utilization of ML has become even more crucial in the search for effective antiviral medications. The pandemic has presented the scientific community with a unique challenge, and the rapid identification of potential treatments has become an urgent priority. Researchers have been able to accelerate the process of identifying drug candidates, repurposing existing drugs, and designing new compounds with desirable properties using machine learning in drug discovery. To train predictive models, ML techniques in drug discovery rely on the analysis of large datasets, including both experimental and clinical data. These models can be used to predict the biological activities, potential side effects, and interactions with specific target proteins of drug candidates. This strategy has proven to be an effective method for identifying potential coronavirus disease 2019 (COVID-19) and other disease treatments. This paper offers a thorough analysis of the various ML techniques implemented to combat COVID-19, including supervised and unsupervised learning, deep learning, and natural language processing. The paper discusses the impact of these techniques on pandemic drug development, including the identification of potential treatments, the understanding of the disease mechanism, and the creation of effective and safe therapeutics. The lessons learned can be applied to future outbreaks and drug discovery initiatives.

Affinity maturation of antibody fragments: A review encompassing the development from random approaches to computational rational optimization

Routinely screened antibody fragments usually require further in vitro maturation to achieve the desired biophysical properties. Blind in vitro strategies can produce improved ligands by introducing random mutations into the original sequences and selecting the resulting clones under more and more stringent conditions. Rational approaches exploit an alternative perspective that aims first at identifying the specific residues potentially involved in the control of biophysical mechanisms, such as affinity or stability, and then to evaluate what mutations could improve those characteristics. The understanding of the antigen-antibody interactions is instrumental to develop this process the reliability of which, consequently, strongly depends on the quality and completeness of the structural information. Recently, methods based on deep learning approaches critically improved the speed and accuracy of model building and are promising tools for accelerating the docking step. Here, we review the features of the available bioinformatic instruments and analyze the reports illustrating the result obtained with their application to optimize antibody fragments, and nanobodies in particular. Finally, the emerging trends and open questions are summarized.

Linear-Scaling Kernels for Protein Sequences and Small Molecules Outperform Deep Learning While Providing Uncertainty Quantitation and Improved Interpretability

Gaussian process (GP) is a Bayesian model which provides several advantages for regression tasks in machine learning such as reliable quantitation of uncertainty and improved interpretability. Their adoption has been precluded by their excessive computational cost and by the difficulty in adapting them for analyzing sequences (e.g., amino acid sequences) and graphs (e.g., small molecules). In this study, we introduce a group of random feature-approximated kernels for sequences and graphs that exhibit linear scaling with both the size of the training set and the size of the sequences or graphs. We incorporate these new kernels into our new Python library for GP regression, xGPR, and develop an efficient and scalable algorithm for fitting GPs equipped with these kernels to large datasets. We compare the performance of xGPR on 17 different benchmarks with both standard and state-of-the-art deep learning models and find that GP regression achieves highly competitive accuracy for these tasks while providing with well-calibrated uncertainty quantitation and improved interpretability. Finally, in a simple experiment, we illustrate how xGPR may be used as part of an active learning strategy to engineer a protein with a desired property in an automated way without human intervention.

How can we discover developable antibody-based biotherapeutics?

Antibody-based biotherapeutics have emerged as a successful class of pharmaceuticals despite significant challenges and risks to their discovery and development. This review discusses the most frequently encountered hurdles in the research and development (R&D) of antibody-based biotherapeutics and proposes a conceptual framework called biopharmaceutical informatics. Our vision advocates for the syncretic use of computation and experimentation at every stage of biologic drug discovery, considering developability (manufacturability, safety, efficacy, and pharmacology) of potential drug candidates from the earliest stages of the drug discovery phase. The computational advances in recent years allow for more precise formulation of disease concepts, rapid identification, and validation of targets suitable for therapeutic intervention and discovery of potential biotherapeutics that can agonize or antagonize them. Furthermore, computational methods for de novo and epitope-specific antibody design are increasingly being developed, opening novel computationally driven opportunities for biologic drug discovery. Here, we review the opportunities and limitations of emerging computational approaches for optimizing antigens to generate robust immune responses, in silico generation of antibody sequences, discovery of potential antibody binders through virtual screening, assessment of hits, identification of lead drug candidates and their affinity maturation, and optimization for developability. The adoption of biopharmaceutical informatics across all aspects of drug discovery and development cycles should help bring affordable and effective biotherapeutics to patients more quickly.

BioAutoMATED: An end-to-end automated machine learning tool for explanation and design of biological sequences

The design choices underlying machine-learning (ML) models present important barriers to entry for many biologists who aim to incorporate ML in their research. Automated machine-learning (AutoML) algorithms can address many challenges that come with applying ML to the life sciences. However, these algorithms are rarely used in systems and synthetic biology studies because they typically do not explicitly handle biological sequences (e.g., nucleotide, amino acid, or glycan sequences) and cannot be easily compared with other AutoML algorithms. Here, we present BioAutoMATED, an AutoML platform for biological sequence analysis that integrates multiple AutoML methods into a unified framework. Users are automatically provided with relevant techniques for analyzing, interpreting, and designing biological sequences. BioAutoMATED predicts gene regulation, peptide-drug interactions, and glycan annotation, and designs optimized synthetic biology components, revealing salient sequence characteristics. By automating sequence modeling, BioAutoMATED allows life scientists to incorporate ML more readily into their work.

Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries

Therapeutic antibodies are an important and rapidly growing drug modality. However, the design and discovery of early-stage antibody therapeutics remain a time and cost-intensive endeavor. Here we present an end-to-end Bayesian, language model-based method for designing large and diverse libraries of high-affinity single-chain variable fragments (scFvs) that are then empirically measured. In a head-to-head comparison with a directed evolution approach, we show that the best scFv generated from our method represents a 28.7-fold improvement in binding over the best scFv from the directed evolution. Additionally, 99% of designed scFvs in our most successful library are improvements over the initial candidate scFv. By comparing a library's predicted success to actual measurements, we demonstrate our method's ability to explore tradeoffs between library success and diversity. Results of our work highlight the significant impact machine learning models can have on scFv development. We expect our method to be broadly applicable and provide value to other protein engineering tasks.

Recent research advances on non-linear phenomena in various biosystems

All biological phenomena can be classified as open, dissipative and non-linear. Moreover, the most typical phenomena are associated with non-linearity, dissipation and openness in biological systems. In this review article, four research topics on non-linear biosystems are described to show the examples from various biological systems. First, membrane dynamics of a lipid bilayer for the cell membrane is described. Since the cell membrane separates the inside of the cell from the outside, self-organizing systems that form spatial patterns on membranes often depend on non-linear dynamics. Second, various data banks based on recent genomics analysis supply the data including vast functional proteins from many organisms and their variable species. Since the proteins existing in nature are only a very small part of the space represented by amino acid sequence, success of mutagenesis-based molecular evolution approach crucially depends on preparing a library with high enrichment of functional proteins. Third, photosynthetic organisms depend on ambient light, the regular and irregular changes of which have a significant impact on photosynthetic processes. The light-driven process proceeds through many redox couples in the cyanobacteria constituting chain of redox reactions. Forth topics focuses on a vertebrate model, the zebrafish, which can help to understand, predict and control the chaos of complex biological systems. In particular, during early developmental stages, developmental differentiation occurs dynamically from a fertilized egg to divided and mature cells. These exciting fields of complexity, chaos, and non-linear science have experienced impressive growth in recent decades. Finally, future directions for non-liner biosystems are presented.

Leveraging deep learning to improve vaccine design

Deep learning has led to incredible breakthroughs in areas of research, from self-driving vehicles to solutions, to formal mathematical proofs. In the biomedical sciences, however, the revolutionary results seen in other fields are only now beginning to be realized. Vaccine research and development efforts represent an application with high public health significance. Protein structure prediction, immune repertoire analysis, and phylogenetics are three principal areas in which deep learning is poised to provide key advances. Here, we opine on some of the current challenges with deep learning and how they are being addressed. Despite the nascent stage of deep learning applications in immunological studies, there is ample opportunity to utilize this new technology to address the most challenging and burdensome infectious diseases confronting global populations.

Accelerating therapeutic protein design with computational approaches toward the clinical stage

Therapeutic protein, represented by antibodies, is of increasing interest in human medicine. However, clinical translation of therapeutic protein is still largely hindered by different aspects of developability, including affinity and selectivity, stability and aggregation prevention, solubility and viscosity reduction, and deimmunization. Conventional optimization of the developability with widely used methods, like display technologies and library screening approaches, is a time and cost-intensive endeavor, and the efficiency in finding suitable solutions is still not enough to meet clinical needs. In recent years, the accelerated advancement of computational methodologies has ushered in a transformative era in the field of therapeutic protein design. Owing to their remarkable capabilities in feature extraction and modeling, the integration of cutting-edge computational strategies with conventional techniques presents a promising avenue to accelerate the progression of therapeutic protein design and optimization toward clinical implementation. Here, we compared the differences between therapeutic protein and small molecules in developability and provided an overview of the computational approaches applicable to the design or optimization of therapeutic protein in several developability issues.

Artificial intelligence in cancer immunotherapy: Applications in neoantigen recognition, antibody design and immunotherapy response prediction

Cancer immunotherapy is a method of controlling and eliminating tumors by reactivating the body's cancer-immunity cycle and restoring its antitumor immune response. The increased availability of data, combined with advancements in high-performance computing and innovative artificial intelligence (AI) technology, has resulted in a rise in the use of AI in oncology research. State-of-the-art AI models for functional classification and prediction in immunotherapy research are increasingly used to support laboratory-based experiments. This review offers a glimpse of the current AI applications in immunotherapy, including neoantigen recognition, antibody design, and prediction of immunotherapy response. Advancing in this direction will result in more robust predictive models for developing better targets, drugs, and treatments, and these advancements will eventually make their way into the clinical setting, pushing AI forward in the field of precision oncology.

Computational and artificial intelligence-based methods for antibody development

Due to their high target specificity and binding affinity, therapeutic antibodies are currently the largest class of biotherapeutics. The traditional largely empirical antibody development process is, while mature and robust, cumbersome and has significant limitations. Substantial recent advances in computational and artificial intelligence (AI) technologies are now starting to overcome many of these limitations and are increasingly integrated into development pipelines. Here, we provide an overview of AI methods relevant for antibody development, including databases, computational predictors of antibody properties and structure, and computational antibody design methods with an emphasis on machine learning (ML) models, and the design of complementarity-determining region (CDR) loops, antibody structural components critical for binding.

The RESP AI model accelerates the identification of tight-binding antibodies

High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interval or uncertainty needed to assess the reliability of the predictions. Here we present a pipeline called RESP for efficient identification of high affinity antibodies. We develop a learned representation trained on over 3 million human B-cell receptor sequences to encode antibody sequences. We then develop a variational Bayesian neural network to perform ordinal regression on a set of the directed evolution sequences binned by off-rate and quantify their likelihood to be tight binders against an antigen. Importantly, this model can assess sequences not present in the directed evolution library and thus greatly expand the search space to uncover the best sequences for experimental evaluation. We demonstrate the power of this pipeline by achieving a 17-fold improvement in the K_D of the PD-L1 antibody Atezolizumab and this success illustrates the potential of RESP in facilitating general antibody development.

Approaches to expand the conventional toolbox for discovery and selection of antibodies with drug-like physicochemical properties

Antibody drugs should exhibit not only high-binding affinity for their target antigens but also favorable physicochemical drug-like properties. Such drug-like biophysical properties are essential for the successful development of antibody drug products. The traditional approaches used in antibody drug development require significant experimentation to produce, optimize, and characterize many candidates. Therefore, it is attractive to integrate new methods that can optimize the process of selecting antibodies with both desired target-binding and drug-like biophysical properties. Here, we summarize a selection of techniques that can complement the conventional toolbox used to de-risk antibody drug development. These techniques can be integrated at different stages of the antibody development process to reduce the frequency of physicochemical liabilities in antibody libraries during initial discovery and to co-optimize multiple antibody features during early-stage antibody engineering and affinity maturation. Moreover, we highlight biophysical and computational approaches that can be used to predict physical degradation pathways relevant for long-term storage and in-use stability to reduce the need for extensive experimentation.

A library approach for the de novo high-throughput isolation of humanized VHH domains with favorable developability properties following camelid immunization

In this study, we generated a novel library approach for high throughput de novo identification of humanized single-domain antibodies following camelid immunization. To achieve this, VHH-derived complementarity-determining regions-3 (CDR3s) obtained from an immunized llama (Lama glama) were grafted onto humanized VHH backbones comprising moderately sequence-diversified CDR1 and CDR2 regions similar to natural immunized and naïve antibody repertoires. Importantly, these CDRs were tailored toward favorable in silico developability properties, by considering human-likeness as well as excluding potential sequence liabilities and predicted immunogenic motifs. Target-specific humanized single-domain antibodies (sdAbs) were readily obtained by yeast surface display. We demonstrate that, by exploiting this approach, high affinity sdAbs with an optimized in silico developability profile can be generated. These sdAbs display favorable biophysical, biochemical, and functional attributes and do not require any further sequence optimization. This approach is generally applicable to any antigen upon camelid immunization and has the potential to significantly accelerate candidate selection and reduce risks and attrition rates in sdAb development.

Selection of target-binding proteins from the information of weakly enriched phage display libraries by deep sequencing and machine learning

Despite the advances in surface-display systems for directed evolution, variants with high affinity are not always enriched due to undesirable biases that increase target-unrelated variants during biopanning. Here, our goal was to design a library containing improved variants from the information of the "weakly enriched" library where functional variants were weakly enriched. Deep sequencing for the previous biopanning result, where no functional antibody mimetics were experimentally identified, revealed that weak enrichment was partly due to undesirable biases during phage infection and amplification steps. The clustering analysis of the deep sequencing data from appropriate steps revealed no distinct sequence patterns, but a Bayesian machine learning model trained with the selected deep sequencing data supplied nine clusters with distinct sequence patterns. Phage libraries were designed on the basis of the sequence patterns identified, and four improved variants with target-specific affinity (EC₅₀ = 80-277 nM) were identified by biopanning. The selection and use of deep sequencing data without undesirable bias enabled us to extract the information on prospective variants. In summary, the use of appropriate deep sequencing data and machine learning with the sequence data has the possibility of finding sequence space where functional variants are enriched.

Mammalian display to secretion switchable libraries for antibody preselection and high throughput functional screening

Recently, there has been a co-evolution of mammalian libraries and diverse microfluidic approaches for therapeutic antibody hit discovery. Mammalian libraries enable the preservation of full immune repertoires, produce hit candidates in final format and facilitate broad combinatorial bispecific antibody screening, while several available microfluidic methodologies offer opportunities for rapid high-content screens. Here, we report proof-of-concept studies exploring the potential of combining microfluidic technologies with mammalian libraries for antibody discovery. First, antibody secretion, target co-expression and integration of appropriate reporter cell lines enabled the selection of in-trans acting agonistic bispecific antibodies. Second, a functional screen for internalization was established and comparison of autocrine versus co-encapsulation setups highlighted the advantages of an autocrine one cell approach. Third, synchronization of antibody-secreting cells prior to microfluidic screens reduced assay variability. Furthermore, a display to secretion switchable system was developed and applied for pre-enrichment of antibody clones with high manufacturability in conjunction with subsequent screening for functional properties. These case studies demonstrate the system's feasibility and may serve as basis for further development of integrated workflows combining manufacturability sorting and functional screens for the identification of optimal therapeutic antibody candidates.

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

Machine learning (ML) is a key technology for accurate prediction of antibody-antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody-antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design.

A dataset comprised of binding interactions for 104,972 antibodies against a SARS-CoV-2 peptide

The dataset presented here contains quantitative binding scores of scFv-format antibodies against a SARS-CoV-2 target peptide collected via an AlphaSeq assay that can be used in the development and benchmarking of machine learning models. Starting from three seed sequences identified from a phage display campaign using a human naïve library, four sets of 29,900 antibodies were designed in silico by creating all k = 1 mutations and random k = 2 and k = 3 mutations throughout the complementary-determining regions (CDRs). Of the 119,600 designs, 104,972 were successfully built in to the AlphaSeq library and target binding was subsequently measured with 71,384 designs resulting in a predicted affinity value for at least one of the triplicate measurements. Data include antibodies with predicted affinity measurements ranging from 37 pM to 22 mM. To our knowledge, this dataset is the largest, publicly available dataset that contains antibody sequences, antigen sequence and quantitative measurements of binding scores and provides an opportunity to serve as a benchmark to evaluate antibody-specific representation models for machine learning.

Measurement(s)	Antibody Binding
Technology Type(s)	AlphaSeq
Factor Type(s)	Antibody sequence
Sample Characteristic - Organism	Homo sapiens

Conformal prediction under feedback covariate shift for biomolecular design

An increasingly high-impact application of machine learning in scientific discovery is its use in the design of novel objects with desired properties, such as the design of proteins, small molecules, and materials. Although a variety of algorithms have been developed for this purpose, it remains unclear when practitioners can trust the predictions made by learned models for designed objects, since design algorithms induce a distinctive shift between the training and test data distributions. We propose a method that provides confidence sets for designed objects, which we show satisfy finite-sample guarantees of statistical validity, for any design algorithm involving any learned regression model. Our work enables more trustworthy use of machine learning for design.

Many applications of machine-learning methods involve an iterative protocol in which data are collected, a model is trained, and then outputs of that model are used to choose what data to consider next. For example, a data-driven approach for designing proteins is to train a regression model to predict the fitness of protein sequences and then use it to propose new sequences believed to exhibit greater fitness than observed in the training data. Since validating designed sequences in the wet laboratory is typically costly, it is important to quantify the uncertainty in the model’s predictions. This is challenging because of a characteristic type of distribution shift between the training and test data that arises in the design setting—one in which the training and test data are statistically dependent, as the latter is chosen based on the former. Consequently, the model’s error on the test data—that is, the designed sequences—has an unknown and possibly complex relationship with its error on the training data. We introduce a method to construct confidence sets for predictions in such settings, which account for the dependence between the training and test data. The confidence sets we construct have finite-sample guarantees that hold for any regression model, even when it is used to choose the test-time input distribution. As a motivating use case, we use real datasets to demonstrate how our method quantifies uncertainty for the predicted fitness of designed proteins and can therefore be used to select design algorithms that achieve acceptable tradeoffs between high predicted fitness and low predictive uncertainty.

Prediction of protein-ligand binding affinity from sequencing data with interpretable machine learning

Protein-ligand interactions are increasingly profiled at high throughput using affinity selection and massively parallel sequencing. However, these assays do not provide the biophysical parameters that most rigorously quantify molecular interactions. Here we describe a flexible machine learning method, called ProBound, that accurately defines sequence recognition in terms of equilibrium binding constants or kinetic rates. This is achieved using a multi-layered maximum-likelihood framework that models both the molecular interactions and the data generation process. We show that ProBound quantifies transcription factor (TF) behavior with models that predict binding affinity over a range exceeding that of previous resources; captures the impact of DNA modifications and conformational flexibility of multi-TF complexes; and infers specificity directly from in vivo data such as ChIP-seq without peak calling. When coupled with an assay called KD-seq, it determines the absolute affinity of protein-ligand interactions. We also apply ProBound to profile the kinetics of kinase-substrate interactions. ProBound opens new avenues for decoding biological networks and rationally engineering protein-ligand interactions.

Designing antibodies as therapeutics

Antibody therapeutics are a large and rapidly expanding drug class providing major health benefits. We provide a snapshot of current antibody therapeutics including their formats, common targets, therapeutic areas, and routes of administration. Our focus is on selected emerging directions in antibody design where progress may provide a broad benefit. These topics include enhancing antibodies for cancer, antibody delivery to organs such as the brain, gastrointestinal tract, and lungs, plus antibody developability challenges including immunogenicity risk assessment and mitigation and subcutaneous delivery. Machine learning has the potential, albeit as yet largely unrealized, for a transformative future impact on antibody discovery and engineering.

Learning what not to select for in antibody drug discovery

Identifying antibodies with high affinity and target specificity is crucial for drug discovery and development; however, filtering out antibody candidates with nonspecific or polyspecific binding profiles is also important. In this issue of Cell Reports Methods, Saksena et al. report a computational counterselection method combining deep sequencing and machine learning for identifying nonspecific antibody candidates and demonstrate that it has advantages over more established molecular counterselection methods.

Computational counterselection identifies nonspecific therapeutic biologic candidates

Effective biologics require high specificity and limited off-target binding, but these properties are not guaranteed by current affinity-selection-based discovery methods. Molecular counterselection against off targets is a technique for identifying nonspecific sequences but is experimentally costly and can fail to eliminate a large fraction of nonspecific sequences. Here, we introduce computational counterselection, a framework for removing nonspecific sequences from pools of candidate biologics using machine learning models. We demonstrate the method using sequencing data from single-target affinity selection of antibodies, bypassing combinatorial experiments. We show that computational counterselection outperforms molecular counterselection by performing cross-target selection and individual binding assays to determine the performance of each method at retaining on-target, specific antibodies and identifying and eliminating off-target, nonspecific antibodies. Further, we show that one can identify generally polyspecific antibody sequences using a general model trained on affinity data from unrelated targets with potential affinity for a broad range of sequences.

PDL1Binder: Identifying programmed cell death ligand 1 binding peptides by incorporating next-generation phage display data and different peptide descriptors

Monoclonal antibody drugs targeting the PD-1/PD-L1 pathway have showed efficacy in the treatment of cancer patients, however, they have many intrinsic limitations and inevitable drawbacks. Peptide inhibitors as alternatives might compensate for the drawbacks of current PD-1/PD-L1 interaction blockers. Identifying PD-L1 binding peptides by random peptide library screening is a time-consuming and labor-intensive process. Machine learning-based computational models enable rapid discovery of peptide candidates targeting the PD-1/PD-L1 pathway. In this study, we first employed next-generation phage display (NGPD) biopanning to isolate PD-L1 binding peptides. Different peptide descriptors and feature selection methods as well as diverse machine learning methods were then incorporated to implement predictive models of PD-L1 binding. Finally, we proposed PDL1Binder, an ensemble computational model for efficiently obtaining PD-L1 binding peptides. Our results suggest that predictive models of PD-L1 binding can be learned from deep sequencing data and provide a new path to discover PD-L1 binding peptides. A web server was implemented for PDL1Binder, which is freely available at http://i.uestc.edu.cn/pdl1binder/cgi-bin/PDL1Binder.pl.

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody–antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space

Therapeutic antibody development requires selection and engineering of molecules with high affinity and other drug-like biophysical properties. Co-optimization of multiple antibody properties remains a difficult and time-consuming process that impedes drug development. Here we evaluate the use of machine learning to simplify antibody co-optimization for a clinical-stage antibody (emibetuzumab) that displays high levels of both on-target (antigen) and off-target (non-specific) binding. We mutate sites in the antibody complementarity-determining regions, sort the antibody libraries for high and low levels of affinity and non-specific binding, and deep sequence the enriched libraries. Interestingly, machine learning models trained on datasets with binary labels enable predictions of continuous metrics that are strongly correlated with antibody affinity and non-specific binding. These models illustrate strong tradeoffs between these two properties, as increases in affinity along the co-optimal (Pareto) frontier require progressive reductions in specificity. Notably, models trained with deep learning features enable prediction of novel antibody mutations that co-optimize affinity and specificity beyond what is possible for the original antibody library. These findings demonstrate the power of machine learning models to greatly expand the exploration of novel antibody sequence space and accelerate the development of highly potent, drug-like antibodies.

Ultra-high-diversity factorizable libraries for efficient therapeutic discovery

The successful discovery of novel biological therapeutics by selection requires highly diverse libraries of candidate sequences that contain a high proportion of desirable candidates. Here we propose the use of computationally designed factorizable libraries made of concatenated segment libraries as a method of creating large libraries that meet an objective function at low cost. We show that factorizable libraries can be designed efficiently by representing objective functions that describe sequence optimality as an inner product of feature vectors, which we use to design an optimization method we call stochastically annealed product spaces (SAPS). We then use this approach to design diverse and efficient libraries of antibody CDR-H3 sequences with various optimized characteristics.

A Novel Synthetic Antibody Library with Complementarity-Determining Region Diversities Designed for an Improved Amplification Profile

Antibody discovery by phage display consists of two phases, i.e., the binding phase and the amplification phase. Ideally, the selection process is dominated by the former, and all the retrieved clones are amplified equally during the latter. In reality, the amplification efficiency of antibody fragments varies widely among different sequences and, after a few rounds of phage display panning, the output repertoire often includes rapidly amplified sequences with low or no binding activity, significantly diminishing the efficiency of antibody isolation. In this work, a novel synthetic single-chain variable fragment (scFv) library with complementarity-determining region (CDR) diversities aimed at improved amplification efficiency was designed and constructed. A previously reported synthetic scFv library with low, non-combinatorial CDR diversities was panned against protein A superantigen, and the library repertoires before and after the panning were analyzed by next generation sequencing. The enrichment or depletion patterns of CDR sequences after panning served as the basis for the design of the new library. Especially for CDR-H3 with a higher and more random diversity, a machine learning method was applied to predict potential fast-amplified sequences among a simulated sequence repertoire. In a direct comparison with the previous generation library, the new library performed better against a panel of antigens in terms of the number of binders isolated, the number of unique sequences, and/or the speed of binder enrichment. Our results suggest that the amplification-centric design of sequence diversity is a valid strategy for the construction of highly functional phage display antibody libraries.

High-Throughput Monoclonal Antibody Discovery from Phage Libraries: Challenging the Current Preclinical Pipeline to Keep the Pace with the Increasing mAb Demand

Simple Summary

Monoclonal antibodies are increasingly used for a broad range of diseases. Rising demand must face with time time-consuming and laborious processes to isolate novel monoclonal antibodies. Next-generation sequencing coupled to phage display provides timely and sustainable high throughput selection strategy to rapidly access novel target. Here, we describe the current NGS-guided strategies to identify potential binders from enriched sub-libraires by applying a user-friendly informatic pipeline to identify and discard false positive clones. Rescue step and strategies to boost mAb yield are also discussed to improve the limiting selection and screening steps.

Abstract

Monoclonal antibodies are among the most powerful therapeutics in modern medicine. Since the approval of the first therapeutic antibody in 1986, monoclonal antibodies keep holding great expectations for application in a range of clinical indications, highlighting the need to provide timely and sustainable access to powerful screening options. However, their application in the past has been limited by time-consuming and expensive steps of discovery and production. The screening of antibody repertoires is a laborious step; however, the implementation of next-generation sequencing-guided screening of single-chain antibody fragments has now largely overcome this issue. This review provides a detailed overview of the current strategies for the identification of monoclonal antibodies from phage display-based libraries. We also discuss the challenges and the possible solutions to improve the limiting selection and screening steps, in order to keep pace with the increasing demand for monoclonal antibodies.

Current advances in biopharmaceutical informatics: guidelines, impact and challenges in the computational developability assessment of antibody therapeutics

Therapeutic monoclonal antibodies and their derivatives are key components of clinical pipelines in the global biopharmaceutical industry. The availability of large datasets of antibody sequences, structures, and biophysical properties is increasingly enabling the development of predictive models and computational tools for the "developability assessment" of antibody drug candidates. Here, we provide an overview of the antibody informatics tools applicable to the prediction of developability issues such as stability, aggregation, immunogenicity, and chemical degradation. We further evaluate the opportunities and challenges of using biopharmaceutical informatics for drug discovery and optimization. Finally, we discuss the potential of developability guidelines based on in silico metrics that can be used for the assessment of antibody stability and manufacturability.

Rapid On-Cell Selection of High-Performance Human Antibodies

Phage display is a critical tool for developing antibodies. However, existing approaches require many time-consuming rounds of biopanning and screening of potential candidates due to a high rate of failure during validation. Herein, we present a rapid on-cell phage display platform which recapitulates the complex in vivo binding environment to produce high-performance human antibodies in a short amount of time. Selection is performed in a highly stringent heterogeneous mixture of cells to quickly remove nonspecific binders. A microfluidic platform then separates antigen-presenting cells with high throughput and specificity. An unsupervised machine learning algorithm analyzes sequences of phage from all pools to identify the structural trends that contribute to affinity and proposes ideal candidates for validation. In a proof-of-concept screen against human Frizzled-7, a key ligand in the Wnt signaling pathway, antibodies with picomolar affinity were discovered in two rounds of selection that outperformed current gold-standard reagents. This approach, termed μCellect, is low cost, high throughput, and compatible with a wide variety of cell types, enabling widespread adoption for antibody development.

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

Although the therapeutic efficacy and commercial success of monoclonal antibodies (mAbs) are tremendous, the design and discovery of new candidates remain a time and cost-intensive endeavor. In this regard, progress in the generation of data describing antigen binding and developability, computational methodology, and artificial intelligence may pave the way for a new era of in silico on-demand immunotherapeutics design and discovery. Here, we argue that the main necessary machine learning (ML) components for an in silico mAb sequence generator are: understanding of the rules of mAb-antigen binding, capacity to modularly combine mAb design parameters, and algorithms for unconstrained parameter-driven in silico mAb sequence synthesis. We review the current progress toward the realization of these necessary components and discuss the challenges that must be overcome to allow the on-demand ML-based discovery and design of fit-for-purpose mAb therapeutic candidates.

Predicting antibody binders and generating synthetic antibodies using deep learning

The antibody drug field has continually sought improvements to methods for candidate discovery and engineering. Historically, most such methods have been laboratory-based, but informatics methods have recently started to make an impact. Deep learning, a subfield of machine learning, is rapidly gaining prominence in the biomedical research. Recent advances in microfluidics technologies and next-generation sequencing have not only revolutionized therapeutic antibody discovery, but also contributed to a vast amount of antibody repertoire sequencing data, providing opportunities for deep learning-based applications. Previously, we used microfluidics, yeast display, and deep sequencing to generate a panel of binder and non-binder antibody sequences to the cancer immunotherapy targets PD-1 and CTLA-4. Here we encoded the antibody light and heavy chain complementarity-determining regions (CDR3s) into antibody images, then built and trained convolutional neural network models to classify binders and non-binders. To improve model interpretability, we performed in silico mutagenesis to identify CDR3 residues that were important for binder classification. We further built generative deep learning models using generative adversarial network models to produce synthetic antibodies against PD-1 and CTLA-4. Our models generated variable length CDR3 sequences that resemble real sequences. Overall, our study demonstrates that deep learning methods can be leveraged to mine and learn patterns in antibody sequences, offering insights into antibody engineering, optimization, and discovery.

Reconstruction of full antibody sequences in NGS datasets and accurate VL:VH coupling by cluster coordinate matching of non-overlapping reads

Next-generation sequencing (NGS) is an indispensable tool in antibody discovery projects. However, the limits on NGS read length make it difficult to reconstruct full antibody sequences from the sequencing runs, especially if the six CDRs are randomized. To overcome that, we took advantage of Illumina’s cluster mapping capabilities to pair non-overlapping reads and reconstruct full Fab sequences with accurate V_L:V_H pairings. The method relies on in silico cluster coordinate information, and not on extensive in vitro manipulation, making the protocol easily deployable and less prone to PCR-derived errors. This work maintains the throughput necessary for antibody discovery campaigns, and a high degree of fidelity, which potentiates not only phage-display and synthetic library-based discovery methods, but also the NGS-driven analysis of naïve and immune libraries.

Adaptive machine learning for protein engineering

Machine-learning models that learn from data to predict how protein sequence encodes function are emerging as a useful protein engineering tool. However, when using these models to suggest new protein designs, one must deal with the vast combinatorial complexity of protein sequences. Here, we review how to use a sequence-to-function machine-learning surrogate model to select sequences for experimental measurement. First, we discuss how to select sequences through a single round of machine-learning optimization. Then, we discuss sequential optimization, where the goal is to discover optimized sequences and improve the model across multiple rounds of training, optimization, and experimental measurement.

Deep mutational scanning for therapeutic antibody engineering

The biophysical and functional properties of monoclonal antibody (mAb) drug candidates are often improved by protein engineering methods to increase the probability of clinical efficacy. One emerging method is deep mutational scanning (DMS) which combines the power of exhaustive protein mutagenesis and functional screening with deep sequencing and bioinformatics. The application of DMS has yielded significant improvements to the affinity, specificity, and stability of several preclinical antibodies alongside novel applications such as introducing multi-specific binding properties. DMS has also been applied directly on target antigens to precisely map antibody-binding epitopes and notably to profile the mutational escape potential of viral targets (e.g., SARS-CoV-2 variants). Finally, DMS combined with machine learning is enabling advances in the computational screening and engineering of therapeutic antibodies.