Technological advancements in recent years, such as next-generation sequencing, have made it possible for large antibody repertoire databases to exist. These comprehensive databases provide an invaluable resource for researchers worldwide, providing scientists with insights into antibody structure, function, and design. This article provides an overview and examples for sequence, antibody structure, therapeutic, and experimental databases, highlighting their great potential to accelerate the development of antibody therapeutics through antibody engineering and discovery.
In the antibody development and engineering process, antibody sequences are required for assessing antigen binding affinity, target specificity, biological efficacy through epitope analysis, and developability properties. Therefore, database information on antibody sequences and properties is highly informative and can provide training data for artificial intelligence (AI) deep learning models.1
The Observed Antibody Space (OAS) is a sequence database collecting immune repertoires for use in large-scale analysis. It contains approximately 1.5 billion paired variable fragments and unpaired sequences, from over 80 different studies, annotated with predicted sequence errors. They cover diverse immune states, organisms, and individuals.2 Various AI models have used this database to develop humanized antibody sequences.3
The International Immunogenetics Information System (IMGT) provides databases for germline antibody sequences and is well-known for integrating sequence, genome, and structural data, particularly gene assignments for recombined antibodies.4,5
Antibody structures are essential in antibody design, as it determines how the antibody will interact with antigens and its binding properties. Databases provide researchers the resources to improve binding affinity and predict epitopes and paratopes.
The Protein Data Bank (PDB) is a database for 3D structures of large biological molecules, including proteins and nucleic acids. Researchers have used it to build up other datasets and integration systems, such as the Antibody Structure Database (AbDb), Structural Antibody Database (SAbDab), and abYsis.1,6
Databases that curate therapeutic antibody information are useful for researchers who are developing therapeutics. TABS is a database offering antibody, antigen, and company data linked to a variety of associated information on clinical trials, patents, papers, news, and regulatory agencies.7
Similarly, the Therapeutic Structural Antibody Database (Thera-SAbDab) describes antibody- and nanobody-derived therapeutics with known sequences recognized by the World Health Organization, including monoclonal antibodies and bispecifics. It also covers structural data from the PDB, and metadata for clinical trials, target antigen specificity, and companies involved in development.8
Researchers can further enrich these sequence and structure databases with antibody-specific experimental data. The Immune Epitope Database (IEDB) contains manually curated antibody and T cell epitopes researched in humans and other species, and links to epitope-specific antibody sequences.9 Furthermore, researchers can determine antibody-epitope interactions using binding affinity information available from the SAbDab and PDBBind databases.4,10
Modern AI models depend on curated antibody databases to aid in humanization, reduce immunogenicity, and enhance affinity. Datasets from OAS and IMGT serve as training inputs for deep learning tools. Machine learning (ML) models identify common motifs across antibody variable regions and complementarity-determining regions (CDRs) to optimize the properties of antibodies computationally. The integration of AI helps reduce design cycles and improve candidate prioritization.
Several databases offer interactive tools for antibody engineering that enable researchers to visualize structural models, align sequences, and analyze epitopes. For instance, abYsis facilitates sequence-structure mapping, humanization scoring, and template selection. Meanwhile, SAbDab provides 3D viewing options along with residue-level insights for structural comparisons. These tools simplify data interpretation and foster collaboration among research teams.
Some databases include metadata on clinical trials, regulatory designations, and company pipelines, which are crucial for aligning antibody development with translational and commercial goals. TABS and Thera-SAbDab offer updates on the status of antibodies in development, detailing trial phases, approval stages, and sponsor information. This information supports risk assessments, CMC planning, and competitive market positioning.
The use of antibody databases has become standard practice in antibody discovery and engineering. These platforms bring together the scientific knowledge necessary to design, optimize, and validate antibody candidates with greater accuracy. By integrating AI tools, visualization platforms, and regulatory insights, researchers can speed up development timelines and minimize costly mistakes.
At Biointron, we are dedicated to accelerating your antibody discovery, optimization, and production needs. Our team of experts can provide customized solutions that meet your specific research needs. Contact us to learn more about our services and how we can help accelerate your research and drug development projects.
Kim, J., McFee, M., Fang, Q., Abdin, O., & Kim, P. M. (2023). Computational and artificial intelligence-based methods for antibody development. Trends in Pharmacological Sciences, 44(3), 175–189. https://www.cell.com/trends/pharmacological-sciences/fulltext/S0165-6147(22)00279-6
Olsen, T. H., Boyles, F., & Deane, C. M. (2022). Observed Antibody Space: A diverse database of cleaned, annotated, and translated unpaired and paired antibody sequences. Protein Science, 31(1), 141–146. https://onlinelibrary.wiley.com/doi/10.1002/pro.4205
Marks, C., Hummer, A. M., Chin, M., & Deane, C. M. (2021). Humanization of antibodies using a machine learning approach on large-scale repertoire data. Bioinformatics, 37(22), 4041-4047. https://academic.oup.com/bioinformatics/article/37/22/4041/6295884
Norman, R. A., Ambrosetti, F., Bonvin, A. M., Colwell, L. J., Kelm, S., Kumar, S., & Krawczyk, K. (2020). Computational approaches to therapeutic antibody design: Established methods and emerging trends. Briefings in Bioinformatics, 21(5), 1549-1567. https://academic.oup.com/bib/article/21/5/1549/5581643
IMGT®, the international ImMunoGeneTics information system®. (2023). IMGT. https://www.imgt.org/
RCSB PDB: Homepage. (2023). RCSB. https://www.rcsb.org/
TABS Therapeutic Antibody Database. (2023). Tabs. https://tabs.craic.com/users/sign_in
SAbDab: The Structural Antibody Database. (2023). Oxford Protein Informatics Group. https://opig.stats.ox.ac.uk/webapps/sabdab-sabpred/sabdab
IEDB.org: Free epitope database and prediction resource. (2023). IEDB. https://iedb.org/
Welcome to PDBbind-CN database. (2020). PDBbind. http://www.pdbbind.org.cn/
Two popular topics discussed at the 2026 BIO International Convention were devel……
AI is changing antibody discovery, but model performance depends on the quality ……
Antibody discovery has become increasingly sequence-rich. Display technologies, ……
Biointron, a leading contract research organization specializing in antibody dis……
You can also contact us on the Scientist and Science Exchange marketplaces.
