AB ‐Bind: Antibody binding mutational database for computational affinity predictions
Open accessAbstract
Antibodies (Abs) are a crucial component of the immune system and are often used as diagnostic and therapeutic agents. The need for high-affinity and high-specificity antibodies in research and medicine is driving the development of computational tools for accelerating antibody design and discovery. We report a diverse set of antibody binding data with accompanying structures that can be used to evaluate methods for modeling antibody interactions. Our Antibody-Bind (AB-Bind) database includes 1101 mutants with experimentally determined changes in binding free energies (ΔΔG) across 32 complexes. Using the AB-Bind data set, we evaluated the performance of protein scoring potentials in their ability to predict changes in binding free energies upon mutagenesis. Numerical correlations between computed and observed ΔΔG values were low (r = 0.16-0.45), but the potentials exhibited predictive power for classifying variants as improved vs weakened binders. Performance was evaluated using the area under the curve (AUC) for receiver operator characteristic (ROC) curves; the highest AUC values for 527 mutants with |ΔΔG| > 1.0 kcal/mol were 0.81, 0.87, and 0.88 using STATIUM, FoldX, and Discovery Studio scoring potentials, respectively. Some methods could also enrich for variants with improved binding affinity; FoldX and Discovery Studio were able to correctly rank 42% and 30%, respectively, of the 80 most improved binders (those with ΔΔG < -1.0 kcal/mol) in the top 5% of the database. This modest predictive performance has value but demonstrates the continuing need to develop and improve protein energy functions for affinity prediction.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Additional dedicated datasets summarize curated information about properties and structure of antibodies, including SKEMPI and AB-Bind.
“Additional dedicated datasets summarize curated information about properties and structure of antibodies.These databases include the structural database of kinetics and energetics of mutant protein interactions (SKEMPI) [17], and the antibody binding mutational database (AB-Bind) [18].”
From Computational and artificial intelligence-based methods for antibody development (2023) · cites this paper as [18]
The six benchmark datasets have been widely used to test the predictive power of PPI prediction methods.
“These datasets have been widely used to test the predictive power of the PPI prediction methods [12, 13, 27–29, 29–35].”
From Deep geometric representations for modeling effects of mutations on protein-protein binding affinity (2021) · cites this paper as [34]
The increasing number of structural, sequence and experimental data on antibodies being deposited in the public domain provides the necessary foundation for improving data-driven methods.
“The increasing number of structural [16], sequence [17] and experimental data [18–21] on antibodies being deposited in the public domain provides the necessary foundation for improving such data-driven methods.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [19]
Other, more specialized, resources exist such as Ab-Bind, which hold data on 1101 mutations across 32 antibody complexes, and SKEMPI, which curates binding energy data for available structures but is not limited to antibody information only.
“Other, more specialized, resources exist such as Ab-Bind [19], which hold data on 1101 mutations across 32 antibody complexes, and SKEMPI [55], which curates binding energy data for available structures but is not limited to antibody information only.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [19]
The RP value between predicted ΔΔG values and experimental data in cross-validations of the commonly used PPI database AB-Bind is only 0.53.
“the RP value between predicted ΔΔG values and experimental data in cross-validations of a commonly used PPI database, AB-Bind10, is only 0.53.”
From A topology-based network tree for the prediction of protein–protein binding affinity changes following mutation (2020) · cites this paper as [10]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 78 · Cited by 179
- Authors
- Sirin, S., Apgar, J. R., Bennett, E. M., & Keating, A. E.
- Affiliations
- Massachusetts Institute of Technology (US)
- Pfizer (United States) (US)
- Corresponding author
- Keating, Amy E.
- Venue
- Protein Science
- Publisher
- Wiley
- Published
- 2015-11-06
- Volume
- 25
- Issue
- 2
- Pages
- 393-409
- ISSN
- 0961-8368 (ISSN-L)
- 1469-896X
- PMC
- PMC4815335
- OpenAlex
- W2283896596
- Cited by
- 179
- References
- 78
- Citations by year
- 2026: 23 · 2025: 37 · 2024: 20 · 2023: 21 · 2022: 20 · 2021: 16 · 2020: 11 · 2019: 7 · 2018: 9 · 2017: 7 · 2016: 7 · 2015: 1
- FWCI
- 3.47
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Protein Science (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Science Foundation (0821391)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Monoclonal and Polyclonal Antibodies Research
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
- Keywords
- antibody-antigen binding, binding free energy, binding affinity prediction, antibody design, FoldX, binding affinity ranking
- MeSH terms
- Animals, Antibodies, Antibody Affinity, Binding Sites, Antibody, Computer Simulation, Humans, Mutation, Thermodynamics, Models, Immunological, Databases, Protein
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
