SprintX: mitigating data scarcity in antibody design via synthetic structural prior knowledge dataset
- 1Department of Data Science, Kangwon National University, Chuncheon, Republic of Korea
- 2UBLBio Corporation, Suwon, Republic of Korea
Abstract
Structure-based artificial intelligence (AI)-driven antibody design is increasingly important for therapeutic development, yet progress has been hindered by the scarcity of high-quality antibody–antigen complex structures for model training. To alleviate this bottleneck, we introduce SprintX (Structural Prior for Antibody–Antigen CompleXes), a large-scale AlphaFold3-derived synthetic dataset designed to provide structural prior knowledge for antibody–antigen modeling. Unlike conventional docking-based synthesis pipelines, SprintX uses AlphaFold3 to generate antigen-conditioned candidate complex-structure predictions from sampled antibody sequences paired with selected antigens, without imposing predefined binding-site or pose constraints. Candidate structures were ranked to select one representative structure per antibody–antigen pair before terminal trimming and multistage quality control. To improve reliability and learning stability, we applied a multi-stage quality-control pipeline integrating global confidence metrics, stereochemical validation, and interface-level contact analysis. SprintX recapitulated key geometric characteristics and physicochemical regularities of experimentally resolved antibody-antigen complexes while filtering out structurally unstable or implausible synthetic outputs. Across downstream tasks including antibody generation, computational binding-affinity prediction, and binding-interface prediction, models pretrained with SprintX showed meaningful improvements in structural plausibility and competitive performance on computational binding-affinity and binding-interface prediction benchmarks. These results support SprintX not as a substitute for experimentally resolved complexes, but as a complementary source of structural prior knowledge for structure-aware antibody modeling. Finally, we release SprintX as an openly accessible resource to facilitate data-efficient learning for AI-driven antibody design.
Related
- Structural basis for cross-alphaherpesvirus neutralization by an antibody targeting a conserved hotspot on glycoprotein B
- FANCM restrains structural genome evolution and defines a synthetic lethal dependency in BRCA1-deficient breast cancer
- Longitudinal Changes in Structural and Functional Brain Imaging and Their Association with Cognitive and Neuropsychiatric Symptoms in Hashimoto Encephalopathy with Anti-NAE Antibody
- Advances and perspectives of next-generation antitumor antibody-based modalities: Structural innovation and target-driven strategies.
- Disease Knowledge Assessed by RAKE-T and Its Sociodemographic and Clinical Correlates in Patients with Rheumatoid Arthritis Receiving Biologic and Targeted Synthetic DMARDs: A Multicenter Cross-Sectional Study
BibTeX
@article{heo2026sprintx,
title = {{SprintX: mitigating data scarcity in antibody design via synthetic structural prior knowledge dataset}},
author = {Ryong Heo and Dahyeon Lee and Jaeho Jung and Byung Ju Kim and Chihyun Park},
journal = {mAbs},
year = {2026},
month = oct,
doi = {10.1080/19420862.2026.2753234},
url = {https://doi.org/10.1080/19420862.2026.2753234},
note = {CC BY},
}
RIS
TY - JOUR
TI - SprintX: mitigating data scarcity in antibody design via synthetic structural prior knowledge dataset
AU - Ryong Heo
AU - Dahyeon Lee
AU - Jaeho Jung
AU - Byung Ju Kim
AU - Chihyun Park
PY - 2026
DA - 2026/10/31
JO - mAbs
DO - 10.1080/19420862.2026.2753234
UR - https://doi.org/10.1080/19420862.2026.2753234
AB - Structure-based artificial intelligence (AI)-driven antibody design is increasingly important for therapeutic development, yet progress has been hindered by the scarcity of high-quality antibody–antigen complex structures for model training. To alleviate this bottleneck, we introduce SprintX (Structural Prior for Antibody–Antigen CompleXes), a large-scale AlphaFold3-derived synthetic dataset designed to provide structural prior knowledge for antibody–antigen modeling. Unlike conventional docking-based synthesis pipelines, SprintX uses AlphaFold3 to generate antigen-conditioned candidate complex-structure predictions from sampled antibody sequences paired with selected antigens, without imposing predefined binding-site or pose constraints. Candidate structures were ranked to select one representative structure per antibody–antigen pair before terminal trimming and multistage quality control. To improve reliability and learning stability, we applied a multi-stage quality-control pipeline integrating global confidence metrics, stereochemical validation, and interface-level contact analysis. SprintX recapitulated key geometric characteristics and physicochemical regularities of experimentally resolved antibody-antigen complexes while filtering out structurally unstable or implausible synthetic outputs. Across downstream tasks including antibody generation, computational binding-affinity prediction, and binding-interface prediction, models pretrained with SprintX showed meaningful improvements in structural plausibility and competitive performance on computational binding-affinity and binding-interface prediction benchmarks. These results support SprintX not as a substitute for experimentally resolved complexes, but as a complementary source of structural prior knowledge for structure-aware antibody modeling. Finally, we release SprintX as an openly accessible resource to facilitate data-efficient learning for AI-driven antibody design.
SN - 1942-0870
SN - 1942-0862
ER -