SNAC ‐ DB : An ML ‐ready database for antibody and NANOBODY ® VHH –antigen complexes with expanded structural diversity and real‐world benchmarking
Protein Science · 2026-07 · 35 (7)
DOI: 10.1002/pro.70655 ↗At a glance
Journal article in Protein Science, published online on 2026-06-07. Written by Abhinav Gupta and 7 co-authors. Institution: Large Molecule Research, Sanofi, Cambridge, Massachusetts, USA. Major MEDLINE topics: Single-Domain Antibodies, Databases, Protein, Antigen-Antibody Complex. Cited 2 times so far (Crossref); 29 references. The full text is freely available in PubMed Central. Funded by: Sanofi.
Abstract (original language)
Predicting antibody and NANOBODY® VHH–antigen complexes remains a critical challenge for state‐of‐the‐art structure prediction models, limiting their impact in therapeutic discovery pipelines. We introduce SNAC‐DB, an ML‐ready database and curation pipeline enriched with structural biology expertise, designed to accelerate model accuracy and generalization by providing 31–37% expanded structural diversity over existing resources like SAbDab through comprehensive re‐curation that extracts maximum value from available experimental structures. SNAC‐DB expands coverage by capturing often‐overlooked complexes and accurately identifying complete multi‐chain epitopes through improved biological‐assembly based logic. Built for ML practitioners, SNAC‐DB provides standardized formats with multi‐threshold structure‐based clustering to enable principled sample weighting during training. Using a rigorous benchmark of public PDB entries deposited post‐May 2024 plus confidential therapeutic structures, we evaluate seven leading models (Protenix‐v1, OpenFold‐3p2, RosettaFold‐3, Boltz‐2, Boltz‐1x, Chai‐1, and AlphaFold2.3‐multimer) with evaluation methodology tailored to antibody/NANOBODY® VHH–antigen complexes to ensure correct handling of multi‐chain epitopes, revealing systematic performance gaps: success rates rarely exceed 25%, confidence‐based ranking fails to identify best predictions even when accurate structures exist in ensembles, and all models consistently struggle with therapeutically relevant NANOBODY® VHHs. Systematic evaluation of sampling strategies demonstrates that while generating 1000 samples per target substantially increases the likelihood of producing accurate structures (oracle selection improves from 11.9% to 50.5%), confidence‐based ranking remains nearly flat (between 10.9% and 14.9%), revealing that improved ranking mechanisms represent a more tractable path to performance gains. Finally, fine‐tuning GeoDock on SNAC‐DB yields higher success rates than training on SAbDab (11.0% vs. 7.1% for antibodies; 7.0% vs. 4.0% for NANOBODY® VHHs), suggesting that SNAC‐DB's expanded structural diversity translates to improved model generalization.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Large Molecule Research, Sanofi, Cambridge, Massachusetts, USA.
- Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, Maryland, USA.
- Large Molecule Research, Sanofi, Barcelona, Spain.
- Large Molecule Research, Sanofi, Frankfurt, Germany.
ORCID profiles: Abhinav Gupta
Funding
- Sanofi
Cite
APA
Gupta, A., Rivero, B. M., Li, R., Roel-Touris, J., Nanfack, Y. F., Wendt, M., Qiu, Y., & Furtmann, N. (2026). SNAC ‐ DB : An ML ‐ready database for antibody and NANOBODY ® VHH –antigen complexes with expanded structural diversity and real‐world benchmarking. Protein Science, 35(7). https://doi.org/10.1002/pro.70655
Vancouver
Gupta A, Rivero BM, Li R, Roel-Touris J, Nanfack YF, Wendt M, et al. SNAC ‐ DB : An ML ‐ready database for antibody and NANOBODY ® VHH –antigen complexes with expanded structural diversity and real‐world benchmarking. Protein Science. 2026;35(7). doi:10.1002/pro.70655
BibTeX
@article{Gupta2026,
author = {Gupta, Abhinav and Rivero, Bryan Munoz and Li, Ruijiang and Roel-Touris, Jorge and Nanfack, Yves Fomekong and Wendt, Maria and Qiu, Yu and Furtmann, Norbert},
title = {SNAC ‐ DB : An ML ‐ready database for antibody and NANOBODY ® VHH –antigen complexes with expanded structural diversity and real‐world benchmarking},
journal = {Protein Science},
year = {2026},
volume = {35},
number = {7},
doi = {10.1002/pro.70655}
}
EUVIMED