{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["17(1)"],"submitter":["Joubbi S"],"pubmed_abstract":["Variable heavy (VH) and variable light (VL) chain pairing is a critical determinant of antibody diversity, stability, and antigen-binding specificity. Identifying productive VH - VL combinations experimentally is labor-intensive and costly, motivating the development of computational methods that can more efficiently predict compatible heavy - light chain pairs. In this work, we present a comprehensive framework that includes a new benchmark dataset and three deep learning models, each trained with a different negative sampling strategy: random pairing, V-gene mismatching, and full V(D)J germline mismatching. Our dataset includes natural pairs and these three types of synthetic negatives to simulate increasingly realistic biological constraints. Furthermore, we present a lightweight yet highly effective BERT-based model that achieves over 90% accuracy in discriminating natural from synthetic VH - VL pairs. Through extensive evaluation, we demonstrate that V(D)J-informed negative sampling significantly improves model generalization and biological interpretability. By providing reproducible baselines and a biologically grounded benchmark, this work lays the foundation for future development of efficient computational tools in antibody engineering."],"journal":["mAbs"],"pagination":["2570749"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12536629"],"repository":["biostudies-literature"],"pubmed_title":["Germline-aware deep learning models and benchmarks for predicting antibody VH-VL pairing."],"pmcid":["PMC12536629"],"pubmed_authors":["Micheli A","D'Arco E","Milazzo P","Maccari G","Joubbi S"],"additional_accession":[]},"is_claimable":false,"name":"Germline-aware deep learning models and benchmarks for predicting antibody VH-VL pairing.","description":"Variable heavy (VH) and variable light (VL) chain pairing is a critical determinant of antibody diversity, stability, and antigen-binding specificity. Identifying productive VH - VL combinations experimentally is labor-intensive and costly, motivating the development of computational methods that can more efficiently predict compatible heavy - light chain pairs. In this work, we present a comprehensive framework that includes a new benchmark dataset and three deep learning models, each trained with a different negative sampling strategy: random pairing, V-gene mismatching, and full V(D)J germline mismatching. Our dataset includes natural pairs and these three types of synthetic negatives to simulate increasingly realistic biological constraints. Furthermore, we present a lightweight yet highly effective BERT-based model that achieves over 90% accuracy in discriminating natural from synthetic VH - VL pairs. Through extensive evaluation, we demonstrate that V(D)J-informed negative sampling significantly improves model generalization and biological interpretability. By providing reproducible baselines and a biologically grounded benchmark, this work lays the foundation for future development of efficient computational tools in antibody engineering.","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Dec","modification":"2026-06-04T13:37:24.25Z","creation":"2026-05-09T03:11:56.663Z"},"accession":"S-EPMC12536629","cross_references":{"pubmed":["41104651"],"doi":["10.1080/19420862.2025.2570749"]}}