biostudies-literatureBurbach SMNIAID NIH HHSNational Institutes of HealthNIAIDNIGMS NIH HHS100967https://www.ebi.ac.uk/biostudies/studies/S-EPMC11117052biostudies-literatureUnknown5(5)Existing antibody language models are limited by their use of unpaired antibody sequence data. A recently published dataset of ∼1.6 × 10⁶ natively paired human antibody sequences offers a unique opportunity to evaluate how antibody language models are improved by training with native pairs. We trained three baseline antibody language models (BALM), using natively paired (BALM-paired), randomly-paired (BALM-shuffled), or unpaired (BALM-unpaired) sequences from this dataset. To address the paucity of paired sequences, we additionally fine-tuned ESM (evolutionary scale modeling)-2 with natively paired antibody sequences (ft-ESM). We provide evidence that training with native pairs allows the model to learn immunologically relevant features that span the light and heavy chains, whicPatterns (New York, N.Y.)Improving antibody language models with native pairing.PMC11117052R01 AI171438R35 GM133682P01 AI177683UM1 AI144462U19-AI135995P30 AI036214R35-GM133682P01-AI177683P30-AI036214UM1-AI144462R01-AI171438U19 AI135995Burbach SMBriney BfalseImproving antibody language models with native pairing.Existing antibody language models are limited by their use of unpaired antibody sequence data. A recently published dataset of ∼1.6 × 10⁶ natively paired human antibody sequences offers a unique opportunity to evaluate how antibody language models are improved by training with native pairs. We trained three baseline antibody language models (BALM), using natively paired (BALM-paired), randomly-paired (BALM-shuffled), or unpaired (BALM-unpaired) sequences from this dataset. To address the paucity of paired sequences, we additionally fine-tuned ESM (evolutionary scale modeling)-2 with natively paired antibody sequences (ft-ESM). We provide evidence that training with native pairs allows the model to learn immunologically relevant features that span the light and heavy chains, whic2024-01-01T00:00:00Z2024 May2026-06-02T08:25:37.547Z2025-08-27T03:07:22.217ZS-EPMC111170523880036010.1016/j.patter.2024.100967