{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Burbach SM"],"funding":["NIAID NIH HHS","National Institutes of Health","NIAID","NIGMS NIH HHS"],"pagination":["100967"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11117052"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["5(5)"],"pubmed_abstract":["Existing antibody language models are limited by their use of unpaired antibody sequence data. A recently published dataset of ∼1.6 × 10<sup>6</sup> 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, whic"],"journal":["Patterns (New York, N.Y.)"],"pubmed_title":["Improving antibody language models with native pairing."],"pmcid":["PMC11117052"],"funding_grant_id":["R01 AI171438","R35 GM133682","P01 AI177683","UM1 AI144462","U19-AI135995","P30 AI036214","R35-GM133682","P01-AI177683","P30-AI036214","UM1-AI144462","R01-AI171438","U19 AI135995"],"pubmed_authors":["Burbach SM","Briney B"],"additional_accession":[]},"is_claimable":false,"name":"Improving antibody language models with native pairing.","description":"Existing antibody language models are limited by their use of unpaired antibody sequence data. A recently published dataset of ∼1.6 × 10<sup>6</sup> 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, whic","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 May","modification":"2026-06-02T08:25:37.547Z","creation":"2025-08-27T03:07:22.217Z"},"accession":"S-EPMC11117052","cross_references":{"pubmed":["38800360"],"doi":["10.1016/j.patter.2024.100967"]}}