Language model-based B cell receptor sequence embeddings can effectively encode receptor specificity
Open Access
- 18 December 2023
- journal article
- research article
- Published by Oxford University Press (OUP) in Nucleic Acids Research
- Vol. 52 (2) , 548-557
Abstract
High throughput sequencing of B cell receptors (BCRs) is increasingly applied to study the immense diversity of antibodies. Learning biologically meaningful embeddings of BCR sequences is beneficial for predictive modeling. Several embedding methods have been developed for BCRs, but no direct performance benchmarking exists. Moreover, the impact of the input sequence length and paired-chain information on the prediction remains to be explored. We evaluated the performance of multiple embedding models to predict BCR sequence properties and receptor specificity. Despite the differences in model architectures, most embeddings effectively capture BCR sequence properties and specificity. BCR-specific embeddings slightly outperform general protein language models in predicting specificity. In addition, incorporating full-length heavy chains and paired light chain sequences improves the prediction performance of all embeddings. This study provides insights into the properties of BCR embeddings to improve downstream prediction applications for antibody analysis and discovery.Keywords
All Related Versions
Funding Information
- National Institute of Health (R01AI104739, R01GM131642, P50CA121974)
This publication has 20 references indexed in Scilit:
- Immune2vec: Embedding B/T Cell Receptor Sequences in ℝN Using Natural Language ProcessingFrontiers in Immunology, 2021
- ProtTrans: Toward Understanding the Language of Life Through Self-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Cutting Edge: Distinct B Cell Repertoires Characterize Patients with Mild and Severe COVID-19The Journal of Immunology, 2021
- Human germinal centres engage memory and naive B cells after influenza vaccinationNature, 2020
- CoV-AbDab: the coronavirus antibody databaseBioinformatics, 2020
- Biophysicochemical Motifs in T-cell Receptor Sequences Distinguish Repertoires from Tumor-Infiltrating Lymphocyte and Adjacent Healthy TissueCancer Research, 2019
- iReceptor: A platform for querying and analyzing antibody/B‐cell and T‐cell receptor repertoire data across federated repositoriesImmunological Reviews, 2018
- Change-O: a toolkit for analyzing large-scale B cell immunoglobulin repertoire sequencing dataBioinformatics, 2015
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Diversity in the CDR3 Region of VH Is Sufficient for Most Antibody SpecificitiesImmunity, 2000