Multi-modal generative modeling for joint analysis of single-cell T cell receptor and gene expression data

• Published in: Nature communications Vol. 15; no. 1; pp. 5577 - 15
• Main Authors: Drost, Felix, An, Yang, Bonafonte-Pardàs, Irene, Dratva, Lisa M., Lindeboom, Rik G. H., Haniffa, Muzlifah, Teichmann, Sarah A., Theis, Fabian, Lotfollahi, Mohammad, Schubert, Benjamin
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 03-07-2024; Nature Publishing Group; Nature Portfolio
• Subjects: 38/91; 631/114/1305; 631/114/2401; 631/250/2152; Antigens; Antigens, Viral - genetics; Antigens, Viral - immunology; COVID-19 - immunology; COVID-19 - virology; Datasets; Deep learning; Gene expression; Gene Expression Profiling - methods; Gene sequencing; Humanities and Social Sciences; Humans; Immune system; Knowledge management; Lymphocytes; Lymphocytes T; multidisciplinary; Phenotypes; Receptors; Receptors, Antigen, T-Cell - genetics; Receptors, Antigen, T-Cell - immunology; Receptors, Antigen, T-Cell - metabolism; Representations; SARS-CoV-2 - genetics; SARS-CoV-2 - immunology; Science; Science (multidisciplinary); Sequence analysis; Severe acute respiratory syndrome coronavirus 2; Single-Cell Analysis - methods; Subpopulations; T cell receptors; T-Lymphocytes - immunology; T-Lymphocytes - metabolism; Transcriptome; Transcriptomes
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-024-49806-9

Recent advances in single-cell immune profiling have enabled the simultaneous measurement of transcriptome and T cell receptor (TCR) sequences, offering great potential for studying immune responses at the cellular level. However, integrating these diverse modalities across datasets is challenging due to their unique data characteristics and technical variations. Here, to address this, we develop the multimodal generative model mvTCR to fuse modality-specific information across transcriptome and TCR into a shared representation. Our analysis demonstrates the added value of multimodal over unimodal approaches to capture antigen specificity. Notably, we use mvTCR to distinguish T cell subpopulations binding to SARS-CoV-2 antigens from bystander cells. Furthermore, when combined with reference mapping approaches, mvTCR can map newly generated datasets to extensive T cell references, facilitating knowledge transfer. In summary, we envision mvTCR to enable a scalable analysis of multimodal immune profiling data and advance our understanding of immune responses.
Although single-cell RNA sequencing analysis now allows simultaneous examination of transcriptome and T cell receptor repertoire sequences, integrating these two modalities remains a challenge. Here, the authors develop mvTCR, a generative deep learning model that integrates transcriptome and T cell receptor data into a joint representation capturing cell functions and phenotypes.