ImmuneLens: linking transcriptional states and TCR clonotypes through disentangled multimodal learning
- 1Beijing Institute of Genomics, Chinese Academy of Sciences/ China National Center for Bioinformation
Abstract
Single-cell multi-omics technologies simultaneously capture the transcriptome and TCR sequence of T cells, providing an opportunity to study the relationship between transcriptional states and clonal architectures. However, jointly modeling the relationships between transcriptional states and TCR sequences while preserving modality-specific information remains challenging. Here, we present ImmuneLens, an interpretable multimodal representation learning framework designed for paired single-cell transcriptome and TCR sequence data. ImmuneLens supports the construction of a transferable multi-cohort immune reference atlas and enables unsupervised mapping of external query data. The complementarity between GEX and TCR information improves the stability of antigen-specificity prediction. In neoadjuvant immunotherapy cohorts, ImmuneLens resolves response-associated T cell heterogeneity and reveals links between clonal expansion and CD8 T cell functional states. Overall, ImmuneLens provides a
Related
- DECIPHER integrates disentangled representation learning and prototype-based cell-type deconvolution across molecular modalities
- Multimodal Insecticidal Activity of α-Humulene Against Chilo suppressalis via Endocrine Disruption and Transcriptional Suppression of Cuticular Proteins
- AC-Diff: Anatomy-Contrast Disentangled Diffusion for Multi-Vendor Liver MRI Harmonization
- A multimodal deep learning for rice crop health monitoring using vegetation index feature selection
- CUBE: Multimodal Representation Learning Reveals Biological Structure Across Histomorphology, Spatial Protein Phenotypes, and Transcriptome-Associated Signals
BibTeX
@misc{duan2026immunelens,
title = {{ImmuneLens: linking transcriptional states and TCR clonotypes through disentangled multimodal learning}},
author = {Z. Duan and Y. Wang and C. Li and G. Li and Y. Cao and X. Bai and F. Yang and S. Song},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.08.749998},
url = {https://www.biorxiv.org/content/10.64898/2026.09.08.749998v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - ImmuneLens: linking transcriptional states and TCR clonotypes through disentangled multimodal learning
AU - Z. Duan
AU - Y. Wang
AU - C. Li
AU - G. Li
AU - Y. Cao
AU - X. Bai
AU - F. Yang
AU - S. Song
PY - 2026
DA - 2026/09/08
PB - bioRxiv
DO - 10.64898/2026.09.08.749998
UR - https://www.biorxiv.org/content/10.64898/2026.09.08.749998v1
AB - Single-cell multi-omics technologies simultaneously capture the transcriptome and TCR sequence of T cells, providing an opportunity to study the relationship between transcriptional states and clonal architectures. However, jointly modeling the relationships between transcriptional states and TCR sequences while preserving modality-specific information remains challenging. Here, we present ImmuneLens, an interpretable multimodal representation learning framework designed for paired single-cell transcriptome and TCR sequence data. ImmuneLens supports the construction of a transferable multi-cohort immune reference atlas and enables unsupervised mapping of external query data. The complementarity between GEX and TCR information improves the stability of antigen-specificity prediction. In neoadjuvant immunotherapy cohorts, ImmuneLens resolves response-associated T cell heterogeneity and reveals links between clonal expansion and CD8 T cell functional states. Overall, ImmuneLens provides a
ER -