ImmuneLens: linking transcriptional states and TCR clonotypes through disentangled multimodal learning
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…
Single-cell multi-omics technologies enable the simultaneous capture of the transcriptome and TCR sequence of T cells, offering a chance to investigate the connection between transcriptional states and clonal architectures. Nevertheless, jointly modeling the relationships between transcriptional states and TCR sequences while preserving modality-specific information proves to be a challenge.
In this research, ImmuneLens, an interpretable multimodal representation learning framework, is introduced for paired single-cell transcriptome and TCR sequence data. ImmuneLens facilitates the creation of a transferable multi-cohort immune reference atlas and allows for unsupervised mapping of external query data. The integration of GEX and TCR information enhances the stability of antigen-specificity prediction.
In neoadjuvant immunotherapy cohorts, ImmuneLens uncovers response-associated T cell heterogeneity and uncovers links between clonal expansion and CD8 T cell functional states. In summary, ImmuneLens offers a comprehensive solution for linking transcriptional states and TCR clonotypes through disentangled multimodal learning.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
