Understanding TCR T cell knockout behavior using interpretable machine learning

Blennemann, M.; Verma, A.; Bachl, S.; Carnevale, J.; Engelhardt, B. E.

doi:10.1101/2024.10.01.616134

Home/Archive/bioRxiv

bioRxiv · 10.1101/2024.10.01.616134

Understanding TCR T cell knockout behavior using interpretable machine learning

Blennemann, M.·Verma, A.·Bachl, S.·Carnevale, J.·Engelhardt, B. E.

View original source ↗Export metadata ↓

Abstract

Genetic perturbation of T cell receptor (TCR) T cells is a promising method to un-lock better TCR T cell performance to create more powerful cancer immunotherapies, but understanding the changes to T cell behavior induced by genetic perturbations remains a challenge. Prior studies have evaluated the effect of different genetic modifications with cytokine production and metabolic activity assays. Live-cell imaging is an inexpensive and robust approach to capture TCR T cell responses to cancer. Most methods to quantify T cell responses in live-cell imaging data use simple approaches to count T cells and cancer cells across time, effectively quantifying how much space in the 2D well each cell type covers, leaving actionable information unexplored. In this study, we characterize changes in TCR T cells interactions with cancer cells from live-cell imaging data using explainable artificial intelligence (AI). We train convolutional neural networks to distinguish behaviors in TCR T cell with CRISPR knock outs of CUL5, RASA2, and a safe harbor control knockout. We use explainable AI to identify specific interaction types that define different knock-out conditions. We find that T cell and cancer cell coverage is a strong marker of TCR T cell modification when comparing similar experimental time points, but differences in cell aggregation characterize CUL5KO and RASA2KO behavior across all time points. Our pipeline for discovery in live-cell imaging data can be used for characterizing complex behaviors in arbitrary live-cell imaging datasets, and we describe best practices for this goal.

Explore related subjects

cell biology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Blennemann, M., Verma, A., Bachl, S., Carnevale, J., Engelhardt, B. E.. 2024-10-01. Understanding TCR T cell knockout behavior using interpretable machine learning. https://doi.org/10.1101/2024.10.01.616134

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Not all TOP RNAs are created equal: 3'UTR length and TSS selection predict the translational regulation of LARP1-bound mRNAs in CD4+ T cells

Naive T cells are poised for activation and contain a pool of translationally repressed ribosomal protein (RP) mRNA prepared to induce ribosome biogenesis to support protein synthesis, cell growth and proliferation. RP mRNA are the prototypical members of a class of transcripts initiating at cytosine followed by a CU rich element called terminal oligo pyrimidine (TOP) RNAs. TOP RNAs are regulated by an RNA binding protein LARP1, which promotes transcript stabilisation and translational repression. We investigated LARP1 function in T cell activation by generating cross-linking immunoprecipitation (CLIP) datasets detailing the LARP1-RNA interactions in naive and activated CD4+ T cells and identifying novel TOP RNAs. TOP RNAs identified by this analysis were functionally diverse. RP mRNAs were typified by high stability, and translational repression in naive T cells followed by MTORC1-dependent translation increases following T cell activation. However, other TOP RNAs varied in these aspects of their regulation. Notably, TOP RNAs with longer 3'UTRs had a relaxed dependency on LARP1 for stability and a reduced dependency on MTORC1 for their translation. Transcription start site heterogeneity also impacted TOP RNA regulation by generating a mixture of transcript isoforms with different TOP motif lengths. Longer terminal oligo pyrimidine stretches were associated with a greater dependency on MTORC1 for translation. Differential regulation of TOP RNAs may allow tuneable translational responses to MTORC1 and indicates potential roles for LARP1 beyond translation regulation and stability.

cell biology↗

bioRxiv2026

Sex-specific metabolic regulation by the Drosophila RNA-binding protein Nab2

Conserved RNA binding proteins (RBPs) regulate key steps of gene expression including mRNA processing, export, localization, stability and translation. Human ZC3H14 is a conserved RBP that regulates pre-mRNA processing in neurons and loss of ZC3H14 leads to neurological defects. Studies of Nab2, the Drosophila orthologue of ZC3H14, have identified potential target RNAs involved in metabolism, suggesting Nab2 may influence neurometabolic circuitry. Here, we show a female-specific increase in dilp2 and dilp5 mRNA levels. The dilps encode insulin-like peptides that signal from the brain insulin producing cells (IPCs) to peripheral tissues. Nab2null females have enlarged lipid droplets in the fat body, a tissue analogous to human adipose tissue and liver. Notably, neuronal depletion of Nab2 increases lipid droplet size while neuronal expression of Nab2 in Nab2null female rescues this phenotype supporting a role for Nab2 in a neuronal circuit that regulates dilp levels. Furthermore, depletion of dilp2 or dilp5 from IPCs rescues the enlarged lipid droplet phenotype in Nab2null females indicating that elevated dilp2/dilp5 contributes to enlarged lipid droplets. Together, these data support a female-specific role for Nab2 in brain neurons to support insulin signaling and fat storage, expanding the known functions of RBPs linking neuronal function and metabolic homeostasis.

cell biology↗

bioRxiv2026

Deep generative embeddings of gene expression and splicing reposition the interpretation of single-cell transcriptomic signatures

Single-cell transcriptomic analysis predominantly derives cell identity from gene expression analysis, while alternative splicing is processed separately despite its fundamental role for cell homeostasis. To overcome the limits of separate investigations, we developed a probabilistic deep learning framework, Crecerelle, enabling resolution of the contributions of gene expression and alternative splicing in each cell. Crecerelle learns cell embeddings from gene expressions and alternative splicing isoforms, to decipher their mutually dependent impact on the functional characterisation of cells in a data-driven manner, exemplified for the Tabula Muris dataset. This is enabled through a zero-and-N-inflated Dirichlet-Multinomial for a variational autoencoder that learns cell embeddings solely from splicing profiles, as well as a bi-modal variational autoencoder with a relevance-weighted mixture-of-experts variational posterior to consolidate the modality-specific contribution at single-cell level. Crecerelle reveals cell-type-specific isoform markers as well as subpopulations with unique isoforms and uncovers regulatory and disease-associated pathways not detected by gene expression analyses alone. This scalable and interpretable framework thus allows a more holistic study of transcriptomic regulation and will open a route to modality-relevance-weighted investigations across single-cell multiomics datasets and their influence on cellular homeostasis, tissue development and disease phenotypes.

cell biology↗