Predicting T cell activation based on intracellular calcium fluctuations
Bibliographic record
Abstract
Abstract Adoptive T cell therapies rely on the transduction of T cells with a predetermined antigen receptor which redirects their specificity towards tumor-specific antigens. Despite the development of multiple platforms for tumor-specific T cell receptor (TCR) discovery, this process remains time consuming and skewed toward high-affinity TCRs. Specifically, the methods for identifying therapeutically-relevant TCR sequences, predominantly achieved through the enrichment of antigen-specific T cells, represents a major bottleneck for the broader application of TCR-engineered cell therapies. Fluctuation of intracellular calcium levels in T cells is a well described, proximal readout of TCR signaling. Hence, it is an attractive candidate marker for identifying antigen-specific T cells that does not require in vitro antigen-specific T cell expansion. However, calcium fluctuations downstream of TCR engagement with antigen are highly variable; we propose that appropriately-trained machine learning algorithms may allow for T cell classification from complex datasets such as those related to polyclonal T cell signaling events. Using deep learning tools, we demonstrate efficient and accurate prediction of antigen-specificity based on intracellular Ca 2+ fluctuations of in vitro -stimulated CD8 + T cells. Using a simple co-culture assay to activate monoclonal TCR transgenic T cells of known specificity, we trained a convolutional neural network to predict T cell reactivity, and we test the algorithm against T cells bearing a distinct TCR transgene as well as a polyclonal T cell response. This approach provides the foundation for a new pipeline to fast-track antigen specific TCR sequence identification for use in adoptive T cell therapy. Significance Statement While T cells engineered to express a cancer-specific T cell receptor (TCR) are emerging as a viable approach for personalized therapies, the platforms for identifying clinically-relevant TCR sequences are often limited in the breadth of antigen receptors they identify or are cumbersome to implement on a personalized basis. Here, we show that imaging of intracellular calcium fluctuations downstream of TCR engagement with antigen can be used, in combination with artificial intelligence approaches, to accurately and efficiently predict T cell specificity. The development of cancer-specific T cell isolation methods based on early calcium fluctuations may avoid the biases of current methodologies for the isolation of patient-specific TCR sequences in the context of adoptive T cell therapy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".