Machine learning recognises senescence in glioblastoma and discovers senescence-inducing compounds
Bibliographic record
Abstract
Abstract Senescence is a cell-intrinsic tumour suppressive response. A one-two-punch cancer treatment strategy aims to induce senescence in cancerous cells before removing them with a senolytic. It is important to accurately recognise senescent cells to investigate the feasibility of such a treatment strategy and identify compounds that induce senescence in cancer. We focus specifically on the terminal brain cancer glioblastoma, firstly identifying senescent glioblastoma cells with conventional stains, before training a machine learning model to distinguish senescent cells using only a DAPI nuclear stain. To demonstrate how our method can aid drug discovery, we apply our pipeline to existing glioblastoma high-throughput phenotypic drug screening imaging data to identify compounds that induce senescence in glioblastoma and verify these predictions experimentally. Author Summary Damaged cells can enter a senescent cell state, in which they do not divide, but continue to interact with the environment around them. A novel potential cancer treatment strategy is to make tumor cells senescent, before removing senescent cancer cells with a targeted drug. To investigate this treatment strategy in the brain cancer glioblastoma, it is important to be able to accurately recognise senescent glioblastoma cells. As identifying senescent cells is challenging, we create a machine learning pipeline which can detect senescent glioblastoma cells in imaging data. We show that by applying our method to existing data we can discover compounds that induce senescence in glioblastoma. We verify our predictions by testing the compounds experimentally.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".