Geometry based gene expression signatures detect cancer treatment responders in clinical trials
Bibliographic record
Abstract
A bstract Aim The overall aim of this project is to determine if gene expression signatures of tumors, constructed from geometrical attributes of data, can be used to both create a definitive classification of responders and non-responders, and to predict patient treatment response in an unbiased manner. This is tested in an open-sourced Pfizer clinical trial data on avelumab plus axitnib in advanced renal cell carcinoma ( n = 726). Results Geometrical gene expression signatures were able to be used to create standardized classification of responders to the intervention, as demonstrated by dramatically different Kaplan-Meier (KM) estimators based on responder category assigned in the Pfizer trial. Furthermore, unbiased prediction based on leave one out methodology was able to correctly predict the responder classification with 82.0% accuracy. Biomarkers of response generated indicated that the strongest predictive gene was PODXL (podocalyxin), with an inconsistent influence on responder class based on over- and underexpression. A KM estimator of the out-of-sample predictions showed nearly four times the average effect in samples predicted to be responders against those predicted to not be responders, and accounted for 79.2% of the treatment effect. Conclusions Gene expression based geometrical signatures are able to create “gold standard” classification of responders and non-responders in clinical trial data, and are highly accurate at predicting these labels in an out-of-sample, unbiased test. These methods can be used to find more stable biomarkers of response, as well as increase the chances of a clinical trial being approved.
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 | 0.006 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".