Individualized Prediction of Drug Response and Rational Combination Therapy in NSCLC Using Artificial Intelligence–Enabled Studies of Acute Phosphoproteomic Changes
Bibliographic record
Abstract
We hypothesize that the study of acute protein perturbation in signal transduction by targeted anticancer drugs can predict drug sensitivity of these agents used as single agents and rational combination therapy. We assayed dynamic changes in 52 phosphoproteins caused by an acute exposure (1 hour) to clinically relevant concentrations of seven targeted anticancer drugs in 35 non-small cell lung cancer (NSCLC) cell lines and 16 samples of NSCLC cells isolated from pleural effusions. We studied drug sensitivities across 35 cell lines and synergy of combinations of all drugs in six cell lines (252 combinations). We developed orthogonal machine-learning approaches to predict drug response and rational combination therapy. Our methods predicted the most and least sensitive quartiles of drug sensitivity with an AUC of 0.79 and 0.78, respectively, whereas predictions based on mutations in three genes commonly known to predict response to the drug studied, for example, EGFR, PIK3CA, and KRAS, did not predict sensitivity (AUC of 0.5 across all quartiles). The machine-learning predictions of combinations that were compared with experimentally generated data showed a bias to the highest quartile of Bliss synergy scores (P = 0.0243). We confirmed feasibility of running such assays on 16 patient samples of freshly isolated NSCLC cells from pleural effusions. We have provided proof of concept for novel methods of using acute ex vivo exposure of cancer cells to targeted anticancer drugs to predict response as single agents or combinations. These approaches could complement current approaches using gene mutations/amplifications/rearrangements as biomarkers and demonstrate the utility of proteomics data to inform treatment selection in the clinic.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".