Abstract A042: Real-world clinical multi-omics and AI/ML analyses reveal bifurcation of drug resistance mechanisms to CDK4/6 inhibitors
Bibliographic record
Abstract
Abstract To better understand the molecular mechanisms of drug resistance to CDK4/6 inhibitors (CDK4/6i) and inform precision medicine strategies, we retrospectively analyzed a multi-omics dataset of 400 HR+/HER2- mBC patients who received CDK4/6i plus endocrine therapies in routine clinical practice, including 200 pre-treatment (Pre), 227 post-progression (Post) samples. Integrative clustering analysis identified three subgroups of tumors harboring different drug resistance mechanisms: ER driven, ER co-driven and ER independent. The ER independent subgroup increased the most in prevalence from 4% pre-treatment to 23% post-progression and is characterized by down-regulation of estrogen signaling and enrichment of drug resistance markers including TP53 and RB1 mutations, Basal-like and Her2-like subtypes and CCNE1 over-expression. We deconvoluted bulk tumor expression profiles to derive cancer-specific expression (CSE) profiles for investigating tumor intrinsic mechanisms that give rise to ER independent drug resistance. We then performed trajectory inference analyses often used in single-cell transcriptomics on CSEs and identified a latent pseudotime variable strongly correlated with ER independence and disease progression. Elastic principal graph (EPG) analysis further revealed bifurcated evolutionary trajectories for drug resistance that correspond to ER-dependent vs. ER-independent mechanisms. Using elastic net models trained on in vitro CRISPR knockout screen data, we predicted a shift in therapeutic dependency on ESR1 and CDK4 among ER-dependent tumors to CDK2 among ER-independent tumors. These predictions were experimentally validated using genetically modified isogenic models. Citation Format: Zhengyan G. Kan, Ji Wen, Wenjing Yang, Vladimir Ivanov, Whijae Roh, Kimberly H. Kim, Chaoting Liu, Vinicius Bonato. Real-world clinical multi-omics and AI/ML analyses reveal bifurcation of drug resistance mechanisms to CDK4/6 inhibitors [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A042.
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 | 0.013 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".