Abstract CT231: Identification of a novel agnostic predictive multiomic signature via Elastic Net/Machine Learning in TALAPRO-2 (TP-2), a phase 3 study of talazoparib (TALA) + enzalutamide (ENZA) vs placebo (PBO) + ENZA as first-line (1L) treatment in patients (pts) with metastatic castration-resistant prostate cancer (mCRPC)
Bibliographic record
Abstract
Abstract Background: TP-2 (NCT03395197) demonstrated significantly improved radiologic progression-free survival (rPFS) regardless of homologous recombination repair (HRR) gene alteration status for pts with mCRPC who received 1L TALA + ENZA (n=402) vs PBO + ENZA (n=403; Agarwal et al. Lancet. 2023. PMID: 37285865). We explore potential associations of ctDNA genomics and tumor gene expression with efficacy in TP-2. Methods: The analysis was based on the safety population (n=799). Two data sets were used: a FoundationOne®Liquid CDx data set (Azad et al. ASCO 2023, #5056) of prospectively collected/retrospectively analyzed plasma samples (n=681); and a tumor transcriptomic data set generated via HTG’s Oncology Biomarker Panel (with 10 additional genes implicated in PARP inhibitor sensitivity; n=304). Correlations between baseline molecular biomarkers and rPFS were assessed via a Cox proportional hazards model. Multivariate elastic net regression analysis incorporated 151 pts in the TALA + ENZA arm with 2,868 molecular features (ctDNA: 309 genes [only short variant alterations incorporated]; HTG: 2,559 tumor transcripts). Results: Positively predictive candidate tumor biomarkers for TALA + ENZA included androgen response signature and individual androgen receptor (AR) target genes such as PSA, ALDH1A3, and CAMKK2. These expression signatures/transcripts had no/minimal predictive value for PBO + ENZA. A 33-feature (3 genes, 30 transcripts) elastic net signature was identified that was predictive of rPFS with TALA + ENZA: TP53 and AR short variant alteration status were each prognostic and associated with worse rPFS. Expression of multiple AR target genes, including ALDH1A3 (top selected feature) and CAMKK2, was positively associated with rPFS. For TALA + ENZA, this multiomic signature was predictive of rPFS in pts regardless of HRR gene alteration status, and to a lesser extent for PBO + ENZA. None of the 12 HRR genes used for stratification in TP-2 were included in the signature. Conclusions: Our exploratory analysis identified candidate gene expression signatures, including AR pathway elements, potentially associated with differential benefit from TALA + ENZA, reinforcing the potential for exploitable crosstalk between AR and DNA repair pathways. Though validation is necessary, a predictive multiomic signature for benefit from TALA + ENZA regardless of HRR alteration status was identified that included alterations in genes previously implicated in prognosis and expression of multiple AR target transcripts. Strikingly, it did not include any of the 12 HRR genes used in prospective stratification for TP-2, reinforcing the potential benefit for TALA + ENZA beyond HRR-deficient tumors. Citation Format: Glenn Liu, Xinmeng Jasmine Mu, Karim Fizazi, A. Douglas Laird, Nobuaki Matsubara, Steven M. Yip, Jie Pu, Joan Carles, Andre P. Fay, Robert J. Jones, Stefanie Zschäbitz, Josep M. Piulats, Jae Young Joung, Whijae Roh, Jijumon Chelliserry, Nicola Di Santo, Michelle Saul, Arun A. Azad, Neeraj Agarwal. Identification of a novel agnostic predictive multiomic signature via Elastic Net/Machine Learning in TALAPRO-2 (TP-2), a phase 3 study of talazoparib (TALA) + enzalutamide (ENZA) vs placebo (PBO) + ENZA as first-line (1L) treatment in patients (pts) with metastatic castration-resistant prostate cancer (mCRPC) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr CT231.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".