Skip to content
Open access

Transcriptome-based synthetic lethality predictions to improve targeted therapy/immunotherapy treatment prioritization in non-metastatic breast cancer: BC-SELECT.

Sep 2026 · Cancer Research Communications · 0 citations
Medicine

Abstract

Patients with non-metastatic triple-negative (TNBC) or HER2-positive (HER2+) breast cancer do not have tools to predict treatment response or prioritize options prior to starting therapy. Pathologic complete response (pCR) is a proxy that requires neoadjuvant treatment. BC-SELECT leverages genetic interactions (e.g. synthetic lethality (SL)/rescue (SR)) to predict treatment response via pCR from breast cancer gene expression data. BC-SELECT involves (1) "Training: Gene-pair identification" that identifies clinically relevant partner genes from large-scale datasets for a given targeted therapy or immunotherapy target, and (2) "Training: Parameter tuning" using clinical trials to predict treatment response. We evaluated BC-SELECT's ability to predict pCR for trastuzumab, poly (ADP-ribose) polymerase (PARP) inhibitors, and immunotherapy, with tuning supported by three trials (n=86) and validation on nine unseen trials (n=722). BC-SELECT significantly predicted pCR in 6/9 trials, including all PARP inhibitors (ROC-AUCs 0.6-0.8; Odds Ratio (OR): 1.9-3.5) and immunotherapy (ROC-AUCs 0.7-0.8; OR: 3.2-7.1). BC-SELECT significantly distinguished between pCR and residual disease in 8/9 trials. No current standard-of-care, pre-treatment approaches predict benefit in non-metastatic TNBC and HER2+ breast cancer. BC-SELECT leverages genetic interactions to predict treatment response from gene expression data. Our findings support development of BC-SELECT towards studying how to prioritize PARP inhibitors and immunotherapy in non-metastatic breast cancer.

Read PDF

Similar papers

Open access Aug 2026

Pre-treatment T-cell Transcriptional Signatures Predict Immunotherapy Outcomes in Melanoma

Distinct signatures in the adjuvant and metastatic settings suggest differences in T-cell programs associated with patient outcomes, and support further evaluation of pre-treatment circulating T-cell transcriptional profiles as predictors of ICI response and toxicity in melanoma.

Noah Lepola, C. Dravillas, Shannon Gray et al. · 0 citations
Open access Sep 2026

A Machine Learning Framework Enables Supervised Treatment Response Prediction from Tumor Transcriptomics across Cancer Types.

Robustness analysis revealed that predictive performance plateaued for some therapies with increasing training cohorts but continued to improve for others, suggesting inherent limits of supervised brute-force learning for certain treatments, but additional data and deeper mechanistic modeling may further enhance transc...

L. Pal, E. Gertz, N. Nair et al. · 0 citations
Open access Aug 2026

From comparative oncology to AI-enabled precision medicine: translational biomodels for triple-negative breast cancer

A patient–model–algorithm–patient reverse-translational loop in which histopathology, radiology, molecular profiles, and functional response data are integrated through computational pathology, radiomics, multi-omics factor models, and supervised multimodal learning is proposed.

T. Collares, F. Seixas, C. Pessoa et al. · 0 citations
Open access Sep 2026

PD-L1 Expression as a Predictor of Response to Neoadjuvant Immunotherapy in Triple-Negative Breast Cancer

Background: Immune checkpoint blockade has changed the treatment of high-risk early-stage triple-negative breast cancer (TNBC), yet the clinical role of programmed death-ligand 1 (PD-L1) expression in the neoadjuvant setting remains unsettled. PD-L1 may identify an immune-enriched tumor microenvironment and therefore c...

Naznin Nahida, Dhruba Tasnim, Israt Jahan Mukta et al. · 0 citations
#artificial intelligence Review Oct 2026

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

A two-stage AI model predicting pathological complete response to neoadjuvant therapy in breast cancer and transcriptome-wide inference improves discrimination over clinical variables alone or one-stage pathology models, and robustness by avoiding genomic assays'gene selection constraints are developed.

Jungkyu Park, D. Biswas, J. Cappadona et al. · 0 citations
Aug 2026

AI-Driven Computational Design of Peptide-Based WWP1 Inhibitors as Promising Therapeutic Agents Against Breast Cancer, Including Triple-Negative Subtype

WI23-B is highlighted as a promising lead peptide with potent WWP1 inhibitory activity and synergistic antiproliferative effects when combined with PI3K inhibitors, and has the potential to reshape therapeutic strategies for BC and TNBC by enabling more effective and less toxic treatment regimens.

E. M. A. Fassi, Sara Mathlouthi, E. Maspero et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.