Precision treatment with artificial intelligence assisted subtyping enhances therapeutic efficacy in HR+/HER2- breast cancer: The LINUXtrial.

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Absolute risk differences: SNF2 +35%, SNF4 +50%

• Primary Outcome: Objective response rates varied by subtype: SNF1 (10% vs 0%), SNF2 (65% vs 30%), SNF3 (40% vs 30%), SNF4 (70% vs 20%)

• Nnt Or Sensitivity: NNT approximately 2-3 for SNF2 and SNF4 subtypes based on response rate differences

• Confidence Interval: Not reported

Clinical Application

Requires AI-assisted molecular subtyping infrastructure and access to precision therapy options - may be challenging in regional centres Relevant to Australian practice where CDK4/6 inhibitors are PBS-subsidised first-line therapy. TGA approval would be needed for AI diagnostic tool. Aligns with Precision Medicine Initiative goals Australian patients with HR+/HER2- metastatic breast cancer progressing on CDK4/6 inhibitors, representing significant proportion of advanced breast cancer cases

Abstract

We report the results of LINUX (NCT05594095), a multicenter, randomized, controlled phase II platform trial aiming to identify effective precision treatments for hormone receptor-positive/human epidermal growth factor receptor 2-negative metastatic breast cancer after resistance to cyclin-dependent kinase 4/6 inhibitor. A total of 105 patients were categorized into four similarity network fusion (SNF) subtypes by artificial intelligence-assisted classification and randomly assigned to receive subtyping-based precision therapy (N = 70) or treatment of physician's choice (N = 35). Results demonstrate superior primary endpoint of objective response rates in the subtyping-based groups compared to controls: 10% versus 0% for SNF1, 65% versus 30% for SNF2, 40% versus 30% for SNF3, and 70% versus 20% for SNF4. Grade 3-4 treatment-related adverse events occurred in 37% of both groups. These findings highlight the clinical benefits of subtyping-based precision therapies, particularly for SNF2 and SNF4 subtypes, warranting further validation in phase III trials.

References

1. 1.Fan, L., Zhang, W-J., Li, H-P., Zeng, X-H., Teng, Y-E., Gong, Y., Jin, X., Zhao, S., Sun, T., Chen, W-Y., Wang, S-S., Yang, J., Zhuang, Z-G., Ni, S-J., He, Z-X., Fu, D-Y., Song, C-G., Lv, Z., Liang, Q-N., Yu, B-H., Shi, J., Wang, N., Liang, X-R., Zhang, N-N., Wang, Y., Ji, P., Liu, X-Y., Chen, L., He, M., Liu, Y., Sui, X-Y., Ma, L-X., Zhu, X-Z., Yang, F., Ge, L-P., Wu, S-Y., Wu, J., Yu, K-D., Liu, G-Y., Hu, X., Shen, Y., Pang, Z., Wang, J-F., Liang, F., Yang, W-T., Wang, Z-H., Jiang, Y-Z., & Shao, Z-M. (2026). Precision treatment with artificial intelligence assisted subtyping enhances therapeutic efficacy in HR+/HER2- breast cancer: The LINUXtrial. Cancer Cell. https://doi.org/10.1016/j.ccell.2025.11.003