Using bioinformatics and artificial intelligence to map the cyclin-dependent kinase 4/6 inhibitor biomarker landscape in breast cancer

A cyclin-dependent kinase 4/6 (CDK4/6) inhibitor combined with endocrine therapy is the standard-of-care for patients with hormone receptor-positive/human epidermal growth factor receptor 2-negative advanced breast cancer. However, not all patients respond to the treatment, resistance often occurs and efficacy outcomes from early breast cancer trials have been mixed. To identify biomarkers associated with CDK4/6 inhibitor response or resistance, we combined bioinformatic-database analyses, artificial intelligence-assisted literature review, and manual literature review (Embase and OVID Medline; search window: January 2012–October 2022) to compile data to comprehensively describe the CDK4/6 inhibitor biomarker landscape. Based on these results, and validation by external experts, we identified 15 biomarkers of clinical importance (<i>AR</i> <b>,</b> <i>AURKA</i>, <i>ERBB2</i>, <i>ESR1</i>, <i>CCNE1</i>, <i>CDKN1A/B</i>, <i>CDK2</i>, <i>CDK6, CDK7</i>, <i>CDK9</i>, <i>FGFR1/2</i>, <i>MYC, PIK3CA/AKT</i>, <i>RB1</i> and <i>STAT3</i>) that could guide future breast cancer research. <b>Finding treatment targets in breast cancer using bioinformatics and artificial intelligence:</b> Hormone receptor-positive (HR+)/human epidermal growth factor receptor 2-negative (HER2-) advanced breast cancer is the most common type of breast cancer. This type of breast cancer responds to hormones like estrogen or progesterone. Inhibitors of cyclin-dependent kinase 4/6 (CDK4/6) reduce the action of hormones. These CDK4/6 inhibitors in combination with other therapies are used to treat HR+/HER2- advanced breast cancer. CDK4/6 inhibitors slow or stop cancer growth in many patients with HR+/HER2- breast cancer. However, in some cases, the drug is not effective or stops working early on in treatment. Finding ways to predict how well and how long these patients will respond to CDK4/6 inhibitors is important for doctors when planning treatment. We used artificial intelligence to search databases and research articles to identify molecules in cancer cells that may predict how well CDK4/6 inhibitors will slow cancer growth. Many molecules were identified that might predict how well CDK4/6 inhibitors will work in people with advanced breast cancer. These types of molecules are called biomarkers. Experts reviewed the findings of the search and based on the evidence, selected 15 biomarkers that may be useful for predicting how well CDK4/6 inhibitors will slow cancer growth. The findings of this study can be used to guide future breast cancer research and help discover new treatments for people with HR+/HER2- advanced breast cancer. CDK4/6 inhibitors in combination with endocrine therapy are the standard-of-care for patients with HR+/HER2 – ABC, but not all patients respond to these drugs, and many become resistant to CDK4/6 inhibitor treatment over time. Identifying biomarkers of response or resistance to CDK4/6 inhibitors may inform the selection of the most appropriate treatment for patients and drive the development of new therapies. This review aimed to identify clinically relevant biomarkers for assessing CDK4/6 inhibitor response or resistance using bioinformatic database analyses, AI-assisted literature review and manual compilation of data to map the current CDK4/6 inhibitor biomarker landscape in HR+/HER2- ABC. Our analyses identified 876 biomarkers with known functions that were potentially related to CDK4/6 inhibitor response in breast cancer; 15 biomarkers were prioritized as potential targets for informing patient treatment decisions and future drug development Most of the identified biomarkers are either currently being investigated in preclinical studies, in clinical trials or are already targeted by US FDA approved drugs By using a range of computational approaches, we were able to explore multiple bioinformatic databases and review a vast amount of literature, providing robust support for the key biomarkers identified. This information may help inform the development of future clinical trials and provide direction for the development of new therapies to treat advanced breast cancer.