Abstract LB339: SYNERGIA Breast Cancer - Revolutionizing breast cancer care with multi-modal data integration for personalised treatment and future trials

Abstract Data from clinical trials (CTs) drive advancements in clinical practice. Despite most CTs now incorporating extensive translational portfolios, the diverse modalities of clinical and sample data they generate often remain disconnected and underutilised. SYNERGIA is a resource designed to integrate multi-modal data from multiple trials in a comparable format, that will be appropriately accessible to clinicians and researchers. The aims of SYNERGIA are to:1) Develop a comprehensive, multi-modal data repository that integrates longitudinal CT data (>5 years), with genomics (for example, whole-genome sequencing, genome wide association data, circulating tumour DNA, transcriptomics, and spatial- and single-cell- omics), radiomics (for example, mammograms, MRIs, and ultrasounds), and digitalised pathology images from five UK-based breast cancer CTs/studies involving up to 5,000 patients. 2) Facilitate the development and validation of multi-modal machine learning tools, including models predicting response to neo-adjuvant treatment, risk of disease recurrence or death, radiology segmentation tools, and pathology tools for assessing residual cancer burden or cellular biomarkers. 3) Inform future trial designs, support research applications and grants, and establish standard operating procedures for the collection, storage, and management of extensive datasets, samples, and imaging resources. The repository will enable integration across data modalities, ensuring that legacy research data continues to have meaningful impact in future research. SYNERGIA’s tools may support the personalisation of treatment regimens for individual patients, particularly for higher risk sub-types such as human epidermal growth factor receptor 2 positive and triple negative breast cancers. The platform offers the potential to differentiate high risk from low-risk breast cancers and assess in detail which data features contribute to risk. It may enable identification of the most critical data modalities/features at each timepoint in a patient’s cancer journey. The multi-modal approach to cancer biomarker discovery and predictive/prognostic tool development promises to enhance patient stratification to the most appropriate care pathways and advance precision breast cancer medicine. Integrating diverse datasets generated from individual patients may provide new insights into long-standing clinical questions such as identifying early indicators of relapse and distinguishing between lethal and non-lethal breast cancers. By enabling data-driven insights, the SYNERGIA platform aims to support the development of rational data-informed clinical research and trials that improve outcomes while reducing unnecessary toxicities and costs. Citation Format: Amy Riddell, Joanna R. Worley, Fatima Begum-Miah, Steven Bell, Samuel Casford, Alexander J. Fulton, Melis O. Irfan, Justine Kane, Ollie Kane, Charlotte King, Zac Kinsella, Jonathan Lay, Bin Liu, Zoe Matthews, Meena Murthy, Claudia Pallucca, Karen Pinilla, Leah Prowse, Nikola Simidjievski, Aris Sionakidis, Deborah Whitehorn, Katrina Xian, Elena Provenzano, Philip C. Schouten, Mateja Jamnik, Pietro Liò, Silvia Tarantino, Akanksha Anand, Kui Hua, Clare A. Rebbeck, Ramona Woitek, Iris Allajbeu, Gregory J. Hannon, Jean E. Abraham. SYNERGIA Breast Cancer - Revolutionizing breast cancer care with multi-modal data integration for personalised treatment and future trials [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_2):Abstract nr LB339.