POETIC-AI: Revolutionizing Cancer Biomarker Discovery with Integrated AI-Powered Analysis

POETIC-AI: Revolutionizing Cancer Biomarker Discovery with Integrated AI-Powered Analysis

(IN BRIEF) A groundbreaking AI-powered research platform, POETIC-AI, has been unveiled by scientists from The Institute of Cancer Research, promising to accelerate cancer biomarker discovery. Demonstrated at The Alan Turing Institute’s fifth AI UK conference, the platform integrates diverse clinical data—from patient records and genetic profiles to digital pathology and imaging—using technology from Palantir’s Foundry. Supported by funding from ICR and its partners, POETIC-AI leverages data from the POETIC trial, which focused on optimizing hormone therapy for early-stage breast cancer patients, to enable rapid hypothesis testing and collaborative research in a secure environment. Dr. Maggie Cheang emphasizes that the platform’s advanced, natural language-based AI analysis will significantly shorten research timelines, facilitate the discovery of new predictive biomarkers, and ultimately enhance personalized cancer treatments. Plans are underway to further expand the platform by incorporating additional trial data and developing interactive visualization tools, marking a major step forward in the field of integrated cancer research.

(PRESS RELEASE) LONDON, 3-Apr-2025 — /EuropaWire/ — Scientists have introduced an innovative research platform powered by artificial intelligence (AI) that promises to transform cancer research by enabling the integration and analysis of vast, complex clinical trial datasets—thereby accelerating the discovery of new cancer biomarkers. A team from The Institute of Cancer Research (ICR) demonstrated this breakthrough at The Alan Turing Institute’s fifth AI UK conference. The platform, named POETIC-AI, harnesses technology from Palantir’s AI platform Foundry and incorporates custom AI tools developed by the ICR team to seamlessly integrate and analyze diverse data sources including patient records, treatment histories, blood and tumor tissue samples, genetic profiles, digital pathology, and medical imaging such as CT and MRI scans.

The development of POETIC-AI was partly funded by ICR and the joint ICR/The Royal Marsden NHS Foundation Trust Integrated Discovery and Diagnostics programme, with the original POETIC trial being supported by Cancer Research UK. This platform is set to empower cancer researchers worldwide by providing a secure, collaborative research environment that enables rapid hypothesis testing and data analysis—tasks that once took years can now be accomplished in mere months or even days. By accelerating these processes, the technology aims to uncover novel predictive biomarkers that can help clinicians tailor cancer treatments more precisely.

The initial AI models on the platform utilize data from the POETIC trial, which investigated the benefits of pre-surgical hormone therapy in postmenopausal women with early-stage, hormone receptor-positive breast cancer. In this trial, changes in the biomarker Ki67, which indicates the rate of cancer cell growth, were used to identify patients likely to benefit from additional treatments after surgery. ICR data scientists repurposed this patient data to build the POETIC-AI platform, enabling secure access for researchers to generate and test hypotheses in both laboratory and clinical settings—paving the way for transformative advances in emerging cancer therapeutics.

Dr. Maggie Cheang, who leads the ICR-CTSU Integrative Genomic Analysis in Clinical Trials Group, explained, “We need prognostic and predictive biomarkers that match the complexity of cancer biology. This platform allows us to move beyond traditional methods that rely solely on blood or tissue samples by combining multiple data sources. It offers personalized insights that can improve diagnosis and treatment, ultimately accelerating biomarker discovery and reducing the time needed for clinical trial analyses.” She added that the platform’s user-friendly AI-powered analysis, which enables queries through natural language, is revolutionary and will fundamentally change how integrated discovery and diagnostics are conducted.

Looking ahead, the ICR-CTSU team plans to expand POETIC-AI by incorporating data from additional clinical trials and refining machine-learning models for real-time analysis. Future research will also focus on developing novel visualization and analytical tools to integrate rich biological data with other patient-derived datasets, creating an interactive AI explorer. This work is being led by Dr. Cheang’s PhD student, Xixuan Zhu, alongside Dr. Ferran Cardo from the Joint ICR/RMH Integrated Pathology Unit under Professor Manuel Salto-Tellez.

Dr. Cheang concluded, “Our platform will significantly enhance academic research by providing investigators with secure access to high-quality, biologically rich clinical trial data, establishing an unprecedented approach in the field.”

Media Contact:

Tel: 0203 437 3502
email: mediaoffice@icr.ac.uk

SOURCE: The Institute of Cancer Research