A multimodal framework integrating genetics, proteomics, and clinical data was deployed on 502,505 UK Biobank participants with >46,000 incident cancers across 22 types for biomarker discovery.
Observational (n=502,505)
Yes
Does a multimodal biomarker discovery engine improve cancer risk prediction compared to individual modalities in a large population cohort?
A scalable multimodal machine-learning framework integrating genetics, proteomics, and clinical data has been developed for unbiased cancer risk biomarker discovery.
Abstract Background: Most existing cancer risk models are built on single modalities and hand-selected features. Systematic, unbiased integration of germline genetics, plasma proteomics, and deep clinical phenotyping holds promise for revealing novel risk biomarkers across diverse cancer types. Methods: We developed a multi-modal biomarker discovery engine that can be used for discovering risk, diagnostic, prognostic, predictive and monitoring biomarkers. Currently the framework handles: • Germline genetics and polygenic risk scores • High-dimensional plasma proteomics (Olink) • Longitudinal primary-care records, hospital episodes, laboratory results, lifestyle questionnaires, and cancer registry linkages Key design features include modular cohort handling, automated data preprocessing, and machine-learning models (including: gradient boosting and neural networks). Application: The platform is currently deployed on the UK Biobank (n = 502,505 participants; 46,000 incident cancers across 22 cancer types) with active model training and biomarker discovery in progress. The architecture is cohort-agnostic and ready for direct application to emerging large-scale resources including Our Future Health and the All of Us Research Program. Poster presentation: We will demonstrate the platform’s configurability through examples of cancer-risk modelling in the UK Biobank, showcasing: (i) comparative performance of individual modalities versus multimodal ensembles, (ii) cancer-specific patterns of modality contribution, and (iii) the effect of time-window filtering on separating true predictive signals from prevalent disease effects. Conclusions: By eliminating bias in feature engineering and supporting seamless integration of diverse health data streams, this scalable framework provides a robust foundation for data-driven discovery of multimodal cancer risk biomarkers, paving the way for next-generation precision prevention strategies. Citation Format: Constantin Petrescu, Lisa Schmunk, Jack Monahan, Abbas Salami, Thomas M. Stubbs. A scalable multimodal framework for unbiased risk biomarker discovery across multiple cancer types abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 1116.
Petrescu et al. (2026) conducted an observational in Cancer (n=502,505). Multimodal biomarker discovery framework vs. Individual modalities was evaluated on Comparative performance of individual modalities versus multimodal ensembles. A multimodal framework integrating genetics, proteomics, and clinical data was deployed on 502,505 UK Biobank participants with >46,000 incident cancers across 22 types for biomarker discovery.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: