Heterogeneity of colorectal cancer, precision oncology, computational methods for cancer biology, open science and DREAM challenges, biological aging,
My scientific career has been focused on the design and application of computational methods for translational cancer medicine. My background includes training in statistics and machine learning, skills that I have adapted to study key questions in cancer genomics. During my graduate training, I focused on pattern recognition and network modeling from high-throughput genomic data to identify the key mechanisms of tumorigenesis and cancer progression. My lab today specializes in integrative data analysis for prognostic and predictive modeling of cancer outcomes and response to therapy, with an emphasis in colorectal cancer. As co-director of the DREAM Challenges, I have organized multiple data challenges in cancer that have resulted in state-of-the-art predictive models in domains spanning diagnostic mammography screening, drug combination therapy, and prognostic modeling in breast and prostate cancer and multiple myeloma.
- Guinney J and Saez-Rodriguez J (2018) Alternative models for sharing sensitive biomedical data, Nature Biotechnology.
- Guinney J, Wang T, Laajala T, et al, (2017) A prognostic model to predict overall survival for patients with metastatic castration-resistant prostate cancer: results from a crowdsourced challenge using retrospective, open clinical trial data, Lancet Oncology.
- Guinney J, Dienstmann R, et al, (2015) The Consensus Molecular Subtypes of Colorectal Cancer, Nature Medicine.
- Dienstmann R, Jang IS, Bot B, Friend S, and Guinney J (2015) Database of genomic biomarkers for cancer drugs and clinical targetability in solid tumors, Cancer Discovery.