A Computational Framework for Systems Pathology of Prostate Cancer
Prostate cancer is the second most frequent cancer type in men, but it is not always possible to make an accurate prognosis of the patient’s survival. This is mainly due to the lack of biomarkers that could be prognostic of a more aggressive phenotype. In this project we aim to search for prostate cancer-specific genomic alterations and study how they could improve the stratification of prostate cancer into two classes: significant and insignificant disease.
For this purpose, we are developing a novel computational framework based on pattern detection via dictionary learning and sparse coding that has been successfully applied in signal processing. The method is able to detect patterns of genomic alterations coming from a relatively small number of samples, representing rare or infrequent variants, but also epistatic interactions.
We intend to use this method in the TCGA Prostate Adenocarcinoma datasets and then validate it using an independent cohort, the Zurich Prostate Cancer Outcome Cohort study. Additionally, it is possible to integrate different types of genomic alterations, such as single nucleotide variations, copy number alterations and mRNA expression, and infer patterns across different -omics datasets.
The project aims to contribute to systems biology not only on the methodology and algorithmic level but also on the clinical level, supporting precise, predictive and personalized medicine (3P-medicine).
Keywords: Prostate cancer, dictionary learning, sparse coding, integrative multi-omics, personalized medicineback