Advanced stratification system based on genomic data and artificial intelligence

The ESTRATAGENIA project has developed a platform for processing clinical and genomic data using machine learning. The platform allows the use of its own data as well as data from The Cancer Genome Atlas (TCGA) repository, which are downloaded using the developed platform. The Cancer Genome Atlas is a cancer genomics project, where more than 20,000 primary cancers spanning 33 cancer types have been molecularly characterised and contains more than 2.5 petabytes of genomic, epigenomic, transcriptomic and proteomic data.
Both clinical and genomic data can be visualised and processed using machine learning techniques. Once the machine learning model has been developed, patients can be stratified or classified based on this information. Decision tree algorithms have been implemented that allow us, on the one hand, to extract the characteristics of a dataset and, based on these characteristics, to study the result of a specific patient.