An official website of the United States government
A machine learning or deep learning model that can predict with high accuracy the primary tumor type from RNA-seq data can help identify any misclassified primary tumor types, provide the precise primary tumor type of more generalized or missing primary tumor types, and differentiate any samples that do not express similar expression profiles to the assigned primary tumor type for further analyses.
With cancer as one of the leading causes of death worldwide, accurate primary tumor type prediction is critical in identifying genetic factors that can inhibit or slow tumor progression. There have been efforts to categorize primary tumor types with gene expression data using machine learning, and more recently with deep learning, in the last several years.
This use case will output predictions of tumor types from TULIP with RNA-seq data as the input data.