TULIP: An RNA-Seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks

Background

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. The community has tried to categorize primary tumor types with gene expression data using machine learning, and more recently with deep learning, in the last several years.

Methods

In this paper, the authors developed four one-dimensional (1D) Convolutional Neural Network (CNN) models to classify RNA-Seq count data as one of 17 highly represented primary tumor types or 32 primary tumor types regardless of imbalanced representation. Additionally, the authors adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). Unlike previous work, the authors avoided selection bias by not filtering genes based on expression values. RNA-Seq count data expressed as FPKM-UQ of 9,025 and 10,940 samples from The Cancer Genome Atlas (TCGA) were downloaded by the authors from the Genomic Data Commons (GDC) corresponding to 17 and 32 primary tumor types respectively for training and validating the models.

Results

All four 1D-CNN models had an overall accuracy of 94.7% to 97.6% on the test dataset. Further evaluation indicates that the models with protein coding genes only as features performed with better accuracy compared to the models with all Ensembl genes for both 17 and 32 primary tumor types. For all models, the accuracy by primary tumor type was above 80% for most primary tumor types.

Conclusions

The authors packaged all four models as a Python-based deep learning classification tool called TULIP (TUmor cLassIfication Predictor) for performing quality control on primary tumor samples and characterizing cancer samples of unknown tumor type. The community needs further optimization of the models to improve the accuracy of certain primary tumor types.