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. There have been efforts to categorize primary tumor types with gene expression data using machine lea...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2022-12-01
|
| Series: | Cancer Informatics |
| Online Access: | https://doi.org/10.1177/11769351221139491 |
| _version_ | 1811185857338540032 |
|---|---|
| author | Sara Jones Matthew Beyers Maulik Shukla Fangfang Xia Thomas Brettin Rick Stevens M Ryan Weil Satishkumar Ranganathan Ganakammal |
| author_facet | Sara Jones Matthew Beyers Maulik Shukla Fangfang Xia Thomas Brettin Rick Stevens M Ryan Weil Satishkumar Ranganathan Ganakammal |
| author_sort | Sara Jones |
| collection | DOAJ |
| description | 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. 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. Methods In this paper, we developed four 1-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, we adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). Unlike previous work, we 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 from the Genomic Data Commons (GDC) corresponding to 17 and 32 primary tumor types respectively for training and validating the models. Results: All 4 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: We packaged all 4 models as a Python-based deep learning classification tool called TULIP ( TU mor C L ass I fication P redictor) for performing quality control on primary tumor samples and characterizing cancer samples of unknown tumor type. Further optimization of the models is needed to improve the accuracy of certain primary tumor types. |
| first_indexed | 2024-04-11T13:36:20Z |
| format | Article |
| id | doaj.art-4936251ad7744b8bb020f50e7aa44780 |
| institution | Directory Open Access Journal |
| issn | 1176-9351 |
| language | English |
| last_indexed | 2024-04-11T13:36:20Z |
| publishDate | 2022-12-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Cancer Informatics |
| spelling | doaj.art-4936251ad7744b8bb020f50e7aa447802022-12-22T04:21:27ZengSAGE PublishingCancer Informatics1176-93512022-12-012110.1177/11769351221139491TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural NetworksSara Jones0Matthew Beyers1Maulik Shukla2Fangfang Xia3Thomas Brettin4Rick Stevens5M Ryan Weil6Satishkumar Ranganathan Ganakammal7Frederick National Laboratory for Cancer Research, Cancer Data Science Initiatives, Cancer Research Technology Program, Rockville, MD, USAFrederick National Laboratory for Cancer Research, Cancer Data Science Initiatives, Cancer Research Technology Program, Rockville, MD, USAArgonne National Laboratory, Computing, Environment and Life Sciences, Lemont, IL, USAArgonne National Laboratory, Computing, Environment and Life Sciences, Lemont, IL, USAArgonne National Laboratory, Computing, Environment and Life Sciences, Lemont, IL, USAArgonne National Laboratory, Computing, Environment and Life Sciences, Lemont, IL, USAFrederick National Laboratory for Cancer Research, Cancer Data Science Initiatives, Cancer Research Technology Program, Rockville, MD, USAFrederick National Laboratory for Cancer Research, Cancer Data Science Initiatives, Cancer Research Technology Program, Rockville, MD, USABackground: 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. Methods In this paper, we developed four 1-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, we adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). Unlike previous work, we 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 from the Genomic Data Commons (GDC) corresponding to 17 and 32 primary tumor types respectively for training and validating the models. Results: All 4 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: We packaged all 4 models as a Python-based deep learning classification tool called TULIP ( TU mor C L ass I fication P redictor) for performing quality control on primary tumor samples and characterizing cancer samples of unknown tumor type. Further optimization of the models is needed to improve the accuracy of certain primary tumor types.https://doi.org/10.1177/11769351221139491 |
| spellingShingle | Sara Jones Matthew Beyers Maulik Shukla Fangfang Xia Thomas Brettin Rick Stevens M Ryan Weil Satishkumar Ranganathan Ganakammal TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks Cancer Informatics |
| title | TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks |
| title_full | TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks |
| title_fullStr | TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks |
| title_full_unstemmed | TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks |
| title_short | TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks |
| title_sort | tulip an rna seq based primary tumor type prediction tool using convolutional neural networks |
| url | https://doi.org/10.1177/11769351221139491 |
| work_keys_str_mv | AT sarajones tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT matthewbeyers tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT maulikshukla tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT fangfangxia tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT thomasbrettin tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT rickstevens tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT mryanweil tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks AT satishkumarranganathanganakammal tulipanrnaseqbasedprimarytumortypepredictiontoolusingconvolutionalneuralnetworks |