Predicting cancer origins with a DNA methylation-based deep neural network model

• Published in: PloS one Vol. 15; no. 5; p. e0226461
• Main Authors: Zheng, Chunlei, Xu, Rong
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 08-05-2020; Public Library of Science (PLoS)
• Subjects: Accuracy; Artificial intelligence; Artificial neural networks; Biochemistry; Biology and life sciences; Biomarkers, Tumor - genetics; Cancer; Cancer diagnosis; Cancer genetics; Cancer metastasis; Cancer patients; Cancer treatment; Classifiers; Computer aided medical diagnosis; Computer and Information Sciences; Databases, Genetic; Datasets; Datasets as Topic; Deep Learning; Deoxyribonucleic acid; DNA; DNA Methylation; Gene expression; Genes; Genetic aspects; Genomes; Genomics; Head & neck cancer; Humans; Medicine and Health Sciences; Metastases; Metastasis; Methods; Methylation; MicroRNAs; Neoplasms - diagnosis; Neoplasms - genetics; Neural networks; Origins; Pathology; Patients; Physical Sciences; Prostate cancer; Proteins; Sensitivity; Setting (Literature); Support vector machines; Tumor cells; Tumors; Variance analysis; United States; United States > US; Ohio
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0226461

Cancer origin determination combined with site-specific treatment of metastatic cancer patients is critical to improve patient outcomes. Existing pathology and gene expression-based techniques often have limited performance. In this study, we developed a deep neural network (DNN)-based classifier for cancer origin prediction using DNA methylation data of 7,339 patients of 18 different cancer origins from The Cancer Genome Atlas (TCGA). This DNN model was evaluated using four strategies: (1) when evaluated by 10-fold cross-validation, it achieved an overall specificity of 99.72% (95% CI 99.69%-99.75%) and sensitivity of 92.59% (95% CI 91.87%-93.30%); (2) when tested on hold-out testing data of 1,468 patients, the model had an overall specificity of 99.83% and sensitivity of 95.95%; (3) when tested on 143 metastasized cancer patients (12 cancer origins), the model achieved an overall specificity of 99.47% and sensitivity of 95.95%; and (4) when tested on an independent dataset of 581 samples (10 cancer origins), the model achieved overall specificity of 99.91% and sensitivity of 93.43%. Compared to existing pathology and gene expression-based techniques, the DNA methylation-based DNN classifier showed higher performance and had the unique advantage of easy implementation in clinical settings. In summary, our study shows that DNA methylation-based DNN models has potential in both diagnosis of cancer of unknown primary and identification of cancer cell types of circulating tumor cells.