Predicting Cancer Tissue-of-Origin by a Machine Learning Method Using DNA Somatic Mutation Data

Abstract

Patients with carcinoma of unknown primary (CUP) account for 3–5% of all cancer cases. A large number of metastatic cancers require further diagnosis to determine their tissue of origin. However, diagnosis of CUP and identification of its primary site are challenging. Previous studies have suggested that molecular profiling of tissue-specific genes could be useful in inferring the primary tissue of a tumor. The purpose of this study was to evaluate the performance somatic mutations detected in a tumor to identify the cancer tissue of origin. We downloaded the somatic mutation datasets from the International Cancer Genome Consortium project. The random forest algorithm was used to extract features, and a classifier was established based on the logistic regression. Specifically, the somatic mutations of 300 genes were extracted, which are significantly enriched in functions, such as cell-to-cell adhesion. In addition, the prediction accuracy on tissue-of-origin inference for 3,374 cancer samples across 13 cancer types reached 81% in a 10-fold cross-validation. Our method could be useful in the identification of cancer tissue of origin, as well as the diagnosis and treatment of cancers.

Genomic pan-cancer classification using image-based deep learning

“…Considering the sequencing covers more than thousands of genes, but most of genes did not contain informative mutations thus making classification difficult by analyzing all those genes [8] , [9] . In order to avoid the mutation data being too sparse (even all zero), most analytical methods screen genes before classification [10] , [11] . These methods are simple and effective in some cases, but important features (genes) may be removed during the screening process.…”

A deep learning model to classify neoplastic state and tissue origin from transcriptomic data

“…While previous models based on transcriptomic data have been attempted for neoplastic classification, these have typically employed a single neural layer and have demonstrated modest performance metrics 25 , 26 . The architecture of our model incorporates five feed forward layers, which affords increased accuracy and a greater number of classifiers.…”

New techniques to identify the tissue of origin for cancer of unknown primary in the era of precision medicine: progress and challenges

“…Using genomic profiling data as an example, bioinformatics and ML algorithms are applied to score and rank the most relevant genes for creating tumor–gene associations and constructing TOO classifiers. Several ML algorithms to identify the TOO of CUP have been applied in this context [ 28 , 29 , 33 , 42 , 44 , 45 , 52–54 , 57 , 58 , 64 , 73 , 96 ] ( Supplementary Figure 3 and Table 2 ). These associations are subsequently assessed through independent validation sets, and the classifier’s efficacy is further verified with challenging clinical cases.…”