TOD-CUP: a gene expression rank-based majority vote algorithm for tissue origin diagnosis of cancers of unknown primary

Abstract

Gene expression profiling holds great potential as a new approach to histological diagnosis and precision medicine of cancers of unknown primary (CUP). Batch effects and different data types greatly decrease the predictive performance of biomarker-based algorithms, and few methods have been widely applied to identify tissue origin of CUP up to now. To address this problem and assist in more precise diagnosis, we have developed a gene expression rank-based majority vote algorithm for tissue origin diagnosis of CUP (TOD-CUP) of most common cancer types. Based on massive tissue-specific RNA-seq data sets (10 553) found in The Cancer Genome Atlas (TCGA), 538 feature genes (biomarkers) were selected based on their gene expression ranks and used to predict tissue types. The top scoring pairs (TSPs) classifier of the tumor type was optimized by the TCGA training samples. To test the prediction accuracy of our TOD-CUP algorithm, we analyzed (1) two microarray data sets (1029 Agilent and 2277 Affymetrix/Illumina chips) and found 91% and 94% prediction accuracy, respectively, (2) RNA-seq data from five cancer types derived from 141 public metastatic cancer tumor samples and achieved 94% accuracy and (3) a total of 25 clinical cancer samples (including 14 metastatic cancer samples) were able to classify 24/25 samples correctly (96.0% accuracy). Taken together, the TOD-CUP algorithm provides a powerful and robust means to accurately identify the tissue origin of 24 cancer types across different data platforms. To make the TOD-CUP algorithm easily accessible for clinical application, we established a Web-based server for tumor tissue origin diagnosis (http://ibi. zju.edu.cn/todcup/).

Site-specific therapy in cancers of unknown primary site: a systematic review and meta-analysis

“…Moreover, in recent years, several molecular and pathological profiling methods have been established, including messenger RNA analysis, 23 , 40 microRNA analysis, 41 , 42 , 43 DNA mutation analysis, 24 copy number variation analysis, 44 liquid biopsies, 45 , 46 and artificial intelligence-based pathology 47 ; the prediction accuracy of these assays reportedly range from 73% to 94%. In studies by Hainsworth et al.…”

“… 18 , 19 , 20 Based on GEP analysis, we also developed several new bioinformatics methods for identifying putative primary tumors. 21 , 22 , 23 In addition, multiple methods based on various omics, including genomics 24 , 25 and epigenomics, 26 have also been harnessed to predict the TOO of CUP.…”

A Neural Network Framework for Predicting the Tissue-of-Origin of 15 Common Cancer Types Based on RNA-Seq Data

“…Another limitation is that our method is based on the expression value without any manipulations. Recently, an algorithm called TSP was applied to this problem, which will generate gene pairs instead of single gene features, giving rise to a leap to the prediction accuracy ( Shen et al, 2020 ). We believe that combining the neural network and the feature generation could further improve the performance for CUP problems.…”

Developmental Deconvolution for Classification of Cancer Origin

“…SML approaches have been previously applied to gene expression data but have been limited by difficulties with model overfitting and representation, due to the high dimensionality of the transcriptome (~22,000 protein coding genes) (33,34). To avoid these issues, some studies have selected small gene subsets (35)(36)(37), but this restricts model input to selected datapoints and compromises accuracy and predictive power. We reasoned a classifier based on developmental deconvolution scores would extract most relevant data from gene expression (Fig.…”