AUTHOR=Liang Ying , Wang Haifeng , Yang Jialiang , Li Xiong , Dai Chan , Shao Peng , Tian Geng , Wang Bo , Wang Yinglong 

TITLE=A Deep Learning Framework to Predict Tumor Tissue-of-Origin Based on Copy Number Alteration

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 8 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2020.00701

DOI=10.3389/fbioe.2020.00701

ISSN=2296-4185

ABSTRACT=Cancer of unknown primary site (CUPS) is a type of metastatic tumor. However, the sites of tumor origin cannot be determined. Precise diagnosis of the tissue origin for metastatic CUPS is crucial for the treatment scheme to improve patients’ prognoses. Recently, there are many studies using various cancer biomarkers to predict the tissue-of-origin (TOO) of CUPS. However, only very few of them use copy number alteration (CNA) to trance TOO. In this paper, a two-step computational framework called CNA_origin was introduced to predict the tissue- of-origin of a tumor from its gene CNA levels. CNA_origin set up an intellectual deep-learning network mainly composed of autoencoder and convolution neural network (CNN). Based on real datasets released from the public database, CNA_origin had an overall accuracy of 83.81% on 10-fold cross-validation and 79% on independent datasets for predicting tumor origin, which improved the accuracy by 7.75% and 9.72% compared with the method published in previous paper. Our results suggested that the autoencoder model can extract key characteristics of CNA, and the CNN classifier model developed in this study can predict the origin of tumors with robustness and effectiveness. CNA_origin was written in python, which can be downloaded from https://github.com/YingLianghnu/CNA_origin.