Cancer of unknown primary site (CUPS) is a type of metastatic tumor for which the sites of tumor origin cannot be determined. Precise diagnosis of the tissue origin for metastatic CUPS is crucial for developing treatment schemes to improve patient prognosis. Recently, there have been many studies using various cancer biomarkers to predict the tissue-of-origin (TOO) of CUPS. However, only a very few of them use copy number alteration (CNA) to trance TOO. In this paper, a two-step computational framework called CNA_origin is 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 an autoencoder and a 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 a previous paper. Our results suggested that the autoencoder model can extract key characteristics of CNA and that the CNN classifier model developed in this study can predict the origin of tumors robustly and effectively. CNA_origin was written in Python and can be downloaded from https://github.com/YingLianghnu/CNA_origin.

中文翻译：

---

基于拷贝数变化预测肿瘤组织来源的深度学习框架

未知原发部位癌症 (CUPS) 是一种无法确定肿瘤起源部位的转移性肿瘤。准确诊断转移性 CUPS 的组织来源对于制定治疗方案以改善患者预后至关重要。最近，有许多研究使用各种癌症生物标志物来预测 CUPS 的起源组织 (TOO)。然而，只有极少数人使用拷贝数改变（CNA）来恍惚。在本文中，引入了一个称为 CNA_origin 的两步计算框架，以从其基因 CNA 水平预测肿瘤的组织起源。CNA_origin 建立了一个智能深度学习网络，主要由一个自动编码器和一个卷积神经网络（CNN）组成。基于从公共数据库发布的真实数据集，CNA_origin 的整体准确率为 83。预测肿瘤起源的 10 折交叉验证为 81%，独立数据集为 79%，与之前论文中发表的方法相比，准确率提高了 7.75% 和 9.72%。我们的结果表明，自动编码器模型可以提取 CNA 的关键特征，并且本研究中开发的 CNN 分类器模型可以稳健有效地预测肿瘤的起源。CNA_origin 是用 Python 编写的，可以从 https://github.com/YingLianghnu/CNA_origin 下载。我们的结果表明，自动编码器模型可以提取 CNA 的关键特征，并且本研究中开发的 CNN 分类器模型可以稳健有效地预测肿瘤的起源。CNA_origin 是用 Python 编写的，可以从 https://github.com/YingLianghnu/CNA_origin 下载。我们的结果表明，自动编码器模型可以提取 CNA 的关键特征，并且本研究中开发的 CNN 分类器模型可以稳健有效地预测肿瘤的起源。CNA_origin 是用 Python 编写的，可以从 https://github.com/YingLianghnu/CNA_origin 下载。