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

Abstract

Sequencing-based identification of tumor tissue-of-origin (TOO) is critical for patients with cancer of unknown primary lesions. Even if the TOO of a tumor can be diagnosed by clinicopathological observation, reevaluations by computational methods can help avoid misdiagnosis. In this study, we developed a neural network (NN) framework using the expression of a 150-gene panel to infer the tumor TOO for 15 common solid tumor cancer types, including lung, breast, liver, colorectal, gastroesophageal, ovarian, cervical, endometrial, pancreatic, bladder, head and neck, thyroid, prostate, kidney, and brain cancers. To begin with, we downloaded the RNA-Seq data of 7,460 primary tumor samples across the above mentioned 15 cancer types, with each type of cancer having between 142 and 1,052 samples, from the cancer genome atlas. Then, we performed feature selection by the Pearson correlation method and performed a 150-gene panel analysis; the genes were significantly enriched in the GO:2001242 Regulation of intrinsic apoptotic signaling pathway and the GO:0009755 Hormonemediated signaling pathway and other similar functions. Next, we developed a novel NN model using the 150 genes to predict tumor TOO for the 15 cancer types. The average prediction sensitivity and precision of the framework are 93.36 and 94.07%, respectively, for the 7,460 tumor samples based on the 10-fold cross-validation; however, the prediction sensitivity and precision for a few specific cancers, like prostate cancer, reached 100%. We also tested the trained model on a 20-sample independent dataset with metastatic tumor, and achieved an 80% accuracy. In summary, we present here a highly accurate method to infer tumor TOO, which has potential clinical implementation.

Perioperative mortality of metastatic spinal disease with unknown primary: A case report and review of literature

“…Metastatic tumors from unknown sources are likely to retain the characteristics of their putative primary origins, therefore large differences in clinical manifestations are usually observed among patients with spinal metastases from UPT[ 24 ]. Nonetheless, several common signatures can be retrieved from the reported literature to depict this peculiar group of diseases: (1) Rapid progression and early dissemination, which contribute to the unidentified origin and aggressive presentation[ 24 ]; (2) Diversity of clinical and biological profiles due to the difference in origin[ 25 ]; (3) Relatively poor prognosis as non-selective empirical therapy rather than targeted management is conducted[ 26 ]; and (4) Traditional diagnostic indicators including tumor markers and immunohistochemical activity may be raised without any diagnostic or predictive value, and new methods such as NGS (next generation sequencing) may be suggested to improve diagnosis and prognosis[ 27 ].…”

Evaluating the Risk of Breast Cancer Recurrence and Metastasis After Adjuvant Tamoxifen Therapy by Integrating Polymorphisms in Cytochrome P450 Genes and Clinicopathological Characteristics

“…Over the recent years, with the rapid development of precision medicine, gene detection has become more and more important for cancer diagnosis, prognosis, and drug selection (56)(57)(58)(59)(60)(61)(62). Several studies have shown that the metabolic efficiency of TAM was related to the genetic polymorphisms of certain P450 enzymes, thereby affecting the efficacy of drug therapy.…”

Status quo and future prospects of artificial neural network from the perspective of gastroenterologists

“…Classification accuracy exceeded 75% based on home stool samples[ 120 ], which is expected as a novel method for convenient screening of colorectal polyps. mRNA profiles also have referential value in predicting the odds of malignant transformation[ 121 , 122 ]. The fruits of high-throughput screening techniques combined with deep analysis can depict the landscape of carcinogenesis.…”