Identification of Tumor Tissue of Origin with RNA-Seq Data and Using Gradient Boosting Strategy

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

Despite a standardized diagnostic examination, cancer of unknown primary (CUP) is a rare metastatic malignancy with an unidentified tissue of origin (TOO). Patients diagnosed with CUP are typically treated with empiric chemotherapy, although their prognosis is worse than those with metastatic cancer of a known origin. TOO identification of CUP has been employed in precision medicine, and subsequent site-specific therapy is clinically helpful. For example, molecular profiling, including genomic profiling, gene expression profiling, epigenetics and proteins, has facilitated TOO identification. Moreover, machine learning has improved identification accuracy, and non-invasive methods, such as liquid biopsy and image omics, are gaining momentum. However, the heterogeneity in prediction accuracy, sample requirements and technical fundamentals among the various techniques is noteworthy. Accordingly, we systematically reviewed the development and limitations of novel TOO identification methods, compared their pros and cons and assessed their potential clinical usefulness. Our study may help patients shift from empirical to customized care and improve their prognoses.

A cross-cohort computational framework to trace tumor tissue-of-origin based on RNA sequencing

Carcinoma of unknown primary (CUP) is a type of metastatic cancer with tissue-of-origin (TOO) unidentifiable by traditional methods. CUP patients typically have poor prognosis but therapy targeting the original cancer tissue can significantly improve patients' prognosis. Thus, it's critical to develop accurate computational methods to infer cancer TOO. While qPCR or microarray-based methods are effective in inferring TOO for most cancer types, the overall prediction accuracy is yet to be improved. In this study, we propose a cross-cohort computational framework to trace TOO of 32 cancer types based on RNA sequencing (RNA-seq). Specifically, we employed logistic regression models to select 80 genes for each cancer type to create a combined 1356-gene set, based on transcriptomic data from 9911 tissue samples covering the 32 cancer types with known TOO from the Cancer Genome Atlas (TCGA). The selected genes are enriched in both tissue-specific and tissue-general functions. The cross-validation accuracy of our framework reaches 97.50% across all cancer types. Furthermore, we tested the performance of our model on the TCGA metastatic dataset and International Cancer Genome Consortium (ICGC) dataset, achieving an accuracy of 91.09% and 82.67%, respectively, despite the differences in experiment procedures and pipelines. In conclusion, we developed an accurate yet robust computational framework for identifying TOO, which holds promise for clinical applications. Our code is available at http://github.com/wangbo00129/classifybysklearn .

Pragmatic Expectancy on Microbiota and Non-Small Cell Lung Cancer: A Narrative Review

It is well known that lung cancer relies on a number of genes aberrantly expressed because of somatic lesions. Indeed, the lungs, based on their anatomical features, are organs at a high risk of development of extremely heterogeneous tumors due to the exposure to several environmental toxic agents. In this context, the microbiome identifies the whole assemblage of microorganisms present in the lungs, as well as in distant organs, together with their structural elements and metabolites, which actively interact with normal and transformed cells. A relevant amount of data suggest that the microbiota plays a role not only in cancer disease predisposition and risk but also in its initiation and progression, with an impact on patients’ prognosis. Here, we discuss the mechanistic insights of the complex interaction between lung cancer and microbiota as a relevant component of the microenvironment, mainly focusing on novel diagnostic and therapeutic objectives.

A Machine Learning Method to Trace Cancer Primary Lesion Using Microarray-Based Gene Expression Data

Cancer of unknown primary site (CUP) is a heterogeneous group of cancers whose tissue of origin remains unknown after detailed investigation by conventional clinical methods. The number of CUP accounts for roughly 3%–5% of all human malignancies. CUP patients are usually treated with broad-spectrum chemotherapy, which often leads to a poor prognosis. Recent studies suggest that the treatment targeting the primary lesion of CUP will significantly improve the prognosis of the patient. Therefore, it is urgent to develop an efficient method to accurately detect tissue of origin of CUP in clinical cancer research. In this work, we developed a novel framework that uses Extreme Gradient Boosting (XGBoost) to trace the primary site of CUP based on microarray-based gene expression data. First, we downloaded the microarray-based gene expression profiles of 59,385 genes for 57,08 samples from The Cancer Genome Atlas (TCGA) and 6,364 genes for 3,101 samples from the Gene Expression Omnibus (GEO). Both data were divided into training and independent testing data with a ratio of 4:1. Then, we obtained in the training data 200 and 290 genes from TCGA and the GEO datasets, respectively, to train XGBoost models for the identification of the primary site of CUP. The overall 5-fold cross-validation accuracies of our methods were 96.9% and 95.3% on TCGA and GEO training datasets, respectively. Meanwhile, the macro-precision for the independent dataset reached 96.75% and 98.8% on, respectively, TCGA and GEO. Experimental results demonstrated that the XGBoost framework not only can reduce the cost of clinical cancer traceability but also has high efficiency, which might be useful in clinical usage.

90-Gene Expression Profiling for Tissue Origin Diagnosis of Cancer of Unknown Primary

Cancer of unknown primary (CUP), in which metastatic diseases exist without an identifiable primary location, accounts for about 3-5% of all cancer diagnoses. Successful diagnosis and treatment of such patients are difficult. This study aimed to assess the expression characteristics of 90 genes as a method of identifying the primary site from CUP samples. We validated a 90-gene expression assay and explored its potential diagnostic utility in 44 patients at Jiangsu Cancer Hospital. For each specimen, the expression of 90 tumor-specific genes in malignant tumors was analyzed, and similarity scores were obtained. The types of malignant tumors predicted were compared with the reference diagnosis to calculate the accuracy. In addition, we verified the consistency of the expression profiles of the 90 genes in CUP secondary malignancies and metastatic malignancies in The Cancer Genome Atlas. We also reported a detailed description of the next-generation coding sequences for CUP patients. For each clinical medical specimen collected, the type of malignant tumor predicted and analyzed by the 90-gene expression assay was compared with its reference diagnosis, and the overall accuracy was 95.4%. In addition, the 90-gene expression profile generally accurately classified CUP into the cluster of its primary tumor. Sequencing of the exome transcriptome containing 556 high-frequency gene mutation oncogenes was not significantly related to the 90 genes analysis. Our results demonstrate that the expression characteristics of these 90 genes can be used as a powerful tool to accurately identify the primary sites of CUP. In the future, the inclusion of the 90-gene expression assay in pathological diagnosis will help oncologists use precise treatments, thereby improving the care and outcomes of CUP patients.