2020
DOI: 10.3389/fbioe.2020.00394
|View full text |Cite
|
Sign up to set email alerts
|

TOOme: A Novel Computational Framework to Infer Cancer Tissue-of-Origin by Integrating Both Gene Mutation and Expression

Abstract: Metastatic cancers require further diagnosis to determine their primary tumor sites. However, the tissue-of-origin for around 5% tumors could not be identified by routine medical diagnosis according to a statistics in the United States. With the development of machine learning techniques and the accumulation of big cancer data from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO), it is now feasible to predict cancer tissue-of-origin by computational tools. Metastatic tumor inherits characteris… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
61
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
9

Relationship

3
6

Authors

Journals

citations
Cited by 84 publications
(61 citation statements)
references
References 54 publications
0
61
0
Order By: Relevance
“…Unfortunately, despite extensive research on the molecular mechanism of liver carcinogenesis, there are still only a few effective treatment options. Very little is known about the pathogenesis of most types of cancers, including liver cancer [ 6 – 8 ]. In the past few decades, about 130-180 anticancer drugs have been approved by the US FDA for use in clinical treatment [ 9 ].…”
Section: Introductionmentioning
confidence: 99%
“…Unfortunately, despite extensive research on the molecular mechanism of liver carcinogenesis, there are still only a few effective treatment options. Very little is known about the pathogenesis of most types of cancers, including liver cancer [ 6 – 8 ]. In the past few decades, about 130-180 anticancer drugs have been approved by the US FDA for use in clinical treatment [ 9 ].…”
Section: Introductionmentioning
confidence: 99%
“…Obviously, from a biological point of view, it is not surprising that there are relationships between primary cells, or/and tissues, or/and cell lines, because tissues are composed of different types of primary cells, and cell lines are immortalized or cancer-transformed cells that resemble their tissue of origin [ 32 ]. In other words, one can expect that many pairs of primary cells, tissues, and cell lines can be similar in terms of their transcriptional activity.…”
Section: Resultsmentioning
confidence: 99%
“…In some reports, the tumor-specific enrichment for mutations in certain genes (sometimes mutations at specific locations within genes) had also been observed and used to infer tumor location ( Dietlein and Eschner, 2014 ; Lawrence et al, 2014 ). Based on this observation, mutation burden in genes were used to infer tumor TOO; however, the performances are usually not very well ( He et al, 2020 ; Liu et al, 2020 ). In addition, Küsters-Vandevelde et al found that particular CNVs may be associated with cancer metastasis ( Küsters-Vandevelde et al, 2017 ; Zhu et al, 2019 ).…”
Section: Introductionmentioning
confidence: 99%
“… Marquard et al (2015) applied both point mutations and copy number aberrations (PM + CN) classifiers to obtain a classification accuracy of 85% across six primary cancers. He et al (2020) combined molecular data of somatic mutation and gene expression profiling to infer cancer TOO and achieved a 10-fold cross-validation prediction accuracy of around 96% using the random forest classification method across 20 solid tumors.…”
Section: Introductionmentioning
confidence: 99%