Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases. / Vincent, Martin; Perell, Katharina; Nielsen, Finn Cilius; Daugaard, Gedske; Hansen, Niels Richard.

In: Bioinformatics, Vol. 30, No. 10, 2014, p. 1417-1423.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Vincent, M, Perell, K, Nielsen, FC, Daugaard, G & Hansen, NR 2014, 'Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases', Bioinformatics, vol. 30, no. 10, pp. 1417-1423. https://doi.org/10.1093/bioinformatics/btu044

APA

Vincent, M., Perell, K., Nielsen, F. C., Daugaard, G., & Hansen, N. R. (2014). Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases. Bioinformatics, 30(10), 1417-1423. https://doi.org/10.1093/bioinformatics/btu044

Vancouver

Vincent M, Perell K, Nielsen FC, Daugaard G, Hansen NR. Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases. Bioinformatics. 2014;30(10):1417-1423. https://doi.org/10.1093/bioinformatics/btu044

Author

Vincent, Martin ; Perell, Katharina ; Nielsen, Finn Cilius ; Daugaard, Gedske ; Hansen, Niels Richard. / Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases. In: Bioinformatics. 2014 ; Vol. 30, No. 10. pp. 1417-1423.

Bibtex

@article{a0e0e79ea34948c8b95e9dc5a00e8bd2,
title = "Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases",
abstract = "Contamination of a cancer tissue by the surrounding benign (non-cancerous) tissue is a concern for molecular cancer diagnostics. This is because an observed molecular signature will be distorted by the surrounding benign tissue, possibly leading to an incorrect diagnosis. One example is molecular identification of the primary tumor site of metastases because biopsies of metastases typically contain a significant amount of benign tissue.Results: A model of tissue contamination is presented. This contamination model works independently of the training of a molecular predictor, and it can be combined with any predictor model. The usability of the model is illustrated on primary tumor site identification of liver biopsies, specifically, on a human dataset consisting of microRNA expression measurements of primary tumor samples, benign liver samples and liver metastases. For a predictor trained on primary tumor and benign liver samples, the contamination model decreased the test error on biopsies from liver metastases from 77 to 45%. A further reduction to 34% was obtained by including biopsies in the training data. ",
author = "Martin Vincent and Katharina Perell and Nielsen, {Finn Cilius} and Gedske Daugaard and Hansen, {Niels Richard}",
year = "2014",
doi = "10.1093/bioinformatics/btu044",
language = "English",
volume = "30",
pages = "1417--1423",
journal = "Computer Applications in the Biosciences",
issn = "1471-2105",
publisher = "Oxford University Press",
number = "10",

}

RIS

TY - JOUR

T1 - Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases

AU - Vincent, Martin

AU - Perell, Katharina

AU - Nielsen, Finn Cilius

AU - Daugaard, Gedske

AU - Hansen, Niels Richard

PY - 2014

Y1 - 2014

N2 - Contamination of a cancer tissue by the surrounding benign (non-cancerous) tissue is a concern for molecular cancer diagnostics. This is because an observed molecular signature will be distorted by the surrounding benign tissue, possibly leading to an incorrect diagnosis. One example is molecular identification of the primary tumor site of metastases because biopsies of metastases typically contain a significant amount of benign tissue.Results: A model of tissue contamination is presented. This contamination model works independently of the training of a molecular predictor, and it can be combined with any predictor model. The usability of the model is illustrated on primary tumor site identification of liver biopsies, specifically, on a human dataset consisting of microRNA expression measurements of primary tumor samples, benign liver samples and liver metastases. For a predictor trained on primary tumor and benign liver samples, the contamination model decreased the test error on biopsies from liver metastases from 77 to 45%. A further reduction to 34% was obtained by including biopsies in the training data.

AB - Contamination of a cancer tissue by the surrounding benign (non-cancerous) tissue is a concern for molecular cancer diagnostics. This is because an observed molecular signature will be distorted by the surrounding benign tissue, possibly leading to an incorrect diagnosis. One example is molecular identification of the primary tumor site of metastases because biopsies of metastases typically contain a significant amount of benign tissue.Results: A model of tissue contamination is presented. This contamination model works independently of the training of a molecular predictor, and it can be combined with any predictor model. The usability of the model is illustrated on primary tumor site identification of liver biopsies, specifically, on a human dataset consisting of microRNA expression measurements of primary tumor samples, benign liver samples and liver metastases. For a predictor trained on primary tumor and benign liver samples, the contamination model decreased the test error on biopsies from liver metastases from 77 to 45%. A further reduction to 34% was obtained by including biopsies in the training data.

U2 - 10.1093/bioinformatics/btu044

DO - 10.1093/bioinformatics/btu044

M3 - Journal article

C2 - 24463184

VL - 30

SP - 1417

EP - 1423

JO - Computer Applications in the Biosciences

JF - Computer Applications in the Biosciences

SN - 1471-2105

IS - 10

ER -

ID: 106541045