TumorTracer: a method to identify the tissue of origin from the somatic mutations of a tumor specimen

Andrea Marion Marquard; Nicolai Juul Birkbak; Cecilia Engel Thomas; Francesco Favero; Marcin Krzystanek; Celine Lefebvre; Charles Ferté; Mariam Jamal-Hanjani; Gareth A Wilson; Seema Shafi; Charles Swanton; Fabrice André; Zoltan Szallasi; Aron Charles Eklund

doi:10.1186/s12920-015-0130-0

TumorTracer: a method to identify the tissue of origin from the somatic mutations of a tumor specimen

Andrea Marion Marquard, Nicolai Juul Birkbak, Cecilia Engel Thomas, Francesco Favero, Marcin Krzystanek, Celine Lefebvre, Charles Ferté, Mariam Jamal-Hanjani, Gareth A Wilson, Seema Shafi, Charles Swanton, Fabrice André, Zoltan Szallasi, Aron Charles Eklund

22 Citations (Scopus)

Abstract

BACKGROUND: A substantial proportion of cancer cases present with a metastatic tumor and require further testing to determine the primary site; many of these are never fully diagnosed and remain cancer of unknown primary origin (CUP). It has been previously demonstrated that the somatic point mutations detected in a tumor can be used to identify its site of origin with limited accuracy. We hypothesized that higher accuracy could be achieved by a classification algorithm based on the following feature sets: 1) the number of nonsynonymous point mutations in a set of 232 specific cancer-associated genes, 2) frequencies of the 96 classes of single-nucleotide substitution determined by the flanking bases, and 3) copy number profiles, if available.

METHODS: We used publicly available somatic mutation data from the COSMIC database to train random forest classifiers to distinguish among those tissues of origin for which sufficient data was available. We selected feature sets using cross-validation and then derived two final classifiers (with or without copy number profiles) using 80 % of the available tumors. We evaluated the accuracy using the remaining 20 %. For further validation, we assessed accuracy of the without-copy-number classifier on three independent data sets: 1669 newly available public tumors of various types, a cohort of 91 breast metastases, and a set of 24 specimens from 9 lung cancer patients subjected to multiregion sequencing.

RESULTS: The cross-validation accuracy was highest when all three types of information were used. On the left-out COSMIC data not used for training, we achieved a classification accuracy of 85 % across 6 primary sites (with copy numbers), and 69 % across 10 primary sites (without copy numbers). Importantly, a derived confidence score could distinguish tumors that could be identified with 95 % accuracy (32 %/75 % of tumors with/without copy numbers) from those that were less certain. Accuracy in the independent data sets was 46 %, 53 % and 89 % respectively, similar to the accuracy expected from the training data.

CONCLUSIONS: Identification of primary site from point mutation and/or copy number data may be accurate enough to aid clinical diagnosis of cancers of unknown primary origin.

Original language	English
Journal	BMC Medical Genomics
Volume	8
Pages (from-to)	58
ISSN	1755-8794
DOIs	https://doi.org/10.1186/s12920-015-0130-0
Publication status	Published - 1 Oct 2015
Externally published	Yes

Keywords

Breast Neoplasms/genetics
Databases, Genetic
Female
Genes, Neoplasm
Humans
Lung Neoplasms/genetics
Male
Organ Specificity
Point Mutation
Polymorphism, Single Nucleotide

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1186/s12920-015-0130-0Licence: CC BY

s12920-015-0130-0Final published version, 784 KBLicence: CC BY

Cite this

Marquard, A. M., Birkbak, N. J., Thomas, C. E., Favero, F., Krzystanek, M., Lefebvre, C., Ferté, C., Jamal-Hanjani, M., Wilson, G. A., Shafi, S., Swanton, C., André, F., Szallasi, Z., & Eklund, A. C. (2015). TumorTracer: a method to identify the tissue of origin from the somatic mutations of a tumor specimen. BMC Medical Genomics, 8, 58. https://doi.org/10.1186/s12920-015-0130-0

@article{948f352c2bfb4b19ab9ceb527a837009,

title = "TumorTracer: a method to identify the tissue of origin from the somatic mutations of a tumor specimen",

abstract = "BACKGROUND: A substantial proportion of cancer cases present with a metastatic tumor and require further testing to determine the primary site; many of these are never fully diagnosed and remain cancer of unknown primary origin (CUP). It has been previously demonstrated that the somatic point mutations detected in a tumor can be used to identify its site of origin with limited accuracy. We hypothesized that higher accuracy could be achieved by a classification algorithm based on the following feature sets: 1) the number of nonsynonymous point mutations in a set of 232 specific cancer-associated genes, 2) frequencies of the 96 classes of single-nucleotide substitution determined by the flanking bases, and 3) copy number profiles, if available.METHODS: We used publicly available somatic mutation data from the COSMIC database to train random forest classifiers to distinguish among those tissues of origin for which sufficient data was available. We selected feature sets using cross-validation and then derived two final classifiers (with or without copy number profiles) using 80 % of the available tumors. We evaluated the accuracy using the remaining 20 %. For further validation, we assessed accuracy of the without-copy-number classifier on three independent data sets: 1669 newly available public tumors of various types, a cohort of 91 breast metastases, and a set of 24 specimens from 9 lung cancer patients subjected to multiregion sequencing.RESULTS: The cross-validation accuracy was highest when all three types of information were used. On the left-out COSMIC data not used for training, we achieved a classification accuracy of 85 % across 6 primary sites (with copy numbers), and 69 % across 10 primary sites (without copy numbers). Importantly, a derived confidence score could distinguish tumors that could be identified with 95 % accuracy (32 %/75 % of tumors with/without copy numbers) from those that were less certain. Accuracy in the independent data sets was 46 %, 53 % and 89 % respectively, similar to the accuracy expected from the training data.CONCLUSIONS: Identification of primary site from point mutation and/or copy number data may be accurate enough to aid clinical diagnosis of cancers of unknown primary origin.",

keywords = "Breast Neoplasms/genetics, Databases, Genetic, Female, Genes, Neoplasm, Humans, Lung Neoplasms/genetics, Male, Organ Specificity, Point Mutation, Polymorphism, Single Nucleotide",

author = "Marquard, {Andrea Marion} and Birkbak, {Nicolai Juul} and Thomas, {Cecilia Engel} and Francesco Favero and Marcin Krzystanek and Celine Lefebvre and Charles Fert{\'e} and Mariam Jamal-Hanjani and Wilson, {Gareth A} and Seema Shafi and Charles Swanton and Fabrice Andr{\'e} and Zoltan Szallasi and Eklund, {Aron Charles}",

year = "2015",

month = oct,

day = "1",

doi = "10.1186/s12920-015-0130-0",

language = "English",

volume = "8",

pages = "58",

journal = "BMC Medical Genomics",

issn = "1755-8794",

publisher = "BioMed Central Ltd.",

}

TY - JOUR

T1 - TumorTracer

T2 - a method to identify the tissue of origin from the somatic mutations of a tumor specimen

AU - Marquard, Andrea Marion

AU - Birkbak, Nicolai Juul

AU - Thomas, Cecilia Engel

AU - Favero, Francesco

AU - Krzystanek, Marcin

AU - Lefebvre, Celine

AU - Ferté, Charles

AU - Jamal-Hanjani, Mariam

AU - Wilson, Gareth A

AU - Shafi, Seema

AU - Swanton, Charles

AU - André, Fabrice

AU - Szallasi, Zoltan

AU - Eklund, Aron Charles

PY - 2015/10/1

Y1 - 2015/10/1

N2 - BACKGROUND: A substantial proportion of cancer cases present with a metastatic tumor and require further testing to determine the primary site; many of these are never fully diagnosed and remain cancer of unknown primary origin (CUP). It has been previously demonstrated that the somatic point mutations detected in a tumor can be used to identify its site of origin with limited accuracy. We hypothesized that higher accuracy could be achieved by a classification algorithm based on the following feature sets: 1) the number of nonsynonymous point mutations in a set of 232 specific cancer-associated genes, 2) frequencies of the 96 classes of single-nucleotide substitution determined by the flanking bases, and 3) copy number profiles, if available.METHODS: We used publicly available somatic mutation data from the COSMIC database to train random forest classifiers to distinguish among those tissues of origin for which sufficient data was available. We selected feature sets using cross-validation and then derived two final classifiers (with or without copy number profiles) using 80 % of the available tumors. We evaluated the accuracy using the remaining 20 %. For further validation, we assessed accuracy of the without-copy-number classifier on three independent data sets: 1669 newly available public tumors of various types, a cohort of 91 breast metastases, and a set of 24 specimens from 9 lung cancer patients subjected to multiregion sequencing.RESULTS: The cross-validation accuracy was highest when all three types of information were used. On the left-out COSMIC data not used for training, we achieved a classification accuracy of 85 % across 6 primary sites (with copy numbers), and 69 % across 10 primary sites (without copy numbers). Importantly, a derived confidence score could distinguish tumors that could be identified with 95 % accuracy (32 %/75 % of tumors with/without copy numbers) from those that were less certain. Accuracy in the independent data sets was 46 %, 53 % and 89 % respectively, similar to the accuracy expected from the training data.CONCLUSIONS: Identification of primary site from point mutation and/or copy number data may be accurate enough to aid clinical diagnosis of cancers of unknown primary origin.

AB - BACKGROUND: A substantial proportion of cancer cases present with a metastatic tumor and require further testing to determine the primary site; many of these are never fully diagnosed and remain cancer of unknown primary origin (CUP). It has been previously demonstrated that the somatic point mutations detected in a tumor can be used to identify its site of origin with limited accuracy. We hypothesized that higher accuracy could be achieved by a classification algorithm based on the following feature sets: 1) the number of nonsynonymous point mutations in a set of 232 specific cancer-associated genes, 2) frequencies of the 96 classes of single-nucleotide substitution determined by the flanking bases, and 3) copy number profiles, if available.METHODS: We used publicly available somatic mutation data from the COSMIC database to train random forest classifiers to distinguish among those tissues of origin for which sufficient data was available. We selected feature sets using cross-validation and then derived two final classifiers (with or without copy number profiles) using 80 % of the available tumors. We evaluated the accuracy using the remaining 20 %. For further validation, we assessed accuracy of the without-copy-number classifier on three independent data sets: 1669 newly available public tumors of various types, a cohort of 91 breast metastases, and a set of 24 specimens from 9 lung cancer patients subjected to multiregion sequencing.RESULTS: The cross-validation accuracy was highest when all three types of information were used. On the left-out COSMIC data not used for training, we achieved a classification accuracy of 85 % across 6 primary sites (with copy numbers), and 69 % across 10 primary sites (without copy numbers). Importantly, a derived confidence score could distinguish tumors that could be identified with 95 % accuracy (32 %/75 % of tumors with/without copy numbers) from those that were less certain. Accuracy in the independent data sets was 46 %, 53 % and 89 % respectively, similar to the accuracy expected from the training data.CONCLUSIONS: Identification of primary site from point mutation and/or copy number data may be accurate enough to aid clinical diagnosis of cancers of unknown primary origin.

KW - Breast Neoplasms/genetics

KW - Databases, Genetic

KW - Female

KW - Genes, Neoplasm

KW - Humans

KW - Lung Neoplasms/genetics

KW - Male

KW - Organ Specificity

KW - Point Mutation

KW - Polymorphism, Single Nucleotide

U2 - 10.1186/s12920-015-0130-0

DO - 10.1186/s12920-015-0130-0

M3 - Journal article

C2 - 26429708

SN - 1755-8794

VL - 8

SP - 58

JO - BMC Medical Genomics

JF - BMC Medical Genomics

ER -

TumorTracer: a method to identify the tissue of origin from the somatic mutations of a tumor specimen

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this