Cargando…
Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach
Understanding the biological factors that are characteristic of metastasis in melanoma remains a key approach to improving treatment. In this study, we seek to identify a gene signature of metastatic melanoma. We configured a new network-based computational pipeline, combined with a machine learning...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5725601/ https://www.ncbi.nlm.nih.gov/pubmed/29229936 http://dx.doi.org/10.1038/s41598-017-17330-0 |
_version_ | 1783285565943185408 |
---|---|
author | Metri, Rahul Mohan, Abhilash Nsengimana, Jérémie Pozniak, Joanna Molina-Paris, Carmen Newton-Bishop, Julia Bishop, David Chandra, Nagasuma |
author_facet | Metri, Rahul Mohan, Abhilash Nsengimana, Jérémie Pozniak, Joanna Molina-Paris, Carmen Newton-Bishop, Julia Bishop, David Chandra, Nagasuma |
author_sort | Metri, Rahul |
collection | PubMed |
description | Understanding the biological factors that are characteristic of metastasis in melanoma remains a key approach to improving treatment. In this study, we seek to identify a gene signature of metastatic melanoma. We configured a new network-based computational pipeline, combined with a machine learning method, to mine publicly available transcriptomic data from melanoma patient samples. Our method is unbiased and scans a genome-wide protein-protein interaction network using a novel formulation for network scoring. Using this, we identify the most influential, differentially expressed nodes in metastatic as compared to primary melanoma. We evaluated the shortlisted genes by a machine learning method to rank them by their discriminatory capacities. From this, we identified a panel of 6 genes, ALDH1A1, HSP90AB1, KIT, KRT16, SPRR3 and TMEM45B whose expression values discriminated metastatic from primary melanoma (87% classification accuracy). In an independent transcriptomic data set derived from 703 primary melanomas, we showed that all six genes were significant in predicting melanoma specific survival (MSS) in a univariate analysis, which was also consistent with AJCC staging. Further, 3 of these genes, HSP90AB1, SPRR3 and KRT16 remained significant predictors of MSS in a joint analysis (HR = 2.3, P = 0.03) although, HSP90AB1 (HR = 1.9, P = 2 × 10(−4)) alone remained predictive after adjusting for clinical predictors. |
format | Online Article Text |
id | pubmed-5725601 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-57256012017-12-13 Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach Metri, Rahul Mohan, Abhilash Nsengimana, Jérémie Pozniak, Joanna Molina-Paris, Carmen Newton-Bishop, Julia Bishop, David Chandra, Nagasuma Sci Rep Article Understanding the biological factors that are characteristic of metastasis in melanoma remains a key approach to improving treatment. In this study, we seek to identify a gene signature of metastatic melanoma. We configured a new network-based computational pipeline, combined with a machine learning method, to mine publicly available transcriptomic data from melanoma patient samples. Our method is unbiased and scans a genome-wide protein-protein interaction network using a novel formulation for network scoring. Using this, we identify the most influential, differentially expressed nodes in metastatic as compared to primary melanoma. We evaluated the shortlisted genes by a machine learning method to rank them by their discriminatory capacities. From this, we identified a panel of 6 genes, ALDH1A1, HSP90AB1, KIT, KRT16, SPRR3 and TMEM45B whose expression values discriminated metastatic from primary melanoma (87% classification accuracy). In an independent transcriptomic data set derived from 703 primary melanomas, we showed that all six genes were significant in predicting melanoma specific survival (MSS) in a univariate analysis, which was also consistent with AJCC staging. Further, 3 of these genes, HSP90AB1, SPRR3 and KRT16 remained significant predictors of MSS in a joint analysis (HR = 2.3, P = 0.03) although, HSP90AB1 (HR = 1.9, P = 2 × 10(−4)) alone remained predictive after adjusting for clinical predictors. Nature Publishing Group UK 2017-12-11 /pmc/articles/PMC5725601/ /pubmed/29229936 http://dx.doi.org/10.1038/s41598-017-17330-0 Text en © The Author(s) 2017 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. |
spellingShingle | Article Metri, Rahul Mohan, Abhilash Nsengimana, Jérémie Pozniak, Joanna Molina-Paris, Carmen Newton-Bishop, Julia Bishop, David Chandra, Nagasuma Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
title | Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
title_full | Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
title_fullStr | Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
title_full_unstemmed | Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
title_short | Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
title_sort | identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5725601/ https://www.ncbi.nlm.nih.gov/pubmed/29229936 http://dx.doi.org/10.1038/s41598-017-17330-0 |
work_keys_str_mv | AT metrirahul identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT mohanabhilash identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT nsengimanajeremie identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT pozniakjoanna identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT molinapariscarmen identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT newtonbishopjulia identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT bishopdavid identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach AT chandranagasuma identificationofagenesignaturefordiscriminatingmetastaticfromprimarymelanomausingamolecularinteractionnetworkapproach |