{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Metri R"],"funding":["Cancer Research UK","Worldwide Cancer Research"],"pagination":["17314"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC5725601"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["7(1)"],"pubmed_abstract":["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, A"],"journal":["Scientific reports"],"pubmed_title":["Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach."],"pmcid":["PMC5725601"],"funding_grant_id":["C588/A19167","C8216/A6129","19167","12-0023","10589","11963"],"pubmed_authors":["Metri R","Chandra N","Mohan A","Molina-Paris C","Bishop D","Newton-Bishop J","Pozniak J","Nsengimana J"],"additional_accession":[]},"is_claimable":false,"name":"Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach.","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, A","dates":{"release":"2017-01-01T00:00:00Z","publication":"2017 Dec","modification":"2025-06-01T00:36:05.464Z","creation":"2025-06-01T00:36:05.464Z"},"accession":"S-EPMC5725601","cross_references":{"pubmed":["29229936"],"doi":["10.1038/s41598-017-17330-0"]}}