{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T08:09:45Z","timestamp":1769069385424,"version":"3.49.0"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2018,2,16]],"date-time":"2018-02-16T00:00:00Z","timestamp":1518739200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000275","name":"Leverhulme Trust","doi-asserted-by":"publisher","award":["No. RPG-2016-015"],"award-info":[{"award-number":["No. RPG-2016-015"]}],"id":[{"id":"10.13039\/501100000275","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>This work uses the Random Forest (RF) classification algorithm to predict if a gene is over-expressed, under-expressed or has no change in expression with age in the brain. RFs have high predictive power, and RF models can be interpreted using a feature (variable) importance measure. However, current feature importance measures evaluate a feature as a whole (all feature values). We show that, for a popular type of biological data (Gene Ontology-based), usually only one value of a feature is particularly important for classification and the interpretation of the RF model. Hence, we propose a new algorithm for identifying the most important and most informative feature values in an RF model.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The new feature importance measure identified highly relevant Gene Ontology terms for the aforementioned gene classification task, producing a feature ranking that is much more informative to biologists than an alternative, state-of-the-art feature importance measure.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The dataset and source codes used in this paper are available as \u2018Supplementary Material\u2019 and the description of the data can be found at: https:\/\/fabiofabris.github.io\/bioinfo2018\/web\/.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty087","type":"journal-article","created":{"date-parts":[[2018,2,15]],"date-time":"2018-02-15T12:10:17Z","timestamp":1518696617000},"page":"2449-2456","source":"Crossref","is-referenced-by-count":53,"title":["A new approach for interpreting Random Forest models and its application to the biology of ageing"],"prefix":"10.1093","volume":"34","author":[{"given":"Fabio","family":"Fabris","sequence":"first","affiliation":[{"name":"School of Computing, University of Kent, Canterbury, Kent, UK"}]},{"given":"Aoife","family":"Doherty","sequence":"additional","affiliation":[{"name":"Integrative Genomics of Ageing Group, Institute of Ageing and Chronic Disease, University of Liverpool, Liverpool, UK"}]},{"given":"Daniel","family":"Palmer","sequence":"additional","affiliation":[{"name":"Integrative Genomics of Ageing Group, Institute of Ageing and Chronic Disease, University of Liverpool, Liverpool, UK"}]},{"given":"Jo\u00e3o Pedro","family":"de Magalh\u00e3es","sequence":"additional","affiliation":[{"name":"Integrative Genomics of Ageing Group, Institute of Ageing and Chronic Disease, University of Liverpool, Liverpool, UK"}]},{"given":"Alex A","family":"Freitas","sequence":"additional","affiliation":[{"name":"School of Computing, University of Kent, Canterbury, Kent, UK"}]}],"member":"286","published-online":{"date-parts":[[2018,2,16]]},"reference":[{"key":"2023012713014545200_bty087-B1","doi-asserted-by":"crossref","first-page":"38231","DOI":"10.1038\/srep38231","article-title":"Defining an olfactory receptor function in airway smooth muscle cells","volume":"6","author":"Aisenberg","year":"2016","journal-title":"Sci. Rep"},{"key":"2023012713014545200_bty087-B2","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1016\/S0140-6736(01)06260-2","article-title":"Neurodegeneration: a failure of neuroregeneration?","volume":"358","author":"Armstrong","year":"2001","journal-title":"Lancet"},{"key":"2023012713014545200_bty087-B3","doi-asserted-by":"crossref","first-page":"149","DOI":"10.3233\/JAD-2005-7208","article-title":"Olfactory involvement in aging and Alzheimer\u2019s disease: an autopsy study","volume":"7","author":"Attems","year":"2005","journal-title":"J. Alzheimer\u2019s Dis"},{"key":"2023012713014545200_bty087-B4","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.18632\/aging.101264","article-title":"Machine learning for predicting lifespan-extending chemical compounds","volume":"9","author":"Barardo","year":"2017","journal-title":"Aging"},{"key":"2023012713014545200_bty087-B5","doi-asserted-by":"crossref","first-page":"D760","DOI":"10.1093\/nar\/gkl887","article-title":"NCBI GEO: mining tens of millions of expression profiles-database and tools update","volume":"35","author":"Barrett","year":"2006","journal-title":"Nucleic Acid Res"},{"key":"2023012713014545200_bty087-B6","doi-asserted-by":"crossref","first-page":"15605","DOI":"10.1073\/pnas.0806883105","article-title":"Gene expression changes in the course of normal brain aging are sexually dimorphic","volume":"105","author":"Berchtold","year":"2008","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023012713014545200_bty087-B7","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1093\/bioinformatics\/btp536","article-title":"QuickGO:a web-based tool for Gene Ontology searching","volume":"25","author":"Binns","year":"2009","journal-title":"Bioinformatics"},{"key":"2023012713014545200_bty087-B8","first-page":"451","article-title":"Area under the precision-recall curve: point estimates and confidence intervals","volume":"8190","author":"Boyd","year":"2013","journal-title":"Machine Learn. Knowledge Dis. Databases"},{"key":"2023012713014545200_bty087-B9","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learn"},{"key":"2023012713014545200_bty087-B10","doi-asserted-by":"crossref","first-page":"R622","DOI":"10.1016\/j.cub.2012.07.004","article-title":"Unfolded protein response","volume":"22","author":"Cao","year":"2012","journal-title":"Curr. Biol"},{"key":"2023012713014545200_bty087-B11","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1007\/s10534-010-9329-x","article-title":"Cadmium stress: an oxidative challenge","volume":"23","author":"Cuypers","year":"2010","journal-title":"BioMetals"},{"key":"2023012713014545200_bty087-B12","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1093\/bioinformatics\/btp073","article-title":"Meta-analysis of age-related gene expression profiles identifies common signatures of aging","volume":"25","author":"De Magalh\u00e3es","year":"2009","journal-title":"Bioinformatics"},{"key":"2023012713014545200_bty087-B13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/1471-2105-7-3","article-title":"Gene selection and classification of microarray data using random forest","volume":"7","author":"D\u00edaz-Uriarte","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"2023012713014545200_bty087-B14","doi-asserted-by":"crossref","first-page":"8354","DOI":"10.1523\/JNEUROSCI.2751-04.2004","article-title":"Aging results in reduced epidermal growth factor receptor signaling, diminished olfactory neurogenesis, and deficits in fine olfactory discrimination","volume":"24","author":"Enwere","year":"2004","journal-title":"J. Neurosci"},{"key":"2023012713014545200_bty087-B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-017-1650-8","article-title":"Intervention in prediction measure: a new approach to assessing variable importance for random forests","volume":"18","author":"Epifanio","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023012713014545200_bty087-B16","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s10522-017-9683-y","article-title":"A review of supervised machine learning applied to ageing research","volume":"18","author":"Fabris","year":"2017","journal-title":"Biogerontology"},{"key":"2023012713014545200_bty087-B17","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1126\/science.279.5350.514","article-title":"A structural scaffolding of intermediate filaments in health and disease","volume":"279","author":"Fuchs","year":"1998","journal-title":"Science"},{"key":"2023012713014545200_bty087-B18","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1007\/s00726-010-0528-0","article-title":"Inflammation-associated S100 proteins: new mechanisms that regulate function","volume":"41","author":"Goyette","year":"2011","journal-title":"Amino Acids"},{"key":"2023012713014545200_bty087-B19","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1016\/j.euroneuro.2011.08.008","article-title":"Cost of disorders of the brain in Europe 2010","volume":"21","author":"Gustavsson","year":"2011","journal-title":"Eur. Neuropsychopharmacol"},{"key":"2023012713014545200_bty087-B20","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1046\/j.1471-4159.2002.00969.x","article-title":"Oxidative damage increases with age in a canine model of human brain aging","volume":"82","author":"Head","year":"2002","journal-title":"J. Neurochem"},{"key":"2023012713014545200_bty087-B21","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/1752-0509-2-80","article-title":"The use of gene ontology terms for predicting highly-connected \u2018hub\u2019 nodes in protein-protein interaction networks","volume":"2","author":"Hsing","year":"2008","journal-title":"BMC Syst. Biol"},{"key":"2023012713014545200_bty087-B22","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1242\/jcs.041244","article-title":"Insights into intermediate filament regulation from development to ageing","volume":"124","author":"Hyder","year":"2011","journal-title":"J. Cell Sci"},{"key":"2023012713014545200_bty087-B23","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1198\/jasa.2009.tm08622","article-title":"High-dimensional variable selection for survival data","volume":"105","author":"Ishwaran","year":"2010","journal-title":"J. Am. Stat. Assoc"},{"key":"2023012713014545200_bty087-B24","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511921803","volume-title":"Evaluating Learning Algorithms, a Classification Perspective","author":"Japkowicz","year":"2011","edition":"1st edn."},{"key":"2023012713014545200_bty087-B25","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1016\/j.bbrc.2015.03.046","article-title":"Expression of human olfactory receptor 10J5 in heart aorta, coronary artery, and endothelial cells and its functional role in angiogenesis","volume":"460","author":"Kim","year":"2015","journal-title":"Biochem. Biophys. Res. Commun"},{"key":"2023012713014545200_bty087-B26","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1038\/nrn1886","article-title":"Aging and neuronal vulnerability","volume":"7","author":"Mattson","year":"2006","journal-title":"Nat. Rev. Neurosci"},{"key":"2023012713014545200_bty087-B27","doi-asserted-by":"crossref","first-page":"1570","DOI":"10.1093\/jn\/109.9.1570","article-title":"Changes in activity of the Cu-Zn superoxide dismutase enzyme in tissues of the rat with changes in dietary copper","volume":"109","author":"Paynter","year":"1979","journal-title":"J. Nutr"},{"key":"2023012713014545200_bty087-B28","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1016\/S0531-5565(01)00139-5","article-title":"Oxidative stress and protein aggregation during biological aging","volume":"36","author":"Squier","year":"2001","journal-title":"Experimental Gerontol"},{"key":"2023012713014545200_bty087-B29","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1186\/1471-2105-9-307","article-title":"Conditional variable importance for random forests","volume":"9","author":"Strobl","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2023012713014545200_bty087-B30","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1093\/bib\/bbs034","article-title":"Data mining in the life sciences with random forest: a walk in the park or lost in the jungle?","volume":"14","author":"Touw","year":"2013","journal-title":"Brief. Bioinformatics"},{"key":"2023012713014545200_bty087-B31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2016\/8426874","article-title":"An update on inflamm-aging: mechanisms, prevention, and treatment","volume":"2016","author":"Xia","year":"2016","journal-title":"J. Immunol. Res"},{"key":"2023012713014545200_bty087-B32","doi-asserted-by":"crossref","first-page":"e201","DOI":"10.1371\/journal.pgen.0030201","article-title":"AGEMAP: a gene expression database for aging in mice","volume":"3","author":"Zahn","year":"2007","journal-title":"PLoS Genetics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/14\/2449\/48917764\/bioinformatics_34_14_2449.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/14\/2449\/48917764\/bioinformatics_34_14_2449.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:59:09Z","timestamp":1674827949000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/14\/2449\/4866010"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,2,16]]},"references-count":32,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2018,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty087","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,7,15]]},"published":{"date-parts":[[2018,2,16]]}}}