{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mining-functional-modules-by-multiview-nmf-of","title":"Mining Functional Modules by Multiview-NMF of Phenome-Genome Association","arxiv_id":"1705.03998","date":"2017-05-11","proceeding":null,"authors":["YaoGong Zhang","YingJie Xu","Xin Fan","YuXiang Hong","Jiahui Liu","ZhiCheng He","YaLou Huang","MaoQiang Xie"],"abstract":"Background: Mining gene modules from genomic data is an important step to\ndetect gene members of pathways or other relations such as protein-protein\ninteractions. In this work, we explore the plausibility of detecting gene\nmodules by factorizing gene-phenotype associations from a phenotype ontology\nrather than the conventionally used gene expression data. In particular, the\nhierarchical structure of ontology has not been sufficiently utilized in\nclustering genes while functionally related genes are consistently associated\nwith phenotypes on the same path in the phenotype ontology. Results: We propose\na hierarchal Nonnegative Matrix Factorization (NMF)-based method, called\nConsistent Multiple Nonnegative Matrix Factorization (CMNMF), to factorize\ngenome-phenome association matrix at two levels of the hierarchical structure\nin phenotype ontology for mining gene functional modules. CMNMF constrains the\ngene clusters from the association matrices at two consecutive levels to be\nconsistent since the genes are annotated with both the child phenotype and the\nparent phenotype in the consecutive levels. CMNMF also restricts the identified\nphenotype clusters to be densely connected in the phenotype ontology hierarchy.\nIn the experiments on mining functionally related genes from mouse phenotype\nontology and human phenotype ontology, CMNMF effectively improved clustering\nperformance over the baseline methods. Gene ontology enrichment analysis was\nalso conducted to reveal interesting gene modules. Conclusions: Utilizing the\ninformation in the hierarchical structure of phenotype ontology, CMNMF can\nidentify functional gene modules with more biological significance than the\nconventional methods. CMNMF could also be a better tool for predicting members\nof gene pathways and protein-protein interactions. Availability:\nhttps://github.com/nkiip/CMNMF","url_abs":"http://arxiv.org/abs/1705.03998v1","url_pdf":"http://arxiv.org/pdf/1705.03998v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mining-functional-modules-by-multiview-nmf-of","repo_url":"https://github.com/nkiip/CMNMF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}