{"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/jumping-across-biomedical-contexts-using","title":"Jumping across biomedical contexts using compressive data fusion","arxiv_id":"1708.03392","date":"2017-08-10","proceeding":null,"authors":["Marinka Zitnik","Blaz Zupan"],"abstract":"Motivation: The rapid growth of diverse biological data allows us to consider\ninteractions between a variety of objects, such as genes, chemicals, molecular\nsignatures, diseases, pathways and environmental exposures. Often, any pair of\nobjects--such as a gene and a disease--can be related in different ways, for\nexample, directly via gene-disease associations or indirectly via functional\nannotations, chemicals and pathways. Different ways of relating these objects\ncarry different semantic meanings. However, traditional methods disregard these\nsemantics and thus cannot fully exploit their value in data modeling.\n  Results: We present Medusa, an approach to detect size-k modules of objects\nthat, taken together, appear most significant to another set of objects. Medusa\noperates on large-scale collections of heterogeneous data sets and explicitly\ndistinguishes between diverse data semantics. It advances research along two\ndimensions: it builds on collective matrix factorization to derive different\nsemantics, and it formulates the growing of the modules as a submodular\noptimization program. Medusa is flexible in choosing or combining semantic\nmeanings and provides theoretical guarantees about detection quality. In a\nsystematic study on 310 complex diseases, we show the effectiveness of Medusa\nin associating genes with diseases and detecting disease modules. We\ndemonstrate that in predicting gene-disease associations Medusa compares\nfavorably to methods that ignore diverse semantic meanings. We find that the\nutility of different semantics depends on disease categories and that, overall,\nMedusa recovers disease modules more accurately when combining different\nsemantics.","url_abs":"http://arxiv.org/abs/1708.03392v1","url_pdf":"http://arxiv.org/pdf/1708.03392v1.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":"jumping-across-biomedical-contexts-using","repo_url":"https://github.com/marinkaz/medusa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}