{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T10:22:36Z","timestamp":1767176556593,"version":"build-2238731810"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009283","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000}}],"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T00:00:00Z","timestamp":1628640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5-UM1-HG006370"],"award-info":[{"award-number":["5-UM1-HG006370"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Integrating reference datasets (e.g. from high-throughput experiments) with unstructured and manually-assembled information (e.g. notes or comments from individual researchers) has the potential to tailor bioinformatic analyses to specific needs and to lead to new insights. However, developing bespoke analysis pipelines from scratch is time-consuming, and general tools for exploring such heterogeneous data are not available. We argue that by treating all data as text, a knowledge-base can accommodate a range of bioinformatic data types and applications. We show that a database coupled to nearest-neighbor algorithms can address common tasks such as gene-set analysis as well as specific tasks such as ontology translation. We further show that a mathematical transformation motivated by diffusion can be effective for exploration across heterogeneous datasets. Diffusion enables the knowledge-base to begin with a sparse query, impute more features, and find matches that would otherwise remain hidden. This can be used, for example, to map multi-modal queries consisting of gene symbols and phenotypes to descriptions of diseases. Diffusion also enables user-driven learning: when the knowledge-base cannot provide satisfactory search results in the first instance, users can improve the results in real-time by adding domain-specific knowledge. User-driven learning has implications for data management, integration, and curation.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1009283","type":"journal-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T13:40:37Z","timestamp":1628689237000},"page":"e1009283","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Diffusion enables integration of heterogeneous data and user-driven learning in a desktop knowledge-base"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3042-4712","authenticated-orcid":true,"given":"Tomasz","family":"Konopka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-6058","authenticated-orcid":true,"given":"Sandra","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Damian","family":"Smedley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2021,8,11]]},"reference":[{"key":"pcbi.1009283.ref001","first-page":"l1","article-title":"Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal","volume":"6","author":"J Gao","year":"2013","journal-title":"Sci Signal"},{"key":"pcbi.1009283.ref002","doi-asserted-by":"crossref","first-page":"D746","DOI":"10.1093\/nar\/gkv1045","article-title":"Expression Atlas update\u2014an integrated database of gene and protein expression in humans, animals and plants","author":"R Petryszak","year":"2016","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1009283.ref003","doi-asserted-by":"crossref","first-page":"D704","DOI":"10.1093\/nar\/gkz997","article-title":"The Monarch Initiative in 2019: an integrative data and analytic platform connecting phenotypes to genotypes across species","volume":"48","author":"KA Shefchek","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009283.ref004","article-title":"Fast searches of large collections of single cell data using scfind","author":"JTH Lee"},{"key":"pcbi.1009283.ref005","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1038\/s41592-019-0509-5","article-title":"Assessment of network module identification across complex diseases","volume":"16","author":"S Choobdar","year":"2019","journal-title":"Nat Methods."},{"key":"pcbi.1009283.ref006","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching Word Vectors with Subword Information","author":"P Bojanowski","year":"2017","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"pcbi.1009283.ref007","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/1472-6785-11-11","article-title":"Simrank: Rapid and sensitive general-purpose k-mer search tool","volume":"11","author":"TZ DeSantis","year":"2011","journal-title":"BMC Ecol"},{"key":"pcbi.1009283.ref008","article-title":"Off the Beaten Path","author":"L Boytsov","year":"2016","journal-title":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management\u2014CIKM \u201816"},{"key":"pcbi.1009283.ref009","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1113","article-title":"Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space","author":"A Neelakantan","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"pcbi.1009283.ref010","article-title":"Character-level convolutional networks for text classification","author":"Xiang Zhang","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"pcbi.1009283.ref011","article-title":"Recurrent Convolutional Neural Networks for Text Classification","author":"Siwei Lai","year":"2015","journal-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"pcbi.1009283.ref012","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"J Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"pcbi.1009283.ref013","doi-asserted-by":"crossref","article-title":"On the effectiveness of small, discriminatively pre-trained language representation models for biomedical text mining","author":"IB Ozyurt","DOI":"10.18653\/v1\/2020.sdp-1.12"},{"key":"pcbi.1009283.ref014","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1016\/j.cell.2018.05.061","article-title":"Recovering Gene Interactions from Single-Cell Data Using Data Diffusion","volume":"174","author":"D van Dijk","year":"2018","journal-title":"Cell"},{"key":"pcbi.1009283.ref015","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1038\/ng.3168","article-title":"Pan-cancer network analysis identifies combinations of rare somatic mutations across pathways and protein complexes","volume":"47","author":"MDM Leiserson","year":"2015","journal-title":"Nat Genet"},{"key":"pcbi.1009283.ref016","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/978-3-642-41062-8_28","article-title":"Engineering Efficient and Effective Non-metric Space Library","author":"L Boytsov","year":"2013","journal-title":"Similarity Search and Applications"},{"key":"pcbi.1009283.ref017","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1093\/bioinformatics\/btm051","article-title":"Analyzing gene expression data in terms of gene sets: methodological issues","volume":"23","author":"JJ Goeman","year":"2007","journal-title":"Bioinformatics"},{"key":"pcbi.1009283.ref018","doi-asserted-by":"crossref","first-page":"i366","DOI":"10.1093\/bioinformatics\/btr228","article-title":"From sets to graphs: towards a realistic enrichment analysis of transcriptomic systems","volume":"27","author":"L Geistlinger","year":"2011","journal-title":"Bioinformatics"},{"key":"pcbi.1009283.ref019","doi-asserted-by":"crossref","first-page":"D330","DOI":"10.1093\/nar\/gky1055","article-title":"The Gene Ontology Resource: 20 years and still GOing strong.","volume":"47","author":"The Gene Ontology Consortium","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009283.ref020","article-title":"Toward a gold standard for benchmarking gene set enrichment analysis","author":"L Geistlinger","year":"2020","journal-title":"Briefings in Bioinformatics"},{"key":"pcbi.1009283.ref021","doi-asserted-by":"crossref","first-page":"2059","DOI":"10.1101\/gr.177220.114","article-title":"Megabase-scale deletion using CRISPR\/Cas9 to generate a fully haploid human cell line","volume":"24","author":"P Essletzbichler","year":"2014","journal-title":"Genome Res"},{"key":"pcbi.1009283.ref022","article-title":"hypeR: an R package for geneset enrichment workflows","author":"A Federico","year":"2019","journal-title":"Bioinformatics"},{"key":"pcbi.1009283.ref023","doi-asserted-by":"crossref","first-page":"D1018","DOI":"10.1093\/nar\/gky1105","article-title":"Expansion of the Human Phenotype Ontology (HPO) knowledge base and resources","volume":"47","author":"S K\u00f6hler","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009283.ref024","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s00335-012-9421-3","article-title":"The Mammalian Phenotype Ontology as a unifying standard for experimental and high-throughput phenotyping data","author":"CL Smith","year":"2012","journal-title":"Mammalian Genome"},{"key":"pcbi.1009283.ref025","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1002\/humu.23633","article-title":"ClinGen\u2019s GenomeConnect registry enables patient-centered data sharing","author":"JM Savatt","year":"2018","journal-title":"Human Mutation"},{"key":"pcbi.1009283.ref026","doi-asserted-by":"crossref","first-page":"D801","DOI":"10.1093\/nar\/gky1056","article-title":"Mouse Genome Database Group. Mouse Genome Database (MGD) 2019.","volume":"47","author":"CJ Bult","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009283.ref027","doi-asserted-by":"crossref","first-page":"bat025","DOI":"10.1093\/database\/bat025","article-title":"Sanger Mouse Genetics Project, Westerfield M, et al. PhenoDigm: analyzing curated annotations to associate animal models with human diseases","volume":"2013","author":"D Smedley","year":"2013","journal-title":"Database"},{"key":"pcbi.1009283.ref028","doi-asserted-by":"crossref","first-page":"e1007586","DOI":"10.1371\/journal.pcbi.1007586","article-title":"Incremental data integration for tracking genotype-disease associations","volume":"16","author":"T Konopka","year":"2020","journal-title":"PLoS Comput Biol."},{"key":"pcbi.1009283.ref029","doi-asserted-by":"crossref","first-page":"e1000247","DOI":"10.1371\/journal.pbio.1000247","article-title":"Linking human diseases to animal models using ontology-based phenotype annotation","volume":"7","author":"NL Washington","year":"2009","journal-title":"PLoS Biol"},{"key":"pcbi.1009283.ref030","doi-asserted-by":"crossref","first-page":"e2005343","DOI":"10.1371\/journal.pbio.2005343","article-title":"Best Match: New relevance search for PubMed","volume":"16","author":"N Fiorini","year":"2018","journal-title":"PLoS Biol"},{"key":"pcbi.1009283.ref031","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1101\/gr.160325.113","article-title":"Improved exome prioritization of disease genes through cross-species phenotype comparison","volume":"24","author":"Sanger Mouse Genetics Project","year":"2014","journal-title":"Genome Res"},{"key":"pcbi.1009283.ref032","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1038\/nmeth.3971","article-title":"Diffusion pseudotime robustly reconstructs lineage branching.","volume":"13","author":"L Haghverdi","year":"2016","journal-title":"Nat Methods"},{"key":"pcbi.1009283.ref033","doi-asserted-by":"crossref","first-page":"e1008569","DOI":"10.1371\/journal.pcbi.1008569","article-title":"Optimal tuning of weighted kNN- and diffusion-based methods for denoising single cell genomics data","volume":"17","author":"A Tj\u00e4rnberg","journal-title":"PLoS Comput Biol. 2021"},{"key":"pcbi.1009283.ref034","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/3233231","article-title":"The mythos of model interpretability","author":"ZC Lipton","year":"2018","journal-title":"Communications of the ACM"},{"key":"pcbi.1009283.ref035","author":"Tomi Peltola Mustafa Mert \u00c7elikok","journal-title":"Interactive AI with a Theory of Mind."},{"key":"pcbi.1009283.ref036","unstructured":"The most popular database for modern apps. In: MongoDB [Internet]. MongoDB; [cited 16 May 2020]. Available: https:\/\/www.mongodb.com"},{"key":"pcbi.1009283.ref037","doi-asserted-by":"crossref","first-page":"D766","DOI":"10.1093\/nar\/gky955","article-title":"GENCODE reference annotation for the human and mouse genomes","volume":"47","author":"A Frankish","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009283.ref038","first-page":"D498","article-title":"The reactome pathway knowledgebase","volume":"48","author":"B Jassal","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009283.ref039","doi-asserted-by":"crossref","first-page":"D607","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets","volume":"47","author":"D Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009283","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T02:07:06Z","timestamp":1699322826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009283"}},"subtitle":[],"editor":[{"given":"K. Bretonnel","family":"Cohen","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,8,11]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,8,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009283","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,11]]}}}