{"id":"https://openalex.org/W3008588639","doi":"https://doi.org/10.1186/s13321-020-0416-x","title":"Visualization of very large high-dimensional data sets as minimum spanning trees","display_name":"Visualization of very large high-dimensional data sets as minimum spanning trees","publication_year":2020,"publication_date":"2020-02-12","ids":{"openalex":"https://openalex.org/W3008588639","doi":"https://doi.org/10.1186/s13321-020-0416-x","mag":"3008588639","pmid":"https://pubmed.ncbi.nlm.nih.gov/33431043"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-020-0416-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-0416-x","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-0416-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-0416-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046410250","display_name":"Daniel Probst","orcid":"https://orcid.org/0000-0003-1737-4407"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Daniel Probst","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland. daniel.probst@dcb.unibe.ch","Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-1737-4407","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland. daniel.probst@dcb.unibe.ch","institution_ids":["https://openalex.org/I118564535"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040848839","display_name":"Jean\u2010Louis Reymond","orcid":"https://orcid.org/0000-0003-2724-2942"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jean-Louis Reymond","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland. jean-louis.reymond@dcb.unibe.ch","Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2724-2942","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland. jean-louis.reymond@dcb.unibe.ch","institution_ids":["https://openalex.org/I118564535"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040848839","https://openalex.org/A5046410250"],"corresponding_institution_ids":["https://openalex.org/I118564535"],"apc_list":{"value":2000,"currency":"USD","value_usd":2000},"apc_paid":{"value":1658,"currency":"EUR","value_usd":1788},"fwci":23.5291,"has_fulltext":true,"cited_by_count":315,"citation_normalized_percentile":{"value":0.99642556,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.832354724407196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.776650071144104},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6204733848571777},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5518789291381836},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.516474723815918},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4729941785335541},{"id":"https://openalex.org/keywords/atlas","display_name":"Atlas (anatomy)","score":0.45294636487960815},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4219667315483093},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3557858467102051},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.1838599145412445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1640576720237732},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11981141567230225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09372818470001221}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.832354724407196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776650071144104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6204733848571777},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5518789291381836},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.516474723815918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4729941785335541},{"id":"https://openalex.org/C2776673561","wikidata":"https://www.wikidata.org/wiki/Q655357","display_name":"Atlas (anatomy)","level":2,"score":0.45294636487960815},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4219667315483093},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3557858467102051},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.1838599145412445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1640576720237732},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11981141567230225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09372818470001221},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-020-0416-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-0416-x","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-0416-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:33431043","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33431043","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7015965","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7015965","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:9373889448634848adf5bc586d811f69","is_oa":true,"landing_page_url":"https://doaj.org/article/9373889448634848adf5bc586d811f69","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 12, Iss 1, Pp 1-13 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-020-0416-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-0416-x","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-0416-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G3188738659","display_name":null,"funder_award_id":"51NF40","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5912266461","display_name":"NCCR TransCure - From transport physiology to identification of therapeutic targets","funder_award_id":"185544","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3008588639.pdf","grobid_xml":"https://content.openalex.org/works/W3008588639.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W986143497","https://openalex.org/W1609518033","https://openalex.org/W1780364926","https://openalex.org/W1870428314","https://openalex.org/W1883316518","https://openalex.org/W1965680834","https://openalex.org/W1966613725","https://openalex.org/W1977287658","https://openalex.org/W1988037271","https://openalex.org/W2019096529","https://openalex.org/W2025948031","https://openalex.org/W2055609675","https://openalex.org/W2064391105","https://openalex.org/W2076433909","https://openalex.org/W2083619093","https://openalex.org/W2092493635","https://openalex.org/W2097706568","https://openalex.org/W2100495367","https://openalex.org/W2104766360","https://openalex.org/W2104846587","https://openalex.org/W2107636931","https://openalex.org/W2110026675","https://openalex.org/W2114704115","https://openalex.org/W2119512897","https://openalex.org/W2130479394","https://openalex.org/W2132069633","https://openalex.org/W2137570937","https://openalex.org/W2145154883","https://openalex.org/W2148781362","https://openalex.org/W2151697120","https://openalex.org/W2158485828","https://openalex.org/W2163025055","https://openalex.org/W2165960883","https://openalex.org/W2187089797","https://openalex.org/W2259122119","https://openalex.org/W2346982987","https://openalex.org/W2408539216","https://openalex.org/W2507517445","https://openalex.org/W2558999090","https://openalex.org/W2596398464","https://openalex.org/W2604850519","https://openalex.org/W2766185799","https://openalex.org/W2767891136","https://openalex.org/W2768017947","https://openalex.org/W2769860552","https://openalex.org/W2779144909","https://openalex.org/W2786672974","https://openalex.org/W2885227878","https://openalex.org/W2889326414","https://openalex.org/W2905012389","https://openalex.org/W2905261310","https://openalex.org/W2911483473","https://openalex.org/W2925830236","https://openalex.org/W2949538565","https://openalex.org/W2961460076","https://openalex.org/W2964331441","https://openalex.org/W2982725072","https://openalex.org/W3102797483","https://openalex.org/W4237307902","https://openalex.org/W6902626566"],"related_works":["https://openalex.org/W2780675302","https://openalex.org/W4294024451","https://openalex.org/W2477626301","https://openalex.org/W4207063555","https://openalex.org/W2585302987","https://openalex.org/W2477820794","https://openalex.org/W2472085920","https://openalex.org/W2890089068","https://openalex.org/W3195955219","https://openalex.org/W4386849092"],"abstract_inverted_index":{"The":[0],"chemical":[1,14],"sciences":[2],"are":[3,21,89],"producing":[4],"an":[5],"unprecedented":[6],"amount":[7],"of":[8,40,65,69,73,101,121,141,160],"large,":[9],"high-dimensional":[10],"data":[11,28,60,67,74,103,137,161],"sets":[12,68,104,138],"containing":[13],"structures":[15],"and":[16,33,47,76,99,112,115,118,176],"associated":[17],"properties.":[18],"However,":[19],"there":[20],"currently":[22],"no":[23],"algorithms":[24],"to":[25,42,54,71,106,132,155],"visualize":[26],"such":[27,143],"while":[29],"preserving":[30],"both":[31],"global":[32,113],"local":[34,111],"features":[35],"with":[36,57,169],"a":[37,52,58,81],"sufficient":[38],"level":[39],"detail":[41],"allow":[43],"for":[44,96],"human":[45],"inspection":[46],"interpretation.":[48],"Here,":[49],"we":[50],"propose":[51],"solution":[53],"this":[55],"problem":[56],"new":[59],"visualization":[61],"method,":[62],"TMAP,":[63],"capable":[64],"representing":[66],"up":[70],"millions":[72],"points":[75],"arbitrary":[77],"high":[78],"dimensionality":[79],"as":[80,144,152,154],"two-dimensional":[82],"tree":[83],"(http://tmap.gdb.tools).":[84],"Visualizations":[85],"based":[86,127],"on":[87],"TMAP":[88,131],"better":[90],"suited":[91],"than":[92],"t-SNE":[93],"or":[94],"UMAP":[95],"the":[97,119,122,124,133,147,156],"exploration":[98],"interpretation":[100],"large":[102],"due":[105],"their":[107],"tree-like":[108],"nature,":[109],"increased":[110],"neighborhood":[114],"structure":[116],"preservation,":[117],"transparency":[120],"methods":[123],"algorithm":[125],"is":[126],"on.":[128],"We":[129,163],"apply":[130],"most":[134],"used":[135],"chemistry":[136],"including":[139],"databases":[140],"molecules":[142],"ChEMBL,":[145],"FDB17,":[146],"Natural":[148],"Products":[149],"Atlas,":[150],"DSSTox,":[151],"well":[153],"MoleculeNet":[157],"benchmark":[158],"collection":[159],"sets.":[162],"also":[164],"show":[165],"its":[166],"broad":[167],"applicability":[168],"further":[170],"examples":[171],"from":[172],"biology,":[173],"particle":[174],"physics,":[175],"literature.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":70},{"year":2023,"cited_by_count":54},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}