{"id":"https://openalex.org/W7208742183","doi":"https://doi.org/10.26434/chemrxiv.15008307/v1","title":"From Proteins and Molecules to Cats and Dogs: Visualization as Scalable Minimum Spanning Trees","display_name":"From Proteins and Molecules to Cats and Dogs: Visualization as Scalable Minimum Spanning Trees","publication_year":2026,"publication_date":"2026-09-04","ids":{"openalex":"https://openalex.org/W7208742183","doi":"https://doi.org/10.26434/chemrxiv.15008307/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008307/v1","doi":"https://doi.org/10.26434/chemrxiv.15008307/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008307/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv.15008307/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014720171","display_name":"A. Sep\u00falveda","orcid":"https://orcid.org/0000-0002-4463-6786","observed_orcids":["https://orcid.org/0000-0002-4463-6786"]},"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":false,"raw_author_name":"Alejandro Flores Sepu\u0301lveda","raw_affiliation_strings":["Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern, Freiestrasse 3, Bern, Switzerland, 3012"],"raw_orcid":"https://orcid.org/0000-0002-4463-6786","affiliations":[{"raw_affiliation_string":"Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern, Freiestrasse 3, Bern, Switzerland, 3012","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147713920","display_name":"Maarten Boneschansker","orcid":"https://orcid.org/0009-0005-2071-8268","observed_orcids":["https://orcid.org/0009-0005-2071-8268"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten Boneschansker","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, Droevendaalsesteeg, Wageningen, Netherlands, 6708 PB"],"raw_orcid":"https://orcid.org/0009-0005-2071-8268","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, Droevendaalsesteeg, Wageningen, Netherlands, 6708 PB","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046410250","display_name":"Daniel Probst","orcid":"https://orcid.org/0000-0003-1737-4407","observed_orcids":["https://orcid.org/0000-0003-1737-4407"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daniel Probst","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, Droevendaalsesteeg, Wageningen, Netherlands, 6708 PB"],"raw_orcid":"https://orcid.org/0000-0003-1737-4407","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, Droevendaalsesteeg, Wageningen, Netherlands, 6708 PB","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040848839","display_name":"Jean\u2010Louis Reymond","orcid":"https://orcid.org/0000-0003-2724-2942","observed_orcids":["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":false,"raw_author_name":"Jean-Louis Reymond","raw_affiliation_strings":["Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern, Freiestrasse 3, Bern, Switzerland, 3012"],"raw_orcid":"https://orcid.org/0000-0003-2724-2942","affiliations":[{"raw_affiliation_string":"Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern, Freiestrasse 3, Bern, Switzerland, 3012","institution_ids":["https://openalex.org/I118564535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.4458000063896179,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.4458000063896179,"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/T10799","display_name":"Data Visualization and Analytics","score":0.353300005197525,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10057","display_name":"Face and Expression Recognition","score":0.0794999971985817,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/minimum-spanning-tree","display_name":"minimum spanning tree","score":0.6110000014305115},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.8389999866485596},{"id":"https://openalex.org/keywords/data-visualization","display_name":"data visualization","score":0.8960000276565552},{"id":"https://openalex.org/keywords/single-cell-data","display_name":"single-cell data","score":0.628000020980835},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.5950000286102295},{"id":"https://openalex.org/keywords/catalytic-activity","display_name":"catalytic activity","score":0.5619999766349792},{"id":"https://openalex.org/keywords/network-embedding","display_name":"graph embedding","score":0.36399999260902405},{"id":"https://openalex.org/keywords/taxonomic-classification","display_name":"taxonomic classification","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123000025749207},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.375},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.36559998989105225},{"id":"https://openalex.org/C13743678","wikidata":"https://www.wikidata.org/wiki/Q240464","display_name":"Minimum spanning tree","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.34790000319480896},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C64331007","wikidata":"https://www.wikidata.org/wiki/Q831672","display_name":"Spanning tree","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C43058520","wikidata":"https://www.wikidata.org/wiki/Q624580","display_name":"Eulerian path","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C106278948","wikidata":"https://www.wikidata.org/wiki/Q1198051","display_name":"R-tree","level":4,"score":0.265500009059906},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.25679999589920044},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.25429999828338623},{"id":"https://openalex.org/C182124507","wikidata":"https://www.wikidata.org/wiki/Q166154","display_name":"Line segment","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008307/v1","doi":"https://doi.org/10.26434/chemrxiv.15008307/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008307/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008307/v1","doi":"https://doi.org/10.26434/chemrxiv.15008307/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008307/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6910692487","https://openalex.org/W7100539386","https://openalex.org/W2346393133","https://openalex.org/W3014040695","https://openalex.org/W7096343275","https://openalex.org/W7202358960","https://openalex.org/W4391380210","https://openalex.org/W4405610287","https://openalex.org/W4412877082","https://openalex.org/W4399880261"],"abstract_inverted_index":{"Dimensionality":[0],"reduction":[1],"and":[2,46,49,69,119],"data":[3,30],"visualization":[4],"are":[5],"essential":[6],"for":[7],"analyzing":[8],"highdimensional":[9,29],"datasets,":[10],"yet":[11],"traditional":[12],"projection":[13],"methods":[14],"obscure":[15],"local":[16],"structural":[17],"relationships.":[18],"We":[19],"present":[20],"TMAP2,":[21],"a":[22,32,65,89,92,96,108,121,125,129,136,170],"scalable":[23],"rewrite":[24],"of":[25,79,107,172],"TMAP":[26,178],"that":[27,82,132],"maps":[28],"as":[31,88,165],"minimum":[33],"spanning":[34],"tree.":[35],"TMAP2":[36,174],"accepts":[37],"diverse":[38],"input":[39],"types,":[40],"including":[41],"continuous":[42],"embeddings,":[43],"sparse":[44],"fingerprints,":[45],"precomputed":[47],"graphs,":[48],"applies":[50],"to":[51,128,181,186],"single-cell,":[52],"image,":[53],"chemistry,":[54],"or":[55],"protein-language-model":[56],"data.":[57],"Every":[58],"line":[59],"on":[60],"the":[61,104,144,152,176],"map":[62],"is":[63],"therefore":[64],"real":[66],"nearest-neighbor":[67],"relationship,":[68],"exactly":[70],"one":[71,166,187],"path":[72],"joins":[73],"any":[74,182],"two":[75],"points.":[76],"The":[77],"number":[78],"edges":[80],"along":[81,91],"path,":[83],"its":[84],"hop":[85],"count,":[86],"works":[87],"coordinate":[90],"progression:":[93],"it":[94],"recovers":[95],"pancreatic":[97],"cell\u2019s":[98],"developmental":[99],"age":[100],"(Spearman":[101,117],"0.90),":[102],"tracks":[103],"collection":[105],"date":[106],"SARS-CoV-2":[109],"spike":[110],"sequence":[111,115],"built":[112],"from":[113,124,179],"raw":[114],"alone":[116],"0.86),":[118],"traces":[120],"smooth":[122],"morph":[123],"Persian":[126],"cat":[127],"Yorkshire":[130],"terrier":[131],"crosses":[133],"species":[134],"at":[135,184],"single":[137],"edge.":[138],"On":[139],"3.6":[140],"million":[141,188],"CAZyme":[142],"sequences":[143,156],"same":[145],"tree":[146],"separates":[147],"taxonomic":[148],"domains":[149],"and,":[150],"within":[151],"family":[153],"GH43,":[154],"sorts":[155],"by":[157],"catalytic":[158],"activity,":[159],"revealing":[160],"an":[161],"anchor":[162],"enzyme":[163],"annotated":[164],"activity":[167],"sitting":[168],"among":[169],"cluster":[171],"another.":[173],"extends":[175],"original":[177],"fingerprints":[180],"embedding,":[183],"up":[185],"points":[189],"with":[190],"95\u201399%":[191],"recall.":[192]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-05T00:00:00"}