{"id":"https://openalex.org/W7201852280","doi":"https://doi.org/10.1039/d6sc06309h","title":"Physics-based molecular fingerprints from spectral graph theory provide efficient geometry-aware measures of chemical similarity","display_name":"Physics-based molecular fingerprints from spectral graph theory provide efficient geometry-aware measures of chemical similarity","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7201852280","doi":"https://doi.org/10.1039/d6sc06309h","pmid":"https://pubmed.ncbi.nlm.nih.gov/42921210","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13693532"},"language":"en","primary_location":{"id":"doi:10.1039/d6sc06309h","doi":"https://doi.org/10.1039/d6sc06309h","is_oa":true,"landing_page_url":"https://doi.org/10.1039/d6sc06309h","pdf_url":null,"source":{"id":"https://openalex.org/S184645833","display_name":"Chemical Science","issn_l":"2041-6520","issn":["2041-6520","2041-6539"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-3","ki-jl-2","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320556","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/P4310320556"],"host_organization_lineage_names":["Royal Society of Chemistry"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chemical Science","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1039/d6sc06309h","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070530038","display_name":"Jacob Toney","orcid":"https://orcid.org/0000-0002-6920-1105","observed_orcids":["https://orcid.org/0000-0002-6920-1105"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob W. Toney","raw_affiliation_strings":["Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":"https://orcid.org/0000-0002-6920-1105","affiliations":[{"raw_affiliation_string":"Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061354551","display_name":"Ayleen Farnood","orcid":"https://orcid.org/0009-0006-8531-6734","observed_orcids":["https://orcid.org/0009-0006-8531-6734"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayleen Y. Farnood","raw_affiliation_strings":["Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":"https://orcid.org/0009-0006-8531-6734","affiliations":[{"raw_affiliation_string":"Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092920905","display_name":"Samir Darouich","orcid":"https://orcid.org/0009-0005-1229-0038","observed_orcids":["https://orcid.org/0009-0005-1229-0038"]},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Samir Darouich","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Institute for Artificial Intelligence, University of Stuttgart, Stuttgart, 70569, Germany","Institute for Theoretical Chemistry, University of Stuttgart, Stuttgart, 70569, Germany"],"raw_orcid":"https://orcid.org/0009-0005-1229-0038","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Institute for Artificial Intelligence, University of Stuttgart, Stuttgart, 70569, Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Theoretical Chemistry, University of Stuttgart, Stuttgart, 70569, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050671822","display_name":"Heather J. Kulik","orcid":"https://orcid.org/0000-0001-9342-0191","observed_orcids":["https://orcid.org/0000-0001-9342-0191"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heather J. Kulik","raw_affiliation_strings":["Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"],"raw_orcid":"https://orcid.org/0000-0001-9342-0191","affiliations":[{"raw_affiliation_string":"Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050671822"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57612792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.7695000171661377,"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":0.7695000171661377,"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/T11476","display_name":"Graph theory and applications","score":0.21070000529289246,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/molecular-fingerprints","display_name":"molecular fingerprints","score":0.9789999723434448},{"id":"https://openalex.org/keywords/spectral-graph-theory","display_name":"spectral graph theory","score":0.953000009059906},{"id":"https://openalex.org/keywords/graph-laplacian","display_name":"graph Laplacian","score":0.8349999785423279},{"id":"https://openalex.org/keywords/3d-molecular-representation","display_name":"3D molecular representation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/molecular-similarity","display_name":"molecular similarity","score":0.9240000247955322},{"id":"https://openalex.org/keywords/molecular-geometry","display_name":"molecular geometry","score":0.4880000054836273},{"id":"https://openalex.org/keywords/stereoisomers","display_name":"stereoisomers","score":0.7350000143051147},{"id":"https://openalex.org/keywords/conformers","display_name":"conformational isomers","score":0.9459999799728394},{"id":"https://openalex.org/keywords/permutation-invariance","display_name":"permutation invariance","score":0.7770000100135803},{"id":"https://openalex.org/keywords/community-detection","display_name":"community detection","score":0.6539999842643738},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"applicability domain","score":0.7250000238418579},{"id":"https://openalex.org/keywords/structure-property-relationships","display_name":"structure-property relationships","score":0.6970000267028809}],"concepts":[{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.6326000094413757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968000292778015},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5098999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49309998750686646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C115178988","wikidata":"https://www.wikidata.org/wiki/Q772067","display_name":"Laplacian matrix","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C74003402","wikidata":"https://www.wikidata.org/wiki/Q3180727","display_name":"Spectral graph theory","level":5,"score":0.365200012922287},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2775000035762787},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.266400009393692},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1039/d6sc06309h","doi":"https://doi.org/10.1039/d6sc06309h","is_oa":true,"landing_page_url":"https://doi.org/10.1039/d6sc06309h","pdf_url":null,"source":{"id":"https://openalex.org/S184645833","display_name":"Chemical Science","issn_l":"2041-6520","issn":["2041-6520","2041-6539"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-3","ki-jl-2","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320556","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/P4310320556"],"host_organization_lineage_names":["Royal Society of Chemistry"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chemical Science","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13693532","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13693532/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13693532/pdf/SC-OLF-D6SC06309H.pdf","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,"listed_in":[],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chem Sci","raw_type":"Text"},{"id":"pmid:42921210","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42921210","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,"listed_in":[],"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":"Chemical science","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2608.05336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05336","pdf_url":"https://arxiv.org/pdf/2608.05336","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2608.05336","doi":"https://doi.org/10.48550/arxiv.2608.05336","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.05336","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1039/d6sc06309h","doi":"https://doi.org/10.1039/d6sc06309h","is_oa":true,"landing_page_url":"https://doi.org/10.1039/d6sc06309h","pdf_url":null,"source":{"id":"https://openalex.org/S184645833","display_name":"Chemical Science","issn_l":"2041-6520","issn":["2041-6520","2041-6539"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-3","ki-jl-2","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320556","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/P4310320556"],"host_organization_lineage_names":["Royal Society of Chemistry"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chemical Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320307783","display_name":"Dow Chemical Company","ror":"https://ror.org/032hx4q18"},{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411532053","https://openalex.org/W4220812397","https://openalex.org/W2168480393","https://openalex.org/W2472085920","https://openalex.org/W2981405700","https://openalex.org/W3184138602","https://openalex.org/W2600261207","https://openalex.org/W2132842501","https://openalex.org/W3136198265","https://openalex.org/W2172024214"],"abstract_inverted_index":{"(3)":[0],"invariance.":[1],"Spectral":[2],"fingerprints":[3,36,81],"differentiate":[4],"between":[5],"unique":[6],"molecular":[7,70],"structures":[8],"with":[9,37],"identical":[10],"2D":[11,17],"connectivity,":[12],"overcoming":[13],"a":[14],"limitation":[15],"of":[16,29,68,89],"descriptors,":[18],"while":[19],"maintaining":[20],"the":[21,66],"low":[22],"computational":[23],"cost":[24,98],"needed":[25],"for":[26],"efficient":[27,87],"screening":[28],"vast":[30],"chemical":[31,90,104],"spaces.":[32],"We":[33,77],"evaluate":[34],"our":[35,69],"community":[38],"detection":[39],"algorithms":[40],"and":[41,55,61,75,86,99],"observe":[42],"strong":[43],"performance":[44],"against":[45],"representative":[46],"baselines":[47],"across":[48,102],"datasets":[49],"from":[50],"organic,":[51],"inorganic,":[52],"biological,":[53],"reticular,":[54],"reaction":[56],"chemistry.":[57],"Nearest-neighbor":[58],"property":[59],"estimation":[60],"applicability":[62],"domain":[63],"analyses":[64],"reveal":[65],"utility":[67],"representation":[71],"in":[72],"machine":[73],"learning":[74],"cheminformatics.":[76],"anticipate":[78],"that":[79,92],"spectral":[80],"will":[82],"serve":[83],"as":[84],"interpretable":[85],"measures":[88],"similarity":[91],"incorporate":[93],"3D":[94],"information":[95],"at":[96],"minimal":[97],"generalize":[100],"well":[101],"diverse":[103],"domains.":[105]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-08-08T00:00:00"}