{"id":"https://openalex.org/W7144325898","doi":"https://doi.org/10.26434/chemrxiv.15001445/v1","title":"Conformational Soft Hash (CSH): A Rotation-Invariant Molecular Fingerprint for Conformation-Sensitive Similarity Search and Blockchain-Based Conformational Registry","display_name":"Conformational Soft Hash (CSH): A Rotation-Invariant Molecular Fingerprint for Conformation-Sensitive Similarity Search and Blockchain-Based Conformational Registry","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7144325898","doi":"https://doi.org/10.26434/chemrxiv.15001445/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15001445/v1","doi":"https://doi.org/10.26434/chemrxiv.15001445/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15001445/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv.15001445/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019499094","display_name":"Jakub Hryc","orcid":"https://orcid.org/0000-0002-6182-4500","observed_orcids":["https://orcid.org/0000-0002-6182-4500"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jakub Hryc","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0000-0002-6182-4500","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5019499094"],"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9970999956130981,"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":0.9970999956130981,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"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/T10044","display_name":"Protein Structure and Dynamics","score":0.00019999999494757503,"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/molecular-fingerprints","display_name":"molecular fingerprints","score":0.5889999866485596},{"id":"https://openalex.org/keywords/simhash","display_name":"SimHash","score":0.7680000066757202},{"id":"https://openalex.org/keywords/dihedral-angle","display_name":"dihedral angle","score":0.7760000228881836},{"id":"https://openalex.org/keywords/blockchain","display_name":"blockchain","score":0.6880000233650208},{"id":"https://openalex.org/keywords/ethereum","display_name":"Ethereum","score":0.7990000247955322},{"id":"https://openalex.org/keywords/drug-molecules","display_name":"drug molecules","score":0.6629999876022339},{"id":"https://openalex.org/keywords/intellectual-property-protection","display_name":"intellectual property protection","score":0.7889999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402000188827515},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4887000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4129999876022339},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C2989255885","wikidata":"https://www.wikidata.org/wiki/Q500256","display_name":"Molecular conformation","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.27390000224113464}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26434/chemrxiv.15001445/v1","doi":"https://doi.org/10.26434/chemrxiv.15001445/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15001445/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.26434/chemrxiv.15001445/v2","doi":"https://doi.org/10.26434/chemrxiv.15001445/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15001445/v2","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15001445/v2","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15001445/v1","doi":"https://doi.org/10.26434/chemrxiv.15001445/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15001445/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7144325898.pdf","grobid_xml":"https://content.openalex.org/works/W7144325898.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1988037271","https://openalex.org/W2038276547","https://openalex.org/W2057350662","https://openalex.org/W2091155135","https://openalex.org/W2120540345","https://openalex.org/W2136567909","https://openalex.org/W2147717514","https://openalex.org/W2151697120","https://openalex.org/W2154418770","https://openalex.org/W2244785476","https://openalex.org/W2295124130","https://openalex.org/W2607166384","https://openalex.org/W2951048875","https://openalex.org/W3011894284","https://openalex.org/W3019459825","https://openalex.org/W4220753591","https://openalex.org/W4248987559","https://openalex.org/W4293570072","https://openalex.org/W4307468223","https://openalex.org/W4382862618","https://openalex.org/W4384927820","https://openalex.org/W4410487992"],"related_works":["https://openalex.org/W4417345818","https://openalex.org/W7163985762","https://openalex.org/W2169546341","https://openalex.org/W7095371181","https://openalex.org/W6977510253","https://openalex.org/W7097765220","https://openalex.org/W7128208130","https://openalex.org/W2146844279","https://openalex.org/W2152903006","https://openalex.org/W1983111365"],"abstract_inverted_index":{"Many":[0],"molecular":[1,389],"descriptors":[2],"are":[3],"currently":[4],"available,":[5],"but":[6],"each":[7,111,287],"has":[8,273,384],"its":[9,145,345,366],"limitations.":[10],"One":[11],"group,":[12],"such":[13],"as":[14,44,58,78,222],"the":[15,22,30,37,53,65,92,106,135,139,142,153,164,195,208,216,223,250,256,264,274,279,303,316,329,357],"Morgan":[16],"and":[17,47,108,117,152,173,179,191,253,268,314,374],"ECFP":[18],"fingerprints,":[19],"encodes":[20,306],"only":[21,52],"connections":[23],"between":[24,94,219,226,319],"atoms.":[25],"Those":[26],"that":[27],"do":[28],"take":[29],"3D":[31,76],"structure":[32],"into":[33,157],"account":[34],"either":[35],"reduce":[36],"geometry":[38],"to":[39,128,149,286,293,356],"a":[40,70,75,79,88,129,158,181,206,233,241,283,337,340,360],"few":[41],"summary":[42],"values,":[43,124],"USR,":[45,170,262],"USRCAT":[46,267],"3DAPfp":[48,172,269,272],"do,":[49],"or":[50],"describe":[51],"environments":[54,309],"of":[55,96,110,123,134,141,184,188,203,205,210,236,245,277,336,349,359,365,381],"individual":[56],"atoms,":[57],"E3FP":[59,174],"does.":[60],"The":[61,132],"present":[62],"work":[63],"uses":[64],"Conformational":[66],"Soft":[67],"Hash":[68],"(CSH),":[69],"simple":[71],"method":[72,196],"for":[73,266,388],"representing":[74],"conformation":[77],"256-bit":[80,159],"binary":[81],"hash.":[82],"Each":[83],"conformer":[84,338],"is":[85],"described":[86,386],"by":[87,161],"feature":[89],"vector":[90,136],"containing":[91],"distances":[93,116],"pairs":[95],"heavy":[97],"atoms":[98],"at":[99,371],"least":[100],"three":[101],"bonds":[102],"apart,":[103],"together":[104],"with":[105,138,169,215,376],"sine":[107],"cosine":[109],"torsion":[112],"angle.":[113],"Because":[114],"interatomic":[115,228],"trigonometric":[118],"functions":[119],"span":[120],"different":[121,291],"ranges":[122],"they":[125],"were":[126,270,352],"brought":[127],"common":[130,234],"scale.":[131],"length":[133],"varied":[137],"size":[140,190],"molecule,":[143,207,288,362],"so":[144,363],"dimensionality":[146],"was":[147,155,167,213,325],"reduced":[148],"32":[150],"components":[151],"result":[154],"converted":[156],"string":[160],"SimHash,":[162],"yielding":[163],"CSH.":[165],"CSH":[166,239,297],"compared":[168,375],"USRCAT,":[171],"on":[175,180,249,255,302,328,339],"28":[176],"drug":[177],"molecules":[178,292,351],"separate":[182],"set":[183,252],"twelve":[185],"approved":[186],"drugs":[187],"varying":[189],"flexibility,":[192],"selected":[193],"after":[194],"had":[197],"been":[198,385],"finalised.":[199],"For":[200],"every":[201],"pair":[202],"conformers":[204,320,348],"similarity":[209],"their":[211,227],"hashes":[212,367],"correlated":[214],"geometric":[217,317],"difference":[218,225],"them,":[220],"measured":[221],"root-mean-square":[224],"distance":[229],"matrices":[230],"(DM-RMSD).":[231],"At":[232],"budget":[235],"256":[237],"bits,":[238],"reached":[240],"mean":[242],"Spearman":[243],"correlation":[244],"\u03c1":[246],"=":[247],"0.508":[248],"first":[251],"0.637":[254],"second.":[257],"It":[258],"performed":[259],"better":[260],"than":[261,311],"while":[263],"results":[265],"similar.":[271],"advantage,":[275],"however,":[276],"reaching":[278],"same":[280],"accuracy":[281],"without":[282,343],"transformation":[284],"fitted":[285],"which":[289,332],"allows":[290],"be":[294,369],"compared,":[295],"something":[296],"does":[298],"not":[299],"offer.":[300],"E3FP,":[301],"other":[304],"hand,":[305],"local":[307],"atom":[308],"rather":[310],"global":[312],"shape":[313],"reflected":[315],"differences":[318],"poorly.":[321],"A":[322],"conformational":[323],"registry":[324,358,380],"also":[326],"implemented":[327],"Ethereum":[330],"blockchain,":[331],"timestamps":[333],"an":[334],"identifier":[335],"public":[341],"chain":[342],"disclosing":[344],"coordinates.":[346],"Eighty":[347],"four":[350],"recorded.":[353],"Records":[354],"belong":[355],"particular":[361],"all":[364],"can":[368],"retrieved":[370],"once,":[372],"browsed":[373],"one":[377],"another.":[378],"No":[379],"this":[382],"kind":[383],"before":[387],"conformations.":[390]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-04-01T00:00:00"}