{"id":"https://openalex.org/W7220476484","doi":"https://doi.org/10.26434/chemrxiv.15010093/v1","title":"StereoAtlas: A Large-Scale Dataset of Chiral Compounds with Distinct Bioactivities Curated from ChEMBL37","display_name":"StereoAtlas: A Large-Scale Dataset of Chiral Compounds with Distinct Bioactivities Curated from ChEMBL37","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7220476484","doi":"https://doi.org/10.26434/chemrxiv.15010093/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15010093/v1","doi":"https://doi.org/10.26434/chemrxiv.15010093/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010093/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010093/v1","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010093/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157379249","display_name":"Saisaran Thangaraj","orcid":"https://orcid.org/0009-0009-8164-0555","observed_orcids":["https://orcid.org/0009-0009-8164-0555"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saisaran Thangaraj","raw_affiliation_strings":["Department of Computational Biology","Indraprastha Institute of Information Technology Delhi (IIIT Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology","institution_ids":[]},{"raw_affiliation_string":"Indraprastha Institute of Information Technology Delhi (IIIT Delhi","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101408967","display_name":"N. Arul Murugan","orcid":"https://orcid.org/0000-0003-0185-5724","observed_orcids":["https://orcid.org/0000-0003-0185-5724"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"N. Arul Murugan","raw_affiliation_strings":["Department of Computational Biology","Indraprastha Institute of Information Technology Delhi (IIIT Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology","institution_ids":[]},{"raw_affiliation_string":"Indraprastha Institute of Information Technology Delhi (IIIT Delhi","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101408967","display_name":"N. Arul Murugan","orcid":"https://orcid.org/0000-0003-0185-5724","observed_orcids":["https://orcid.org/0000-0003-0185-5724"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arul Murugan Natarajan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9922000169754028,"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":0.9922000169754028,"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/T12527","display_name":"Chemistry and Stereochemistry Studies","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12748","display_name":"Molecular spectroscopy and chirality","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chiral-compounds","display_name":"chiral compounds","score":0.9819999933242798},{"id":"https://openalex.org/keywords/stereoisomers","display_name":"stereoisomers","score":0.9049999713897705},{"id":"https://openalex.org/keywords/bioactivity","display_name":"biological activity","score":0.7329999804496765},{"id":"https://openalex.org/keywords/stereoselectivity","display_name":"stereoselectivity","score":0.8730000257492065},{"id":"https://openalex.org/keywords/biological-targets","display_name":"biological targets","score":0.7680000066757202},{"id":"https://openalex.org/keywords/stereochemistry","display_name":"stereochemistry","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C181647583","wikidata":"https://www.wikidata.org/wiki/Q903429","display_name":"Stereoselectivity","level":3,"score":0.490200012922287},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.48730000853538513},{"id":"https://openalex.org/C71240020","wikidata":"https://www.wikidata.org/wiki/Q186011","display_name":"Stereochemistry","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C129694887","wikidata":"https://www.wikidata.org/wiki/Q47455153","display_name":"Stereoisomerism","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3138999938964844},{"id":"https://openalex.org/C21951064","wikidata":"https://www.wikidata.org/wiki/Q899212","display_name":"Combinatorial chemistry","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C2989255885","wikidata":"https://www.wikidata.org/wiki/Q500256","display_name":"Molecular conformation","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2768000066280365}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.26434/chemrxiv.15010093/v1","doi":"https://doi.org/10.26434/chemrxiv.15010093/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010093/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010093/v1","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:10.5281/zenodo.23158758","doi":"https://doi.org/10.5281/zenodo.23158758","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23158758","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},{"id":"doi:10.5281/zenodo.23158759","doi":"https://doi.org/10.5281/zenodo.23158759","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23158759","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15010093/v1","doi":"https://doi.org/10.26434/chemrxiv.15010093/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010093/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010093/v1","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":[{"id":"https://openalex.org/F4320313288","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52"},{"id":"https://openalex.org/F4320330597","display_name":"Indraprastha Institute of Information Technology, Delhi","ror":"https://ror.org/03vfp4g33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220476484.pdf","grobid_xml":"https://content.openalex.org/works/W7220476484.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1991998089","https://openalex.org/W2010933199","https://openalex.org/W2042239308","https://openalex.org/W2090277229","https://openalex.org/W2158604280","https://openalex.org/W2558999090","https://openalex.org/W2802385907","https://openalex.org/W2900090807","https://openalex.org/W2991607161","https://openalex.org/W3000593833","https://openalex.org/W3091069112","https://openalex.org/W4200462511","https://openalex.org/W4306737665","https://openalex.org/W4310603653","https://openalex.org/W4392093325","https://openalex.org/W4408720145","https://openalex.org/W4410826990"],"related_works":["https://openalex.org/W4399775134","https://openalex.org/W2050226919","https://openalex.org/W7212374401","https://openalex.org/W1754299563","https://openalex.org/W6960297033","https://openalex.org/W2133912096","https://openalex.org/W4281288816","https://openalex.org/W7095495645","https://openalex.org/W1997589104","https://openalex.org/W2331963447"],"abstract_inverted_index":{"Stereoisomers":[0],"share":[1],"identical":[2],"two-dimensional":[3],"molecular":[4],"topology":[5],"and":[6,81,83,97,110,130,135,146,165],"exhibit":[7],"a":[8,36,153],"Tanimoto":[9],"similarity":[10],"score":[11],"of":[12,38,53],"exactly":[13],"1.0":[14],"under":[15,75],"standard":[16],"fingerprint":[17],"methods,":[18],"rendering":[19],"their":[20],"bioactivity":[21],"differences":[22,68],"invisible":[23],"to":[24],"conventional":[25],"data-driven":[26],"or":[27,51],"physics-based":[28],"activity":[29,57,70,148],"prediction":[30],"approaches.":[31],"Here,":[32],"we":[33],"present":[34],"StereoAtlas,":[35],"dataset":[37,151],"155,526":[39],"experimentally":[40],"measured":[41],"true":[42],"isomer":[43],"families":[44,52,126],"derived":[45],"from":[46],"ChEMBL37,":[47],"in":[48,63,69],"which":[49],"paired":[50],"stereoisomers":[54],"exhibited":[55],"pharmacological":[56],"for":[58,123,159],"the":[59,64,106,111,119,124],"same":[60,65],"biological":[61,142],"target,":[62],"organism.":[66],"Fold":[67],"between":[71],"stereoforms":[72],"were":[73],"computed":[74],"two":[76],"complementary":[77],"strategies":[78],"\u2014":[79],"MinMax":[80],"reference-form\u2014":[82],"classified":[84],"into":[85],"five":[86],"stereoselectivity":[87],"tiers:":[88],"None":[89],"(<2\u00d7),":[90],"Mild":[91],"(2\u20135\u00d7),":[92],"Moderate":[93],"(5\u201310\u00d7),":[94],"Strong":[95],"(10\u201350\u00d7),":[96],"Extreme":[98,108],"(>50\u00d7).":[99],"Among":[100],"38,446":[101],"IC50":[102],"families,":[103],"9.5%":[104],"exceed":[105],"50-fold":[107],"threshold,":[109],"maximum":[112],"fold":[113],"difference":[114],"observed":[115],"is":[116],"195,000,000\u00d7":[117],"at":[118],"oxytocin":[120],"receptor":[121],"(Kd)":[122],"stereoisomeric":[125],"CHEMBL386547":[127],"(potent":[128],"isomer)":[129],"its":[131],"inactive":[132],"counterparts":[133],"(CHEMBL274635":[134],"CHEMBL414373).":[136],"Spanning":[137],"420,721":[138],"unique":[139],"compounds,":[140],"4,519":[141],"targets,":[143],"471":[144],"organisms,":[145],"879":[147],"types,":[149],"this":[150],"provides":[152],"detailed,":[154],"systematic,":[155],"large-scale":[156],"experimental":[157],"resource":[158],"chirality":[160],"cliff-based":[161],"analysis.":[162],"All":[163],"data":[164],"pipeline":[166],"scripts":[167],"are":[168],"publicly":[169],"available.":[170]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-06T00:00:00"}
