{"id":"https://openalex.org/W7221087724","doi":"https://doi.org/10.26434/chemrxiv.15010189/v1","title":"MolSanitizer: An open-source pipeline to prepare small-molecule databases for large-scale virtual screening","display_name":"MolSanitizer: An open-source pipeline to prepare small-molecule databases for large-scale virtual screening","publication_year":2026,"publication_date":"2026-10-09","ids":{"openalex":"https://openalex.org/W7221087724","doi":"https://doi.org/10.26434/chemrxiv.15010189/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15010189/v1","doi":"https://doi.org/10.26434/chemrxiv.15010189/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010189/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010189/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":"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://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010189/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081145348","display_name":"Thua-Phong Lam","orcid":"https://orcid.org/0000-0002-8149-9952","observed_orcids":["https://orcid.org/0000-0002-8149-9952"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Thua-Phong Lam","raw_affiliation_strings":["Department of Cell and Molecular Biology","Uppsala University"],"raw_orcid":"https://orcid.org/0000-0002-8149-9952","affiliations":[{"raw_affiliation_string":"Department of Cell and Molecular Biology","institution_ids":[]},{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070857677","display_name":"Szymon Pach","orcid":"https://orcid.org/0000-0001-6109-7123","observed_orcids":["https://orcid.org/0000-0001-6109-7123"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Szymon Pach","raw_affiliation_strings":["Department of Cell and Molecular Biology","Uppsala University"],"raw_orcid":"https://orcid.org/0000-0001-6109-7123","affiliations":[{"raw_affiliation_string":"Department of Cell and Molecular Biology","institution_ids":[]},{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074284782","display_name":"Philip Ullmann","orcid":"https://orcid.org/0000-0003-2391-4609","observed_orcids":["https://orcid.org/0000-0003-2391-4609"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Philip Ullmann","raw_affiliation_strings":["Department of Cell and Molecular Biology","Uppsala University"],"raw_orcid":"https://orcid.org/0000-0003-2391-4609","affiliations":[{"raw_affiliation_string":"Department of Cell and Molecular Biology","institution_ids":[]},{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158159021","display_name":"Hocine El Khaoudi Enyoury","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hocine El Khaoudi Enyoury","raw_affiliation_strings":["Institute of Pharmaceutical Chemistry","Philipps-Universit\u00e4t Marburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pharmaceutical Chemistry","institution_ids":[]},{"raw_affiliation_string":"Philipps-Universit\u00e4t Marburg","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036784729","display_name":"Ruth Brenk","orcid":"https://orcid.org/0000-0002-6204-5488","observed_orcids":["https://orcid.org/0000-0002-6204-5488"]},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ruth Brenk","raw_affiliation_strings":["Department of Biomedicine","University of Bergen"],"raw_orcid":"https://orcid.org/0000-0002-6204-5488","affiliations":[{"raw_affiliation_string":"Department of Biomedicine","institution_ids":[]},{"raw_affiliation_string":"University of Bergen","institution_ids":["https://openalex.org/I4432739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004266252","display_name":"Flavio Ballante","orcid":"https://orcid.org/0000-0002-4831-3423","observed_orcids":["https://orcid.org/0000-0002-4831-3423"]},"institutions":[{"id":"https://openalex.org/I28166907","display_name":"Karolinska Institutet","ror":"https://ror.org/056d84691","country_code":"SE","type":"education","lineage":["https://openalex.org/I28166907"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Flavio Ballante","raw_affiliation_strings":["Department of Medical Biochemistry and Biophysics","Karolinska Institutet"],"raw_orcid":"https://orcid.org/0000-0002-4831-3423","affiliations":[{"raw_affiliation_string":"Department of Medical Biochemistry and Biophysics","institution_ids":[]},{"raw_affiliation_string":"Karolinska Institutet","institution_ids":["https://openalex.org/I28166907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041554247","display_name":"Trent E. Balius","orcid":"https://orcid.org/0000-0002-6811-4667","observed_orcids":["https://orcid.org/0000-0002-6811-4667"]},"institutions":[{"id":"https://openalex.org/I4396570585","display_name":"Leidos Biomedical Research Inc. (United States)","ror":"https://ror.org/00bardy64","country_code":"US","type":"company","lineage":["https://openalex.org/I114662689","https://openalex.org/I4396570585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trent E. Balius","raw_affiliation_strings":["Cancer Research Technology Program, Leidos Biomedical Research, Inc., P.O. Box B, Frederick, Maryland, 21702"],"raw_orcid":"https://orcid.org/0000-0002-6811-4667","affiliations":[{"raw_affiliation_string":"Cancer Research Technology Program, Leidos Biomedical Research, Inc., P.O. Box B, Frederick, Maryland, 21702","institution_ids":["https://openalex.org/I4396570585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048470753","display_name":"Peter Kolb","orcid":"https://orcid.org/0000-0003-4089-614X","observed_orcids":["https://orcid.org/0000-0003-4089-614X"]},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Kolb","raw_affiliation_strings":["Institute of Pharmaceutical Chemistry","Philipps-Universit\u00e4t Marburg"],"raw_orcid":"https://orcid.org/0000-0003-4089-614X","affiliations":[{"raw_affiliation_string":"Institute of Pharmaceutical Chemistry","institution_ids":[]},{"raw_affiliation_string":"Philipps-Universit\u00e4t Marburg","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054045417","display_name":"John J. Irwin","orcid":"https://orcid.org/0000-0002-1195-6417","observed_orcids":["https://orcid.org/0000-0002-1195-6417"]},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Irwin","raw_affiliation_strings":["Department of Pharmaceutical Chemistry","University of California"],"raw_orcid":"https://orcid.org/0000-0002-1195-6417","affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Chemistry","institution_ids":[]},{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075811022","display_name":"Jens Carlsson","orcid":"https://orcid.org/0000-0003-4623-2977","observed_orcids":["https://orcid.org/0000-0003-4623-2977"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]},{"id":"https://openalex.org/I2800139495","display_name":"Science for Life Laboratory","ror":"https://ror.org/04ev03g22","country_code":"SE","type":"facility","lineage":["https://openalex.org/I2800139495"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jens Carlsson","raw_affiliation_strings":["Department of Cell and Molecular Biology","Science for Life Laboratory (SciLifeLab","Uppsala University"],"raw_orcid":"https://orcid.org/0000-0003-4623-2977","affiliations":[{"raw_affiliation_string":"Department of Cell and Molecular Biology","institution_ids":[]},{"raw_affiliation_string":"Science for Life Laboratory (SciLifeLab","institution_ids":["https://openalex.org/I2800139495"]},{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029965580","display_name":"Israel Cabeza de Vaca","orcid":"https://orcid.org/0000-0002-6208-1091","observed_orcids":["https://orcid.org/0000-0002-6208-1091"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Israel Cabeza de Vaca","raw_affiliation_strings":["Department of Cell and Molecular Biology","Uppsala University"],"raw_orcid":"https://orcid.org/0000-0002-6208-1091","affiliations":[{"raw_affiliation_string":"Department of Cell and Molecular Biology","institution_ids":[]},{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"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":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":9.999999747378752e-05,"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/T14099","display_name":"Synthesis and Characterization of Heterocyclic Compounds","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/virtual-screening","display_name":"virtual screening","score":0.7699999809265137},{"id":"https://openalex.org/keywords/rdkit","display_name":"RDKit","score":0.7129999995231628},{"id":"https://openalex.org/keywords/protonation","display_name":"protonation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/tautomerism","display_name":"tautomerism","score":0.996999979019165},{"id":"https://openalex.org/keywords/conformer-generation","display_name":"conformer generation","score":0.9440000057220459},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.7080000042915344},{"id":"https://openalex.org/keywords/molecular-docking","display_name":"molecular docking","score":0.6510000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770000100135803},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.724399983882904},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6290000081062317},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.6272000074386597},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6014999747276306},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5737000107765198},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15010189/v1","doi":"https://doi.org/10.26434/chemrxiv.15010189/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010189/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010189/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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15010189/v1","doi":"https://doi.org/10.26434/chemrxiv.15010189/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010189/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010189/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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1441096865","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"},{"id":"https://openalex.org/G3344207039","display_name":null,"funder_award_id":"2019 . 0130","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"},{"id":"https://openalex.org/G3631573628","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320321040","funder_display_name":"National Science Council"},{"id":"https://openalex.org/G429838583","display_name":null,"funder_award_id":"KAW 2019.0130","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"},{"id":"https://openalex.org/G4560995112","display_name":"Ultra-rapid lead generation for antiviral drug discovery: Structure-based design of dengue virus inhibitors","funder_award_id":"2025-06720","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G4632909464","display_name":null,"funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322327","funder_display_name":"Knut och Alice Wallenbergs Stiftelse"},{"id":"https://openalex.org/G5404377299","display_name":null,"funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320321040","funder_display_name":"National Science Council"},{"id":"https://openalex.org/G6326013329","display_name":"Molecular control of dopaminergic signaling by allosteric modulators and designer receptors","funder_award_id":"2025-06266","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G796431723","display_name":null,"funder_award_id":"201805973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G8869864247","display_name":"NAISS","funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320321491","display_name":"Cancerfonden","ror":"https://ror.org/0527jb766"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221087724.pdf","grobid_xml":"https://content.openalex.org/works/W7221087724.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W304035826","https://openalex.org/W1469544863","https://openalex.org/W1653739410","https://openalex.org/W1968319881","https://openalex.org/W1984075743","https://openalex.org/W1988437166","https://openalex.org/W2000350990","https://openalex.org/W2014123957","https://openalex.org/W2016455326","https://openalex.org/W2021093184","https://openalex.org/W2027423337","https://openalex.org/W2031168104","https://openalex.org/W2031450906","https://openalex.org/W2033863142","https://openalex.org/W2038638444","https://openalex.org/W2042129725","https://openalex.org/W2043509228","https://openalex.org/W2046336719","https://openalex.org/W2047245810","https://openalex.org/W2050226017","https://openalex.org/W2052030759","https://openalex.org/W2058835307","https://openalex.org/W2069152576","https://openalex.org/W2078374001","https://openalex.org/W2095026430","https://openalex.org/W2113364934","https://openalex.org/W2114779636","https://openalex.org/W2127790232","https://openalex.org/W2128629409","https://openalex.org/W2135732933","https://openalex.org/W2151255437","https://openalex.org/W2158219301","https://openalex.org/W2169678694","https://openalex.org/W2244785476","https://openalex.org/W2314484349","https://openalex.org/W2319902168","https://openalex.org/W2334483166","https://openalex.org/W2336040088","https://openalex.org/W2343847023","https://openalex.org/W2394923207","https://openalex.org/W2620143000","https://openalex.org/W2761273232","https://openalex.org/W2806664897","https://openalex.org/W2890361239","https://openalex.org/W2909063104","https://openalex.org/W2911847761","https://openalex.org/W2920724574","https://openalex.org/W2947285137","https://openalex.org/W2965068418","https://openalex.org/W3002554271","https://openalex.org/W3011894284","https://openalex.org/W3014091199","https://openalex.org/W3035965352","https://openalex.org/W3082081167","https://openalex.org/W3126031592","https://openalex.org/W3127467109","https://openalex.org/W3135127269","https://openalex.org/W3168436232","https://openalex.org/W4220790075","https://openalex.org/W4311104054","https://openalex.org/W4385638623","https://openalex.org/W4386151261","https://openalex.org/W4387002014","https://openalex.org/W4387664865","https://openalex.org/W4388615774","https://openalex.org/W4391752837","https://openalex.org/W4392348271","https://openalex.org/W4402555999","https://openalex.org/W4403922670","https://openalex.org/W4404511389","https://openalex.org/W4417250662","https://openalex.org/W7155495211"],"related_works":["https://openalex.org/W2947285137","https://openalex.org/W4403921621","https://openalex.org/W2621548818","https://openalex.org/W2950721223","https://openalex.org/W7161060275","https://openalex.org/W4393374903","https://openalex.org/W2271352405","https://openalex.org/W3195157142","https://openalex.org/W2176516200","https://openalex.org/W7164401852"],"abstract_inverted_index":{"Accurate":[0],"preparation":[1,38],"of":[2,13],"small-molecule":[3],"databases":[4],"for":[5,10,45,58,138,143],"virtual":[6,47],"screening":[7],"is":[8,141],"crucial":[9],"the":[11,113],"success":[12],"computer-aided":[14],"drug":[15],"discovery.":[16],"Although":[17],"numerous":[18],"free":[19,90,144],"software":[20,91],"options":[21],"are":[22],"available,":[23],"they":[24],"often":[25],"underperform":[26],"compared":[27],"to":[28,98,110,115],"commercial":[29,99],"alternatives.":[30],"Here,":[31],"we":[32],"introduce":[33],"MolSanitizer,":[34],"an":[35],"open-source":[36,52,106],"molecular":[37,130],"pipeline":[39],"built":[40],"on":[41],"RDKit":[42],"and":[43,60,65,105,147],"designed":[44],"large-scale":[46],"screening.":[48],"MolSanitizer":[49,84,101,120,140],"extends":[50],"existing":[51],"functionality":[53],"through":[54],"curated,":[55],"chemical-environment-aware":[56],"rules":[57],"protonation":[59],"tautomerization,":[61],"systematic":[62],"stereoisomer":[63],"enumeration,":[64],"a":[66,103,135,149],"dedicated":[67],"conformer":[68],"generator":[69],"that":[70,83],"combines":[71],"knowledge-based":[72],"structural":[73],"preferences":[74],"with":[75,126],"stochastic":[76],"torsional":[77],"sampling.":[78],"Our":[79],"benchmarking":[80],"results":[81],"show":[82],"achieves":[85],"better":[86],"performance":[87,95],"than":[88],"several":[89,127],"alternatives":[92],"while":[93],"achieving":[94],"levels":[96],"comparable":[97],"software.":[100],"features":[102],"modular":[104],"design,":[107],"allowing":[108],"users":[109],"easily":[111],"customize":[112],"tool":[114],"meet":[116],"their":[117],"specific":[118],"needs.":[119],"also":[121],"generates":[122],"output":[123],"files":[124],"compatible":[125],"widely":[128],"used":[129],"docking":[131],"programs,":[132],"thereby":[133],"facilitating":[134],"streamlined":[136],"workflow":[137],"users.":[139],"available":[142],"at":[145,152],"https://github.com/carlssonlab/MolSanitizer":[146],"via":[148],"web":[150],"server":[151],"https://carlssonlabtools.icm.uu.se/molsani.":[153]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-10T00:00:00"}