{"id":"https://openalex.org/W7225835380","doi":"https://doi.org/10.26434/chemrxiv.15011954/v1","title":"pKasso: Accurate and accessible prediction of small-molecule protonation states","display_name":"pKasso: Accurate and accessible prediction of small-molecule protonation states","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225835380","doi":"https://doi.org/10.26434/chemrxiv.15011954/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15011954/v1","doi":"https://doi.org/10.26434/chemrxiv.15011954/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011954/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011954/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.15011954/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016674669","display_name":"S\u00f6ren von B\u00fclow","orcid":"https://orcid.org/0000-0001-7125-5973","observed_orcids":["https://orcid.org/0000-0001-7125-5973"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00f6ren von B\u00fclow","raw_affiliation_strings":["Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE"],"raw_orcid":"https://orcid.org/0000-0001-7125-5973","affiliations":[{"raw_affiliation_string":"Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029568273","display_name":"Candide Champion","orcid":"https://orcid.org/0000-0001-6982-1569","observed_orcids":["https://orcid.org/0000-0001-6982-1569"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Candide Champion","raw_affiliation_strings":["Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE"],"raw_orcid":"https://orcid.org/0000-0001-6982-1569","affiliations":[{"raw_affiliation_string":"Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008081293","display_name":"Gogulan Karunanithy","orcid":"https://orcid.org/0000-0002-8072-5911","observed_orcids":["https://orcid.org/0000-0002-8072-5911"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gogulan Karunanithy","raw_affiliation_strings":["Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE"],"raw_orcid":"https://orcid.org/0000-0002-8072-5911","affiliations":[{"raw_affiliation_string":"Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056600397","display_name":"Gabriella T. Heller","orcid":"https://orcid.org/0000-0002-5672-0467","observed_orcids":["https://orcid.org/0000-0002-5672-0467"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gabriella T. Heller","raw_affiliation_strings":["Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE","Department of Structural and Molecular Biology, Division of Biosciences","University College London"],"raw_orcid":"https://orcid.org/0000-0002-5672-0467","affiliations":[{"raw_affiliation_string":"Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE","institution_ids":[]},{"raw_affiliation_string":"Department of Structural and Molecular Biology, Division of Biosciences","institution_ids":[]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052200585","display_name":"Thomas L\u00f6hr","orcid":"https://orcid.org/0000-0003-2969-810X","observed_orcids":["https://orcid.org/0000-0003-2969-810X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas L\u00f6hr","raw_affiliation_strings":["Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE"],"raw_orcid":"https://orcid.org/0000-0003-2969-810X","affiliations":[{"raw_affiliation_string":"Bind Research, Apex, 1 Tribeca Walk, London, UK, NW1 0QE","institution_ids":[]}]}],"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":0.9965999722480774,"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":0.9965999722480774,"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":0.0017999999690800905,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0005000000237487257,"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":[],"concepts":[{"id":"https://openalex.org/C30095370","wikidata":"https://www.wikidata.org/wiki/Q899488","display_name":"Protonation","level":3,"score":0.8210999965667725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666100025177002},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6291999816894531},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6133999824523926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5112000107765198},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.34860000014305115},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15011954/v1","doi":"https://doi.org/10.26434/chemrxiv.15011954/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011954/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011954/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.15011954/v1","doi":"https://doi.org/10.26434/chemrxiv.15011954/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011954/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011954/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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225835380.pdf","grobid_xml":"https://content.openalex.org/works/W7225835380.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1971849220","https://openalex.org/W2003655883","https://openalex.org/W2042678771","https://openalex.org/W2047245810","https://openalex.org/W2058583339","https://openalex.org/W2076407822","https://openalex.org/W2079601010","https://openalex.org/W2086806820","https://openalex.org/W2096541451","https://openalex.org/W2801073898","https://openalex.org/W2886715180","https://openalex.org/W3006469265","https://openalex.org/W3006560560","https://openalex.org/W3047663514","https://openalex.org/W3157403564","https://openalex.org/W3181755904","https://openalex.org/W4281847108","https://openalex.org/W4308931182","https://openalex.org/W4362677501","https://openalex.org/W4399327027","https://openalex.org/W4400734433","https://openalex.org/W4404529425","https://openalex.org/W4416667942","https://openalex.org/W7151081315","https://openalex.org/W7155495211","https://openalex.org/W7215049079"],"related_works":[],"abstract_inverted_index":{"The":[0],"protonation":[1,14,93],"states":[2,15],"of":[3,87,140],"molecules":[4],"are":[5],"tightly":[6],"linked":[7],"to":[8,82],"their":[9,108,134],"physicochemical":[10],"properties.":[11],"Accurately":[12],"predicting":[13],"is":[16,166],"therefore":[17],"important":[18],"for":[19],"applications":[20],"such":[21],"as":[22,136,168],"docking-based":[23],"virtual":[24],"screening":[25],"in":[26],"drug":[27],"discovery.":[28],"Modern":[29],"machine-learning":[30],"models":[31,50,102,131],"can":[32,51,64,122],"predict":[33],"molecular":[34],"p":[35,98,115,127],"K":[36,99,116,128],"a":[37,100,117,129,137,169,175,182],"values":[38],"with":[39,156],"good":[40],"accuracy,":[41],"but":[42,63],"obtaining":[43],"pH-dependent":[44,84],"protonation-state":[45,85],"ensembles":[46,86],"from":[47,125],"available":[48,167],"open-source":[49,80],"cause":[52],"substantial":[53,66],"installation":[54],"and":[55,78,104,106,113,132,162,181],"workflow":[56],"overhead.":[57],"Commercial":[58],"tools":[59],"provide":[60],"convenient":[61],"alternatives":[62],"entail":[65],"licensing":[67],"costs.":[68],"We":[69,143],"here":[70],"present":[71],"pKasso,":[72],"an":[73],"accurate,":[74],"fast,":[75],"accessible,":[76],"extensible,":[77],"easy-to-use":[79],"package":[81],"compute":[83],"small":[88],"molecules.":[89],"pKasso":[90,121,145,159],"enumerates":[91],"relevant":[92],"microstates,":[94],"integrates":[95],"the":[96],"existing":[97],"-prediction":[101,130],"MolGpKa":[103],"Uni-pKa,":[105],"converts":[107],"predictions":[109,124],"into":[110],"microstate":[111],"populations":[112],"macroscopic":[114],"values.":[118],"In":[119],"addition,":[120],"combine":[123],"multiple":[126],"report":[133],"disagreement":[135],"qualitative":[138],"indicator":[139],"predictive":[141],"uncertainty.":[142],"evaluate":[144],"on":[146],"six":[147],"benchmark":[148],"datasets,":[149],"where":[150],"it":[151],"achieves":[152],"prediction":[153],"accuracy":[154],"competitive":[155],"state-of-the-art":[157],"models.":[158],"supports":[160],"single-molecule":[161],"batch":[163],"workflows.":[164],"It":[165],"web":[170],"server":[171],"(":[172,185],"tools.bindresearch.org/pkasso":[173],"),":[174],"Python":[176],"library":[177],"(pip":[178],"install":[179],"pkasso),":[180],"command-line":[183],"interface":[184],"github.com/bindresearch/pkasso":[186],").":[187]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}