{"id":"https://openalex.org/W7130658430","doi":"https://doi.org/10.1186/s13321-025-01135-9","title":"PROTAC-Splitter: a machine learning framework for automated identification of PROTAC substructures","display_name":"PROTAC-Splitter: a machine learning framework for automated identification of PROTAC substructures","publication_year":2026,"publication_date":"2026-02-20","ids":{"openalex":"https://openalex.org/W7130658430","doi":"https://doi.org/10.1186/s13321-025-01135-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/41721433"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01135-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01135-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01135-9.pdf","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01135-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061274269","display_name":"Stefano Ribes","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Stefano Ribes","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052308625","display_name":"R Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ranxuan Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088070530","display_name":"T\u00e9lio Cropsal","orcid":"https://orcid.org/0009-0006-9040-5029"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"T\u00e9lio Cropsal","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126494879","display_name":"Anders K\u00e4llberg","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Anders K\u00e4llberg","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051401603","display_name":"Christian Tyrchan","orcid":"https://orcid.org/0000-0002-6470-984X"},"institutions":[{"id":"https://openalex.org/I4210109524","display_name":"AstraZeneca (Australia)","ror":"https://ror.org/018nw3344","country_code":"AU","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210109524"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christian Tyrchan","raw_affiliation_strings":["Medicinal Chemistry, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210109524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077542460","display_name":"Eva Nittinger","orcid":"https://orcid.org/0000-0001-7231-7996"},"institutions":[{"id":"https://openalex.org/I4210109524","display_name":"AstraZeneca (Australia)","ror":"https://ror.org/018nw3344","country_code":"AU","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210109524"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Eva Nittinger","raw_affiliation_strings":["Medicinal Chemistry, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Gothenburg, Sweden. eva.nittinger@astrazeneca.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Gothenburg, Sweden. eva.nittinger@astrazeneca.com","institution_ids":["https://openalex.org/I4210109524"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090993508","display_name":"Roc\u00edo Mercado","orcid":"https://orcid.org/0000-0002-6170-6088"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Roc\u00edo Mercado","raw_affiliation_strings":["Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden. rocio.mercado@chalmers.se"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Chalmersplatsen 1, 412 96, Gothenburg, Sweden. rocio.mercado@chalmers.se","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077542460","https://openalex.org/A5090993508"],"corresponding_institution_ids":["https://openalex.org/I4210109524","https://openalex.org/I66862912"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":9.8935,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97887501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12534","display_name":"Protein Degradation and Inhibitors","score":0.9627000093460083,"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"}},"topics":[{"id":"https://openalex.org/T12534","display_name":"Protein Degradation and Inhibitors","score":0.9627000093460083,"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"}},{"id":"https://openalex.org/T12820","display_name":"Chromatin Remodeling and Cancer","score":0.004600000102072954,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.0038999998942017555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6532999873161316},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5576000213623047},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.46540001034736633},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.4629000127315521},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865999937057495},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6044999957084656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C2779145975","wikidata":"https://www.wikidata.org/wiki/Q347690","display_name":"Workbench","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01135-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01135-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01135-9.pdf","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41721433","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41721433","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,"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":"Journal of cheminformatics","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:92d409889521464eb9cfbb081e737de8","is_oa":true,"landing_page_url":"https://doaj.org/article/92d409889521464eb9cfbb081e737de8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12924545","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12924545/","pdf_url":null,"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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01135-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01135-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01135-9.pdf","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"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/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"},{"id":"https://openalex.org/F4320321523","display_name":"Chalmers Tekniska H\u00f6gskola","ror":"https://ror.org/040wg7k59"},{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130658430.pdf","grobid_xml":"https://content.openalex.org/works/W7130658430.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2148143831","https://openalex.org/W2171707538","https://openalex.org/W2295598076","https://openalex.org/W3044640842","https://openalex.org/W3136546688","https://openalex.org/W4226159083","https://openalex.org/W4296128995","https://openalex.org/W4297632148","https://openalex.org/W4307362175","https://openalex.org/W4309447026","https://openalex.org/W4309650743","https://openalex.org/W4385245566","https://openalex.org/W4391248371","https://openalex.org/W4400441613","https://openalex.org/W4400616986","https://openalex.org/W4402170913","https://openalex.org/W4402926321","https://openalex.org/W4404174012","https://openalex.org/W4407277074","https://openalex.org/W4408509051","https://openalex.org/W4409784459"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Proteolysis-targeting":[1],"chimeras":[2],"(PROTACs)":[3],"are":[4],"heterobifunctional":[5],"molecules":[6],"composed":[7],"of":[8,21,61,216],"an":[9],"E3":[10],"ligase":[11],"ligand,":[12],"a":[13,16,19,53,73,98,103,183,221,234],"linker,":[14],"and":[15,29,37,43,70,102,115,156,208,243],"warhead":[17],"targeting":[18],"protein":[20],"interest.":[22],"Despite":[23],"their":[24],"modular":[25],"structure,":[26],"accurately":[27],"identifying":[28],"annotating":[30],"these":[31],"components":[32],"in":[33],"PROTACs":[34,118,142,227],"is":[35,244],"challenging":[36],"typically":[38],"relies":[39],"on":[40,111,131,138,160,167,173,206,210],"manual":[41],"curation":[42],"predefined":[44],"substructure":[45,96],"matching.":[46],"To":[47,64,178],"address":[48,65],"this,":[49],"we":[50,68,89,181,219],"developed":[51,90],"PROTAC-Splitter,":[52],"machine":[54],"learning":[55],"framework":[56],"designed":[57],"for":[58,94,186],"automated":[59,240],"annotation":[60],"PROTAC":[62,80,95,241],"substructures.":[63],"data":[66,114,133],"scarcity,":[67],"generated":[69],"openly":[71],"released":[72],"synthetic":[74],"dataset":[75],"containing":[76],"approximately":[77],"1.3":[78],"million":[79],"structures":[81],"with":[82,163],"annotated":[83],"ligand":[84],"splits.":[85],"Leveraging":[86],"this":[87],"dataset,":[88],"two":[91],"complementary":[92],"approaches":[93,110],"annotation:":[97],"Transformer-based":[99,124],"sequence-to-sequence":[100],"model":[101,125,151],"graph-based":[104],"XGBoost":[105,150],"model.":[106],"We":[107],"evaluated":[108],"both":[109,161,217],"held-out":[112],"public":[113,132,207],"structurally":[116,139],"novel":[117,140],"from":[119],"AstraZeneca\u2019s":[120],"proprietary":[121],"collection.":[122],"The":[123],"achieved":[126],"high":[127],"exact-match":[128,165],"accuracy":[129,159,166,203],"(86%)":[130],"but":[134,170],"dropped":[135],"significantly":[136],"(18%)":[137],"internal":[141,175,211],"due":[143],"to":[144,204,238],"occasional":[145],"hallucinations.":[146],"In":[147],"contrast,":[148],"the":[149,174,187,214],"can":[152],"ensure":[153],"chemical":[154,230],"validity":[155],"perfect":[157],"reassembly":[158,202],"sets,":[162],"lower":[164],"open-data":[168],"(42.2%)":[169],"comparable":[171],"performance":[172],"set":[176],"(23%).":[177],"improve":[179],"reliability,":[180],"implemented":[182],"wrapper":[184],"function":[185],"Transformer":[188],"(Transformer-":[189],"$$\\Delta$$":[190],"<mml:math":[191],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[192],"<mml:mi>\u0394</mml:mi>":[193],"</mml:math>":[194],"),":[195],"which":[196],"corrects":[197],"partial":[198],"prediction":[199],"errors,":[200],"raising":[201],"96%":[205],"70%":[209],"datasets.":[212],"Combining":[213],"strengths":[215],"models,":[218],"propose":[220],"hybrid":[222],"approach":[223],"that":[224],"reliably":[225],"annotates":[226],"across":[228],"diverse":[229],"spaces.":[231],"PROTAC-Splitter":[232],"provides":[233],"robust,":[235],"scalable":[236],"tool":[237],"facilitate":[239],"analysis":[242],"available":[245],"open-source":[246],"at":[247],"https://github.com/ribesstefano/PROTAC-Splitter":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2026-02-20T00:00:00"}