{"id":"https://openalex.org/W7212283287","doi":"https://doi.org/10.26434/chemrxiv.15008687/v1","title":"Automatic Text-fishing, Unification, and Normalization Application in Python (aTUNApy): a tool to build molecular databases","display_name":"Automatic Text-fishing, Unification, and Normalization Application in Python (aTUNApy): a tool to build molecular databases","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7212283287","doi":"https://doi.org/10.26434/chemrxiv.15008687/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008687/v1","doi":"https://doi.org/10.26434/chemrxiv.15008687/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008687/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008687/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.15008687/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067427751","display_name":"Aylin Del Moral\u2010Morales","orcid":"https://orcid.org/0000-0003-3985-628X","observed_orcids":["https://orcid.org/0000-0003-3985-628X"]},"institutions":[{"id":"https://openalex.org/I200362191","display_name":"Universidad Aut\u00f3noma Metropolitana","ror":"https://ror.org/02kta5139","country_code":"MX","type":"education","lineage":["https://openalex.org/I200362191"]},{"id":"https://openalex.org/I8961855","display_name":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25","country_code":"MX","type":"education","lineage":["https://openalex.org/I8961855"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Aylin Del Moral Morales","raw_affiliation_strings":["1 Grupo de Investigaci\u00f3n DIFACQUIM, Departamento de Farmacia, Facultad de Qu\u00edmica","Ciencias Naturales","Universidad Aut\u00f3noma Metropolitana-Cuajimalpa (UAM-C)","Universidad Nacional Aut\u00f3noma de M\u00e9xico"],"raw_orcid":"https://orcid.org/0000-0003-3985-628X","affiliations":[{"raw_affiliation_string":"1 Grupo de Investigaci\u00f3n DIFACQUIM, Departamento de Farmacia, Facultad de Qu\u00edmica","institution_ids":[]},{"raw_affiliation_string":"Ciencias Naturales","institution_ids":[]},{"raw_affiliation_string":"Universidad Aut\u00f3noma Metropolitana-Cuajimalpa (UAM-C)","institution_ids":["https://openalex.org/I200362191"]},{"raw_affiliation_string":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","institution_ids":["https://openalex.org/I8961855"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086421148","display_name":"Jos\u00e9 L. Medina\u2010Franco","orcid":"https://orcid.org/0000-0003-4940-1107","observed_orcids":["https://orcid.org/0000-0003-4940-1107"]},"institutions":[{"id":"https://openalex.org/I8961855","display_name":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25","country_code":"MX","type":"education","lineage":["https://openalex.org/I8961855"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L. Medina-Franco","raw_affiliation_strings":["1 Grupo de Investigaci\u00f3n DIFACQUIM, Departamento de Farmacia, Facultad de Qu\u00edmica","Universidad Nacional Aut\u00f3noma de M\u00e9xico"],"raw_orcid":"https://orcid.org/0000-0003-4940-1107","affiliations":[{"raw_affiliation_string":"1 Grupo de Investigaci\u00f3n DIFACQUIM, Departamento de Farmacia, Facultad de Qu\u00edmica","institution_ids":[]},{"raw_affiliation_string":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","institution_ids":["https://openalex.org/I8961855"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.015399999916553497,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0008999999845400453,"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":[{"id":"https://openalex.org/keywords/chemical-information-extraction","display_name":"chemical information extraction","score":0.6140000224113464},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6940000057220459},{"id":"https://openalex.org/keywords/molecular-databases","display_name":"molecular databases","score":0.6439999938011169},{"id":"https://openalex.org/keywords/pubmed-abstracts","display_name":"PubMed abstracts","score":0.7329999804496765},{"id":"https://openalex.org/keywords/dietary-compounds","display_name":"dietary compounds","score":0.621999979019165},{"id":"https://openalex.org/keywords/epigenetic-effects","display_name":"epigenetic effects","score":0.9490000009536743},{"id":"https://openalex.org/keywords/llm-hallucination","display_name":"LLM hallucination","score":0.675000011920929},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.4390000104904175}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.8238000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699000239372253},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6891999840736389},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.42149999737739563},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2779980791","wikidata":"https://www.wikidata.org/wiki/Q1789476","display_name":"Bibliographic database","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.31679999828338623},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2984717058","wikidata":"https://www.wikidata.org/wiki/Q1789476","display_name":"Reference database","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C176734034","wikidata":"https://www.wikidata.org/wiki/Q259432","display_name":"Worksheet","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2778473407","wikidata":"https://www.wikidata.org/wiki/Q1459574","display_name":"Compendium","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008687/v1","doi":"https://doi.org/10.26434/chemrxiv.15008687/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008687/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008687/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.15008687/v1","doi":"https://doi.org/10.26434/chemrxiv.15008687/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008687/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008687/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/W7212283287.pdf","grobid_xml":"https://content.openalex.org/works/W7212283287.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1976892175","https://openalex.org/W2122709242","https://openalex.org/W2136794542","https://openalex.org/W2523785361","https://openalex.org/W2909063104","https://openalex.org/W3007260111","https://openalex.org/W3112129603","https://openalex.org/W4236951833","https://openalex.org/W4391836235","https://openalex.org/W4399130081","https://openalex.org/W4399442007","https://openalex.org/W4399714295","https://openalex.org/W4399803256","https://openalex.org/W4404107838","https://openalex.org/W4404225840","https://openalex.org/W4404511389","https://openalex.org/W4405590246","https://openalex.org/W4412654017","https://openalex.org/W4415356872","https://openalex.org/W7130653306","https://openalex.org/W7133221954","https://openalex.org/W7221121450"],"related_works":["https://openalex.org/W6931264825","https://openalex.org/W4205886257","https://openalex.org/W7027839274","https://openalex.org/W6893004536","https://openalex.org/W7104443750","https://openalex.org/W2523785361","https://openalex.org/W7067802510","https://openalex.org/W4412007538","https://openalex.org/W3137481621","https://openalex.org/W4414886726"],"abstract_inverted_index":{"The":[0],"construction":[1],"and":[2,23,37,63,88,112,152,188],"maintenance":[3],"of":[4,21,52,124,172,190,197],"chemical":[5],"databases":[6],"from":[7,55,186],"the":[8,137,153],"scientific":[9],"literature":[10],"remain":[11],"labor-intensive,":[12],"largely":[13],"because":[14],"relevant":[15],"information":[16,54],"is":[17],"dispersed":[18],"across":[19,205],"thousands":[20],"publications":[22],"compounds":[24,200],"are":[25,107],"reported":[26,202],"under":[27],"inconsistent":[28],"nomenclature.":[29],"Here":[30],"we":[31,180],"present":[32],"aTUNApy":[33,68,182],"(automatic":[34],"Text-fishing,":[35],"Unification,":[36],"Normalization":[38],"Application":[39],"in":[40],"Python),":[41],"an":[42],"open-source":[43],"tool":[44],"that":[45],"couples":[46],"large":[47],"language":[48],"model":[49],"(LLM)-based":[50],"extraction":[51],"compound":[53,76],"PubMed":[56,187],"abstracts":[57],"with":[58,66,79,201],"nomenclature":[59],"harmonization":[60],"through":[61],"PubChem":[62,95],"SMILES":[64],"standardization":[65],"RDKit.":[67],"retrieves":[69],"articles":[70,185],"for":[71],"a":[72,93,100,119,163,195],"user-defined":[73],"query,":[74],"extracts":[75],"names":[77],"together":[78],"user-specified":[80],"attributes":[81],"such":[82],"as":[83],"bioactivity,":[84],"mechanism":[85],"or":[86,170],"source,":[87],"maps":[89],"each":[90],"mention":[91],"to":[92,168,176,183,192],"unique":[94,133],"identifier,":[96],"collapsing":[97],"synonyms":[98],"onto":[99],"single":[101],"canonical":[102],"entry.":[103],"Four":[104],"LLM":[105],"families":[106],"supported:":[108],"GPT,":[109],"Claude,":[110],"LLaMA":[111],"Gemini.":[113],"We":[114],"benchmarked":[115],"all":[116],"four":[117],"against":[118],"manually":[120],"curated":[121],"reference":[122],"set":[123],"507":[125],"articles,":[126],"including":[127],"100":[128],"negative":[129],"controls,":[130],"covering":[131],"148":[132],"compounds.":[134],"Claude":[135],"achieved":[136],"highest":[138],"performance":[139],"(precision":[140],"0.98,":[141],"recall":[142],"0.95,":[143],"F1":[144],"0.97),":[145],"while":[146],"Gemini":[147],"reached":[148],"comparable":[149],"precision":[150],"(0.98)":[151],"lowest":[154],"hallucination":[155],"rate":[156],"(0.2%)":[157],"at":[158],"no":[159],"API":[160],"cost,":[161],"reducing":[162],"five-day":[164],"manual":[165],"curation":[166],"task":[167],"minutes":[169],"hours":[171],"automated":[173],"processing.":[174],"Finally,":[175],"demonstrate":[177],"end-to-end":[178],"utility,":[179],"applied":[181],"8,273":[184],"Web":[189],"Science":[191],"build":[193],"NutriEpiDB,":[194],"database":[196],"653":[198],"dietary":[199],"epigenetic":[203],"effects":[204],"917":[206],"food":[207],"sources.":[208]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-12T00:00:00"}