{"id":"https://openalex.org/W4416239659","doi":"https://doi.org/10.1109/jbhi.2025.3631538","title":"Applications of Large Language Models and Prompt Optimization for Knowledge Extraction From Biological Pathway Figures","display_name":"Applications of Large Language Models and Prompt Optimization for Knowledge Extraction From Biological Pathway Figures","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416239659","doi":"https://doi.org/10.1109/jbhi.2025.3631538","pmid":"https://pubmed.ncbi.nlm.nih.gov/41231698"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3631538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3631538","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13015812/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103942638","display_name":"Muhammad Azam","orcid":"https://orcid.org/0000-0002-6847-6449"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhammad Azam","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103082007","display_name":"Shuai Zeng","orcid":"https://orcid.org/0000-0001-7632-427X"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Zeng","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120449845","display_name":"Hasanain Aldihis","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasanain Aldihis","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060329217","display_name":"Mihail Popescu","orcid":"https://orcid.org/0000-0002-6145-8096"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihail Popescu","raw_affiliation_strings":["Department of Biomedical Informatics, Biostatistics and Medical Epidemiology, and the School of Medicine, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Biostatistics and Medical Epidemiology, and the School of Medicine, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082428303","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0002-4809-0514"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science and the Bond Life Sciences Center, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103942638"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27695707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"2","first_page":"1680","last_page":"1692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.26109999418258667,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.26109999418258667,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.24770000576972961,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.09449999779462814,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6287999749183655},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48890000581741333},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4578999876976013},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44519999623298645},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.3919000029563904},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3912000060081482},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.37709999084472656},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.36660000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750999927520752},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892000198364258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.576200008392334},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4578999876976013},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3711000084877014},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jbhi.2025.3631538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3631538","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:41231698","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41231698","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":"IEEE journal of biomedical and health informatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13015812","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13015812/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE J Biomed Health Inform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:13015812","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13015812/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE J Biomed Health Inform","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2051689038","https://openalex.org/W2081556416","https://openalex.org/W2106144115","https://openalex.org/W2108598243","https://openalex.org/W2150026213","https://openalex.org/W2155254562","https://openalex.org/W2618530766","https://openalex.org/W2885240937","https://openalex.org/W2908201961","https://openalex.org/W2911436281","https://openalex.org/W2982574415","https://openalex.org/W3111471029","https://openalex.org/W3125884253","https://openalex.org/W3134138028","https://openalex.org/W3136501774","https://openalex.org/W4205730624","https://openalex.org/W4225597912","https://openalex.org/W4295951577","https://openalex.org/W4307575433","https://openalex.org/W4309224528","https://openalex.org/W4313525421","https://openalex.org/W4368275356","https://openalex.org/W4385574139","https://openalex.org/W4386346728","https://openalex.org/W4389520756","https://openalex.org/W4393906047","https://openalex.org/W4398775037","https://openalex.org/W4400851854","https://openalex.org/W4401290054","https://openalex.org/W4402193259","https://openalex.org/W4402480400","https://openalex.org/W4402897195","https://openalex.org/W4405025785","https://openalex.org/W4405669265","https://openalex.org/W4405786429","https://openalex.org/W4405825568","https://openalex.org/W4406261944","https://openalex.org/W4408503864","https://openalex.org/W4408954544","https://openalex.org/W4409186581","https://openalex.org/W4409361716","https://openalex.org/W4410032048","https://openalex.org/W4410617089"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,190,200,230],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"demonstrated":[8],"remarkable":[9],"capabilities":[10],"for":[11,72,197,211,218],"image":[12],"comprehension.":[13],"This":[14],"study":[15],"aims":[16],"to":[17,53,69],"automate":[18],"and":[19,33,64,82,105,129,138,144,174,193,215,225],"enhance":[20],"the":[21,47,55,212],"extraction":[22,91],"of":[23,40,57,102,110,123,127,133,142,221],"gene":[24,84],"interactions":[25],"from":[26,46],"biological":[27,49],"pathway":[28,44],"images":[29],"by":[30,136,167],"integrating":[31],"LLMs":[32],"a":[34,121,125,208,216],"Genetic":[35],"Algorithm":[36],"(GA).":[37],"A":[38],"dataset":[39],"200":[41],"tumor":[42],"signaling":[43],"figures":[45],"recent":[48],"literature":[50],"was":[51,77],"employed":[52],"assess":[54],"performance":[56,76],"four":[58],"AI":[59,228],"chatbots:":[60],"GPT-4oV,":[61],"Claude-3.5V,":[62],"Gemini-1.5V,":[63],"Llama-3.2V,":[65],"with":[66,96,140,150,160],"GA":[67],"used":[68],"optimize":[70],"prompts":[71,88],"each":[73],"model.":[74],"Model":[75],"evaluated":[78],"on":[79,240],"both":[80],"directional":[81,153],"non-directional":[83,114],"relationship":[85],"extraction.":[86],"GA-optimized":[87],"significantly":[89],"improved":[90],"accuracies":[92],"across":[93],"all":[94,156],"LLMs,":[95],"GPT":[97],"4oV":[98],"achieving":[99,107],"an":[100,108,130],"F1-score":[101,109],"0.645":[103],"(\u00b10.055)":[104],"Llama-3.2V":[106,137,168],"0.616":[111],"(\u00b10.068).":[112],"For":[113],"interactions,":[115],"GPT-4oV":[116,161],"outperformed":[117],"other":[118],"models,":[119],"reaching":[120],"precision":[122],"0.805,":[124],"recall":[126],"0.695,":[128],"F1":[131],"score":[132],"0.757,":[134],"followed":[135,166],"Claude-3.5V":[139,171],"F1-scores":[141],"0.702":[143],"0.697,":[145],"respectively,":[146],"while":[147],"Gemini-1.5V":[148,175],"lagged":[149],"0.612.":[151],"In":[152],"interaction":[154],"predictions,":[155],"models":[157,224],"performed":[158],"lower,":[159],"leading":[162],"at":[163,169,172,176],"0.687":[164],"F1-score,":[165],"0.656,":[170],"0.641,":[173],"0.573.":[177],"While":[178],"these":[179,205],"results":[180],"demonstrate":[181],"substantial":[182],"improvements":[183],"over":[184],"traditional":[185],"OCR-based":[186],"approaches,":[187],"further":[188],"advances":[189],"model":[191],"accuracy":[192],"explainability":[194],"are":[195],"needed":[196],"widespread":[198],"adoption":[199],"critical":[201],"biomedical":[202,231],"applications.":[203],"Nevertheless,":[204],"findings":[206],"provide":[207],"valuable":[209],"benchmark":[210],"research":[213],"community":[214],"foundation":[217],"future":[219],"development":[220],"specialized,":[222],"fine-tuned":[223],"scalable":[226],"multimodal":[227],"frameworks":[229],"data":[232],"analysis.":[233],"The":[234],"source":[235],"code":[236],"is":[237],"publicly":[238],"available":[239],"https://github.com/Muh-aza/LLM_GPV.":[241]},"counts_by_year":[],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-11-13T00:00:00"}