{"id":"https://openalex.org/W4390970101","doi":"https://doi.org/10.1109/bibm58861.2023.10385858","title":"Enhancing Protein Solubility Prediction through Pre-trained Language Models and Graph Convolutional Neural Networks","display_name":"Enhancing Protein Solubility Prediction through Pre-trained Language Models and Graph Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390970101","doi":"https://doi.org/10.1109/bibm58861.2023.10385858"},"language":"en","primary_location":{"id":"doi:10.1109/bibm58861.2023.10385858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm58861.2023.10385858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100343375","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0002-7887-3747"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Xinjiang University,School of Software,Urumqi,China","School of Software, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Software,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002981402","display_name":"Yurong Qian","orcid":"https://orcid.org/0000-0001-6564-4745"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurong Qian","raw_affiliation_strings":["Xinjiang University,School of Software,Urumqi,China","School of Software, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Software,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015986813","display_name":"Zhijian Huang","orcid":"https://orcid.org/0000-0003-1601-3802"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Huang","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering,Changsha,China","School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering,Changsha,China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102884329","display_name":"Xiaojun Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Xiao","raw_affiliation_strings":["Xinjiang University,School of Software,Urumqi,China","School of Software, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Software,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085608332","display_name":"Lei Deng","orcid":"https://orcid.org/0000-0003-2869-1619"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Deng","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering,Changsha,China","School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering,Changsha,China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"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":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9944999814033508,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9944999814033508,"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/T11124","display_name":"Protein purification and stability","score":0.988099992275238,"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":0.9787999987602234,"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/computer-science","display_name":"Computer science","score":0.6984652280807495},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5668387413024902},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5607478618621826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261880159378052},{"id":"https://openalex.org/keywords/solubility","display_name":"Solubility","score":0.5136896967887878},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.5032097697257996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47558915615081787},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.296149879693985},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16943404078483582},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1276974380016327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984652280807495},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5668387413024902},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5607478618621826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261880159378052},{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.5136896967887878},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.5032097697257996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47558915615081787},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.296149879693985},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16943404078483582},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1276974380016327},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm58861.2023.10385858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm58861.2023.10385858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W148376511","https://openalex.org/W1540355323","https://openalex.org/W1588724272","https://openalex.org/W1970898345","https://openalex.org/W1976731339","https://openalex.org/W1993282040","https://openalex.org/W2051210555","https://openalex.org/W2075644998","https://openalex.org/W2076048958","https://openalex.org/W2080187647","https://openalex.org/W2094535327","https://openalex.org/W2096495474","https://openalex.org/W2119246926","https://openalex.org/W2133458779","https://openalex.org/W2147209844","https://openalex.org/W2158714788","https://openalex.org/W2171533950","https://openalex.org/W2557595285","https://openalex.org/W2607268717","https://openalex.org/W2611281850","https://openalex.org/W2611685413","https://openalex.org/W2752782242","https://openalex.org/W2766578745","https://openalex.org/W2794004073","https://openalex.org/W2808950571","https://openalex.org/W3129073614","https://openalex.org/W3146944767","https://openalex.org/W3166925323","https://openalex.org/W3216325381","https://openalex.org/W4225724920","https://openalex.org/W4239510810","https://openalex.org/W4289653737"],"related_works":["https://openalex.org/W1990608904","https://openalex.org/W1539400370","https://openalex.org/W2007219878","https://openalex.org/W1934224411","https://openalex.org/W1561807720","https://openalex.org/W2005109573","https://openalex.org/W1564792705","https://openalex.org/W2393951301","https://openalex.org/W2080187647","https://openalex.org/W2312308847"],"abstract_inverted_index":{"Achieving":[0],"optimal":[1],"protein":[2,20,39,71,77,84,92,101,156,167],"solubility":[3,21,72,157],"is":[4,119],"pivotal":[5],"for":[6,18,37,90,154],"efficient":[7],"high-throughput":[8],"purification,":[9],"especially":[10],"in":[11,22,61,185],"industrial":[12],"settings.":[13],"However,":[14],"conventional":[15],"experimental":[16],"techniques":[17,96],"assessing":[19],"such":[23],"contexts":[24],"are":[25,35,50,97],"not":[26],"only":[27],"costly":[28],"but":[29],"also":[30],"time-intensive.":[31],"Currently,":[32],"numerous":[33],"methods":[34],"available":[36],"predicting":[38],"solubility,":[40],"yet":[41],"their":[42],"effectiveness":[43],"remains":[44],"limited.":[45],"Most":[46],"of":[47,110,131,151,165],"these":[48,64],"approaches":[49],"predominantly":[51],"sequence-based,":[52],"failing":[53],"to":[54,82,99,189],"harness":[55],"the":[56,88,108,111,129,152,163],"invaluable":[57],"structural":[58,133],"insights":[59],"inherent":[60],"proteins.":[62,136],"Addressing":[63],"limitations,":[65],"we":[66],"introduce":[67],"PPSol,":[68],"an":[69],"innovative":[70],"prediction":[73],"methodology.":[74],"Operating":[75],"on":[76],"sequences,":[78],"PPSol":[79,176],"employs":[80],"ESM2":[81],"predict":[83,100],"contact":[85],"maps,":[86],"forming":[87],"basis":[89],"constructing":[91],"graphs.":[93],"Subsequently,":[94],"well-established":[95],"employed":[98],"feature":[102],"representations":[103],"as":[104],"node":[105],"features,":[106],"including":[107],"utilization":[109],"Position-Specific":[112],"Scoring":[113],"Matrix":[114],"(PSSM).":[115],"The":[116],"resulting":[117],"graph":[118,123],"fed":[120],"into":[121,148],"a":[122,181],"convolutional":[124],"neural":[125],"network":[126],"(GCN),":[127],"enabling":[128],"acquisition":[130],"spatial":[132],"information":[134],"from":[135],"Concurrently,":[137],"ESM2-generated":[138],"features":[139],"undergo":[140],"dimensional":[141],"reduction":[142],"via":[143],"fully":[144],"connected":[145],"layers,":[146],"integrating":[147],"every":[149],"layer":[150],"GCN":[153],"precise":[155],"prediction.":[158],"Our":[159],"approach":[160],"excels":[161],"through":[162],"fusion":[164],"pre-trained":[166],"language":[168],"models":[169],"and":[170],"GCNs,":[171],"surpassing":[172],"existing":[173],"methodologies.":[174],"Notably,":[175],"attains":[177],"state-of-the-art":[178],"performance,":[179],"showcasing":[180],"remarkable":[182],"2.8%":[183],"enhancement":[184],"AUROC":[186],"performance":[187],"com-pared":[188],"prior":[190],"strategies.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}