{"id":"https://openalex.org/W4379985112","doi":"https://doi.org/10.1109/access.2023.3284464","title":"RPPSP: A Robust and Precise Protein Solubility Predictor by Utilizing Novel Protein Sequence Encoder","display_name":"RPPSP: A Robust and Precise Protein Solubility Predictor by Utilizing Novel Protein Sequence Encoder","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4379985112","doi":"https://doi.org/10.1109/access.2023.3284464"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3284464","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3284464","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10147217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10147217.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011390265","display_name":"Faiza Mehmood","orcid":null},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Faiza Mehmood","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-3222-7424","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112227840","display_name":"Shazia Arshad","orcid":null},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Shazia Arshad","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080064006","display_name":"Muhammad Shoaib","orcid":"https://orcid.org/0000-0002-7327-9861"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Shoaib","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Lahore, Lahore, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011390265"],"corresponding_institution_ids":["https://openalex.org/I142732210"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.3721,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88693003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"59397","last_page":"59416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9911999702453613,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9887999892234802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/solubility","display_name":"Solubility","score":0.6524937748908997},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6523865461349487},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6438853740692139},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6156049966812134},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5834984183311462},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4530075788497925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44158506393432617},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43776530027389526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4303610324859619},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.42840924859046936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3406679034233093},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3242289423942566},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.20278307795524597},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1733919382095337},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10225504636764526}],"concepts":[{"id":"https://openalex.org/C155574463","wikidata":"https://www.wikidata.org/wiki/Q170731","display_name":"Solubility","level":2,"score":0.6524937748908997},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6523865461349487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438853740692139},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6156049966812134},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5834984183311462},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4530075788497925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44158506393432617},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43776530027389526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4303610324859619},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.42840924859046936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3406679034233093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3242289423942566},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.20278307795524597},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1733919382095337},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10225504636764526},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3284464","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3284464","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10147217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a37c0a45fe864df6965c3b7e6812bcf0","is_oa":true,"landing_page_url":"https://doaj.org/article/a37c0a45fe864df6965c3b7e6812bcf0","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":"IEEE Access, Vol 11, Pp 59397-59416 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3284464","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3284464","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10147217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379985112.pdf","grobid_xml":"https://content.openalex.org/works/W4379985112.grobid-xml"},"referenced_works_count":97,"referenced_works":["https://openalex.org/W5135654","https://openalex.org/W148376511","https://openalex.org/W1523829503","https://openalex.org/W1588724272","https://openalex.org/W1602803234","https://openalex.org/W1665229127","https://openalex.org/W1921523184","https://openalex.org/W1964574427","https://openalex.org/W1964940342","https://openalex.org/W1966548097","https://openalex.org/W1972516851","https://openalex.org/W1978734434","https://openalex.org/W1988146888","https://openalex.org/W1993282040","https://openalex.org/W1999212541","https://openalex.org/W2008767710","https://openalex.org/W2008968116","https://openalex.org/W2013701819","https://openalex.org/W2014201485","https://openalex.org/W2017526934","https://openalex.org/W2024970329","https://openalex.org/W2029369328","https://openalex.org/W2046842005","https://openalex.org/W2047672715","https://openalex.org/W2070980386","https://openalex.org/W2075644998","https://openalex.org/W2090256785","https://openalex.org/W2094403468","https://openalex.org/W2098740506","https://openalex.org/W2102592002","https://openalex.org/W2103083136","https://openalex.org/W2114358087","https://openalex.org/W2116595386","https://openalex.org/W2119246926","https://openalex.org/W2119331235","https://openalex.org/W2123525093","https://openalex.org/W2132292391","https://openalex.org/W2133458779","https://openalex.org/W2137433045","https://openalex.org/W2140356722","https://openalex.org/W2141062474","https://openalex.org/W2145957695","https://openalex.org/W2147863530","https://openalex.org/W2149653886","https://openalex.org/W2152705149","https://openalex.org/W2171533950","https://openalex.org/W2289965054","https://openalex.org/W2320049087","https://openalex.org/W2339546206","https://openalex.org/W2548536600","https://openalex.org/W2588978745","https://openalex.org/W2620185010","https://openalex.org/W2766578745","https://openalex.org/W2794004073","https://openalex.org/W2806146459","https://openalex.org/W2809902670","https://openalex.org/W2883534252","https://openalex.org/W2884715962","https://openalex.org/W2951433247","https://openalex.org/W2962915600","https://openalex.org/W2971668307","https://openalex.org/W2972223935","https://openalex.org/W2979588939","https://openalex.org/W2979986977","https://openalex.org/W2989133356","https://openalex.org/W2990589737","https://openalex.org/W2995514860","https://openalex.org/W2995997429","https://openalex.org/W2996089053","https://openalex.org/W3036344389","https://openalex.org/W3040078053","https://openalex.org/W3090711245","https://openalex.org/W3097457694","https://openalex.org/W3100730518","https://openalex.org/W3119780302","https://openalex.org/W3129073614","https://openalex.org/W3134163647","https://openalex.org/W3160518394","https://openalex.org/W3182224655","https://openalex.org/W3190020188","https://openalex.org/W3191161296","https://openalex.org/W3193416643","https://openalex.org/W3197939376","https://openalex.org/W3216325381","https://openalex.org/W4225724920","https://openalex.org/W4248350370","https://openalex.org/W4284691226","https://openalex.org/W4285165904","https://openalex.org/W4296564676","https://openalex.org/W4309314692","https://openalex.org/W4311860578","https://openalex.org/W4367599410","https://openalex.org/W6640185926","https://openalex.org/W6657779969","https://openalex.org/W6736221594","https://openalex.org/W6763868836","https://openalex.org/W6847187844"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1990608904","https://openalex.org/W2110523656","https://openalex.org/W1482209366"],"abstract_inverted_index":{"Protein":[0,47],"solubility":[1,48,65,209],"prediction":[2,49,66],"is":[3,53,237],"essential":[4],"to":[5,13,88,117],"understand":[6],"diverse":[7],"types":[8,112,142],"of":[9,17,24,32,63,90,113,131,135,143,161,215,230,234],"biological":[10],"processes":[11],"and":[12,26,43,57,67,93,120,148,157,163,182,194,219,225],"explore":[14],"the":[15,30,61],"impact":[16],"different":[18,73,141],"factors":[19],"(ionic":[20],"strength,":[21],"temperature,":[22],"PH":[23],"medium":[25],"electrostatic":[27],"repulsion)":[28],"on":[29],"productivity":[31],"proteins.":[33,122],"It":[34],"also":[35],"plays":[36],"an":[37],"important":[38,116],"role":[39],"in":[40,179,228],"disease":[41],"analysis":[42,160],"drug":[44],"development":[45],"processes.":[46],"through":[50],"experimental":[51],"approaches":[52],"time-consuming,":[54],"labour":[55],"intensive":[56],"error-prone.":[58],"To":[59],"empower":[60],"process":[62],"protein":[64,98,136,169,184,208],"facilitate":[68],"large":[69],"scale":[70],"analysis,":[71],"16":[72],"computational":[74],"predictors":[75,81,101,210],"have":[76,82],"been":[77],"proposed.":[78],"However,":[79],"these":[80],"low":[83],"predictive":[84],"performance":[85,159],"mainly":[86],"due":[87],"extraction":[89],"less":[91],"semantic":[92],"discriminative":[94,190],"features":[95],"from":[96],"raw":[97],"sequences.":[99],"Existing":[100],"either":[102],"extract":[103],"sequence":[104,170],"order":[105],"information":[106,114,144],"or":[107],"positional":[108],"information,":[109],"while":[110],"both":[111],"are":[115],"discriminate":[118],"soluble":[119,181,193],"insoluble":[121,183,195],"This":[123],"paper":[124],"presents":[125],"a":[126,154,212],"novel":[127],"encoder":[128,175,198],"CTAPAAC":[129],"capable":[130],"generating":[132],"statistical":[133,187],"representations":[134],"sequences":[137,185],"by":[138],"extracting":[139],"4":[140,151],"correlation,":[145],"distribution,":[146],"composition":[147],"transition.":[149],"Over":[150],"benchmark":[152],"datasets":[153,227],"comprehensive":[155],"intrinsic":[156],"extrinsic":[158],"proposed":[162,174,235],"14":[164],"most":[165],"widely":[166],"used":[167],"existing":[168,205],"encoders":[171],"reveals":[172],"that":[173],"has":[176],"more":[177],"potential":[178],"transforming":[180],"into":[186],"vectors":[188],"having":[189],"patterns":[191],"among":[192],"classes.":[196],"Proposed":[197],"along":[199],"with":[200,211],"random":[201],"forest":[202],"classifier":[203],"outperforms":[204],"best":[206],"performing":[207],"significant":[213],"margin":[214],"6%,":[216],"7%,":[217],"25%":[218],"10%":[220],"over":[221],"PSI:Biology,":[222],"E.coli,":[223],"price":[224],"Esol":[226],"terms":[229],"accuracy.":[231],"Source":[232],"code":[233],"predictor":[236],"publicly":[238],"available":[239],"at":[240],"<uri":[241],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[242],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Faiza-Mehmood/RPPSP</uri>":[243],".":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}