{"id":"https://openalex.org/W1976521702","doi":"https://doi.org/10.1089/cmb.2005.12.355","title":"Linear Regression Models for Solvent Accessibility Prediction in Proteins","display_name":"Linear Regression Models for Solvent Accessibility Prediction in Proteins","publication_year":2005,"publication_date":"2005-04-01","ids":{"openalex":"https://openalex.org/W1976521702","doi":"https://doi.org/10.1089/cmb.2005.12.355","mag":"1976521702","pmid":"https://pubmed.ncbi.nlm.nih.gov/15857247"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2005.12.355","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2005.12.355","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5034994947","display_name":"Michael Wagner","orcid":"https://orcid.org/0000-0003-3421-4763"},"institutions":[{"id":"https://openalex.org/I1285204247","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285204247"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Wagner","raw_affiliation_strings":["Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229","Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229, USA"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229","institution_ids":[]},{"raw_affiliation_string":"Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229, USA","institution_ids":["https://openalex.org/I1285204247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021471080","display_name":"Rafa\u0142 Adamczak","orcid":"https://orcid.org/0000-0002-0261-8184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafa\u2113 Adamczak","raw_affiliation_strings":["Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090468327","display_name":"Aleksey Porollo","orcid":"https://orcid.org/0000-0002-3202-5099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksey Porollo","raw_affiliation_strings":["Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229"],"affiliations":[{"raw_affiliation_string":"Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090178417","display_name":"Jarek Meller","orcid":"https://orcid.org/0000-0002-1162-8253"},"institutions":[{"id":"https://openalex.org/I3019271933","display_name":"Nicolaus Copernicus University","ror":"https://ror.org/0102mm775","country_code":"PL","type":"education","lineage":["https://openalex.org/I3019271933"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jaros\u2113aw Meller","raw_affiliation_strings":["Department of Informatics, Nicholas Copernicus University, 87-100 Toru\u0144, Poland","Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Nicholas Copernicus University, 87-100 Toru\u0144, Poland","institution_ids":["https://openalex.org/I3019271933"]},{"raw_affiliation_string":"Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034994947"],"corresponding_institution_ids":["https://openalex.org/I1285204247"],"apc_list":null,"apc_paid":null,"fwci":2.0921,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.85967678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"12","issue":"3","first_page":"355","last_page":"369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.9950000047683716,"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/support-vector-machine","display_name":"Support vector machine","score":0.7239733934402466},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.6211060285568237},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.566559374332428},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5242029428482056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.517171323299408},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4824817478656769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46771472692489624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4474508762359619},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.41679781675338745},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3929850161075592},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35550040006637573},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32916533946990967},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2758041024208069}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7239733934402466},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.6211060285568237},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.566559374332428},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5242029428482056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.517171323299408},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4824817478656769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46771472692489624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4474508762359619},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.41679781675338745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3929850161075592},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35550040006637573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32916533946990967},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2758041024208069}],"mesh":[{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012995","descriptor_name":"Solubility","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012997","descriptor_name":"Solvents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012997","descriptor_name":"Solvents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012997","descriptor_name":"Solvents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1089/cmb.2005.12.355","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2005.12.355","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:15857247","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15857247","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 computational biology : a journal of computational molecular cell biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1791679738","https://openalex.org/W1971747108","https://openalex.org/W1985204165","https://openalex.org/W2008708467","https://openalex.org/W2013136212","https://openalex.org/W2013945499","https://openalex.org/W2034852683","https://openalex.org/W2050625197","https://openalex.org/W2057289558","https://openalex.org/W2072649575","https://openalex.org/W2074732152","https://openalex.org/W2099886875","https://openalex.org/W2106116715","https://openalex.org/W2109553965","https://openalex.org/W2111705855","https://openalex.org/W2117121871","https://openalex.org/W2117519369","https://openalex.org/W2123957843","https://openalex.org/W2130479394","https://openalex.org/W2137259082","https://openalex.org/W2139582206","https://openalex.org/W2141885858","https://openalex.org/W2144667265","https://openalex.org/W2153187042","https://openalex.org/W2154106236","https://openalex.org/W2158714788","https://openalex.org/W2161628345","https://openalex.org/W2170962128","https://openalex.org/W4246395620","https://openalex.org/W4255847514"],"related_works":["https://openalex.org/W2550904580","https://openalex.org/W2610868774","https://openalex.org/W2092994918","https://openalex.org/W3216594821","https://openalex.org/W2390006526","https://openalex.org/W3215700490","https://openalex.org/W1915333409","https://openalex.org/W2393341384","https://openalex.org/W4289356671","https://openalex.org/W4363647291"],"abstract_inverted_index":{"The":[0,31],"relative":[1,29],"solvent":[2,21],"accessibility":[3],"(RSA)":[4],"of":[5,25,33,117,189,223,234,239,252],"an":[6],"amino":[7,40,81],"acid":[8,41,82],"residue":[9,27],"in":[10,28,187,303],"a":[11,15,48,61,79,139],"protein":[12,224,324],"structure":[13,325],"is":[14],"real":[16],"number":[17],"that":[18,238,249,283],"represents":[19],"the":[20,35,38,73,118,232,235,250,253,261,265,275,284],"exposed":[22],"surface":[23],"area":[24],"this":[26,163],"terms.":[30],"problem":[32],"predicting":[34],"RSA":[36,52,86,107,120,171,200,313],"from":[37],"primary":[39],"sequence":[42],"can":[43,269,300],"therefore":[44],"be":[45,91,94,270,301],"cast":[46,59],"as":[47,60,96,209,211,260],"regression":[49,111,168,197,206,241],"problem.":[50,63],"Nevertheless,":[51],"prediction":[53,108,172,190,201,276,314,326],"has":[54],"so":[55],"far":[56],"typically":[57],"been":[58,70],"classification":[62,74],"Consequently,":[64],"various":[65],"machine":[66],"learning":[67],"techniques":[68,112],"have":[69,101],"used":[71,129,302],"within":[72],"framework":[75],"to":[76,93,98,127,137,155,273,295,305,309,318],"predict":[77],"whether":[78],"given":[80],"exceeds":[83],"some":[84],"(arbitrary)":[85],"threshold":[87],"and":[88,121,157,183,226,242,264,286,298,321],"would":[89],"thus":[90,299],"predicted":[92],"\"exposed,\"":[95],"opposed":[97],"\"buried.\"":[99],"We":[100,281],"recently":[102],"developed":[103],"novel":[104],"methods":[105,151],"for":[106,170,199,278],"using":[109,202],"nonlinear":[110,296],"which":[113,173],"provide":[114,138],"accurate":[115,312],"estimates":[116],"real-valued":[119],"outperform":[122],"classification-based":[123],"approaches":[124,208],"with":[125,237,316],"respect":[126],"commonly":[128],"two-class":[130],"projections.":[131],"However,":[132],"while":[133],"their":[134],"performance":[135,233],"seems":[136],"significant":[140],"improvement":[141],"over":[142],"previously":[143],"published":[144],"approaches,":[145],"these":[146],"Neural":[147],"Network":[148],"(NN)":[149],"based":[150],"are":[152,174,184],"computationally":[153,175,287],"expensive":[154],"train":[156],"involve":[158,179],"several":[159,196],"thousand":[160],"parameters.":[161],"In":[162,192,245],"work,":[164],"we":[165,194,230,247],"develop":[166],"alternative":[167],"models":[169,198,297],"much":[176,288],"less":[177],"expensive,":[178],"orders-of-magnitude":[180],"fewer":[181],"parameters,":[182],"still":[185],"competitive":[186],"terms":[188],"quality.":[191],"particular,":[193,246],"investigate":[195],"linear":[203,213,291],"L1-support":[204],"vector":[205],"(SVR)":[207],"well":[210],"standard":[212],"least":[214],"squares":[215],"(LS)":[216],"regression.":[217],"Using":[218],"rigorously":[219],"derived":[220],"validation":[221],"sets":[222],"structures":[225],"extensive":[227],"cross-validation":[228],"analysis,":[229],"compare":[231],"SVR":[236,254,292],"LS":[240],"NN-based":[243],"methods.":[244,327],"show":[248],"flexibility":[251],"(as":[255],"encoded":[256],"by":[257],"metaparameters":[258],"such":[259],"error":[262,266],"insensitivity":[263],"penalization":[267],"terms)":[268],"very":[271],"beneficial":[272],"optimize":[274],"accuracy":[277],"buried":[279],"residues.":[280],"conclude":[282],"simple":[285],"more":[289,311],"efficient":[290],"performs":[293],"comparably":[294],"order":[304],"facilitate":[306],"further":[307],"attempts":[308],"design":[310],"methods,":[315],"applications":[317],"fold":[319],"recognition":[320],"de":[322],"novo":[323]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}