{"id":"https://openalex.org/W4289699056","doi":"https://doi.org/10.7287/peerj.preprints.27111v1","title":"SHsearch: a method for fast remote homology detection","display_name":"SHsearch: a method for fast remote homology detection","publication_year":2018,"publication_date":"2018-08-13","ids":{"openalex":"https://openalex.org/W4289699056","doi":"https://doi.org/10.7287/peerj.preprints.27111v1"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.27111v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27111v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7287/peerj.preprints.27111v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079006716","display_name":"Mohamed Baddar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mohamed Baddar","raw_affiliation_strings":["Data Science, Careem GmbH, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Data Science, Careem GmbH, Berlin, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079006716"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25136074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.984499990940094,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.984499990940094,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9822999835014343,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8728944063186646},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7480382323265076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6756739020347595},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.6747879981994629},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5348061323165894},{"id":"https://openalex.org/keywords/persistent-homology","display_name":"Persistent homology","score":0.5219413638114929},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.5139746069908142},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5026335716247559},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4222843050956726},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3907952606678009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3560293912887573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3396979868412018},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.28713396191596985},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.23059526085853577},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09523129463195801},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07520496845245361},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.07499334216117859},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06540811061859131}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8728944063186646},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7480382323265076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756739020347595},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.6747879981994629},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5348061323165894},{"id":"https://openalex.org/C2874115","wikidata":"https://www.wikidata.org/wiki/Q17099562","display_name":"Persistent homology","level":2,"score":0.5219413638114929},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.5139746069908142},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5026335716247559},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4222843050956726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3907952606678009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3560293912887573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3396979868412018},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.28713396191596985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.23059526085853577},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09523129463195801},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07520496845245361},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.07499334216117859},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06540811061859131},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.27111v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27111v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.27111v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.27111v1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2783918938","https://openalex.org/W2811338992","https://openalex.org/W2127279938","https://openalex.org/W2045575721","https://openalex.org/W2143599190","https://openalex.org/W1980160788","https://openalex.org/W2171474230","https://openalex.org/W2753093005","https://openalex.org/W1482324242"],"abstract_inverted_index":{"Remote":[0],"homology":[1,8,80,94],"detection":[2,95],"is":[3,16,59,84],"the":[4,110,124,128,136],"problem":[5,20],"of":[6,11,89,113,127,134,171],"detecting":[7,44],"in":[9,27,55,150,162],"cases":[10],"low":[12],"sequence":[13],"similarity.":[14],"It":[15],"a":[17,74,87,91,142],"hard":[18],"computational":[19],"with":[21,116,147,159,164],"no":[22],"approach":[23],"that":[24],"works":[25],"well":[26],"all":[28],"cases.":[29],"Methods":[30],"based":[31,97],"on":[32,98,122],"profile":[33,56,101],"hidden":[34],"Markov":[35],"models":[36],"(HMM)":[37],"often":[38],"exhibit":[39],"relatively":[40],"higher":[41],"sensitivity":[42,118,163],"for":[43,77,105],"remote":[45,78,92],"homologies":[46],"than":[47],"commonly":[48],"used":[49],"approaches.":[50],"However,":[51],"calculating":[52],"similarity":[53],"scores":[54],"HMM":[57],"methods":[58],"computationally":[60],"intensive":[61],"as":[62,86],"they":[63],"use":[64],"dynamic":[65],"programming":[66],"algorithms.":[67],"In":[68],"this":[69],"paper":[70],"we":[71],"introduce":[72],"SHsearch:":[73],"new":[75],"method":[76,83,96],"protein":[79,93],"detection.":[81],"Our":[82],"implemented":[85],"modification":[88,106],"HHsearch:":[90],"comparing":[99,123,135],"two":[100],"HMMs.":[102],"The":[103],"motivation":[104],"was":[107],"to":[108,166,175],"reduce":[109],"run":[111],"time":[112],"HHsearch":[114,146,167],"significantly":[115],"minimal":[117,148],"loss.":[119],"SHsearch":[120,140,155],"focuses":[121],"important":[125],"submodels":[126],"query":[129],"and":[130],"database":[131],"HMMs":[132],"instead":[133],"complete":[137],"models.":[138],"Hence,":[139],"achieves":[141],"significant":[143],"speedup":[144,158],"over":[145],"loss":[149,161],"sensitivity.":[151],"On":[152],"SCOP":[153],"1.63,":[154],"achieved":[156],"88X":[157],"8.2%":[160],"respect":[165],"at":[168],"error":[169],"rate":[170],"10%,":[172],"which":[173],"deemed":[174],"be":[176],"an":[177],"acceptable":[178],"tradeoff.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}