{"id":"https://openalex.org/W4214812055","doi":"https://doi.org/10.1093/bib/bbac108","title":"A tool for feature extraction from biological sequences","display_name":"A tool for feature extraction from biological sequences","publication_year":2022,"publication_date":"2022-03-04","ids":{"openalex":"https://openalex.org/W4214812055","doi":"https://doi.org/10.1093/bib/bbac108","pmid":"https://pubmed.ncbi.nlm.nih.gov/35383372"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac108","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac108","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5059419691","display_name":"Sare Amerifar","orcid":null},"institutions":[{"id":"https://openalex.org/I1516879","display_name":"Tarbiat Modares University","ror":"https://ror.org/03mwgfy56","country_code":"IR","type":"education","lineage":["https://openalex.org/I1516879"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Sare Amerifar","raw_affiliation_strings":["Bioinformatics, Tatbiat Modares University, Jalal Al Ahmad, 14115-111, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Bioinformatics, Tatbiat Modares University, Jalal Al Ahmad, 14115-111, Tehran, Iran","institution_ids":["https://openalex.org/I1516879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024991042","display_name":"Mahammad Norouzi","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mahammad Norouzi","raw_affiliation_strings":["Computer Science, Technical University of Darmstadt, Hochschulstr. 1, 64293, Hesse, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Science, Technical University of Darmstadt, Hochschulstr. 1, 64293, Hesse, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000230644","display_name":"Mahmoud Ghandi","orcid":"https://orcid.org/0000-0003-1897-2265"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahmoud Ghandi","raw_affiliation_strings":["Bioinformatics, Monte Rosa Therapeutics, Summer Street, 02210, Boston, United States"],"affiliations":[{"raw_affiliation_string":"Bioinformatics, Monte Rosa Therapeutics, Summer Street, 02210, Boston, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059419691"],"corresponding_institution_ids":["https://openalex.org/I1516879"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":1.2009,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.77251442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"23","issue":"3","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":0.9997000098228455,"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":0.9997000098228455,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7791436910629272},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7622398734092712},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5205191373825073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5050264000892639},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5021572113037109},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4993252754211426},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.4545944035053253},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.44345003366470337},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.436198890209198},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3723059594631195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35455024242401123},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34226274490356445},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.21276187896728516},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11000126600265503},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10651293396949768},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.10627931356430054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791436910629272},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7622398734092712},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5205191373825073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5050264000892639},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5021572113037109},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4993252754211426},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.4545944035053253},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.44345003366470337},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.436198890209198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3723059594631195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35455024242401123},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34226274490356445},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.21276187896728516},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11000126600265503},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10651293396949768},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.10627931356430054},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbac108","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac108","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35383372","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35383372","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1480577415","https://openalex.org/W1494484168","https://openalex.org/W1783180009","https://openalex.org/W1969956377","https://openalex.org/W1982267716","https://openalex.org/W1990212480","https://openalex.org/W1999212541","https://openalex.org/W2004146038","https://openalex.org/W2008767710","https://openalex.org/W2009113274","https://openalex.org/W2024213882","https://openalex.org/W2025282821","https://openalex.org/W2038681300","https://openalex.org/W2059971420","https://openalex.org/W2074231493","https://openalex.org/W2075715210","https://openalex.org/W2091374952","https://openalex.org/W2107247090","https://openalex.org/W2115228331","https://openalex.org/W2123525093","https://openalex.org/W2152339342","https://openalex.org/W2152800101","https://openalex.org/W2160257187","https://openalex.org/W2171464043","https://openalex.org/W2224020790","https://openalex.org/W2268267797","https://openalex.org/W2315928616","https://openalex.org/W2338148720","https://openalex.org/W2401640772","https://openalex.org/W2403896150","https://openalex.org/W2513786151","https://openalex.org/W2559275412","https://openalex.org/W2612935389","https://openalex.org/W2749122933","https://openalex.org/W2793168264","https://openalex.org/W2794498378","https://openalex.org/W2805467558","https://openalex.org/W2891797582","https://openalex.org/W2897958267","https://openalex.org/W2899616402","https://openalex.org/W2912803222","https://openalex.org/W2967960129","https://openalex.org/W2972223935","https://openalex.org/W2987349979","https://openalex.org/W2992029569","https://openalex.org/W3112376646","https://openalex.org/W3130238914","https://openalex.org/W3132291562","https://openalex.org/W3133088376","https://openalex.org/W3134163647","https://openalex.org/W3134745987","https://openalex.org/W3137264139","https://openalex.org/W3153629024","https://openalex.org/W3155024268","https://openalex.org/W3158849862","https://openalex.org/W3201039529","https://openalex.org/W3212684988","https://openalex.org/W4247001379","https://openalex.org/W4249920046","https://openalex.org/W6689416639","https://openalex.org/W6731016343","https://openalex.org/W6749494330","https://openalex.org/W6790282376","https://openalex.org/W6803495874","https://openalex.org/W6806115372"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"With":[0],"the":[1,22,44,90,103,123,148,160],"advances":[2],"in":[3,113,122,187],"sequencing":[4],"technologies,":[5],"a":[6,28,58,63,73,169,179,193],"huge":[7],"amount":[8,17],"of":[9,18,24,66,102,151,156,171,181,196],"biological":[10,80],"data":[11,19],"is":[12,20,128],"extracted":[13],"nowadays.":[14],"Analyzing":[15],"this":[16,54,69],"beyond":[21],"ability":[23],"human":[25],"beings,":[26],"creating":[27],"splendid":[29],"opportunity":[30],"for":[31,137,183],"machine":[32,93],"learning":[33,94],"methods":[34],"to":[35,92,139],"grow.":[36],"The":[37],"methods,":[38],"however,":[39],"are":[40,46,89],"practical":[41],"only":[42,109],"when":[43],"sequences":[45,81,141,161],"converted":[47],"into":[48,142],"feature":[49,143],"vectors.":[50,144],"Many":[51],"tools":[52],"target":[53],"task":[55],"including":[56],"iLearnPlus,":[57],"Python-based":[59],"tool":[60,75,107,127,153,191],"which":[61,120,133],"supports":[62,110],"rich":[64],"set":[65],"features.":[67],"In":[68],"paper,":[70],"we":[71,158,175],"propose":[72],"holistic":[74],"that":[76,96,155],"extracts":[77],"features":[78,88,112,119],"from":[79],"(i.e.":[82],"DNA,":[83],"RNA":[84],"and":[85],"Protein).":[86],"These":[87],"inputs":[91],"models":[95],"predict":[97],"properties,":[98],"structures":[99],"or":[100],"functions":[101],"input":[104],"sequences.":[105,185],"Our":[106],"not":[108],"all":[111],"iLearnPlus":[114,177],"but":[115],"also":[116],"30":[117],"additional":[118],"exist":[121],"literature.":[124],"Moreover,":[125],"our":[126,152,190],"based":[129],"on":[130],"R":[131],"language":[132],"makes":[134],"an":[135],"alternative":[136],"bioinformaticians":[138],"transform":[140,159],"We":[145,164],"have":[146],"compared":[147],"conversion":[149],"time":[150],"with":[154],"iLearnPlus:":[157],"much":[162],"faster.":[163],"convert":[165],"small":[166],"nucleotides":[167],"by":[168,178],"median":[170,180,194],"2.8X":[172],"faster,":[173],"while":[174],"outperform":[176],"6.3X":[182],"large":[184],"Finally,":[186],"amino":[188],"acids,":[189],"achieves":[192],"speedup":[195],"23.9X.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
