{"id":"https://openalex.org/W4409157289","doi":"https://doi.org/10.1109/bibm62325.2024.10947607","title":"Protein Family Sequence Generation Through ProGen2 Fine-Tuning","display_name":"Protein Family Sequence Generation Through ProGen2 Fine-Tuning","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4409157289","doi":"https://doi.org/10.1109/bibm62325.2024.10947607"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10947607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10947607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","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/A5115832265","display_name":"Hugo Hrb\u00e1\u0148","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Hugo Hrb\u00e1\u0148","raw_affiliation_strings":["Charles University,Department of Software Engineering, Faculty of Mathematics and Physics,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University,Department of Software Engineering, Faculty of Mathematics and Physics,Prague,Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049617942","display_name":"David Hoksza","orcid":"https://orcid.org/0000-0003-4679-0557"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"David Hoksza","raw_affiliation_strings":["Charles University,Department of Software Engineering, Faculty of Mathematics and Physics,Prague,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University,Department of Software Engineering, Faculty of Mathematics and Physics,Prague,Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21424482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9453999996185303,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9453999996185303,"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/sequence","display_name":"Sequence (biology)","score":0.5856284499168396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5327112078666687},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12770816683769226},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11251884698867798}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5856284499168396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5327112078666687},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12770816683769226},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11251884698867798}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10947607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10947607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2069458148","https://openalex.org/W2130479394","https://openalex.org/W2950954328","https://openalex.org/W3095583226","https://openalex.org/W4327550249","https://openalex.org/W4388024559"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Proteins":[0],"are":[1],"biomolecules":[2],"involved":[3],"in":[4],"virtually":[5],"all":[6],"biological":[7,24,46],"processes,":[8],"making":[9],"the":[10,75,98,108],"design":[11],"of":[12,88],"novel":[13],"proteins":[14],"with":[15,66],"specific":[16,64],"functions":[17],"crucial":[18],"for":[19,31,59,85],"advancing":[20],"drug":[21],"development":[22],"and":[23,105],"research.":[25],"Large":[26],"protein":[27,51,77,89,94,115],"sequence":[28],"databases":[29],"allow":[30],"training":[32],"language":[33,38,52,78],"models":[34,53],"adapted":[35],"from":[36,91],"natural":[37],"processing,":[39],"treating":[40],"amino":[41],"acid":[42],"sequences":[43,65,90,100,116],"as":[44],"a":[45,55],"\u201clanguage\u201d.":[47],"However,":[48],"these":[49],"generative":[50],"lack":[54],"straightforward,":[56],"user-friendly":[57],"method":[58],"prompting":[60],"them":[61],"to":[62,112,121],"generate":[63,113],"desired":[67],"properties.":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"demonstrate":[73],"how":[74],"pre-trained":[76],"model":[79,109],"ProGen2":[80],"can":[81],"be":[82],"effectively":[83],"fine-tuned":[84],"controllable":[86],"generation":[87],"several":[92],"distinct":[93],"families.":[95],"We":[96],"validate":[97],"generated":[99],"using":[101],"various":[102],"in-silico":[103],"metrics":[104],"show":[106],"that":[107,117],"is":[110],"able":[111],"viable":[114],"exhibit":[118],"low":[119],"similarity":[120],"existing":[122],"proteins.":[123]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}