{"id":"https://openalex.org/W4416756970","doi":"https://doi.org/10.1186/s13321-025-01115-z","title":"How to build machine learning models able to extrapolate from standard to modified peptides","display_name":"How to build machine learning models able to extrapolate from standard to modified peptides","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416756970","doi":"https://doi.org/10.1186/s13321-025-01115-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/41310881"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01115-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01115-z","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13321-025-01115-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092249392","display_name":"Ra\u00fal Fern\u00e1ndez-D\u00edaz","orcid":"https://orcid.org/0000-0002-7383-6568"},"institutions":[{"id":"https://openalex.org/I4210145784","display_name":"IBM Research - Ireland","ror":"https://ror.org/04jnxr720","country_code":"IE","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145784"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Ra\u00fal Fern\u00e1ndez-D\u00edaz","raw_affiliation_strings":["Conway Institute for Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland. raul.fernandezdiaz@ucdconnect.ie","IBM Research, Dublin, Ireland. raul.fernandezdiaz@ucdconnect.ie","School of Medicine, University College Dublin, Dublin, Ireland. raul.fernandezdiaz@ucdconnect.ie","The Research Ireland Center for Research Training on Genomics Data Science, Galway, Ireland. raul.fernandezdiaz@ucdconnect.ie","IBM Research, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Conway Institute for Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland. raul.fernandezdiaz@ucdconnect.ie","institution_ids":[]},{"raw_affiliation_string":"IBM Research, Dublin, Ireland. raul.fernandezdiaz@ucdconnect.ie","institution_ids":[]},{"raw_affiliation_string":"School of Medicine, University College Dublin, Dublin, Ireland. raul.fernandezdiaz@ucdconnect.ie","institution_ids":[]},{"raw_affiliation_string":"The Research Ireland Center for Research Training on Genomics Data Science, Galway, Ireland. raul.fernandezdiaz@ucdconnect.ie","institution_ids":[]},{"raw_affiliation_string":"IBM Research, Dublin, Ireland","institution_ids":["https://openalex.org/I4210145784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041873604","display_name":"Rodrigo Ochoa","orcid":"https://orcid.org/0000-0003-0734-2196"},"institutions":[{"id":"https://openalex.org/I189090001","display_name":"Novo Nordisk (Denmark)","ror":"https://ror.org/0435rc536","country_code":"DK","type":"company","lineage":["https://openalex.org/I189090001","https://openalex.org/I2801134892","https://openalex.org/I4210159963"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rodrigo Ochoa","raw_affiliation_strings":["Novo Nordisk A/S, M\u00e5l\u00f8v, Denmark"],"affiliations":[{"raw_affiliation_string":"Novo Nordisk A/S, M\u00e5l\u00f8v, Denmark","institution_ids":["https://openalex.org/I189090001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044216056","display_name":"Thanh Lam Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145784","display_name":"IBM Research - Ireland","ror":"https://ror.org/04jnxr720","country_code":"IE","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145784"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Thanh Lam Hoang","raw_affiliation_strings":["IBM Research, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Dublin, Ireland","institution_ids":["https://openalex.org/I4210145784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030268064","display_name":"Vanessa L\u00f3pez","orcid":"https://orcid.org/0000-0002-0674-5324"},"institutions":[{"id":"https://openalex.org/I4210145784","display_name":"IBM Research - Ireland","ror":"https://ror.org/04jnxr720","country_code":"IE","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145784"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Vanessa Lopez","raw_affiliation_strings":["IBM Research, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Dublin, Ireland","institution_ids":["https://openalex.org/I4210145784"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004065601","display_name":"Denis C. Shields","orcid":"https://orcid.org/0000-0003-4015-2474"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I4210131847","display_name":"Genomics Medicine (Ireland)","ror":"https://ror.org/03c5c0a39","country_code":"IE","type":"company","lineage":["https://openalex.org/I4210131847"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Denis C. Shields","raw_affiliation_strings":["Conway Institute for Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland. denis.shields@ucd.ie","School of Medicine, University College Dublin, Dublin, Ireland. denis.shields@ucd.ie","The Research Ireland Center for Research Training on Genomics Data Science, Galway, Ireland. denis.shields@ucd.ie","The Research Ireland Center for Research Training on Genomics Data Science, Galway, Ireland","Conway Institute for Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Conway Institute for Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland. denis.shields@ucd.ie","institution_ids":[]},{"raw_affiliation_string":"School of Medicine, University College Dublin, Dublin, Ireland. denis.shields@ucd.ie","institution_ids":[]},{"raw_affiliation_string":"The Research Ireland Center for Research Training on Genomics Data Science, Galway, Ireland. denis.shields@ucd.ie","institution_ids":[]},{"raw_affiliation_string":"The Research Ireland Center for Research Training on Genomics Data Science, Galway, Ireland","institution_ids":["https://openalex.org/I4210131847"]},{"raw_affiliation_string":"Conway Institute for Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092249392"],"corresponding_institution_ids":["https://openalex.org/I4210145784"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35744497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":"185","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.35190001130104065,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.35190001130104065,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.2071000039577484,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.07460000365972519,"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/similarity","display_name":"Similarity (geometry)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5457000136375427},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.498199999332428},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4666000008583069},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.44830000400543213},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41269999742507935},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.33799999952316284},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.3303000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753000259399414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7117999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6700000166893005},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5899999737739563},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C24259465","wikidata":"https://www.wikidata.org/wiki/Q2272153","display_name":"Chemical similarity","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01115-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01115-z","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41310881","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41310881","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 cheminformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:fdd9059a51924198acbc79c3a3a2969d","is_oa":true,"landing_page_url":"https://doaj.org/article/fdd9059a51924198acbc79c3a3a2969d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 17, Iss 1, Pp 1-13 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12751563","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12751563/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01115-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01115-z","pdf_url":null,"source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6885446146","display_name":null,"funder_award_id":"18/CRT/6214","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1984994707","https://openalex.org/W1988037271","https://openalex.org/W1996423252","https://openalex.org/W2064440950","https://openalex.org/W2083224653","https://openalex.org/W2949676527","https://openalex.org/W2950954328","https://openalex.org/W3035302862","https://openalex.org/W3048439402","https://openalex.org/W3127297964","https://openalex.org/W3177500196","https://openalex.org/W3186118520","https://openalex.org/W4212959738","https://openalex.org/W4214618924","https://openalex.org/W4292361108","https://openalex.org/W4313015712","https://openalex.org/W4313485929","https://openalex.org/W4327694659","https://openalex.org/W4366819307","https://openalex.org/W4367727879","https://openalex.org/W4375856225","https://openalex.org/W4387255146","https://openalex.org/W4387687322","https://openalex.org/W4391431291","https://openalex.org/W4392344527","https://openalex.org/W4392885668","https://openalex.org/W4396854777","https://openalex.org/W4402585620","https://openalex.org/W4404153423","https://openalex.org/W4404204929","https://openalex.org/W4406002524","https://openalex.org/W4406075530","https://openalex.org/W4406136053","https://openalex.org/W4406182978","https://openalex.org/W4408280008","https://openalex.org/W4409502001","https://openalex.org/W4411730005"],"related_works":[],"abstract_inverted_index":{"Bioactive":[0],"peptides":[1,33],"are":[2,61,119],"an":[3,99],"important":[4],"class":[5],"of":[6,35,77,83,92],"natural":[7],"products":[8],"with":[9],"great":[10],"functional":[11],"versatility.":[12],"Chemical":[13],"modifications":[14],"can":[15],"improve":[16],"their":[17,20],"pharmacology,":[18],"yet":[19],"structural":[21],"diversity":[22],"presents":[23],"unique":[24],"challenges":[25],"for":[26,31,45,86],"computational":[27],"modeling.":[28],"Furthermore,":[29],"data":[30,60],"standard":[32,59],"(composed":[34],"the":[36,78,104,113,116,126],"20":[37],"canonical":[38],"amino":[39],"acids)":[40],"is":[41,98],"more":[42],"abundant":[43],"than":[44],"modified":[46,66],"ones.":[47],"Thus,":[48],"we":[49,71],"set":[50,118],"out":[51],"to":[52,58,65,124],"identify":[53],"whether":[54],"predictive":[55],"models":[56],"fitted":[57],"reliable":[62],"when":[63],"applied":[64],"peptides.":[67],"To":[68],"do":[69],"this,":[70],"first":[72],"considered":[73],"two":[74],"critical":[75],"aspects":[76],"modeling":[79],"problem,":[80],"namely,":[81],"choice":[82,91],"similarity":[84],"function":[85],"guiding":[87],"dataset":[88,96,105],"partitioning":[89,97],"and":[90,108],"molecular":[93],"representation.":[94],"Similarity-based":[95],"evaluation":[100],"technique":[101],"that":[102,112],"divides":[103],"into":[106],"train":[107],"test":[109,117],"subsets,":[110],"such":[111],"molecules":[114],"in":[115],"different":[120],"from":[121],"those":[122],"used":[123],"fit":[125],"model.":[127]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}