{"id":"https://openalex.org/W4409762646","doi":"https://doi.org/10.1021/acs.jcim.5c00205","title":"COLOR: A Compositional Linear Operation-Based Representation of Protein Sequences for Identification of Monomer Contributions to Properties","display_name":"COLOR: A Compositional Linear Operation-Based Representation of Protein Sequences for Identification of Monomer Contributions to Properties","publication_year":2025,"publication_date":"2025-04-24","ids":{"openalex":"https://openalex.org/W4409762646","doi":"https://doi.org/10.1021/acs.jcim.5c00205","pmid":"https://pubmed.ncbi.nlm.nih.gov/40272990"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00205","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00205","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","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/A5101484748","display_name":"Akash Pandey","orcid":"https://orcid.org/0009-0003-5324-8667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akash Pandey","raw_affiliation_strings":["Department of Mechanical Engineering","Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering","institution_ids":[]},{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344439","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-4653-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Department of Mechanical Engineering","Northwestern University"],"raw_orcid":"https://orcid.org/0000-0002-4653-7124","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering","institution_ids":[]},{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014744105","display_name":"Sinan Keten","orcid":"https://orcid.org/0000-0003-2203-1425"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sinan Keten","raw_affiliation_strings":["Department of Civil and Environmental Engineering","Department of Mechanical Engineering","Northwestern University"],"raw_orcid":"https://orcid.org/0000-0003-2203-1425","affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering","institution_ids":[]},{"raw_affiliation_string":"Department of Mechanical Engineering","institution_ids":[]},{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5014744105"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4604,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8055157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"65","issue":"9","first_page":"4320","last_page":"4333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9986000061035156,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9986000061035156,"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":0.9973999857902527,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9926999807357788,"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/monomer","display_name":"Monomer","score":0.7759909629821777},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7029123306274414},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6804499626159668},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5023043155670166},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.4676641523838043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42521244287490845},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3803336024284363},{"id":"https://openalex.org/keywords/polymer-science","display_name":"Polymer science","score":0.3374723792076111},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.16885361075401306},{"id":"https://openalex.org/keywords/polymer","display_name":"Polymer","score":0.1649136245250702},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09874248504638672},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.09305712580680847},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0684874951839447}],"concepts":[{"id":"https://openalex.org/C166940927","wikidata":"https://www.wikidata.org/wiki/Q178827","display_name":"Monomer","level":3,"score":0.7759909629821777},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7029123306274414},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6804499626159668},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5023043155670166},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.4676641523838043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42521244287490845},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3803336024284363},{"id":"https://openalex.org/C126348684","wikidata":"https://www.wikidata.org/wiki/Q3456979","display_name":"Polymer science","level":1,"score":0.3374723792076111},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.16885361075401306},{"id":"https://openalex.org/C521977710","wikidata":"https://www.wikidata.org/wiki/Q81163","display_name":"Polymer","level":2,"score":0.1649136245250702},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09874248504638672},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.09305712580680847},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0684874951839447},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c00205","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00205","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:40272990","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40272990","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G2376289361","display_name":null,"funder_award_id":"DMR-2308691","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"}],"funders":[{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W1491063910","https://openalex.org/W1864150816","https://openalex.org/W1969012077","https://openalex.org/W1975147762","https://openalex.org/W1975304761","https://openalex.org/W1976005460","https://openalex.org/W1977872596","https://openalex.org/W1989362683","https://openalex.org/W1996685148","https://openalex.org/W1999919945","https://openalex.org/W2015470526","https://openalex.org/W2042182257","https://openalex.org/W2057021995","https://openalex.org/W2058206198","https://openalex.org/W2062798855","https://openalex.org/W2064675550","https://openalex.org/W2066106355","https://openalex.org/W2092845657","https://openalex.org/W2124236598","https://openalex.org/W2160075959","https://openalex.org/W2168901333","https://openalex.org/W2272574296","https://openalex.org/W2465481521","https://openalex.org/W2472351724","https://openalex.org/W2612690371","https://openalex.org/W2729090457","https://openalex.org/W2892113269","https://openalex.org/W2899771611","https://openalex.org/W2910382351","https://openalex.org/W2911872747","https://openalex.org/W2913423296","https://openalex.org/W2939880928","https://openalex.org/W2950768109","https://openalex.org/W2962858109","https://openalex.org/W2970726176","https://openalex.org/W2977379019","https://openalex.org/W3014805132","https://openalex.org/W3027325047","https://openalex.org/W3033341870","https://openalex.org/W3037888463","https://openalex.org/W3093687066","https://openalex.org/W3098839135","https://openalex.org/W3117081956","https://openalex.org/W3118749273","https://openalex.org/W3119780302","https://openalex.org/W3131648425","https://openalex.org/W3135156311","https://openalex.org/W3164046276","https://openalex.org/W3168767448","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3186261494","https://openalex.org/W3203588026","https://openalex.org/W3206995700","https://openalex.org/W3208147779","https://openalex.org/W3209685337","https://openalex.org/W3209986690","https://openalex.org/W4205773061","https://openalex.org/W4206060008","https://openalex.org/W4210738256","https://openalex.org/W4223644783","https://openalex.org/W4281399757","https://openalex.org/W4281551093","https://openalex.org/W4281610211","https://openalex.org/W4283012069","https://openalex.org/W4286721853","https://openalex.org/W4288436665","https://openalex.org/W4292296492","https://openalex.org/W4296806433","https://openalex.org/W4304820604","https://openalex.org/W4308211947","https://openalex.org/W4310895557","https://openalex.org/W4311970063","https://openalex.org/W4312129273","https://openalex.org/W4312222866","https://openalex.org/W4317433395","https://openalex.org/W4321350922","https://openalex.org/W4321502832","https://openalex.org/W4327550249","https://openalex.org/W4365513331","https://openalex.org/W4366262984","https://openalex.org/W4383483391","https://openalex.org/W4385576706","https://openalex.org/W4385858237","https://openalex.org/W4387951124","https://openalex.org/W4388773681","https://openalex.org/W4389538269","https://openalex.org/W4393849074","https://openalex.org/W4396514423","https://openalex.org/W4396721167","https://openalex.org/W4396760140","https://openalex.org/W4399013224","https://openalex.org/W4399020156","https://openalex.org/W4401844424","https://openalex.org/W4403064295","https://openalex.org/W4404585832","https://openalex.org/W4405194283"],"related_works":["https://openalex.org/W2357692583","https://openalex.org/W2045488530","https://openalex.org/W4387781933","https://openalex.org/W2045468340","https://openalex.org/W2374513464","https://openalex.org/W1979677112","https://openalex.org/W2011621065","https://openalex.org/W2912217925","https://openalex.org/W760974036","https://openalex.org/W2036222533"],"abstract_inverted_index":{"The":[0],"properties":[1,162],"of":[2,39,54,62,129,163,216],"biological":[3],"materials":[4],"like":[5],"proteins":[6],"and":[7,82,109,141,170,181,190,196],"nucleic":[8],"acids":[9],"are":[10,92,202],"largely":[11],"determined":[12],"by":[13,133],"their":[14],"primary":[15],"sequence.":[16],"Certain":[17],"segments":[18],"in":[19,56,70,76,139,199,206,219],"the":[20,37,52,60,134,179,214],"sequence":[21],"strongly":[22],"influence":[23],"specific":[24],"functions,":[25],"but":[26],"identifying":[27,71],"these":[28,57,90,116],"segments,":[29],"or":[30],"so-called":[31],"motifs,":[32],"is":[33],"challenging":[34],"due":[35],"to":[36,65,95,209],"complexity":[38],"sequential":[40],"data.":[41],"While":[42],"deep":[43],"learning":[44],"(DL)":[45],"models":[46,58],"can":[47],"accurately":[48],"capture":[49],"sequence\u2013property":[50],"relationships,":[51],"degree":[53],"nonlinearity":[55],"limits":[59],"assessment":[61],"monomer":[63],"contributions":[64],"a":[66,120,148],"property\u2500a":[67],"critical":[68,186],"step":[69],"key":[72],"motifs.":[73],"Recent":[74],"advances":[75],"explainable":[77],"AI":[78],"(XAI)":[79],"offer":[80],"attention":[81],"gradient-based":[83],"methods":[84,91],"for":[85,154,223],"estimating":[86],"monomeric":[87,130],"contributions.":[88,131],"However,":[89],"primarily":[93],"applied":[94],"classification":[96],"tasks,":[97],"such":[98],"as":[99],"binding":[100],"site":[101],"identification,":[102],"where":[103],"they":[104],"achieve":[105],"limited":[106],"accuracy":[107],"(40\u201345%)":[108],"rely":[110],"on":[111,157],"qualitative":[112],"evaluations.":[113],"To":[114],"address":[115],"limitations,":[117],"we":[118,146],"introduce":[119],"DL":[121],"model":[122,173,218],"with":[123],"interpretable":[124],"steps,":[125],"enabling":[126],"direct":[127],"tracing":[128],"Inspired":[132],"masking":[135],"technique":[136],"commonly":[137],"used":[138],"vision":[140],"natural":[142],"language":[143],"processing":[144],"domains,":[145],"propose":[147],"new":[149],"metric":[150],"(":[151],"I":[152],")":[153],"quantitative":[155],"analysis":[156],"datasets":[158],"mainly":[159],"containing":[160],"distinct":[161],"anticancer":[164],"peptides":[165,168],"(ACP),":[166],"antimicrobial":[167],"(AMP),":[169],"collagen.":[171],"Our":[172],"exhibits":[174],"22%":[175],"higher":[176],"explainability":[177],"than":[178],"gradient":[180],"attention-based":[182],"state-of-the-art":[183],"models,":[184],"recognizes":[185],"motifs":[187,198],"(RRR,":[188],"RRI,":[189],"RSS)":[191],"that":[192,201],"significantly":[193],"destabilize":[194],"ACPs,":[195],"identifies":[197],"AMPs":[200],"50%":[203],"more":[204],"effective":[205],"converting":[207],"non-AMPs":[208],"AMPs.":[210],"These":[211],"findings":[212],"highlight":[213],"potential":[215],"our":[217],"guiding":[220],"mutation":[221],"strategies":[222],"designing":[224],"protein-based":[225],"biomaterials.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}