{"id":"https://openalex.org/W4382652848","doi":"https://doi.org/10.1021/acs.jcim.3c00144","title":"Augmenting Polymer Datasets by Iterative Rearrangement","display_name":"Augmenting Polymer Datasets by Iterative Rearrangement","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4382652848","doi":"https://doi.org/10.1021/acs.jcim.3c00144","pmid":"https://pubmed.ncbi.nlm.nih.gov/37390494"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00144","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00144","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/A5068032257","display_name":"Stanley Lo","orcid":"https://orcid.org/0000-0003-0278-5318"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Stanley Lo","raw_affiliation_strings":["Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, Ontario M5S 3H6, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0278-5318","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, Ontario M5S 3H6, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031911852","display_name":"Martin Seifrid","orcid":"https://orcid.org/0000-0001-5238-0058"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Seifrid","raw_affiliation_strings":["Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, Ontario M5S 3H6, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5238-0058","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, Ontario M5S 3H6, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094339899","display_name":"Th\u00e9ophile Gaudin","orcid":"https://orcid.org/0000-0003-3914-854X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CA","CH"],"is_corresponding":false,"raw_author_name":"Th\u00e9ophile Gaudin","raw_affiliation_strings":["Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, Ontario M5S 2E4, Canada","IBM Research Z\u00fcrich, R\u00fcschlikon, Z\u00fcrich 8803, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, Ontario M5S 2E4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"IBM Research Z\u00fcrich, R\u00fcschlikon, Z\u00fcrich 8803, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071495561","display_name":"Al\u00e1n Aspuru\u2010Guzik","orcid":"https://orcid.org/0000-0002-8277-4434"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Al\u00e1n Aspuru-Guzik","raw_affiliation_strings":["CIFAR Artificial Intelligence Research Chair, Vector Institute, Toronto, Ontario M5S 1M1, Canada","Department of Chemical Engineering and Applied Chemistry, University of Toronto, 200 College St., Toronto, Ontario M5S 3E5, Canada","Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, Ontario M5S 3H6, Canada","Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, Ontario M5S 2E4, Canada","Department of Materials Science and Engineering, University of Toronto, 184 College St., Toronto, Ontario M5S 3E4, Canada","Canadian Institute for Advanced Research (CIFAR), Toronto, Ontario M5S 1M1, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8277-4434","affiliations":[{"raw_affiliation_string":"CIFAR Artificial Intelligence Research Chair, Vector Institute, Toronto, Ontario M5S 1M1, Canada","institution_ids":["https://openalex.org/I109736498","https://openalex.org/I4210127509"]},{"raw_affiliation_string":"Department of Chemical Engineering and Applied Chemistry, University of Toronto, 200 College St., Toronto, Ontario M5S 3E5, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, Ontario M5S 3H6, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, Ontario M5S 2E4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Materials Science and Engineering, University of Toronto, 184 College St., Toronto, Ontario M5S 3E4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Canadian Institute for Advanced Research (CIFAR), Toronto, Ontario M5S 1M1, Canada","institution_ids":["https://openalex.org/I109736498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071495561"],"corresponding_institution_ids":["https://openalex.org/I109736498","https://openalex.org/I185261750","https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":1.5889,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.82345431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"63","issue":"14","first_page":"4266","last_page":"4276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994000196456909,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9810000061988831,"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/representation","display_name":"Representation (politics)","score":0.785047173500061},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.7197507619857788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062901258468628},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6895543336868286},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6797134876251221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115197896957397},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4528456926345825},{"id":"https://openalex.org/keywords/polymer","display_name":"Polymer","score":0.442689448595047},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3355908989906311},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09824368357658386}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.785047173500061},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.7197507619857788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062901258468628},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6895543336868286},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6797134876251221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115197896957397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4528456926345825},{"id":"https://openalex.org/C521977710","wikidata":"https://www.wikidata.org/wiki/Q81163","display_name":"Polymer","level":2,"score":0.442689448595047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3355908989906311},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09824368357658386},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011108","descriptor_name":"Polymers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011108","descriptor_name":"Polymers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011108","descriptor_name":"Polymers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.3c00144","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00144","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:37390494","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37390494","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":[],"awards":[{"id":"https://openalex.org/G3606353641","display_name":null,"funder_award_id":"509300","funder_id":"https://openalex.org/F4320334601","funder_display_name":"National Research Council Canada"}],"funders":[{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334601","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06"},{"id":"https://openalex.org/F4320334620","display_name":"Natural Resources Canada","ror":"https://ror.org/05hepy730"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1551909886","https://openalex.org/W1985258458","https://openalex.org/W1988037271","https://openalex.org/W1992985800","https://openalex.org/W1998577416","https://openalex.org/W2022476850","https://openalex.org/W2038702914","https://openalex.org/W2081709350","https://openalex.org/W2083224653","https://openalex.org/W2092368765","https://openalex.org/W2145578524","https://openalex.org/W2258866110","https://openalex.org/W2415372084","https://openalex.org/W2472085920","https://openalex.org/W2473190403","https://openalex.org/W2514794892","https://openalex.org/W2594183968","https://openalex.org/W2604296437","https://openalex.org/W2754122850","https://openalex.org/W2899070097","https://openalex.org/W2909063104","https://openalex.org/W2938625151","https://openalex.org/W2944851425","https://openalex.org/W2950128007","https://openalex.org/W2954996726","https://openalex.org/W2963784900","https://openalex.org/W2973074478","https://openalex.org/W2989615256","https://openalex.org/W2991006719","https://openalex.org/W2991541823","https://openalex.org/W2999847078","https://openalex.org/W3009321976","https://openalex.org/W3018875774","https://openalex.org/W3024033076","https://openalex.org/W3024761859","https://openalex.org/W3045928028","https://openalex.org/W3087318293","https://openalex.org/W3095106934","https://openalex.org/W3096386116","https://openalex.org/W3097513514","https://openalex.org/W3102659967","https://openalex.org/W3107551345","https://openalex.org/W3114168740","https://openalex.org/W3125983160","https://openalex.org/W3155755963","https://openalex.org/W3177828909","https://openalex.org/W3188589934","https://openalex.org/W3198212763","https://openalex.org/W3214987860","https://openalex.org/W4200608739","https://openalex.org/W4210810773","https://openalex.org/W4231045650","https://openalex.org/W4242133681","https://openalex.org/W4250998378","https://openalex.org/W4281619372","https://openalex.org/W4293232267","https://openalex.org/W4295312788","https://openalex.org/W4306252481","https://openalex.org/W4306809818","https://openalex.org/W4307975993","https://openalex.org/W4317215164","https://openalex.org/W6912727864"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2071516466","https://openalex.org/W2966686650","https://openalex.org/W2159790760"],"abstract_inverted_index":{"One":[0],"of":[1,19,29,71,77],"the":[2,17,27,47,52,69,75,114,121],"biggest":[3],"obstacles":[4],"to":[5,89,107,138],"successful":[6],"polymer":[7,42,84,122],"property":[8,103,116,140],"prediction":[9,104,141],"is":[10,60,117],"an":[11],"effective":[12],"representation":[13,49],"that":[14,59],"accurately":[15],"captures":[16],"sequence":[18,123],"repeat":[20],"units":[21],"in":[22,32,63,100],"a":[23,64],"polymer.":[24],"Motivated":[25],"by":[26,44,120],"success":[28],"data":[30,43,129],"augmentation":[31,94,130],"computer":[33],"vision":[34],"and":[35,86],"natural":[36],"language":[37],"processing,":[38],"we":[39],"explore":[40],"augmenting":[41],"iteratively":[45],"rearranging":[46],"molecular":[48,91,133],"while":[50],"preserving":[51],"correct":[53],"connectivity,":[54],"revealing":[55],"additional":[56],"substructural":[57],"information":[58,137],"not":[61,96],"present":[62],"single":[65],"representation.":[66],"We":[67],"evaluate":[68],"effects":[70],"this":[72,128],"technique":[73,131],"on":[74,82],"performance":[76,105],"machine":[78,101],"learning":[79,102],"models":[80],"trained":[81],"three":[83],"datasets":[85,112],"compare":[87],"them":[88],"common":[90],"representations.":[92,110],"Data":[93],"does":[95],"yield":[97],"significant":[98],"improvements":[99],"compared":[106],"equivalent":[108],"(non-augmented)":[109],"In":[111],"where":[113],"target":[115],"primarily":[118],"influenced":[119],"rather":[124],"than":[125],"experimental":[126],"parameters,":[127],"provides":[132],"embedding":[134],"with":[135],"more":[136],"improve":[139],"accuracy.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}