{"id":"https://openalex.org/W7215938972","doi":"https://doi.org/10.48550/arxiv.2610.01663","title":"pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows","display_name":"pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7215938972","doi":"https://doi.org/10.48550/arxiv.2610.01663"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01663","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01663","pdf_url":"https://arxiv.org/pdf/2610.01663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.01663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055918149","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0002-2715-5278","observed_orcids":["https://orcid.org/0000-0002-2715-5278"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Tong","raw_affiliation_strings":["Department of Computer and Information Science , University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science , University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204268","display_name":"Maximilian Holsman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Holsman, Maximilian","raw_affiliation_strings":["Department of Computer Science , Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154881549","display_name":"Lin Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Lin","raw_affiliation_strings":["Department of Bioengineering , University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering , University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016342562","display_name":"Pranam Chatterjee","orcid":"https://orcid.org/0000-0003-3957-8478","observed_orcids":["https://orcid.org/0000-0003-3957-8478"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chatterjee, Pranam","raw_affiliation_strings":["Department of Bioengineering , University of Pennsylvania","Department of Computer and Information Science , University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering , University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Computer and Information Science , University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.2939000129699707,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.2939000129699707,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.12790000438690186,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.09910000115633011,"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/multi-objective-optimization","display_name":"multi-objective optimization","score":0.8650000095367432},{"id":"https://openalex.org/keywords/feasibility-constraints","display_name":"feasibility constraints","score":0.671999990940094},{"id":"https://openalex.org/keywords/doob-h-transform","display_name":"Doob h-transform","score":0.9049999713897705},{"id":"https://openalex.org/keywords/protein-sequence-design","display_name":"protein sequence design","score":0.47600001096725464},{"id":"https://openalex.org/keywords/gfp-variants","display_name":"GFP variants","score":0.4959999918937683},{"id":"https://openalex.org/keywords/peptide-binders","display_name":"peptide binders","score":0.8199999928474426},{"id":"https://openalex.org/keywords/peptidomimetics","display_name":"peptidomimetics","score":0.9950000047683716},{"id":"https://openalex.org/keywords/drug-properties","display_name":"drug properties","score":0.33000001311302185},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987000107765198},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C62064638","wikidata":"https://www.wikidata.org/wiki/Q553878","display_name":"Design for manufacturability","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41260001063346863},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C144501496","wikidata":"https://www.wikidata.org/wiki/Q5533489","display_name":"Genome editing","level":4,"score":0.4027000069618225},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C142613039","wikidata":"https://www.wikidata.org/wiki/Q272983","display_name":"Green fluorescent protein","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C124790011","wikidata":"https://www.wikidata.org/wiki/Q2069797","display_name":"Peptidomimetic","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C98108389","wikidata":"https://www.wikidata.org/wiki/Q412563","display_name":"CRISPR","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C70636015","wikidata":"https://www.wikidata.org/wiki/Q4300350","display_name":"Molecular biophysics","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C9418097","wikidata":"https://www.wikidata.org/wiki/Q440681","display_name":"Directed evolution","level":4,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01663","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01663","pdf_url":"https://arxiv.org/pdf/2610.01663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.01663","doi":"https://doi.org/10.48550/arxiv.2610.01663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01663","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.01663","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01663","pdf_url":"https://arxiv.org/pdf/2610.01663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215938972.pdf","grobid_xml":"https://content.openalex.org/works/W7215938972.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W3093934881","https://openalex.org/W4396570182","https://openalex.org/W4415337901","https://openalex.org/W4416045826","https://openalex.org/W4416159325","https://openalex.org/W4417258187","https://openalex.org/W7084421079","https://openalex.org/W7128404100","https://openalex.org/W7139143455","https://openalex.org/W7160509743"],"related_works":["https://openalex.org/W7084421079","https://openalex.org/W4387100361","https://openalex.org/W6948219166","https://openalex.org/W4414588140","https://openalex.org/W4385784138","https://openalex.org/W7197004320","https://openalex.org/W7162654593","https://openalex.org/W4312272300","https://openalex.org/W7160946611","https://openalex.org/W7135167556"],"abstract_inverted_index":{"Biomolecular":[0],"therapeutics":[1],"often":[2],"start":[3],"from":[4],"known":[5],"sequences":[6,191],"and":[7,19,34,82,143],"require":[8],"targeted":[9],"editing":[10,36,188],"to":[11],"improve":[12],"multiple":[13],"properties":[14,154],"while":[15,67,131,139],"satisfying":[16],"hard":[17,32,156],"biochemical":[18],"manufacturability":[20],"constraints.":[21,157],"However,":[22],"existing":[23],"generative":[24],"methods":[25],"do":[26],"not":[27],"jointly":[28],"support":[29],"multi-objective":[30],"optimization,":[31],"feasibility,":[33],"sequence":[35],"in":[37,171,192],"discrete,":[38,193],"variable-length":[39,194],"biological":[40],"spaces.":[41,195],"In":[42,158],"this":[43,99],"work,":[44],"we":[45,102],"introduce":[46],"Pareto-Constrained":[47],"Molecule":[48],"Editing":[49],"(pCoMole),":[50],"a":[51,60,73,89],"framework":[52],"built":[53],"on":[54],"discrete":[55],"flow":[56],"matching":[57],"that":[58,150],"steers":[59],"pre-trained":[61],"Edit":[62],"Flow":[63],"toward":[64],"user-specified":[65],"preferences":[66],"enforcing":[68],"terminal":[69,75],"feasibility.":[70],"pCoMole":[71,127,184],"defines":[72],"feasibility-gated":[74],"distribution":[76],"using":[77,108],"an":[78,117],"augmented":[79],"Tchebycheff":[80],"utility":[81],"realizes":[83],"the":[84,93,104],"resulting":[85],"preference":[86,123],"tilt":[87],"through":[88],"Doob-h":[90],"transform":[91],"of":[92,189],"underlying":[94],"edit":[95],"process.":[96],"To":[97],"make":[98],"construction":[100],"practical,":[101],"approximate":[103],"required":[105],"harmonic":[106],"function":[107],"short":[109,148],"Monte":[110],"Carlo":[111],"rollouts":[112],"over":[113],"candidate":[114],"edits,":[115],"yielding":[116],"efficient":[118],"guided":[119],"editor":[120],"with":[121,177],"provable":[122],"consistency.":[124],"We":[125],"validate":[126],"by":[128],"shrinking":[129],"GFP":[130],"retaining":[132],"fluorescence-related":[133],"properties,":[134],"shortening":[135],"diverse":[136],"Cas9":[137],"orthologs":[138],"preserving":[140],"PAM":[141],"specificity,":[142],"compressing":[144],"peptide":[145],"binders":[146],"into":[147],"peptidomimetics":[149],"optimize":[151],"seven":[152],"drug-related":[153],"under":[155],"wet":[159],"lab":[160],"testing,":[161],"two":[162,181],"229-residue":[163],"pCoMole-designed":[164],"eGFP":[165],"variants":[166],"retained":[167],"clear":[168],"green":[169],"fluorescence":[170],"BL21":[172],"cells":[173],"after":[174],"10":[175],"deletions,":[176],"either":[178],"one":[179],"or":[180],"substitutions.":[182],"Together,":[183],"enables":[185],"constraint-aware,":[186],"Pareto-aligned":[187],"biomolecular":[190]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}
