{"id":"https://openalex.org/W7213454987","doi":"https://doi.org/10.64898/2026.09.11.750664","title":"ML4SD: Leveraging Machine Learning and High-Throughput Search Algorithms for an Iterative Growth-Coupled Design Innovation","display_name":"ML4SD: Leveraging Machine Learning and High-Throughput Search Algorithms for an Iterative Growth-Coupled Design Innovation","publication_year":2026,"publication_date":"2026-09-16","ids":{"openalex":"https://openalex.org/W7213454987","doi":"https://doi.org/10.64898/2026.09.11.750664"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.11.750664","doi":"https://doi.org/10.64898/2026.09.11.750664","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.11.750664","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/16/2026.09.11.750664.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/16/2026.09.11.750664.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087949732","display_name":"\u00c1lvaro Gargantilla-Becerra","orcid":"https://orcid.org/0000-0003-0429-2365","observed_orcids":["https://orcid.org/0000-0003-0429-2365"]},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alvaro Garantilla Becerra","raw_affiliation_strings":["Systems Biotechnology Group, Department of Systems Biology, Centro Nacional de Biotecnolog\u00eda, CSIC, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0429-2365","affiliations":[{"raw_affiliation_string":"Systems Biotechnology Group, Department of Systems Biology, Centro Nacional de Biotecnolog\u00eda, CSIC, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081652637","display_name":"Juan Nogales","orcid":"https://orcid.org/0000-0002-4961-0833","observed_orcids":["https://orcid.org/0000-0002-4961-0833"]},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Juan Nogales","raw_affiliation_strings":["CNB DNA Biofoundry (CNBio), CSIC, Madrid, Spain","Interdisciplinary Platform for Sustainable Plastics towards a Circular Economy-Spanish National Research Council (SusPlast-CSIC), Madrid, Spain","Systems Biotechnology Group, Department of Systems Biology, Centro Nacional de Biotecnolog\u00eda, CSIC, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-4961-0833","affiliations":[{"raw_affiliation_string":"CNB DNA Biofoundry (CNBio), CSIC, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]},{"raw_affiliation_string":"Interdisciplinary Platform for Sustainable Plastics towards a Circular Economy-Spanish National Research Council (SusPlast-CSIC), Madrid, Spain","institution_ids":["https://openalex.org/I134820265"]},{"raw_affiliation_string":"Systems Biotechnology Group, Department of Systems Biology, Centro Nacional de Biotecnolog\u00eda, CSIC, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081652637"],"corresponding_institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776"],"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":1.0,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":1.0,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.0,"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/T11798","display_name":"Optimal Experimental Design Methods","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.8209999799728394},{"id":"https://openalex.org/keywords/design-build-test-learn","display_name":"design-build-test-learn","score":0.7979999780654907},{"id":"https://openalex.org/keywords/genome-scale-metabolic-models","display_name":"genome-scale metabolic models","score":0.9319999814033508},{"id":"https://openalex.org/keywords/p-hydroxybenzoic-acid","display_name":"p-hydroxybenzoic acid","score":0.8700000047683716},{"id":"https://openalex.org/keywords/lignin-valorization","display_name":"lignin valorization","score":0.7960000038146973},{"id":"https://openalex.org/keywords/tca-cycle-flux","display_name":"TCA cycle flux","score":0.7379999756813049},{"id":"https://openalex.org/keywords/acetyl-coa","display_name":"acetyl-CoA","score":0.8769999742507935},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.699999988079071},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.4909999966621399},{"id":"https://openalex.org/keywords/biomanufacturing","display_name":"bioproduction","score":0.6949999928474426}],"concepts":[{"id":"https://openalex.org/C2775893736","wikidata":"https://www.wikidata.org/wiki/Q25324110","display_name":"Biomanufacturing","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5954999923706055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.4447999894618988},{"id":"https://openalex.org/C6350086","wikidata":"https://www.wikidata.org/wiki/Q6822347","display_name":"Metabolic engineering","level":3,"score":0.38440001010894775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C183696295","wikidata":"https://www.wikidata.org/wiki/Q2487696","display_name":"Biochemical engineering","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C2780543182","wikidata":"https://www.wikidata.org/wiki/Q2738168","display_name":"Pseudomonas putida","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C2781468064","wikidata":"https://www.wikidata.org/wiki/Q1267117","display_name":"Lead time","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2982969694","wikidata":"https://www.wikidata.org/wiki/Q7247859","display_name":"Production efficiency","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C77957584","wikidata":"https://www.wikidata.org/wiki/Q1133550","display_name":"Gene knockout","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C2780301381","wikidata":"https://www.wikidata.org/wiki/Q864683","display_name":"Biorefinery","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C2993678126","wikidata":"https://www.wikidata.org/wiki/Q167751","display_name":"Carbon flux","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.11.750664","doi":"https://doi.org/10.64898/2026.09.11.750664","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.11.750664","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/16/2026.09.11.750664.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.11.750664","doi":"https://doi.org/10.64898/2026.09.11.750664","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.11.750664","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/16/2026.09.11.750664.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production","score":0.6000000238418579}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213454987.pdf","grobid_xml":"https://content.openalex.org/works/W7213454987.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1576825000","https://openalex.org/W1665355332","https://openalex.org/W1975597731","https://openalex.org/W2068010915","https://openalex.org/W2107480049","https://openalex.org/W2174873063","https://openalex.org/W2294693772","https://openalex.org/W2472803348","https://openalex.org/W2608468474","https://openalex.org/W2702996822","https://openalex.org/W2783515600","https://openalex.org/W2929263296","https://openalex.org/W2949071206","https://openalex.org/W2976374236","https://openalex.org/W2982500515","https://openalex.org/W2989747508","https://openalex.org/W2990956831","https://openalex.org/W3016745570","https://openalex.org/W3088063380","https://openalex.org/W3118116414","https://openalex.org/W3178956972","https://openalex.org/W3179950556","https://openalex.org/W3194548117","https://openalex.org/W4200190418","https://openalex.org/W4210404558","https://openalex.org/W4237831286","https://openalex.org/W4281482167","https://openalex.org/W4281839867","https://openalex.org/W4281999764","https://openalex.org/W4283385398","https://openalex.org/W4295992391","https://openalex.org/W4309974596","https://openalex.org/W4324145324","https://openalex.org/W4386116890","https://openalex.org/W4386346728","https://openalex.org/W4386399783","https://openalex.org/W4386918905","https://openalex.org/W4387996933","https://openalex.org/W4388554734","https://openalex.org/W4392015251","https://openalex.org/W4393086073","https://openalex.org/W4400016576","https://openalex.org/W4400419697","https://openalex.org/W4400844842","https://openalex.org/W4402047030","https://openalex.org/W4402511169","https://openalex.org/W4404511389","https://openalex.org/W4404670517","https://openalex.org/W4405248055","https://openalex.org/W4406553823","https://openalex.org/W4409019364","https://openalex.org/W4412971922","https://openalex.org/W4413119387","https://openalex.org/W4417294786","https://openalex.org/W7155555210","https://openalex.org/W7166183151"],"related_works":["https://openalex.org/W2802280146","https://openalex.org/W4393262213","https://openalex.org/W4411413683","https://openalex.org/W4386116890","https://openalex.org/W4223613691","https://openalex.org/W2771011948","https://openalex.org/W2943995236","https://openalex.org/W2910030584","https://openalex.org/W2921389849","https://openalex.org/W7169575824"],"abstract_inverted_index":{"Abstract":[0],"Optimizing":[1],"microbial":[2],"biomanufacturing":[3],"is":[4,38,54,119],"required":[5,39],"if":[6,115],"renewable":[7],"and":[8,20,56,109,121,125,155],"waste":[9],"carbon":[10,189],"are":[11],"to":[12,32,72,130,138,175,186,209],"replace":[13],"petrochemical":[14],"routes":[15],"at":[16],"competitive":[17],"titers,":[18],"rates,":[19],"yields.":[21],"Growth-coupled":[22],"(GC)":[23],"production":[24,47],"supports":[25],"that":[26,89,196,205],"goal":[27],"by":[28],"linking":[29],"target":[30],"synthesis":[31],"biomass":[33],"formation,":[34],"so":[35],"product":[36],"formation":[37],"for":[40,76,157],"growth.":[41],"Constructing":[42],"knockout":[43,99],"strains":[44],"yielding":[45],"GC":[46,74],"from":[48,105],"a":[49,147,158,192,214],"list":[50],"of":[51,98,161,184,221],"candidate":[52],"genes":[53],"labor":[55],"time":[57],"demanding.":[58],"This":[59],"results":[60,181],"in":[61,63,168],"few":[62],"vivo":[64],"tested":[65,156,165],"designs,":[66,100],"which":[67],"hampers":[68],"standard":[69],"machine-learning":[70],"methods":[71],"learn":[73],"patterns":[75],"specific":[77,145],"bioprocesses.":[78,162],"We":[79],"therefore":[80],"developed":[81,154],"ML4SD,":[82],"an":[83,167],"active-learning":[84],"Design\u2013Build\u2013":[85],"Test\u2013Learn":[86],"(DBTL)":[87],"cycle":[88,112],"trains":[90],"ensembles":[91],"on":[92,188],"genome-scale":[93],"metabolic":[94],"model":[95,107],"(GEM)":[96],"scores":[97],"sampling":[101],"the":[102,116,177,218],"next":[103],"designs":[104,132,212],"predicted":[106],"performance":[108],"error.":[110],"That":[111],"generalizes":[113],"only":[114],"initial":[117],"library":[118],"large":[120],"diverse,":[122],"including":[123],"suboptimal":[124],"non-viable":[126],"designs;":[127],"libraries":[128],"restricted":[129],"minimal":[131],"or":[133],"Pareto-optimal":[134],"knockouts":[135],"were":[136],"found":[137],"generate":[139],"models":[140],"overfitting.":[141],"To":[142],"meet":[143],"those":[144],"demands":[146],"novel":[148],"strain":[149],"design":[150],"algorithm,":[151],"gcSwarms,":[152],"was":[153,164],"diverse":[159],"set":[160],"ML4SD":[163,180],"with":[166],"silico":[169],"case":[170],"study":[171],"converting":[172],"lignin-derived":[173],"4-hydroxybenzoate":[174],"6-caprolactam,":[176],"nylon-6":[178],"monomer.":[179],"showed":[182],"improvements":[183],"up":[185],"164%":[187],"yield,":[190],"recovering":[191],"shared":[193],"SHAP":[194],"motif":[195],"redirects":[197],"TCA":[198],"flux":[199],"through":[200],"acetyl-CoA.":[201],"Importantly":[202],"it":[203],"reaches":[204],"result":[206],"using":[207],"2.5-":[208],"7.1-fold":[210],"fewer":[211],"than":[213],"gcSwarms-only":[215],"search,":[216],"demonstrating":[217],"data":[219],"efficiency":[220],"this":[222],"method.":[223]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-17T00:00:00"}