{"id":"https://openalex.org/W7204238653","doi":"https://doi.org/10.48550/arxiv.2608.23722","title":"Optimizing RNA yield using deep neural networks coupled to massively parallel screening","display_name":"Optimizing RNA yield using deep neural networks coupled to massively parallel screening","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204238653","doi":"https://doi.org/10.48550/arxiv.2608.23722"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.23722","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23722","pdf_url":"https://arxiv.org/pdf/2608.23722","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23722","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003301809","display_name":"Dinghai Zheng","orcid":"https://orcid.org/0000-0002-4500-7666","observed_orcids":["https://orcid.org/0000-0002-4500-7666"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Dinghai","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146620857","display_name":"Justin Hong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Justin","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148188481","display_name":"Jun Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jun","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057579663","display_name":"Adrien Villain","orcid":"https://orcid.org/0000-0001-5338-8959","observed_orcids":["https://orcid.org/0000-0001-5338-8959"]},"institutions":[{"id":"https://openalex.org/I3018075036","display_name":"Sanofi (France)","ror":"https://ror.org/02n6c9837","country_code":"FR","type":"company","lineage":["https://openalex.org/I3018075036"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Villain, Adrien","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Marcy L'Etoile , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Marcy L'Etoile , France","institution_ids":["https://openalex.org/I3018075036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047794344","display_name":"Micka\u00ebl Costallat","orcid":"https://orcid.org/0000-0002-3048-7038","observed_orcids":["https://orcid.org/0000-0002-3048-7038"]},"institutions":[{"id":"https://openalex.org/I3018075036","display_name":"Sanofi (France)","ror":"https://ror.org/02n6c9837","country_code":"FR","type":"company","lineage":["https://openalex.org/I3018075036"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Costallat, Micka\u00ebl","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Marcy L'Etoile , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Marcy L'Etoile , France","institution_ids":["https://openalex.org/I3018075036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024834436","display_name":"Fernando Ulloa Montoya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3018075036","display_name":"Sanofi (France)","ror":"https://ror.org/02n6c9837","country_code":"FR","type":"company","lineage":["https://openalex.org/I3018075036"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Montoya, Fernando Ulloa","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Marcy L'Etoile , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Marcy L'Etoile , France","institution_ids":["https://openalex.org/I3018075036"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103219999","display_name":"Vikram Agarwal","orcid":"https://orcid.org/0000-0001-8148-952X","observed_orcids":["https://orcid.org/0000-0001-8148-952X","https://orcid.org/0000-0003-2256-0888"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Vikram","raw_affiliation_strings":["Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Computational Sciences , mRNA Center of Excellence , Sanofi , Waltham , MA , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.8906000256538391,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.8906000256538391,"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/T10725","display_name":"RNA Interference and Gene Delivery","score":0.07199999690055847,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0027000000700354576,"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/in-vitro-transcription","display_name":"in vitro transcription","score":0.9860000014305115},{"id":"https://openalex.org/keywords/promoter","display_name":"promoter","score":0.5170000195503235},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.6549999713897705},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8619999885559082},{"id":"https://openalex.org/keywords/next-generation-sequencing","display_name":"next-generation sequencing","score":0.7509999871253967},{"id":"https://openalex.org/keywords/rna-engineering","display_name":"RNA engineering","score":0.38499999046325684},{"id":"https://openalex.org/keywords/vaccine-antigen-design","display_name":"vaccine antigen design","score":0.7319999933242798},{"id":"https://openalex.org/keywords/synthetic-biology","display_name":"synthetic biology","score":0.5350000262260437},{"id":"https://openalex.org/keywords/high-throughput-screening","display_name":"high-throughput screening","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.728600025177002},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.618399977684021},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.5562999844551086},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5202999711036682},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4465000033378601},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4413999915122986},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3321000039577484},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C98108389","wikidata":"https://www.wikidata.org/wiki/Q412563","display_name":"CRISPR","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.3158999979496002},{"id":"https://openalex.org/C192800701","wikidata":"https://www.wikidata.org/wiki/Q6784807","display_name":"Massive parallel sequencing","level":4,"score":0.2962999939918518},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C129312508","wikidata":"https://www.wikidata.org/wiki/Q133686","display_name":"Oligonucleotide","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C64350747","wikidata":"https://www.wikidata.org/wiki/Q15334993","display_name":"RNA polymerase II","level":5,"score":0.2745000123977661},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.27000001072883606}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23722","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23722","pdf_url":"https://arxiv.org/pdf/2608.23722","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23722","doi":"https://doi.org/10.48550/arxiv.2608.23722","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23722","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23722","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23722","pdf_url":"https://arxiv.org/pdf/2608.23722","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307781","display_name":"Sanofi","ror":"https://ror.org/027vj4x92"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204238653.pdf","grobid_xml":"https://content.openalex.org/works/W7204238653.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Messenger":[0],"RNA":[1,29,34,50,73,100,147,177,203,235],"(mRNA)-based":[2],"therapeutics":[3],"have":[4],"emerged":[5],"as":[6,31],"a":[7,94,129,137,150,169,196],"powerful":[8],"platform":[9],"for":[10],"vaccines,":[11],"protein":[12,214],"replacement":[13],"therapies,":[14],"and":[15,99,121,144,174,202,216,233],"cancer":[16],"immunotherapy.":[17],"A":[18,79],"critical":[19],"bottleneck":[20],"in":[21,39,104,168],"mRNA":[22],"development":[23],"is":[24],"manufacturing":[25],"large":[26,76],"quantities":[27],"of":[28,81,112,140,188],"economically,":[30],"measured":[32,146],"by":[33,180],"yield":[35,51,74,148],"emerging":[36],"from":[37],"an":[38,58],"vitro":[40],"transcription":[41],"(IVT)":[42],"reaction.":[43],"However,":[44],"how":[45],"promoter-adjacent":[46],"DNA":[47,98,201],"sequences":[48,85],"influence":[49],"remains":[52],"poorly":[53],"characterized.":[54],"Here,":[55],"we":[56],"present":[57],"integrated":[59],"deep":[60,125,225],"learning":[61,126,226],"framework":[62,194],"that":[63],"leverages":[64],"massively":[65],"parallel":[66,105],"next-generation":[67],"sequencing":[68],"(NGS)":[69],"assays":[70],"to":[71,88,123,172,200,209],"measure":[72],"across":[75,157],"sequence":[77,91,159,178,204],"spaces.":[78],"library":[80],"10^5":[82],"randomized":[83],"oligonucleotide":[84],"was":[86],"designed":[87],"systematically":[89],"explore":[90],"diversity":[92],"within":[93],"defined":[95],"structural":[96],"context.":[97],"abundances":[101],"were":[102,118],"quantified":[103],"using":[106,128],"Illumina":[107],"sequencing,":[108],"enabling":[109,184],"high-resolution":[110],"measurement":[111],"sequence-to-yield":[113],"relationships":[114],"at":[115],"scale.":[116],"Sequences":[117],"one-hot":[119],"encoded":[120],"used":[122],"train":[124],"models,":[127],"convolutional":[130],"neural":[131],"network":[132],"architecture.":[133],"The":[134],"model":[135,164],"achieved":[136],"Pearson":[138],"correlation":[139],"0.94":[141],"between":[142],"predicted":[143,181],"experimentally":[145],"on":[149],"held-out":[151],"test":[152],"set,":[153],"demonstrating":[154],"strong":[155],"generalization":[156],"diverse":[158],"contexts.":[160],"Importantly,":[161],"the":[162,189],"trained":[163],"can":[165],"be":[166],"deployed":[167],"production":[170],"environment":[171],"score":[173],"rank":[175],"novel":[176],"designs":[179],"IVT":[182],"yield,":[183],"cost-effective,":[185],"pre-experimental":[186],"prioritization":[187],"most":[190],"manufacturable":[191],"candidates.":[192],"This":[193],"establishes":[195],"scalable,":[197],"data-driven":[198],"approach":[199],"optimization,":[205],"with":[206,223],"broad":[207],"applicability":[208],"vaccine":[210],"antigen":[211],"design,":[212],"therapeutic":[213],"delivery,":[215],"synthetic":[217],"biology.":[218],"By":[219],"integrating":[220],"high-throughput":[221],"experimentation":[222],"advanced":[224],"modeling,":[227],"it":[228],"significantly":[229],"reduces":[230],"screening":[231],"costs":[232],"accelerates":[234],"engineering":[236],"cycle":[237],"times.":[238]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2026-08-27T00:00:00"}