{"doi":"10.1093/nar/gkaf863","title":"Deep learning guided programmable design of\n                    <i>Escherichia coli</i>\n                    core promoters from sequence architecture to strength control","abstract":"<jats:title>Abstract</jats:title>\n                  <jats:p>Core promoters are essential regulatory elements that control transcription initiation, but accurately predicting and designing their strength remains challenging due to complex sequence-function relationships and the limited generalizability of existing AI-based approaches. To address this, we developed a modular platform integrating rational library design, predictive modelling, and generative optimization into a closed-loop workflow for end-to-end core promoter engineering. Conserved and spacer region of core promoters exert distinct effects on transcriptional strength, with the former driving large-scale variation and the latter enabling finer gradation. Based on this insight, Mutation-Barcoding-Reverse Sequencing approach was used and constructed a synthetic promoter library comprising 112 955 variants with minimal redundancy and a 16 226-fold expression range. A Transformer-based model trained on this dataset achieved a Pearson correlation of 0.87 with experimentally measured promoter strengths. When combined with a conditional diffusion model, the system enabled de novo generation of promoter sequences with defined strengths, achieving a design-to-measurement correlation of 0.95 and maintaining high accuracy (R = 0.93) across varied sequence contexts. The designed promoters consistently preserved their intended strength gradients, demonstrating robust plug-and-play functionality. This work establishes a scalable and extensible platform (www.yudenglab.com) for deep learning-guided programmable design of Escherichia coli core promoters, enabling precise transcriptional control.</jats:p>","journal":"Nucleic Acids Research","year":2025,"id":605319,"datarank":0.44166584687496613,"base_score":2.9444389791664403,"endowment":2.9444389791664403,"self_citation_contribution":0.44166584687496613,"citation_network_contribution":0.0,"self_endowment_contribution":0.44166584687496613,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":18,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1553453,"name":"Renxu Feng","orcid":null,"position":1,"is_corresponding":false},{"id":1553454,"name":"Nana Ding","orcid":null,"position":2,"is_corresponding":false},{"id":1553455,"name":"Wenyan Cao","orcid":null,"position":3,"is_corresponding":false},{"id":803778,"name":"Yang Liu","orcid":"0000-0003-2890-686X","position":4,"is_corresponding":false},{"id":1553456,"name":"Shenghu Zhou","orcid":"0000-0002-7058-430X","position":5,"is_corresponding":false},{"id":1172797,"name":"Yu Deng","orcid":"0000-0002-1909-7223","position":6,"is_corresponding":false},{"id":1288957,"name":"Xuan Zhou","orcid":"0000-0003-3429-6092","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Deep learning guided programmable design of\n                    <i>Escherichia coli</i>\n                    core promoters from sequence architecture to strength control","abstract":"<jats:title>Abstract</jats:title>\n                  <jats:p>Core promoters are essential regulatory elements that control transcription initiation, but accurately predicting and designing their strength remains challenging due to complex sequence-function relationships and the limited generalizability of existing AI-based approaches. To address this, we developed a modular platform integrating rational library design, predictive modelling, and generative optimization into a closed-loop workflow for end-to-end core promoter engineering. Conserved and spacer region of core promoters exert distinct effects on transcriptional strength, with the former driving large-scale variation and the latter enabling finer gradation. Based on this insight, Mutation-Barcoding-Reverse Sequencing approach was used and constructed a synthetic promoter library comprising 112 955 variants with minimal redundancy and a 16 226-fold expression range. A Transformer-based model trained on this dataset achieved a Pearson correlation of 0.87 with experimentally measured promoter strengths. When combined with a conditional diffusion model, the system enabled de novo generation of promoter sequences with defined strengths, achieving a design-to-measurement correlation of 0.95 and maintaining high accuracy (R = 0.93) across varied sequence contexts. The designed promoters consistently preserved their intended strength gradients, demonstrating robust plug-and-play functionality. This work establishes a scalable and extensible platform (www.yudenglab.com) for deep learning-guided programmable design of Escherichia coli core promoters, enabling precise transcriptional control.</jats:p>","is_dataset_classified":null,"base_score":2.8903717578961645,"endowment":2.8903717578961645,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"40902006","pmcid":"PMC12407095","openalex_id":"https://openalex.org/W4414003024","authors":[],"funders":[{"funder_name":"National Key R&D Program of China","grant_id":"2024YFA0918000","title":null},{"funder_name":"Distinguished Young Scholars of Jiangsu Province","grant_id":"BK20220089","title":null},{"funder_name":"Key R&D Project of Jiangsu Province","grant_id":"BE2022322","title":null},{"funder_name":"National Natural Science Foundation of China","grant_id":"22378170","title":null},{"funder_name":"National Natural Science Foundation of China","grant_id":"22478156","title":null},{"funder_name":"“Pilot Plan” Internet of Things Special Project","grant_id":"2022SP-T16-B","title":null}],"total_grants":6,"fwci":16.236,"citation_percentile":0.99413308,"influential_citations":0,"citation_trend":[{"year":2025,"count":4},{"year":2026,"count":13}],"oa_status":"gold","license":"cc-by-nc","oa_locations":[{"url":"https://doi.org/10.1093/nar/gkaf863","host_type":"journal"},{"url":"https://doi.org/10.1093/nar/gkaf863","host_type":"publisher"},{"url":"https://academic.oup.com/nar/article-pdf/53/16/gkaf863/64201257/gkaf863.pdf","host_type":"publisher"},{"url":"https://pubmed.ncbi.nlm.nih.gov/40902006","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12407095","host_type":"repository"},{"url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12407095/","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC12407095","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC12407095?pdf=render","host_type":"Europe_PMC"}],"fields_of_study":["Bacterial Genetics and Biotechnology","Genomics and Chromatin Dynamics","RNA and protein synthesis mechanisms"],"mesh_terms":["Deep Learning","Escherichia coli","Promoter Regions, Genetic","Gene Library","Gene Expression Regulation, Bacterial"],"keywords":["Biology","Promoter","Escherichia coli","Sequence (biology)","Core (optical fiber)","Computational biology","Genetics","Gene","Engineering","Gene expression"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-07-30T02:11:01.410029Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}