{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:48:55Z","timestamp":1742957335167,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031580710"},{"type":"electronic","value":"9783031580727"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-58072-7_11","type":"book-chapter","created":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T19:01:42Z","timestamp":1713121302000},"page":"213-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transcription Factors Across the\u00a0Escherichia coli Pangenome: A\u00a03D Perspective"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2457-4450","authenticated-orcid":false,"given":"Gabriel","family":"Moreno-Hagelsieb","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,15]]},"reference":[{"issue":"1","key":"11_CR1","doi-asserted-by":"publisher","first-page":"iyad031","DOI":"10.1093\/genetics\/iyad031","volume":"224","author":"SA Aleksander","year":"2023","unstructured":"Aleksander, S.A., et al.: The gene ontology knowledgebase in 2023. Genetics 224(1), iyad031 (2023). https:\/\/doi.org\/10.1093\/genetics\/iyad031","journal-title":"Genetics"},{"issue":"6557","key":"11_CR2","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1126\/science.abj8754","volume":"373","author":"M Baek","year":"2021","unstructured":"Baek, M., et al.: Accurate prediction of protein structures and interactions using a three-track neural network. Science 373(6557), 871\u2013876 (2021). https:\/\/doi.org\/10.1126\/science.abj8754","journal-title":"Science"},{"key":"11_CR3","doi-asserted-by":"publisher","unstructured":"Barrio-Hernandez, I., et al.: Clustering-predicted structures at the scale of the known protein universe. Nature 1\u20139 (2023). https:\/\/doi.org\/10.1038\/s41586-023-06510-w","DOI":"10.1038\/s41586-023-06510-w"},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Bittrich, S., et al.: RCSB protein data bank: efficient searching and simultaneous access to one million computed structure moddels alongside the pdb structures enabled by architectural advances. J. Mol. Biol. 167994 (2023). https:\/\/doi.org\/10.1016\/j.jmb.2023.167994","DOI":"10.1016\/j.jmb.2023.167994"},{"issue":"4","key":"11_CR5","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","volume":"18","author":"B Buchfink","year":"2021","unstructured":"Buchfink, B., Reuter, K., Drost, H.G.: Sensitive protein alignments at tree-of-life scale using DIAMOND. Nat. Methods 18(4), 366\u2013368 (2021). https:\/\/doi.org\/10.1038\/s41592-021-01101-x","journal-title":"Nat. Methods"},{"issue":"Suppl 11","key":"11_CR6","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1038\/80697","volume":"7","author":"SK Burley","year":"2000","unstructured":"Burley, S.K.: An overview of structural genomics. Nat. Struct. Biol. 7(Suppl 11), 932\u2013934 (2000). https:\/\/doi.org\/10.1038\/80697","journal-title":"Nat. Struct. Biol."},{"issue":"2","key":"11_CR7","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1038\/13783","volume":"23","author":"SK Burley","year":"1999","unstructured":"Burley, S.K., et al.: Structural genomics: beyond the human genome project. Nat. Genet. 23(2), 151\u2013157 (1999). https:\/\/doi.org\/10.1038\/13783","journal-title":"Nat. Genet."},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1186\/1471-2105-10-421","volume":"10","author":"C Camacho","year":"2009","unstructured":"Camacho, C., et al.: BLAST+: architecture and applications. BMC Bioinform. 10(1), 421 (2009). https:\/\/doi.org\/10.1186\/1471-2105-10-421","journal-title":"BMC Bioinform."},{"issue":"3","key":"11_CR9","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.jbiotec.2012.03.028","volume":"161","author":"JA Freyre-Gonz\u00e1lez","year":"2012","unstructured":"Freyre-Gonz\u00e1lez, J.A., Trevi\u00f1o-Quintanilla, L.G., Valtierra-Guti\u00e9rrez, I.A., Guti\u00e9rrez-R\u00edos, R.M., Alonso-Pav\u00f3n, J.A.: Prokaryotic regulatory systems biology: common principles governing the functional architectures of Bacillus subtilis and Escherichia coli unveiled by the natural decomposition approach. J. Biotechnol. 161(3), 278\u2013286 (2012). https:\/\/doi.org\/10.1016\/j.jbiotec.2012.03.028","journal-title":"J. Biotechnol."},{"issue":"D1","key":"11_CR10","doi-asserted-by":"publisher","first-page":"D762","DOI":"10.1093\/nar\/gkad988","volume":"52","author":"DH Haft","year":"2023","unstructured":"Haft, D.H., Badretdin, A., et al.: RefSeq and the prokaryotic genome annotation pipeline in the age of metagenomes. Nucleic Acids Res. 52(D1), D762\u2013D769 (2023). https:\/\/doi.org\/10.1093\/nar\/gkad988","journal-title":"Nucleic Acids Res."},{"issue":"9","key":"11_CR11","doi-asserted-by":"publisher","first-page":"e0291492","DOI":"10.1371\/journal.pone.0291492","volume":"18","author":"JE Hern\u00e1ndez-Salmer\u00f3n","year":"2023","unstructured":"Hern\u00e1ndez-Salmer\u00f3n, J.E., Irani, T., Moreno-Hagelsieb, G.: Fast genome-based delimitation of Enterobacterales species. PLoS ONE 18(9), e0291492 (2023). https:\/\/doi.org\/10.1371\/journal.pone.0291492","journal-title":"PLoS ONE"},{"issue":"1","key":"11_CR12","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1186\/s12864-020-07132-6","volume":"21","author":"JE Hern\u00e1ndez-Salmer\u00f3n","year":"2020","unstructured":"Hern\u00e1ndez-Salmer\u00f3n, J.E., Moreno-Hagelsieb, G.: Progress in quickly finding orthologs as reciprocal best hits: comparing blast, last, diamond and MMseqs2. BMC Genom. 21(1), 741 (2020). https:\/\/doi.org\/10.1186\/s12864-020-07132-6","journal-title":"BMC Genom."},{"issue":"3","key":"11_CR13","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1002\/prot.22458","volume":"77","author":"K Illerg\u00e5rd","year":"2009","unstructured":"Illerg\u00e5rd, K., Ardell, D.H., Elofsson, A.: Structure is three to ten times more conserved than sequence\u2014a study of structural response in protein cores. Proteins: Struct. Funct. Bioinform. 77(3), 499\u2013508 (2009). https:\/\/doi.org\/10.1002\/prot.22458","journal-title":"Proteins: Struct. Funct. Bioinform."},{"issue":"1","key":"11_CR14","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1186\/1471-2105-11-431","volume":"11","author":"LS Johnson","year":"2010","unstructured":"Johnson, L.S., Eddy, S.R., Portugaly, E.: Hidden Markov model speed heuristic and iterative HMM search procedure. BMC Bioinform. 11(1), 431 (2010). https:\/\/doi.org\/10.1186\/1471-2105-11-431","journal-title":"BMC Bioinform."},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Kempen, M.V., et al.: Fast and accurate protein structure search with Foldseek. Nat. Biotechnol. 1\u20134 (2023). https:\/\/doi.org\/10.1038\/s41587-023-01773-0","DOI":"10.1038\/s41587-023-01773-0"},{"issue":"1","key":"11_CR16","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1038\/s41467-023-37896-w","volume":"14","author":"JK Leman","year":"2023","unstructured":"Leman, J.K., et al.: Sequence-structure-function relationships in the microbial protein universe. Nat. Commun. 14(1), 2351 (2023). https:\/\/doi.org\/10.1038\/s41467-023-37896-w","journal-title":"Nat. Commun."},{"issue":"D1","key":"11_CR17","doi-asserted-by":"publisher","first-page":"D265","DOI":"10.1093\/nar\/gkz991","volume":"48","author":"S Lu","year":"2019","unstructured":"Lu, S., et al.: CDD\/SPARCLE: the conserved domain database in 2020. Nucleic Acids Res. 48(D1), D265\u2013D268 (2019). https:\/\/doi.org\/10.1093\/nar\/gkz991","journal-title":"Nucleic Acids Res."},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Mistry, J., et al.: Pfam: the protein families database in 2021. Nucleic Acids Res. 49(D1), gkaa913 (2020). https:\/\/doi.org\/10.1093\/nar\/gkaa913","DOI":"10.1093\/nar\/gkaa913"},{"issue":"1","key":"11_CR19","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1186\/s13059-016-0997-x","volume":"17","author":"BD Ondov","year":"2016","unstructured":"Ondov, B.D., et al.: Mash: fast genome and metagenome distance estimation using MinHash. Genome Biol. 17(1), 132 (2016). https:\/\/doi.org\/10.1186\/s13059-016-0997-x","journal-title":"Genome Biol."},{"issue":"D1","key":"11_CR20","doi-asserted-by":"publisher","first-page":"D418","DOI":"10.1093\/nar\/gkac993","volume":"51","author":"T Paysan-Lafosse","year":"2022","unstructured":"Paysan-Lafosse, T., et al.: InterPro in 2022. Nucleic Acids Res. 51(D1), D418\u2013D427 (2022). https:\/\/doi.org\/10.1093\/nar\/gkac993","journal-title":"Nucleic Acids Res."},{"issue":"1","key":"11_CR21","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/genes11010052","volume":"11","author":"I Sanchez","year":"2020","unstructured":"Sanchez, I., Hernandez-Guerrero, R., Mendez-Monroy, P.E., Martinez-Nu\u00f1ez, M.A., Ibarra, J.A., P\u00e9rez-Rueda, E.: Evaluation of the abundance of DNA-binding transcription factors in prokaryotes. Genes 11(1), 52 (2020). https:\/\/doi.org\/10.3390\/genes11010052","journal-title":"Genes"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Sayers, E.W., et al.: Database resources of the national center for biotechnology information in 2023. Nucleic Acids Res. 51(D1), gkac1032 (2022). https:\/\/doi.org\/10.1093\/nar\/gkac1032","DOI":"10.1093\/nar\/gkac1032"},{"issue":"3","key":"11_CR23","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1038\/73723","volume":"18","author":"J Skolnick","year":"2000","unstructured":"Skolnick, J., Fetrow, J.S., Kolinski, A.: Structural genomics and its importance for gene function analysis. Nat. Biotechnol. 18(3), 283\u2013287 (2000). https:\/\/doi.org\/10.1038\/73723","journal-title":"Nat. Biotechnol."},{"issue":"11","key":"11_CR24","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","volume":"35","author":"M Steinegger","year":"2017","unstructured":"Steinegger, M., S\u00f6ding, J.: MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35(11), 1026\u20131028 (2017). https:\/\/doi.org\/10.1038\/nbt.3988","journal-title":"Nat. Biotechnol."},{"key":"11_CR25","doi-asserted-by":"publisher","unstructured":"The\u00a0UniProt\u00a0Consortium, et al.: UniProt: the universal protein knowledge base in 2023. Nucleic Acids Res. 51(D1), D523\u2013D531 (2022). https:\/\/doi.org\/10.1093\/nar\/gkac1052","DOI":"10.1093\/nar\/gkac1052"},{"key":"11_CR26","doi-asserted-by":"publisher","unstructured":"Tierrafr\u00eda, V.H., et al.: RegulonDB 11.0: comprehensive high-throughput datasets on transcriptional regulation in Escherichia coli K-12. Microb. Genom. 8(5), mgen000833 (2022). https:\/\/doi.org\/10.1099\/mgen.0.000833","DOI":"10.1099\/mgen.0.000833"},{"issue":"D1","key":"11_CR27","doi-asserted-by":"publisher","first-page":"D439","DOI":"10.1093\/nar\/gkab1061","volume":"50","author":"M Varadi","year":"2021","unstructured":"Varadi, M., et al.: AlphaFold protein structure database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res. 50(D1), D439\u2013D444 (2021). https:\/\/doi.org\/10.1093\/nar\/gkab1061","journal-title":"Nucleic Acids Res."},{"issue":"D1","key":"11_CR28","doi-asserted-by":"publisher","first-page":"D368","DOI":"10.1093\/nar\/gkad1011","volume":"52","author":"M Varadi","year":"2023","unstructured":"Varadi, M., et al.: AlphaFold protein structure database in 2024: providing structure coverage for over 214 million protein sequences. Nucleic Acids Res. 52(D1), D368\u2013D375 (2023). https:\/\/doi.org\/10.1093\/nar\/gkad1011","journal-title":"Nucleic Acids Res."},{"key":"11_CR29","doi-asserted-by":"publisher","unstructured":"Xu, J., Zhang, Y.: How significant is a protein structure similarity with TM-score = 0.5? Bioinformatics 26(7), 889\u2013895 (2010). https:\/\/doi.org\/10.1093\/bioinformatics\/btq066","DOI":"10.1093\/bioinformatics\/btq066"},{"issue":"9","key":"11_CR30","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1038\/s41592-022-01585-1","volume":"19","author":"C Zhang","year":"2022","unstructured":"Zhang, C., Shine, M., Pyle, A.M., Zhang, Y.: US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes. Nat. Methods 19(9), 1109\u20131115 (2022). https:\/\/doi.org\/10.1038\/s41592-022-01585-1","journal-title":"Nat. Methods"}],"container-title":["Lecture Notes in Computer Science","Comparative Genomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58072-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T13:03:24Z","timestamp":1728911004000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58072-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031580710","9783031580727"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58072-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RECOMB-CG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"RECOMB International Workshop on Comparative Genomics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Boston, MA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rcg2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}