<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">vavilov</journal-id><journal-title-group><journal-title xml:lang="ru">Вавиловский журнал генетики и селекции</journal-title><trans-title-group xml:lang="en"><trans-title>Vavilov Journal of Genetics and Breeding</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2500-3259</issn><publisher><publisher-name>Institute of Cytology and Genetics of Siberian Branch of the RAS</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18699/vjgb-26-10</article-id><article-id custom-type="elpub" pub-id-type="custom">vavilov-4976</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>БИОИНФОРМАТИКА И СИСТЕМНАЯ БИОЛОГИЯ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>BIOINFORMATICS AND SYSTEMS BIOLOGY</subject></subj-group></article-categories><title-group><article-title>Развитие метода филогенетического футпринтинга для распознавания сайтов связывания транскрипционных факторов на основе использования bootstrap-испытаний для анализа больших бактериальных геномных данных</article-title><trans-title-group xml:lang="en"><trans-title>Improvement of a phylogenetic footprinting method for transcription factor binding sites recognition based on the use of bootstrap trials for the analysis of large bacterial genomic data</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1102-0934</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Мухин</surname><given-names>А. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Mukhin</surname><given-names>A. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новосибирск</p></bio><bio xml:lang="en"><p>Novosibirsk</p></bio><email xlink:type="simple">mukhin@bionet.nsc.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Хлебодарова</surname><given-names>Т. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Khlebodarova</surname><given-names>T. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новосибирск</p></bio><bio xml:lang="en"><p>Novosibirsk</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-6097-5155</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ощепков</surname><given-names>Д. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Oshchepkov</surname><given-names>D. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новосибирск</p></bio><bio xml:lang="en"><p>Novosibirsk</p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Курчатовский геномный центр ИЦиГ СО РАН; Федеральный исследовательский центр Институт цитологии и генетики Сибирского отделения Российской академии наук; Новосибирский национальный исследовательский государственный университет<country>Россия</country></aff><aff xml:lang="en">Kurchatov Genomic Center of ICG SB RAS; Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences; Novosibirsk State University<country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru">Курчатовский геномный центр ИЦиГ СО РАН; Федеральный исследовательский центр Институт цитологии и генетики Сибирского отделения Российской академии наук<country>Россия</country></aff><aff xml:lang="en">Kurchatov Genomic Center of ICG SB RAS; Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of Sciences<country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>05</day><month>03</month><year>2026</year></pub-date><volume>30</volume><issue>1</issue><fpage>15</fpage><lpage>26</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Мухин А.М., Хлебодарова Т.М., Ощепков Д.Ю., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Мухин А.М., Хлебодарова Т.М., Ощепков Д.Ю.</copyright-holder><copyright-holder xml:lang="en">Mukhin A.M., Khlebodarova T.M., Oshchepkov D.Y.</copyright-holder><license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://vavilov.elpub.ru/jour/article/view/4976">https://vavilov.elpub.ru/jour/article/view/4976</self-uri><abstract><p>Активное развитие технологий высокопроизводительного секвенирования привело к взрывообразному накоплению высококачественных данных по последовательностям бактериальных геномов – их число приближается к трем миллионам, и дальнейший рост продолжается. Это, в свою очередь, дает дополнительный импульс развитию технологий для более эффективной их аннотации аналитическими методами с прицелом на применение таких больших геномных данных, а также получение нового качества аннотаций. Одним из таких аналитических подходов стал метод филогенетического футпринтинга, направленный на выявление мотивов, соответствующих сайтам связывания транскрипционных факторов в промоторных областях бактериальных геномов путем сравнения соответствующих выборок регуляторных последовательностей генов-ортологов для родственных организмов. Дальнейшее накопление геномных данных стало стимулом для развития подхода. Так, было обнаружено, что избыточное число последовательностей в выборке, анализируемой с использованием филогенетического футпринтинга, лишь ухудшает точность метода, тогда как включение этапа отбора последовательностей в анализируемую выборку с учетом данных о взаимных эволюционных расстояниях повышает качество работы метода. В настоящей статье нами предложен и реализован следующий шаг развития метода филогенетического футпринтинга, основанный на множественном запуске описанного выше этапа отбора для формирования различающихся подвыборок, последующего запуска конвейера для каждой из подвыборок и на статистическом анализе получаемых результатов множественных запусков конвейера. Предложенный подход, реализованный в методе MotifsOnFly, позволяет повысить устойчивость получаемых результатов распознавания мотивов, выявляемых в многократных запусках конвейера. Эффективность метода MotifsOnFly продемонстрирована на примере анализа хорошо аннотированного промотора гена OmpW Escherichia coli.</p></abstract><trans-abstract xml:lang="en"><p>The rapid development of high-throughput sequencing technologies has led to an explosive accumulation of high-quality bacterial genome sequence data – their number is approaching three million, and this growth continues. This, in turn, provides additional impetus for the development of technologies for more efficient annotation using analytical methods designed to utilize such large-scale genomic data, as well as for achieving new levels of annotation quality. One such analytical approach is phylogenetic footprinting, which aims to identify motifs corresponding to transcription factor binding sites in the promoter regions of bacterial genomes by comparing corresponding sets of regulatory sequences of orthologous genes in related organisms. The continued accumulation of genomic data has served as the basis for further development of this approach. It has been found that an excessive number of sequences in a set analyzed using phylogenetic footprinting only reduces the accuracy of the method, whereas the inclusion of a sequence selection step in the analyzed set based on data on mutual evolutionary distances improves the method’s performance. In this paper, we propose and implement a further step in the development of the phylogenetic footprinting method. This step involves multiple runs of the selection step described above to generate distinct subsamples, subsequent pipeline runs for each subsample, and statistical analysis of the results obtained from multiple pipeline runs. The proposed approach, implemented in the MotifsOnFly method, improves the robustness of motif recognition results obtained from multiple pipeline runs. The effectiveness of the MotifsOnFly method is demonstrated using the analysis of the well-annotated promoter of the Escherichia coli OmpW gene.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>филогенетический футпринтинг</kwd><kwd>бактериальный геном</kwd><kwd>сайты связывания транскрипционных факторов</kwd><kwd>мотивы</kwd><kwd>бутстреп</kwd><kwd>Python</kwd></kwd-group><kwd-group xml:lang="en"><kwd>phylogenetic footprinting</kwd><kwd>bacterial genome</kwd><kwd>transcription factor binding sites</kwd><kwd>motifs</kwd><kwd>bootstrap</kwd><kwd>Python</kwd></kwd-group><funding-group xml:lang="en"><funding-statement>This work was supported by the Ministry of Science and Higher Education of the Russian Federation (Federal Scientific and Technical Program for the Development of Genetic Technologies for 2019–2030, Agreement No. 075-15-2025-516).</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Bailey T.L., Boden M., Buske F.A., Frith M., Grant C.E., Clementi L., Ren J., Li W.W., Noble W.S. MEME SUITE: tools for motif discovery and searching. Nucleic Acids Res. 2009;37(W):W202-W208. doi 10.1093/nar/gkp335</mixed-citation><mixed-citation xml:lang="en">Bailey T.L., Boden M., Buske F.A., Frith M., Grant C.E., Clementi L., Ren J., Li W.W., Noble W.S. MEME SUITE: tools for motif discovery and searching. Nucleic Acids Res. 2009;37(W):W202-W208. doi 10.1093/nar/gkp335</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Blanchette M., Tompa M. Discovery of regulatory elements by a computational method for phylogenetic footprinting. Genome Res. 2002; 12(5):739-748. doi 10.1101/gr.6902</mixed-citation><mixed-citation xml:lang="en">Blanchette M., Tompa M. Discovery of regulatory elements by a computational method for phylogenetic footprinting. Genome Res. 2002; 12(5):739-748. doi 10.1101/gr.6902</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Blanchette M., Tompa M. FootPrinter: a program designed for phylogenetic footprinting. Nucleic Acids Res. 2003;31(13):3840-3842. doi 10.1093/nar/gkg606</mixed-citation><mixed-citation xml:lang="en">Blanchette M., Tompa M. FootPrinter: a program designed for phylogenetic footprinting. Nucleic Acids Res. 2003;31(13):3840-3842. doi 10.1093/nar/gkg606</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Browning D.F., Busby S.J. The regulation of bacterial transcription initiation. Nat Rev Microbiol. 2004;2(1):57-65. doi 10.1038/nrmicro787</mixed-citation><mixed-citation xml:lang="en">Browning D.F., Busby S.J. The regulation of bacterial transcription initiation. Nat Rev Microbiol. 2004;2(1):57-65. doi 10.1038/nrmicro787</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Chen X., Guo L., Fan Z., Jiang T. W-AlignACE: an improved Gibbs sampling algorithm based on more accurate position weight matrices learned from sequence and gene expression/ChIP-chip data. Bioinformatics. 2008;24(9):1121-1128. doi 10.1093/bioinformatics/btn088</mixed-citation><mixed-citation xml:lang="en">Chen X., Guo L., Fan Z., Jiang T. W-AlignACE: an improved Gibbs sampling algorithm based on more accurate position weight matrices learned from sequence and gene expression/ChIP-chip data. Bioinformatics. 2008;24(9):1121-1128. doi 10.1093/bioinformatics/btn088</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Claeys M., Storms V., Sun H., Michoel T., Marchal K. MotifSuite: workflow for probabilistic motif detection and assessment. Bioinformatics. 2012;28(14):1931-1932. doi 10.1093/bioinformatics/bts293</mixed-citation><mixed-citation xml:lang="en">Claeys M., Storms V., Sun H., Michoel T., Marchal K. MotifSuite: workflow for probabilistic motif detection and assessment. Bioinformatics. 2012;28(14):1931-1932. doi 10.1093/bioinformatics/bts293</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Constantinidou C., Hobman J.L., Griffiths L., Patel M.D., Penn C.W., Cole J.A., Overton T.W. A reassessment of the FNR regulon and transcriptomic analysis of the effects of nitrate, nitrite, NarXL, and NarQP as Escherichia coli K12 adapts from aerobic to anaerobic growth. J Biol Chem. 2006;281(8):4802-4815. doi 10.1074/jbc.M512312200</mixed-citation><mixed-citation xml:lang="en">Constantinidou C., Hobman J.L., Griffiths L., Patel M.D., Penn C.W., Cole J.A., Overton T.W. A reassessment of the FNR regulon and transcriptomic analysis of the effects of nitrate, nitrite, NarXL, and NarQP as Escherichia coli K12 adapts from aerobic to anaerobic growth. J Biol Chem. 2006;281(8):4802-4815. doi 10.1074/jbc.M512312200</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Diesh C., Stevens G.J., Xie P., De Jesus Martinez T., Hershberg E.A., Leung A., Guo E., … Haw R., Cain S., Buels R.M., Stein L.D., Holmes I.H. JBrowse 2: a modular genome browser with views of synteny and structural variation. Genome Biol. 2023;24(1):74. doi 10.1186/s13059-023-02914-z</mixed-citation><mixed-citation xml:lang="en">Diesh C., Stevens G.J., Xie P., De Jesus Martinez T., Hershberg E.A., Leung A., Guo E., … Haw R., Cain S., Buels R.M., Stein L.D., Holmes I.H. JBrowse 2: a modular genome browser with views of synteny and structural variation. Genome Biol. 2023;24(1):74. doi 10.1186/s13059-023-02914-z</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Dudek C.-A., Jahn D. PRODORIC: state-of-the-art database of prokaryotic gene regulation. Nucleic Acids Res. 2022;50(D1):D295- D302. doi 10.1093/nar/gkab1110</mixed-citation><mixed-citation xml:lang="en">Dudek C.-A., Jahn D. PRODORIC: state-of-the-art database of prokaryotic gene regulation. Nucleic Acids Res. 2022;50(D1):D295- D302. doi 10.1093/nar/gkab1110</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Gaston K., Bell A., Kolb A., Buc H., Busby S. Stringent spacing requirements for transcription activation by CRP. Cell. 1990;62(4):733-743. doi 10.1016/0092-8674(90)90118-x</mixed-citation><mixed-citation xml:lang="en">Gaston K., Bell A., Kolb A., Buc H., Busby S. Stringent spacing requirements for transcription activation by CRP. Cell. 1990;62(4):733-743. doi 10.1016/0092-8674(90)90118-x</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Graham A.I., Sanguinetti G., Bramall N., McLeod C.W., Poole R.K. Dynamics of a starvation-to-surfeit shift: a transcriptomic and modelling analysis of the bacterial response to zinc reveals transient behaviour of the Fur and SoxS regulators. Microbiology (Reading). 2012;158(Pt.1):284-292. doi 10.1099/mic.0.053843-0</mixed-citation><mixed-citation xml:lang="en">Graham A.I., Sanguinetti G., Bramall N., McLeod C.W., Poole R.K. Dynamics of a starvation-to-surfeit shift: a transcriptomic and modelling analysis of the bacterial response to zinc reveals transient behaviour of the Fur and SoxS regulators. Microbiology (Reading). 2012;158(Pt.1):284-292. doi 10.1099/mic.0.053843-0</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Gupta S., Stamatoyannopoulos J.A., Bailey T.L., Noble W.S. Quantifying similarity between motifs. Genome Biol. 2007;8(2):R24. doi 10.1186/gb-2007-8-2-r24</mixed-citation><mixed-citation xml:lang="en">Gupta S., Stamatoyannopoulos J.A., Bailey T.L., Noble W.S. Quantifying similarity between motifs. Genome Biol. 2007;8(2):R24. doi 10.1186/gb-2007-8-2-r24</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Hertz G.Z., Stormo G.D. Identifying DNA and protein patterns with statistically significant alignments of multiple sequences. Bioinformatics. 1999;15(7-8):563-577. doi 10.1093/bioinformatics/15.7.563</mixed-citation><mixed-citation xml:lang="en">Hertz G.Z., Stormo G.D. Identifying DNA and protein patterns with statistically significant alignments of multiple sequences. Bioinformatics. 1999;15(7-8):563-577. doi 10.1093/bioinformatics/15.7.563</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Horne C.R., Venugopal H., Panjikar S., Wood D.M., Henrickson A., Brookes E., North R.A., Murphy J.M., Friemann R., Griffin M.D.W., Ramm G., Demeler B., Dobson R.C.J. Mechanism of NanR gene repression and allosteric induction of bacterial sialic acid metabolism. Nat Commun. 2021;12(1):1988. doi 10.1038/s41467-021-22253-6</mixed-citation><mixed-citation xml:lang="en">Horne C.R., Venugopal H., Panjikar S., Wood D.M., Henrickson A., Brookes E., North R.A., Murphy J.M., Friemann R., Griffin M.D.W., Ramm G., Demeler B., Dobson R.C.J. Mechanism of NanR gene repression and allosteric induction of bacterial sialic acid metabolism. Nat Commun. 2021;12(1):1988. doi 10.1038/s41467-021-22253-6</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Huerta-Cepas J., Serra F., Bork P. ETE 3: reconstruction, analysis, and visualization of phylogenomic data. Mol Biol Evol. 2016;33(6): 1635-1638. doi 10.1093/molbev/msw046</mixed-citation><mixed-citation xml:lang="en">Huerta-Cepas J., Serra F., Bork P. ETE 3: reconstruction, analysis, and visualization of phylogenomic data. Mol Biol Evol. 2016;33(6): 1635-1638. doi 10.1093/molbev/msw046</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Hunter J.D. Matplotlib: a 2D graphics environment. Comput Sci Eng. 2007;9(3):90-95. doi 10.1109/MCSE.2007.55</mixed-citation><mixed-citation xml:lang="en">Hunter J.D. Matplotlib: a 2D graphics environment. Comput Sci Eng. 2007;9(3):90-95. doi 10.1109/MCSE.2007.55</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Kalivoda K.A., Steenbergen S.M., Vimr E.R. Control of the Escherichia coli sialoregulon by transcriptional repressor NanR. J Bacteriol. 2013;195(20):4689-4701. doi 10.1128/JB.00692-13</mixed-citation><mixed-citation xml:lang="en">Kalivoda K.A., Steenbergen S.M., Vimr E.R. Control of the Escherichia coli sialoregulon by transcriptional repressor NanR. J Bacteriol. 2013;195(20):4689-4701. doi 10.1128/JB.00692-13</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Katara P., Grover A., Sharma V. Phylogenetic footprinting: a boost for microbial regulatory genomics. Protoplasma. 2012;249(4):901-907. doi 10.1007/s00709-011-0351-9</mixed-citation><mixed-citation xml:lang="en">Katara P., Grover A., Sharma V. Phylogenetic footprinting: a boost for microbial regulatory genomics. Protoplasma. 2012;249(4):901-907. doi 10.1007/s00709-011-0351-9</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Larkin M.A., Blackshields G., Brown N.P., Chenna R., McGettigan P.A., McWilliam H., Valentin F., Wallace I.M., Wilm A., Lopez R., Thompson J.D., Gibson T.J., Higgins D.G. Clustal W and Clustal X version 2.0. Bioinformatics. 2007;23(21):2947-2948. doi 10.1093/bioinformatics/btm404</mixed-citation><mixed-citation xml:lang="en">Larkin M.A., Blackshields G., Brown N.P., Chenna R., McGettigan P.A., McWilliam H., Valentin F., Wallace I.M., Wilm A., Lopez R., Thompson J.D., Gibson T.J., Higgins D.G. Clustal W and Clustal X version 2.0. Bioinformatics. 2007;23(21):2947-2948. doi 10.1093/bioinformatics/btm404</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Levy S., Hannenhalli S., Workman C. Enrichment of regulatory signals in conserved non-coding genomic sequence. Bioinformatics. 2001; 17(10):871-877. doi 10.1093/bioinformatics/17.10.871</mixed-citation><mixed-citation xml:lang="en">Levy S., Hannenhalli S., Workman C. Enrichment of regulatory signals in conserved non-coding genomic sequence. Bioinformatics. 2001; 17(10):871-877. doi 10.1093/bioinformatics/17.10.871</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Li G., Liu B., Ma Q., Xu Y. A new framework for identifying cis-regulatory motifs in prokaryotes. Nucleic Acids Res. 2011a;39(7):e42. doi 10.1093/nar/gkq948</mixed-citation><mixed-citation xml:lang="en">Li G., Liu B., Ma Q., Xu Y. A new framework for identifying cis-regulatory motifs in prokaryotes. Nucleic Acids Res. 2011a;39(7):e42. doi 10.1093/nar/gkq948</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Li G., Ma Q., Mao X., Yin Y., Zhu X., Xu Y. Integration of sequencesimilarity and functional association information can overcome intrinsic problems in orthology mapping across bacterial genomes. Nucleic Acids Res. 2011b;39(22):e150. doi 10.1093/nar/gkr766</mixed-citation><mixed-citation xml:lang="en">Li G., Ma Q., Mao X., Yin Y., Zhu X., Xu Y. Integration of sequencesimilarity and functional association information can overcome intrinsic problems in orthology mapping across bacterial genomes. Nucleic Acids Res. 2011b;39(22):e150. doi 10.1093/nar/gkr766</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Liu B., Zhang H., Zhou C., Li G., Fennell A., Wang G., Kang Y., Liu Q., Ma Q. An integrative and applicable phylogenetic footprinting framework for cis-regulatory motifs identification in prokaryotic genomes. BMC Genomics. 2016;17:578. doi 10.1186/s12864-016-2982-x</mixed-citation><mixed-citation xml:lang="en">Liu B., Zhang H., Zhou C., Li G., Fennell A., Wang G., Kang Y., Liu Q., Ma Q. An integrative and applicable phylogenetic footprinting framework for cis-regulatory motifs identification in prokaryotic genomes. BMC Genomics. 2016;17:578. doi 10.1186/s12864-016-2982-x</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Liu X., Brutlag D.L., Liu J.S. BioProspector: discovering conserved DNA motifs in upstream regulatory regions of co-expressed genes. Pac Symp Biocomput. 2001;6:127-138</mixed-citation><mixed-citation xml:lang="en">Liu X., Brutlag D.L., Liu J.S. BioProspector: discovering conserved DNA motifs in upstream regulatory regions of co-expressed genes. Pac Symp Biocomput. 2001;6:127-138</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Liu X.S., Brutlag D.L., Liu J.S. An algorithm for finding protein-DNA binding sites with applications to chromatin-immunoprecipitation microarray experiments. Nat Biotechnol. 2002;20(8):835-839. doi 10.1038/nbt717</mixed-citation><mixed-citation xml:lang="en">Liu X.S., Brutlag D.L., Liu J.S. An algorithm for finding protein-DNA binding sites with applications to chromatin-immunoprecipitation microarray experiments. Nat Biotechnol. 2002;20(8):835-839. doi 10.1038/nbt717</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Mao X., Ma Q., Zhou C., Chen X., Zhang H., Yang J., Mao F., Lai W., Xu Y. DOOR 2.0: presenting operons and their functions through dynamic and integrated views. Nucleic Acids Res. 2014;42(D1): D654-D659. doi 10.1093/nar/gkt1048</mixed-citation><mixed-citation xml:lang="en">Mao X., Ma Q., Zhou C., Chen X., Zhang H., Yang J., Mao F., Lai W., Xu Y. DOOR 2.0: presenting operons and their functions through dynamic and integrated views. Nucleic Acids Res. 2014;42(D1): D654-D659. doi 10.1093/nar/gkt1048</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">McCue L.A., Thompson W., Carmack C.S., Lawrence C.E. Factors influencing the identification of transcription factor binding sites by cross-species comparison. Genome Res. 2002;12(10):1523-1532. doi 10.1101/gr.323602</mixed-citation><mixed-citation xml:lang="en">McCue L.A., Thompson W., Carmack C.S., Lawrence C.E. Factors influencing the identification of transcription factor binding sites by cross-species comparison. Genome Res. 2002;12(10):1523-1532. doi 10.1101/gr.323602</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Mukhin A., Oschepkov D., Lashin S. A computational pipeline for de novo recognition of transcription factor binding sites in bacterial genomes. Problems of Informatics. 2024;4(65):69-83. doi 10.24412/ 2073-0667-2024-4-69-83 (in Russian)</mixed-citation><mixed-citation xml:lang="en">Mukhin A., Oschepkov D., Lashin S. A computational pipeline for de novo recognition of transcription factor binding sites in bacterial genomes. Problems of Informatics. 2024;4(65):69-83. doi 10.24412/ 2073-0667-2024-4-69-83 (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Myers K.S., Yan H., Ong I.M., Chung D., Liang K., Tran F., Keleş S., Landick R., Kiley P.J. Genome-scale analysis of Escherichia coli FNR reveals complex features of transcription factor binding. PLoS Genet. 2013;9(6):e1003565. doi 10.1371/journal.pgen.1003565</mixed-citation><mixed-citation xml:lang="en">Myers K.S., Yan H., Ong I.M., Chung D., Liang K., Tran F., Keleş S., Landick R., Kiley P.J. Genome-scale analysis of Escherichia coli FNR reveals complex features of transcription factor binding. PLoS Genet. 2013;9(6):e1003565. doi 10.1371/journal.pgen.1003565</mixed-citation></citation-alternatives></ref><ref id="cit30"><label>30</label><citation-alternatives><mixed-citation xml:lang="ru">Olman V., Xu D., Xu Y. CUBIC: identification of regulatory binding sites through data clustering. J Bioinform Comput Biol. 2003;1(1): 21-40. doi 10.1142/s0219720003000162</mixed-citation><mixed-citation xml:lang="en">Olman V., Xu D., Xu Y. CUBIC: identification of regulatory binding sites through data clustering. J Bioinform Comput Biol. 2003;1(1): 21-40. doi 10.1142/s0219720003000162</mixed-citation></citation-alternatives></ref><ref id="cit31"><label>31</label><citation-alternatives><mixed-citation xml:lang="ru">Pachkov M., Balwierz P.J., Arnold P., Ozonov E., van Nimwegen E. SwissRegulon, a database of genome-wide annotations of regulatory sites: recent updates. Nucleic Acids Res. 2013;41(D1):D214-D220. doi 10.1093/nar/gks1145</mixed-citation><mixed-citation xml:lang="en">Pachkov M., Balwierz P.J., Arnold P., Ozonov E., van Nimwegen E. SwissRegulon, a database of genome-wide annotations of regulatory sites: recent updates. Nucleic Acids Res. 2013;41(D1):D214-D220. doi 10.1093/nar/gks1145</mixed-citation></citation-alternatives></ref><ref id="cit32"><label>32</label><citation-alternatives><mixed-citation xml:lang="ru">Park D.M., Akhtar M.S., Ansari A.Z., Landick R., Kiley P.J. The bacterial response regulator ArcA uses a diverse binding site architecture to regulate carbon oxidation globally. PLoS Genet. 2013;9(10): e1003839. doi 10.1371/journal.pgen.1003839</mixed-citation><mixed-citation xml:lang="en">Park D.M., Akhtar M.S., Ansari A.Z., Landick R., Kiley P.J. The bacterial response regulator ArcA uses a diverse binding site architecture to regulate carbon oxidation globally. PLoS Genet. 2013;9(10): e1003839. doi 10.1371/journal.pgen.1003839</mixed-citation></citation-alternatives></ref><ref id="cit33"><label>33</label><citation-alternatives><mixed-citation xml:lang="ru">Peltek S., Bannikova S., Khlebodarova T.M., Uvarova Y., MukhinA.M., Vasiliev G., Scheglov M., Shipova A., Vasilieva A., Oshchepkov D., Bryanskaya A., Popik V. The transcriptomic response of cells of the thermophilic bacterium Geobacillus icigianus to terahertz irradiation. Int J Mol Sci. 2024;25(22):12059. doi 10.3390/ijms252212059</mixed-citation><mixed-citation xml:lang="en">Peltek S., Bannikova S., Khlebodarova T.M., Uvarova Y., MukhinA.M., Vasiliev G., Scheglov M., Shipova A., Vasilieva A., Oshchepkov D., Bryanskaya A., Popik V. The transcriptomic response of cells of the thermophilic bacterium Geobacillus icigianus to terahertz irradiation. Int J Mol Sci. 2024;25(22):12059. doi 10.3390/ijms252212059</mixed-citation></citation-alternatives></ref><ref id="cit34"><label>34</label><citation-alternatives><mixed-citation xml:lang="ru">Salgado H., Gama-Castro S., Lara P., Mejia-Almonte C., Alarcón-Carranza G., López-Almazo A.G., Betancourt-Figueroa F., … Hernández-Alvarez A.J., Santos-Zavaleta A., Capella-Gutierrez S., Gelpi J.L., Collado-Vides J. RegulonDB v12.0: a comprehensive resource of transcriptional regulation in E. coli K-12. Nucleic Acids Res. 2024;52(D1):D255-D264. doi 10.1093/nar/gkad1072</mixed-citation><mixed-citation xml:lang="en">Salgado H., Gama-Castro S., Lara P., Mejia-Almonte C., Alarcón-Carranza G., López-Almazo A.G., Betancourt-Figueroa F., … Hernández-Alvarez A.J., Santos-Zavaleta A., Capella-Gutierrez S., Gelpi J.L., Collado-Vides J. RegulonDB v12.0: a comprehensive resource of transcriptional regulation in E. coli K-12. Nucleic Acids Res. 2024;52(D1):D255-D264. doi 10.1093/nar/gkad1072</mixed-citation></citation-alternatives></ref><ref id="cit35"><label>35</label><citation-alternatives><mixed-citation xml:lang="ru">Sayers E.W., Beck J., Bolton E.E., Bourexis D., Brister J.R., Canese K., Comeau D.C., … Wang J., Ye J., Trawick B.W., Pruitt K.D., Sherry S.T. Database resources of the National Center for Biotechnology Information. Nucleic Acids Res. 2021;49(D1):D10-D17. doi 10.1093/nar/gkaa892</mixed-citation><mixed-citation xml:lang="en">Sayers E.W., Beck J., Bolton E.E., Bourexis D., Brister J.R., Canese K., Comeau D.C., … Wang J., Ye J., Trawick B.W., Pruitt K.D., Sherry S.T. Database resources of the National Center for Biotechnology Information. Nucleic Acids Res. 2021;49(D1):D10-D17. doi 10.1093/nar/gkaa892</mixed-citation></citation-alternatives></ref><ref id="cit36"><label>36</label><citation-alternatives><mixed-citation xml:lang="ru">Shimada T., Ogasawara H., Ishihama A. Single-target regulators form a minor group of transcription factors in Escherichia coli K-12. Nucleic Acids Res. 2018;46(8):3921-3936. doi 10.1093/nar/gky138</mixed-citation><mixed-citation xml:lang="en">Shimada T., Ogasawara H., Ishihama A. Single-target regulators form a minor group of transcription factors in Escherichia coli K-12. Nucleic Acids Res. 2018;46(8):3921-3936. doi 10.1093/nar/gky138</mixed-citation></citation-alternatives></ref><ref id="cit37"><label>37</label><citation-alternatives><mixed-citation xml:lang="ru">Tagle D.A., Koop B.F., Goodman M., Slightom J.L., Hess D.L., Jones R.T. Embryonic epsilon and gamma globin genes of a prosimian primate (Galago crassicaudatus). Nucleotide and amino acid sequences, developmental regulation and phylogenetic footprints. J Mol Biol. 1988;203(2):439-455. doi 10.1016/0022-2836(88)90011-3</mixed-citation><mixed-citation xml:lang="en">Tagle D.A., Koop B.F., Goodman M., Slightom J.L., Hess D.L., Jones R.T. Embryonic epsilon and gamma globin genes of a prosimian primate (Galago crassicaudatus). Nucleotide and amino acid sequences, developmental regulation and phylogenetic footprints. J Mol Biol. 1988;203(2):439-455. doi 10.1016/0022-2836(88)90011-3</mixed-citation></citation-alternatives></ref><ref id="cit38"><label>38</label><citation-alternatives><mixed-citation xml:lang="ru">Taliaferro L.P., Keen E.F., Sanchez-Alberola N., Wolf R.E. Transcription activation by Escherichia coli Rob at class II promoters: proteinprotein interactions between Rob’s N-terminal domain and the σ70 subunit of RNA polymerase. J Mol Biol. 2012;419(3-4):139-157. doi 10.1016/j.jmb.2012.03.019</mixed-citation><mixed-citation xml:lang="en">Taliaferro L.P., Keen E.F., Sanchez-Alberola N., Wolf R.E. Transcription activation by Escherichia coli Rob at class II promoters: proteinprotein interactions between Rob’s N-terminal domain and the σ70 subunit of RNA polymerase. J Mol Biol. 2012;419(3-4):139-157. doi 10.1016/j.jmb.2012.03.019</mixed-citation></citation-alternatives></ref><ref id="cit39"><label>39</label><citation-alternatives><mixed-citation xml:lang="ru">Tompa M., Li N., Bailey T.L., Church G.M., De Moor B., Eskin E., Favorov A.V., … Vandenbogaert M., Weng Z., Workman C., Ye C., Zhu Z. Assessing computational tools for the discovery of transcription factor binding sites. Nat Biotechnol. 2005;23(1):137-144. doi 10.1038/nbt1053</mixed-citation><mixed-citation xml:lang="en">Tompa M., Li N., Bailey T.L., Church G.M., De Moor B., Eskin E., Favorov A.V., … Vandenbogaert M., Weng Z., Workman C., Ye C., Zhu Z. Assessing computational tools for the discovery of transcription factor binding sites. Nat Biotechnol. 2005;23(1):137-144. doi 10.1038/nbt1053</mixed-citation></citation-alternatives></ref><ref id="cit40"><label>40</label><citation-alternatives><mixed-citation xml:lang="ru">Tyson K.L., Bell A.I., Cole J.A., Busby S.J. Definition of nitrite and nitrate response elements at the anaerobically inducible Escherichia coli nirB promoter: interactions between FNR and NarL. Mol Microbiol. 1993;7(1):151-157. doi 10.1111/j.1365-2958.1993.tb01106.x</mixed-citation><mixed-citation xml:lang="en">Tyson K.L., Bell A.I., Cole J.A., Busby S.J. Definition of nitrite and nitrate response elements at the anaerobically inducible Escherichia coli nirB promoter: interactions between FNR and NarL. Mol Microbiol. 1993;7(1):151-157. doi 10.1111/j.1365-2958.1993.tb01106.x</mixed-citation></citation-alternatives></ref><ref id="cit41"><label>41</label><citation-alternatives><mixed-citation xml:lang="ru">Tyson K.L., Cole J.A., Busby S.J. Nitrite and nitrate regulation at the promoters of two Escherichia coli operons encoding nitrite reductase: identification of common target heptamers for both NarP- and NarL-dependent regulation. Mol Microbiol. 1994;13(6):1045-1055. doi 10.1111/j.1365-2958.1994.tb00495.x</mixed-citation><mixed-citation xml:lang="en">Tyson K.L., Cole J.A., Busby S.J. Nitrite and nitrate regulation at the promoters of two Escherichia coli operons encoding nitrite reductase: identification of common target heptamers for both NarP- and NarL-dependent regulation. Mol Microbiol. 1994;13(6):1045-1055. doi 10.1111/j.1365-2958.1994.tb00495.x</mixed-citation></citation-alternatives></ref><ref id="cit42"><label>42</label><citation-alternatives><mixed-citation xml:lang="ru">Ushida C., Aiba H. Helical phase dependent action of CRP: effect of the distance between the CRP site and the –35 region on promoter activity. Nucleic Acids Res. 1990;18(21):6325-6330. doi 10.1093/nar/18.21.6325</mixed-citation><mixed-citation xml:lang="en">Ushida C., Aiba H. Helical phase dependent action of CRP: effect of the distance between the CRP site and the –35 region on promoter activity. Nucleic Acids Res. 1990;18(21):6325-6330. doi 10.1093/nar/18.21.6325</mixed-citation></citation-alternatives></ref><ref id="cit43"><label>43</label><citation-alternatives><mixed-citation xml:lang="ru">Xiao M., Lai Y., Sun J., Chen G., Yan A. Transcriptional regulation of the outer membrane porin gene ompW reveals its physiological role during the transition from the aerobic to the anaerobic lifestyle of Escherichia coli. Front Microbiol. 2016;7:799. doi 10.3389/fmicb.2016.00799</mixed-citation><mixed-citation xml:lang="en">Xiao M., Lai Y., Sun J., Chen G., Yan A. Transcriptional regulation of the outer membrane porin gene ompW reveals its physiological role during the transition from the aerobic to the anaerobic lifestyle of Escherichia coli. Front Microbiol. 2016;7:799. doi 10.3389/fmicb.2016.00799</mixed-citation></citation-alternatives></ref><ref id="cit44"><label>44</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang P., Ye Z., Ye C., Zou H., Gao Z., Pan J. OmpW is positively regulated by iron via Fur, and negatively regulated by SoxS contribution to oxidative stress resistance in Escherichia coli. Microb Pathog. 2020;138:103808. doi 10.1016/j.micpath.2019.103808</mixed-citation><mixed-citation xml:lang="en">Zhang P., Ye Z., Ye C., Zou H., Gao Z., Pan J. OmpW is positively regulated by iron via Fur, and negatively regulated by SoxS contribution to oxidative stress resistance in Escherichia coli. Microb Pathog. 2020;138:103808. doi 10.1016/j.micpath.2019.103808</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
