<?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">uprinmatus</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1536</issn><publisher><publisher-name>Юго-Западный государственный университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1536-2025-15-3-122-141</article-id><article-id custom-type="elpub" pub-id-type="custom">uprinmatus-353</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>СИСТЕМНЫЙ АНАЛИЗ И ПРИНЯТИЕ РЕШЕНИЙ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>SYSTEM ANALYSIS AND DECISION-MAKING</subject></subj-group></article-categories><title-group><article-title>Оценка точности методов контроля частоты ложных срабатываний при аннотации спектра de novo</article-title><trans-title-group xml:lang="en"><trans-title>Evaluation of the accuracy of false alarm frequency control methods for de novo spectrum</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-5597-5037</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тевяшов</surname><given-names>М. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Tevyashov</surname><given-names>M. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тевяшов Михаил Михайлович, младший научный сотрудник</p><p>наб. канала Грибоедова, д. 30-32, г. Санкт-Петербург 191023</p></bio><bio xml:lang="en"><p>Mikhail M. Teviashov, Research Assistant</p><p>30-32 Griboedov canal Emb., St. Petersburg 191023</p></bio><email xlink:type="simple">tukaramm@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный экономический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State University of Economics</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>22</day><month>11</month><year>2025</year></pub-date><volume>15</volume><issue>3</issue><fpage>122</fpage><lpage>141</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Тевяшов М.М., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Тевяшов М.М.</copyright-holder><copyright-holder xml:lang="en">Tevyashov M.M.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" 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://uprinmatus.elpub.ru/jour/article/view/353">https://uprinmatus.elpub.ru/jour/article/view/353</self-uri><abstract><p>Цель – сравнение подходов на основе машинного обучения (deep learning) и классических методов по качеству аннотации масс-спектров в условиях больших данных, а также выявление оптимального сценария их интеграции.</p><sec><title>Методы</title><p>Методы. Исследование базируется на использовании набора данных PXD004452, содержащего 2,5 млн уникальных пептидов.</p><p>Разработана схема взаимодействия на основе Python/TensorFlow/PyTorch, который обеспечивает параллельную обработку пептидных спектров на GPU-кластере. Использованы следующие этапы: фильтрация топ‑150 пиков по интенсивности; генерация теоретических B-/Y-ионов с учетом модификаций; предсказание пептидов (PepNet – сверточная+рекуррентная сеть; Tide-search – индексная перехеширующая стратегия). Метрики: количества совпадений, дельта-масса, расстояние Левенштейна, ROC‑кривые, распределение ошибок.</p></sec><sec><title>Результаты</title><p>Результаты. PepNet требует значительных вычислительных ресурсов, при этом качество предсказаний уступает Tide-search, особенно на длинных пептидах и модификациях (~среднее совпадение: 4,2 пика vs 9,7; p &lt; 0,001). Однако PepNet лучше показывает себя при тех спектрах, где в database search отсутствуют релевантные последовательности, демонстрируя важную способность выявлять novel‑пептиды. Распределение расстояния Левенштейна: ~30% – полное совпадение (0); ~52% – небольшое отклонение (1–5); остальное – значительные расхождения (&gt;5).</p></sec><sec><title>Заключение</title><p>Заключение. Метод deep learning (PepNet) демонстрирует перспективы, но без интеграции с database search уступает по точности.</p><p>Предлагается гибридная архитектура: pep‑tagging через PepNet, затем уточнение и верификация через database search. Такой конвейер на больших данных позволит сочетать открытие новых пептидов (de novo) и высокую достоверность идентификации (database search).</p></sec></abstract><trans-abstract xml:lang="en"><p>The purpose of the research is comparison of machine learning-based approaches (deep learning) and classical methods for mass spectrum annotation in big data conditions, as well as identification of the optimal scenario for their integration.</p><sec><title>Methods</title><p>Methods. The study is based on the PXD004452 dataset containing 2,5 million unique peptides. An interaction scheme based on Python/TensorFlow/PyTorch has been developed, which provides parallel processing of peptide spectra on a GPU cluster. The following steps were used: filtering of the top 150 peaks by intensity; generation of theoretical B-/Y-ions, taking into account modifications; prediction of peptides (PepNet – convolutional+recurrent network; Tidesearch – index-shifting strategy). Metrics: number of matches, delta mass, Levenshtein distance, ROC curves, error distribution.</p></sec><sec><title>Results</title><p>Results. PepNet requires significant computational resources, while the prediction quality is inferior to Tide-search, especially for long peptides and modifications (~average match: 4,2 pi vs 9,7; p &lt; 0,001). However, PepNet performs better in those spectra where relevant sequences are missing in the database search, demonstrating an important ability to identify novel peptides. Levenshtein distance distribution: ~30% is a complete match (0); ~52% is a small deviation (1-5); the rest is significant discrepancies (&gt;5).</p></sec><sec><title>Conclusions</title><p>Conclusions. The deep learning (PepNet) method shows promise, but without integration with database search, it is inferior in accuracy. A hybrid architecture is proposed: pep-tagging via PepNet, followed by refinement and verification via database search. Such a big data pipeline will combine the discovery of new peptides (de novo) and high identification reliability (database search).</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>машинное обучение</kwd><kwd>масс-спектрометрия</kwd><kwd>расстояние Левенштайна</kwd><kwd>спектры</kwd></kwd-group><kwd-group xml:lang="en"><kwd>machine learning</kwd><kwd>mass spectrometry</kwd><kwd>Levenstein distance</kwd><kwd>spectra</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Выражаем благодарность заведующему научно-учебной лабораторией искусственного интеллекта для вычислительной биологии НИУ ВШЭ доктору наук Кертес-Фаркаш Аттила за формирование методологии исследования и предоставление данных для статьи.</funding-statement><funding-statement xml:lang="en">We would like to thank Dr. Kertes-Farkash Attila, Head of the HSE Scientific and Educational Laboratory of Artificial Intelligence for Computational Biology, for developing the research methodology and providing data for the article.</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">De novo: определение, применение, значение. URL: https://www.cd-genomics.com/blog/de-novo-definition-applications-meaning/ (дата обращения: 15.06.2025).</mixed-citation><mixed-citation xml:lang="en">De novo: definition, application, meaning. (In Russ.) Available at: https://www.cd-genomics.com/ blog/de-novo-definition-applications-meaning/ (accessed 15.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Acquaye F. L., Kertesz-Farkas A., Noble W. S. Эффективное индексирование пептидов для поиска в базе данных с использованием Tide // Journal of Proteome Research. 2023. Vol. 22, N 2. P. 577–584.</mixed-citation><mixed-citation xml:lang="en">Acquaye F.L., Kertesz-Farkas A., Noble W.S. Efficient indexing of peptides for database search using Tide. Journal of Proteome Research. 2023;22(2):577–584. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Секвенирование белков de novo: приложения, проблемы и достижения. URL: https://www.creative-proteomics.com/resource/protein-de-novo-sequencing-applicationschallenges-advances.htm (дата обращения: 11.06.2025).</mixed-citation><mixed-citation xml:lang="en">De novo protein sequencing: applications, problems and achievements. (In Russ.) Available at: https://www.creative-proteomics.com/resource/protein-de-novo-sequencing-applications-challenges-advances.htm (accessed 11.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Ng C. C. A., Zhou Y., Yao Z. P. Algorithms for de novo sequencing of peptides by tandem mass spectrometry: A review // Analytica Chimica Acta. 2023. N 1268. P. 341330.</mixed-citation><mixed-citation xml:lang="en">Ng C.C.A., Zhou Y., Yao Z.P. Algorithms for de novo sequencing of peptides by tandem mass spectrometry: A review. Analytica Chimica Acta. 2023;(1268):341330. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Секвенирование белков de novo: приложения, проблемы и достижения. URL: https://www.creative-proteomics.com/resource/protein-de-novo-sequencing-applicationschallenges-advances.htm (дата обращения: 13.06.2025).</mixed-citation><mixed-citation xml:lang="en">De novo protein sequencing: applications, challenges, and achievements. (In Russ.) Available at: https://www.creative-proteomics.com/resource/protein-de-novo-sequencing-applications-challenges-advances.htm (accessed 13.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Accurate de novo peptide sequencing using fully convolutional neural networks / Kaiyuan Liu, Yuzhen Ye, Sujun Li, Haixu Tang // Nature Communications. 2023. N 14. P. 7974.</mixed-citation><mixed-citation xml:lang="en">Kaiyuan Liu, Yuzhen Ye, Sujun Li, Haixu Tang. Accurate de novo peptide se-quencing using fully convolutional neural networks. Nature Communications. 2023;(14):7974. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Основные термины фрагментации: B ионы и Y ионы в масс спектрометрии пептидов. URL: https://www.mtoz-biolabs.com/how-are-the-b-ions-and-y-ions-defined-in-massspectrometry.html (дата обращения: 15.06.2025).</mixed-citation><mixed-citation xml:lang="en">Basic fragmentation terms: B-ions and Y-ions in peptide mass spectrometry. (In Russ.) Available at: https://www.mtoz-biolabs.com/how-are-the-b-ions-and-y-ions-defined-in-massspectrometry.html (accessed 15.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Расстояние Левенштейна. URL: https://en.wikipedia.org/wiki/Levenshtein_distance (дата обращения: 15.06.2025).</mixed-citation><mixed-citation xml:lang="en">Levenshtein distance. (In Russ.) Available at: https://en.wikipedia.org/wiki/Levenshtein_distance (accessed 15.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Integrating Database Search and de Novo Sequencing for Immunopeptidomics with DIA Approach / P. Shan, H. Tran [et al.]. URL: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6936894/ (дата обращения: 15.06.2025).</mixed-citation><mixed-citation xml:lang="en">Shan P., Tran H., et al. Integrating Database Search and de Novo Sequencing for Immunopeptidomics with DIA Approach. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6936894/ (accessed 15.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Ebrahimi S., Guo X. Transformer based de novo peptide sequencing for data independent acquisition mass spectrometry (DiaTrans) // 2023 IEEE 23rd International Conference on Bioinformatics and Bioengineering (BIBE). P. 17–22. URL: https://arxiv.org/abs/2402.11363 (дата обращения: 22.06.2025).</mixed-citation><mixed-citation xml:lang="en">Ebrahimi S., Guo X. Transformer based de novo peptide sequencing for data independent acquisition mass spectrometry (DiaTrans). In: 2023 IEEE 23rd International Conference on Bioinformatics and Bioengineering (BIBE). P. 17–22. Available at: https://arxiv.org/abs/2402.11363 (accessed 22.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Bioinformatics Methods for Mass Spectrometry Based Proteomics Data Analysis / Chen Chen, Jie Hou, John J. Tanner, Jianlin Cheng // Int. J. Mol. Sci. 2020. N 21(8). P. 2873. https://doi.org/10.3390/ijms21082873</mixed-citation><mixed-citation xml:lang="en">Chen Chen, Jie Hou, John J. Tanner, Jianlin Cheng. Bioinformatics Methods for Mass Spectrometry Based Proteomics Data Analysis. Int. J. Mol. Sci. 2020;(21):2873. https://doi.org/10.3390/ijms21082873</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">DePS: An improved deep learning model for de novo peptide sequencing / C. Ge [et al.]. URL: https://arxiv.org/abs/2203.08820 (дата обращения: 22.06.2025).</mixed-citation><mixed-citation xml:lang="en">Ge C., et al. DePS: An improved deep learning model for de novo peptide sequencing. Available at: https://arxiv.org/abs/2203.08820 (accessed 22.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">PowerNovo: de novo peptide sequencing via tandem mass spectrometry using an ensemble of transformer and BERT models / D. V. Petrovskiy [et al.] // Sci. Rep. 2024. N 14. P. 15000.</mixed-citation><mixed-citation xml:lang="en">Petrovskiy D. V., et al. PowerNovo: de novo peptide sequencing via tandem mass spectrometry using an ensemble of transformer and BERT models. Sci. Rep. 2024;(14):15000.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing (LIPNovo) / Y. Du [et al.]. URL: https://arxiv.org/html/2505.17524v1 (дата обращения: 22.06.2025).</mixed-citation><mixed-citation xml:lang="en">Du Y., et al. Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing (LIPNovo). Available at: https://arxiv.org/html/2505.17524v1 (accessed 22.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">π PrimeNovo: an accurate and efficient non autoregressive deep learning model for de novo peptide sequencing / X. Zhang [et al.] // Nat. Commun. 2025. N 16. P. 267.</mixed-citation><mixed-citation xml:lang="en">Zhang X., et al. π PrimeNovo: an accurate and efficient non autoregressive deep learning model for de novo peptide sequencing. Nat. Commun. 2025;(16):267.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Peptide-Spectra Matching from Weak Supervision / S. S. Schoenholz, S. Hackett, L. Deming [et al.]. URL: https://arxiv.org/abs/1808.06576. (дата обращения: 12.06.2025).</mixed-citation><mixed-citation xml:lang="en">Schoenholz S.S., Hackett S., Deming L., et al. Peptide-Spectra Matching from Weak Supervision. Available at: https://arxiv.org/abs/1808.06576. (accessed 12.06.2025).</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Complementary methods for de novo monoclonal antibody sequencing to achieve complete sequence coverage / J. Cheng [et al.] // J. Proteome. Res. 2020. N 19(7). P. 2700– 2707.</mixed-citation><mixed-citation xml:lang="en">Cheng J., et al. Complementary methods for de novo monoclonal antibody sequencing to achieve complete sequence coverage. J. Proteome. Res. 2020;19(7):2700–2707.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">De novo peptide sequencing by deep learning / N. H. Tran [et al.] // Proceedings of the National Academy of Sciences (PNAS). 2017. Vol. 114, N 31. P. 8247–8252. https://doi.org/10.1073/pnas.1705691114</mixed-citation><mixed-citation xml:lang="en">Tran N.H., et al. De novo peptide sequencing by deep learning. Proceedings of the National Academy of Sciences (PNAS). 2017;114(31):8247–8252. https://doi.org/10.1073/pnas.1705691114</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">DPST: De Novo Peptide Sequencing with Amino Acid Aware Transformers / Y. Yang [et al.]. URL: https://arxiv.org/abs/2203.13132 (дата обращения: 22.06.2025).</mixed-citation><mixed-citation xml:lang="en">Yang Y., et al. DPST: De Novo Peptide Sequencing with Amino Acid Aware Transformers. Available at: https://arxiv.org/abs/2203.13132 (accessed 22.06.2025).</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>
