Potential Biomarker Discovery with Auto-Encoder from 16s Sequence Data in Inflammatory Bowel Disease (IBD)

Year 2024, Volume: 6 Issue: 2, 347 - 357, 31.08.2024

Aysenur Soyturk Patat , Eda Dağdevir

Abstract

Microbial communities with functional and ecological balance (homeostasis) in a habitat are called microbiota. Microbiome is the name given to the total genetic material that makes up this community and the interaction of these genetic materials with the environment. Studies have shown that we have a symbiotic relationship with our microbiota. With the widespread use of new generation DNA sequencing technologies and the development of computers with high computational capabilities, studies to explore the human microbiome and its effects on health have increased. Recent studies have shown that a person's microbiome profile is associated with many diseases. Microbiome studies, which can change the method of treatment in case of disease, and high-potential translational outputs have become a priority area. However, it is very difficult to find high accuracy features that can be used in the diagnosis or treatment of the disease in this very complex data. Deep learning techniques, on the other hand, achieve inspiring success in various studies on complex data, especially in the field of classification. The emergence of auto-coding (AE) techniques is a neural network architecture designed for the feature selection task. In our study, the attributes that were considered important in representing the data were determined by an auto-encoder, and IBD patients and healthy controls were successfully classified with the XGBoost algorithm with an accuracy value of 88.89%, just by looking at the frequency of occurrence of these determined attributes in the groups. With the proposed method, microbial species representing IBD disease are thought to constitute possible biomarkers for the diagnosis of the disease.

Keywords

Inflammatory Bowel Disease (IBD), Auto-Encoding, 16S Sequencing

Supporting Institution

Tubitak

Project Number

Project number 1919B012217100

Thanks

This study was supported by TÜBİTAK with program 2209 and project number 1919B012217100.

İnflamatuar Bağırsak Hastalığında (İBH) 16s Sekans Verilerinden Oto-Kodlayıcı ile Muhtemel Biyobelirteç Keşfi

Abstract

Bir habitattaki fonksiyonel ve ekolojik dengeye (homeostasis) sahip mikrobiyal komünitelere mikrobiyota denir. Mikrobiyom ise bu komüniteyi oluşturan toplam genetik materyal ve bu genetik materyallerin çevre ile etkileşimine verilen isimdir. Mikrobiyotamız ile simbiyotik bir ilişki içinde olduğumuz yapılan çalışmalarla gösterilmiştir. Yeni nesil DNA dizileme teknolojilerinin yaygınlaşması ve hesaplama kabiliyeti yüksek bilgisayarların gelişmesi ile insan mikrobiyomunu ve sağlığa etkilerini keşfetmeye yönelik çalışmalar artmıştır. Yakın zamandaki araştırmalar birçok hastalıkla, kişinin mikrobiyom profilinin ilişkili olduğunu göstermiştir. Hastalık durumunda tedavinin yöntemini değiştirebilecek nitelikteki mikrobiyom çalışmaları, yüksek potansiyelli translasyonel çıktıları öncelikli alan haline gelmiştir. Ancak oldukça karmaşık olan bu verinin içerisinde hastalığın tanı ya da tedavisinde kullanılabilecek yüksek doğrulukta özniteliklerin bulunması oldukça zordur. Derin öğrenme teknikleri ise çeşitli çalışmalarda özellikle sınıflandırma alanında karmaşık verilerde ilham verici başarılar elde etmektedir. Oto-kodlama (AE) tekniklerinin ortaya çıkışı ise özellik seçme görevi için tasarlanmış bir sinir ağı mimarisidir. Bizim çalışmamızda veriyi yeniden temsil etmede önemli olarak görülen öznitelikler bir oto-kodlayıcısı tarafından belirlenmiş ve sadece belirlenen bu özniteliklerin gruplarda görülme sıklığına bakılarak İBH hastaları ve sağlıklı kontroller XGBoost algoritmasıyla %88.89 doğruluk değeri ile başarılı bir şekilde sınıflandırılmıştır. Önerilen yöntemle İBH hastalığını temsil eden mikrobiyol türler hastalığın tanısı için muhtemel biyobelirteçleri oluşturduğu düşünülmektedir.

Keywords

İnflamatuar Bağırsak Hastalığında (İBH), Oto-Kodlayıcı, 16S Sekanslama

Supporting Institution

Tubitak

Project Number

Project number 1919B012217100

Thanks

This study was supported by TÜBİTAK with program 2209 and project number 1919B012217100.

References

• L.-H. Lee, S. H. Wong, S.-F. Chin, V. Singh, and N.-S. Ab Mutalib, Editorial: Human Microbiome: symbiosis to pathogenesis, Frontiers in Microbiology. 12 (2021), doi: 10.3389/fmicb.2021.605783.
• P. J. Turnbaugh, R. E. Ley, M. Hamady, C. M. Fraser-Liggett, R. Knight, and J. I. Gordon, The human microbiome project, Nature, 449(7164) (2007), 804–810, doi: 10.1038/nature06244.
• C. G. Buffie, M.Equinda, L.Lipuma, A.Gobourne, A.Viale, C.Ubeda, J.Xavier, E.G.Pamer, Profound alterations of intestinal microbiota following a single dose of clindamycin results in sustained susceptibility to Clostridium difficile-induced colitis, Infection and Immunity. 80(1) (2012), 62–73, doi: 10.1128/IAI.05496-11.
• A. Gundogdu, Bir ‘Süper Organizma’ olarak insan; mikrobiyomun genetik kontrolü, Türk Mikrobiyoloji Cemiyeti Dergisi. 46(4) (2016), doi: 10.5222/TMCD.2016.147.
• X. Yang, L. Xie, Y. Li, C. Wei, More than 9,000,000 unique genes in human gut bacterial community: estimating gene numbers inside a human body, PLoS ONE. 4(6) (2009), doi: 10.1371/journal.pone.0006074.
• G. Berg, D. Rybakova, D. Fischer, T. Cernava, M.C. Vergès, T. Charles, X. Chen, L. Cocolin, K. Eversole, G.H. Corral, M. Kazou, L. Kinkel, L. Lange, N. Lima, A. Loy, J.A. Macklin, E. Maguin, T. Mauchline, R. McClure, B. Mitter, M. Ryan, I. Sarand, H. Smidt, B. Schelkle, H. Roume, G.S. Kiran, J. Selvin, R.S.C. Souza, L. van Overbeek, B.K. Singh BK, M. Wagner, A. Walsh, A. Sessitsch, M. Schloter, Microbiome definition re-visited: old concepts and new challenges, Microbiome. 8(1) (2020) 119. doi: 10.1186/s40168-020-00875-0
• F & H Löchel, D. Heider, Comparative analyses of error handling strategies for next-generation sequencing in precision medicine, Scientific Reports. 10(1) (2020), 5750. doi: 10.1038/s41598-020-62675-8
• A.L. Lapidus, A.I. Korobeynikov, Metagenomic Data Assembly - The Way of Decoding Unknown Microorganisms, Frontiers in Microbiology. 12 (2021), 613791. doi:10.3389/fmicb.2021.613791
• S. Jünemann, N. Kleinbölting, S. Jaenicke, C. Henke, J. Hassa, J. Nelkner, Y. Stolze, S.-P. Albaum, A. Schlüter, A. Goesmann, A. Sczyrba, J.Stoye, Bioinformatics for NGS-based metagenomics and the application to biogas research, Journal of Biotechnology. 261 (2017), 10–23. doi: 10.1016/j.jbiotec.2017.08.012.
• J. Reinartz, E. Bruyns, J. Z. Lin, T. Burcham, S. Brenner, B. Bowen, M. Kramer, R. Woychik, Massively parallel signature sequencing (MPSS) as a tool for in-depth quantitative gene expression profiling in all organisms, Briefings in Functional Genomics & Proteomics, 1(1), (2002), 95–104. doi:10.1093/bfgp/1.1.95
• E.L. van Dijk, Y. Jaszczyszyn, D. Naquin, C. Thermes, The Third Revolution in Sequencing Technology, Trends in Genetics. 34(9) (2018), 666–681. doi:10.1016/j.tig.2018.05.008
• Q. Wang, G. M. Garrity, J. M. Tiedje, and J. R. Cole, Naive Bayesian classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy, Applied and Environmental Microbiology, 73(16), (2007), 5261–5267. doi: 10.1128/AEM.00062-07.
• F.-H. Karlsson, V. Tremaroli, I. Nookaew, G., Bergström, C.-J. Behre, B. Fagerberg, J. Nielsen, F. Bäckhed, Gut metagenome in European women with normal, impaired and diabetic glucose control, Nature. 498(7452) (2013), 99–103. doi: 10.1038/nature12198.
• K. Forslund, F. Hildebrand, T. Nielsen, G. Falony, E. Le Chatelier, S. Sunagawa, E. Prifti, S. Vieira-Silva, V. Gudmundsdottir, H.-K. Pedersen, M. Arumugam, K. Kristiansen, A.Y. Voigt, Vestergaard, H., Hercog, R., P. I. Costea, J. R. Kultima, J. Li, T. Jørgensen, F. Levenez, O. Pedersen, Corrigendum: Disentangling type 2 diabetes and metformin treatment signatures in the human gut microbiota, Nature. 545(7652), (2017), 116. doi: 10.1038/nature22318.
• H. İ. Ayaz ve Z. Kamışlı Öztürk, Shilling attack detection with one class support vector machines, Necmettin Erbakan University Journal of Science and Engineering. 5(2) (2023), 246–256. doi: 10.47112/neufmbd.2023.22.
• M. Hacıbeyoğlu, M. Çelik, Ö. Erdaş Çiçek, Energy efficiency estimation in buildings with K nearest neighbor algorithm, Necmettin Erbakan University Journal of Science and Engineering. 5(2) (2023), 65–74. doi: 10.47112/neufmbd.2023.10.
• A. Mathieu, M. Leclercq, M. Sanabria, O. Perin, A. Droit, Machine learning and deep learning applications in metagenomic taxonomy and functional annotation, Frontiers in Microbiology. 13 (2022). doi:10.3389/fmicb.2022.811495
• P. Li, Y. Pei, and J. Li, A comprehensive survey on design and application of autoencoder in deep learning, Applied Soft Computing. 138 (2023). doi:10.1016/j.asoc.2023.110176
• E. Bolyen, J. R. Rideout, M. R. Dillon, N. A. Bokulich, C. C. Abnet, G. A. Al-Ghalith, H. Alexander, E. J.Alm, M. Arumugam, F. Asnicar, Y. Bai, J. E. Bisanz, K. Bittinger, A. Brejnrod, C. J. Brislawn, C. T. Brown, B. J. Callahan, A. M. Caraballo-Rodríguez, J. Chase, E. K. Cope, J. G. Caporaso, Reproducible, interactive, scalable and extensible microbiome data science using QIIME 2, Nature Biotechnology. 37(8) (2019), 852–857. doi: 10.1038/s41587-019-0209-9.
• P.P. Líndez, J. Johansen, S. Kutuzova, Adversarial and variational autoencoders improve metagenomic binning, Commununications Biology. 1073 (2023). doi:10.1038/s42003-023-05452-3
• T. Chen and C. Guestrin, XGBoost: A Scalable Tree Boosting System, in: Volume 16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 2016, 785–794. doi: 10.1145/2939672.2939785.
• J. Carriere, A. Darfeuille-Michaud, HTT. Nguyen, Infectious etiopathogenesis of Crohn’s disease, World Journal of Gastroenterology, (2014). doi: 10.3748/wjg.v20.i34.12102
• S.C. Ng, C.N. Bernstein, M.H. Vatn, P.L. Kakatos, E.V. Loftus, C. Tysk, Geographic variability and environmental risk factors in inflammatory bowel disease, Gut, 62, (2013),630–49. doi: 10.1136/gutjnl-2012-303661
• M. Leon, T. Markovic, and S. Punnekkat, Feature Encoding with Autoencoder and Differential Evolution for Network Intrusion Detection Using Machine Learning, in: GECCO ’22: Proceedings of the Genetic and Evolutionary Computation Conference Companion, New York, NY, USA, 2022, 2152–2159. doi: 10.1145/3520304.3534009.
• J. Lloyd-Price, C. Arze, A.N. Ananthakrishnan, M. Schirmer, J. Avila-Pacheco, T. W. Poon, E. Andrews, N.J. Ajami, K. S. Bonham, C. J. Brislawn, D. Casero, H. Courtney, A. Gonzalez, T. G. Graeber, A. B. Hall, A, K. Lake, C. J. Landers, H. Mallick, D. R. Plichta, M. Prasad, C. Huttenhower, Multi-omics of the gut microbial ecosystem in inflammatory bowel diseases, Nature. 569(7758) (2019) 655–662. doi:10.1038/s41586-019-1237-9
• G. S. Navgire, N. Goel, G. Sawhney, M. Sharma, P. Kaushik, Y.K. Mohanta, T. K. Mohanta, A. Al-Harrasi, Analysis and ınterpretation of metagenomics data: an approach, Biological Procedures Online. 24(1) (2022) 18. doi:10.1186/s12575-022-00179-7