1,455
Views
2
CrossRef citations to date
0
Altmetric
Research Paper

Ordering taxa in image convolution networks improves microbiome-based machine learning accuracy

, , , &
Article: 2224474 | Received 15 Dec 2022, Accepted 08 Jun 2023, Published online: 21 Jun 2023

References

  • Bunyavanich S, Shen N, Grishin A, Wood R, Burks W, Dawson P, Jones SM, Leung DYM, Sampson H, Sicherer S, et al. Early-life gut microbiome composition and milk allergy resolution. J Allergy Clin Immunol. 2016;138(4):1122–22. doi:10.1016/j.jaci.2016.03.041.
  • Lee K. Hung, Guo J, Song Y, Ariff A, O’sullivan M, Hales B, Mullins BJ, Zhang G. Dysfunctional gut microbiome networks in childhood IgE-mediated food allergy. Int J Mol Sci. 2021;22(4):2079. doi:10.3390/ijms22042079.
  • Fettweis JM, Serrano MG, Paul Brooks J, Edwards DJ, Girerd PH, Parikh HI, Huang B, Arodz TJ, Edupuganti L, Glascock AL, et al. The vaginal microbiome and preterm birth. Nat Med. 2019;25(6):1012–1021. doi:10.1038/s41591-019-0450-2.
  • Michail S, Durbin M, Turner D, Griffiths AM, Mack DR, Hyams J, Leleiko N, Kenche H, Stolfi A, Wine E. Alterations in the gut microbiome of children with severe ulcerative colitis. Inflamm Bowel Dis. 2012;18(10):1799–1808. doi:10.1002/ibd.22860.
  • Goldberg MR, Mor H, Magid Neriya D, Magzal F, Muller E, Appel MY, Nachshon L, Borenstein E, Tamir S, Louzoun Y, et al. Microbial signature in IgE-mediated food allergies. Genome Med. 2020;12(1):1–18. doi:10.1186/s13073-020-00789-4.
  • Binyamin D, Werbner N, Nuriel-Ohayon M, Uzan A, Mor H, Abbas A, Ziv O, Teperino R, Gutman R, Koren O. The aging mouse microbiome has obesogenic characteristics. Genome Med. 2020;12(1):1–9. doi:10.1186/s13073-020-00784-9.
  • Ward DM, Weller R, Bateson MM. 16s rRNA sequences reveal numerous uncultured microorganisms in a natural community. Nature. 1990;345(6270):63–65. doi:10.1038/345063a0.
  • Poretsky R, Rodriguez-R LM, Luo C, Tsementzi D, Konstantinidis KT, Rodriguez-Valera F. Strengths and limitations of 16s rRNA gene amplicon sequencing in revealing temporal microbial community dynamics. PLos One. 2014;9(4):e93827. doi:10.1371/journal.pone.0093827.
  • Ross AB, Bruce SJ, Blondel-Lubrano A, Oguey-Araymon S, Beaumont M, Bourgeois A, Nielsen-Moennoz C, Vigo M, Fay L-B, Kochhar S, et al. A whole-grain cereal-rich diet increases plasma betaine, and tends to decrease total and ldl-cholesterol compared with a refined-grain diet in healthy subjects. Br J Nutr. 2011;105(10):1492–1502. doi:10.1017/S0007114510005209.
  • Gupta VK, Kim M, Bakshi U, Cunningham KY, Davis JM III, Lazaridis KN, Nelson H, Chia N, Sung J. A predictive index for health status using species-level gut microbiome profiling. Nat Commun. 2020;11(1):4635. doi:10.1038/s41467-020-18476-8.
  • Wang J, Zheng J, Shi W, Du N, Xiaomin X, Zhang Y, Peifeng J, Zhang F, Jia Z, Wang Y, et al. Dysbiosis of maternal and neonatal microbiota associated with gestational diabetes mellitus. Gut. 2018;67(9):1614–1625. doi:10.1136/gutjnl-2018-315988.
  • Prodan A, Tremaroli V, Brolin H, Zwinderman AH, Nieuwdorp M, Levin E, Seo J-S. Comparing bioinformatic pipelines for microbial 16s rRNA amplicon sequencing. PLoS One. 2020;15(1):e0227434. doi:10.1371/journal.pone.0227434.
  • Darcy JL, Washburne AD, Robeson MS, Prest T, Schmidt SK, Lozupone CA. A phylogenetic model for the recruitment of species into microbial communities and application to studies of the human microbiome. Isme J. 2020;14(6):1359–1368. doi:10.1038/s41396-020-0613-7.
  • Qiu Y-Q, Tian X, Zhang S. Infer metagenomic abundance and reveal homologous genomes based on the structure of taxonomy tree. IEEE/ACM Trans Comput Biol Bioinf. 2015;12(5):1112–1122. doi:10.1109/TCBB.2015.2415814.
  • Asgari E, Münch PC, Lesker TR, McHardy AC, Mofrad MRK, Birol I. Ditaxa: nucleotide-pair encoding of 16s rRNA for host phenotype and biomarker detection. Bioinformatics. 2019;35(14):2498–2500. doi:10.1093/bioinformatics/bty954.
  • Lee H, Lee HK, Min SK, Lee WH. 16s rDNA microbiome composition pattern analysis as a diagnostic biomarker for biliary tract cancer. World J Surg Oncol. 2020;18(1):1–10. doi:10.1186/s12957-020-1793-3.
  • Turjeman S, Koren O. Using the microbiome in clinical practice. Microb Biotechnol. 2021;15(1):129–134. doi:10.1111/1751-7915.13971.
  • Nishijima S, Suda W, Oshima K, Kim S-W, Hirose Y, Morita H, Hattori M. The gut microbiome of healthy Japanese and its microbial and functional uniqueness. DNA Res. 2016;23(2):125–133. doi:10.1093/dnares/dsw002.
  • VijiyaKumar K, Lavanya B, Nirmala I, Caroline SS. Random forest algorithm for predicting chronic diabetes disease. 2019 IEEE International Conference on System, Computation, Automation and Networking (ICSCAN). 2019. p. 1–5. doi:10.1109/ICSCAN.2019.8878802.
  • Jacobs JP, Goudarzi M, Singh N, Tong M, McHardy IH, Ruegger P, Asadourian M, Moon B-H, Ayson A, Borneman J, et al. A disease-associated microbial and metabolomics state in relatives of pediatric inflammatory bowel disease patients. Cell Mol Gastroenterol Hepatol. 2016;2(6):750–766. doi:10.1016/j.jcmgh.2016.06.004.
  • Ben Izhak M, Eshel A, Cohen R, Madar-Shapiro L, Meiri H, Wachtel C, Leung C, Messick E, Jongkam N, Mavor E, et al. Projection of gut microbiome pre-and post-bariatric surgery to predict surgery outcome. mSystems. 2020;6(3):e01367–20. doi:10.1128/mSystems.01367-20.
  • Oudah M, Henschel A. Taxonomy-aware feature engineering for microbiome classification. BMC Bioinform. 2018;19(1):1–13. doi:10.1186/s12859-018-2205-3.
  • Albanese D, De Filippo C, Cavalieri D, Donati C, Brem R. Explaining diversity in metagenomic datasets by phylogenetic-based feature weighting. PLoS Comput Biol. 2015;11(3):e1004186. doi:10.1371/journal.pcbi.1004186.
  • Xiao J, Chen L, Yue Y, Zhang X, Chen J. A phylogeny-regularized sparse regression model for predictive modeling of microbial community data. Front Microbiol. 2018;9:3112. doi:10.3389/fmicb.2018.03112.
  • Ditzler G, Polikar R, Rosen G. Multi-layer and recursive neural networks for metagenomic classification. IEEE Trans Nanobioscience. 2015;14(6):608–616. doi:10.1109/TNB.2015.2461219.
  • Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097–1105.
  • Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv Preprint arXiv: 1609 02907. 2016.
  • Park E, Han X, Berg TL, Berg AC. Combining multiple sources of knowledge in deep CNNs for action recognition. 2016 IEEE Winter Conference on Applications of Computer Vision (WACV); Lake Placid, NY, USA. IEEE; 2016. p. 1–8.
  • Bai J, Chen Z, Feng B, Xu B. Image character recognition using deep convolutional neural network learned from different languages. 2014 IEEE International Conference on Image Processing (ICIP); Phoenix, AZ, USA. IEEE; 2014. p. 2560–2564.
  • Sun W, Zheng B, Qian W. Computer aided lung cancer diagnosis with deep learning algorithms. Medical imaging 2016: computer-aided diagnosis. International Society for Optics and Photonics; 2016. Vol. 9785. p. 97850.
  • Reiman D, Metwally AA, Sun J, Dai Y. PopPhy-CNN: a phylogenetic tree embedded architecture for convolutional neural networks to predict host phenotype from metagenomic data. IEEE J Biomed Health Informatics. 2020;24(10):2993–3001. doi:10.1109/JBHI.2020.2993761.
  • Sharma D, Paterson AD, Xu W, Luigi Martelli P. TaxoNN: ensemble of neural networks on stratified microbiome data for disease prediction. Bioinformatics. 2020;36(17):4544–4550. doi:10.1093/bioinformatics/btaa542.
  • Bojing L, Zhong D, Jiang X, Tingting H TopoPhy-CNN: integrating topological information of phylogenetic tree for host phenotype prediction from metagenomic data. 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Virtual. IEEE; 2021. p. 456–461.
  • Ling W, Youran Q, Hua X, Wu MC. Deep ensemble learning over the microbial phylogenetic tree (DeepEn-Phy). 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Virtual. IEEE; 2021. P. 470–477.
  • Gordon-Rodriguez E, Quinn TP, Cunningham JP, Luigi Martelli P. Learning sparse log-ratios for high-throughput sequencing data. Bioinformatics. 2022;38(1):157–163. doi:10.1093/bioinformatics/btab645.
  • Khan S, Kelly L. Multiclass disease classification from microbial whole-community metagenomes. In: Pacific symposium on biocomputing 2020. World Scientific; 2019. p. 55–66. PMID: 31797586.
  • Guang Wang Y, Ming L, Zheng M, Montufar G, Zhuang X, Fan Y. Haar graph pooling. Proceedings of the 37th International Conference on Machine Learning; Virtual. 2020.
  • Diehl F. Edge contraction pooling for graph neural networks. arXiv Preprint arXiv: 190510990. 2019.
  • Luzhnica E, Day B, Lio P. Clique pooling for graph classification. Rlgm, Iclr 2019. 2019.
  • Ying R, You J, Morris C, Ren X, Hamilton WL, Leskovec J. Hierarchical Graph Representation Learning with Differentiable Pooling. Red Hook, NY, USA: Curran Associates Inc; 2018. doi: 10.5555/3327345.3327389.
  • Yuan H, Ji S. Structpool: structured graph pooling via conditional random fields. Proceedings of the 8th International Conference on Learning Representations; Addis Ababa, Ethiopia. 2020.
  • Yao M, Wang S, Aggarwal CC, Tang J. Graph convolutional networks with eigenpooling. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; Washington, DC, USA. 2019. p. 723–731.
  • Nagar O, Frydman S, Hochman O, Louzoun Y. Quadratic GCN for graph classification. arXiv Preprint arXiv: 210406750. 2021.
  • Cao Q, Sun X, Rajesh K, Chalasani N, Gelow K, Katz B, Shah VH, Sanyal AJ, Smirnova E. Effects of rare microbiome taxa filtering on statistical analysis. Front Microbiol. 2021;11:607325. doi:10.3389/fmicb.2020.607325.
  • Xiong C, Ji-Zheng H, Singh BK, Zhu Y-G, Wang J-T, Li P-P, Zhang Q-B, Han L-L, Shen J-P, Ge A-H, et al. Rare taxa maintain the stability of crop mycobiomes and ecosystem functions. Environ Microbiol. 2021;23(4):1907–1924. doi:10.1111/1462-2920.15262.
  • van der Giessen J, Binyamin D, Belogolovski A, Frishman S, Tenenbaum-Gavish K, Hadar E, Louzoun Y, Petrus Peppelenbosch M, van der Woude CJ, Koren O, et al. Modulation of cytokine patterns and microbiome during pregnancy in IBD. Gut. 2020;69(3):473–486. doi:10.1136/gutjnl-2019-318263.
  • Human Microbiome Project Consortium. Structure, function and diversity of the healthy human microbiome. Nature. 2012;486(7402):207. doi:10.1038/nature11234.
  • Ravel J, Gajer P, Zaid Abdo GMS, Koenig SSK, McCulle SL, Karlebach S, Gorle R, Russell J, Tacket CO, Brotman RM. Vaginal microbiome of reproductive-age women. Proc Natl Acad Sci USA. 2011;108(supplement_1):4680–4687. doi:10.1073/pnas.1002611107.
  • Jasner Y, Belogolovski A, Ben-Itzhak M, Koren O, Louzoun Y. Microbiome preprocessing machine learning pipeline. Front Immunol. 2021;12. doi:10.3389/fimmu.2021.677870.
  • Microsoft. Neural Network Intell. 2021;1. doi:10.1155/2021/5512728
  • Fujimura KE, Sitarik AR, Havstad S, Lin DL, Levan S, Fadrosh D, Panzer AR, LaMere B, Rackaityte E, Lukacs NW, et al. Neonatal gut microbiota associates with childhood multisensitized atopy and T cell differentiation. Nat Med. 2016;22(10):1187–1191. doi:10.1038/nm.4176.
  • Willing BP, Dicksved J, Halfvarson J, Andersson AF, Lucio M, Zheng Z, Järnerot G, Tysk C, Jansson JK, Engstrand L. A pyrosequencing study in twins shows that gastrointestinal microbial profiles vary with inflammatory bowel disease phenotypes. Gastroenterology. 2010;139(6):1844–1854. doi:10.1053/j.gastro.2010.08.049.
  • Morgan XC, Tickle TL, Sokol H, Gevers D, Devaney KL, Ward DV, Reyes JA, Shah SA, LeLeiko N, Snapper SB, et al. Dysfunction of the intestinal microbiome in inflammatory bowel disease and treatment. Genome Biol. 2012;13(9):1–18. doi:10.1186/gb-2012-13-9-r79.
  • Duvallet C, Gibbons S, Gurry T, Irizarry R, Alm E. MicrobiomeHD: the human gut microbiome in health and disease [Data set]. Zenodo; 2017. doi:10.5281/zenodo.569601.
  • Doran D, Schulz S, Besold TR. What does explainable ai really mean? a new conceptualization of perspectives. arXiv Preprint arXiv: 171000794. 2017.
  • Chattopadhay A, Sarkar A, Howlader P, Balasubramanian VN. Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV); Lake Tahoe, NV, USA. IEEE; 2018. p. 839–847.
  • Mukhopadhya I, Hansen R, El-Omar EM, Hold GL. IBD—what role do Proteobacteria play? Nat Rev Gastro Hepat. 2012;9(4):219–230. doi:10.1038/nrgastro.2012.14.
  • Zhou Y, He Y, Liu L, Zhou W, Wang P, Han H, Nie Y, Chen Y. Alterations in gut microbial communities across anatomical locations in inflammatory bowel diseases. Front Nutr. 2021;8:58. doi:10.3389/fnut.2021.615064.
  • Zhen H, Wu J, Gong J, Ke J, Ding T, Zhao W, Ming Cheng W, Luo Z, He Q, Zeng W, et al. Microbiota in mesenteric adipose tissue from crohn’s disease promote colitis in mice. Microbiome. 2021;9(1):1–14. doi:10.1186/s40168-021-01178-8.
  • O’callaghan A, Van Sinderen D. Bifidobacteria and their role as members of the human gut microbiota. Front Microbiol. 2016;7:925. doi:10.3389/fmicb.2016.00925.
  • Picard C, Fioramonti J, Francois A, Robinson T, Neant F, Matuchansky C. Bifidobacteria as probiotic agents–physiological effects and clinical benefits. Aliment Pharmacol Ther. 2005;22(6):495–512. doi:10.1111/j.1365-2036.2005.02615.x.
  • Zhang T, Li Q, Cheng L, Buch H, Zhang F. Akkermansia muciniphila is a promising probiotic. Microb Biotechnol. 2019;12(6):1109–1125. doi:10.1111/1751-7915.13410.
  • Sharma D, Xu W. Divya Sharma and Wei Xu. phyLostm: a novel deep learning model on disease prediction from longitudinal microbiome data. Bioinformatics. 2021;37(21):3707–3714. doi:10.1093/bioinformatics/btab482.
  • Goodfellow L, Verwijs MC, Care A, Sharp A, Ivandic J, Poljak B, Roberts D, Christina Bronowski ACG, Darby AC, Alfirevic A. Vaginal bacterial load in the second trimester is associated with early preterm birth recurrence: a nested case–control study. BJOG: Int J Obstet Gynaecol. 2021;128(13):2061–2072. doi:10.1111/1471-0528.16816.
  • Rougé C, Goldenberg O, Ferraris L, Berger B, Rochat F, Legrand A, Göbel UB, Vodovar M, Voyer M, Rozé J-C, et al. Investigation of the intestinal microbiota in preterm infants using different methods. Anaerobe. 2010;16(4):362–370. doi:10.1016/j.anaerobe.2010.06.002.
  • Korpela K, Blakstad EW, Moltu SJ, Strømmen K, Nakstad B, Rønnestad AE, Brække K, Iversen PO, Drevon CA, de Vos W. Intestinal microbiota development and gestational age in preterm neonates. Sci Rep. 2018;8(1):1–9. doi:10.1038/s41598-018-20827-x.
  • Turroni F, Milani C, Duranti S, Andrea Lugli G, Bernasconi S, Margolles A, Di Pierro F, Van Sinderen D, Ventura M. The infant gut microbiome as a microbial organ influencing host well-being. Ital J Pediatr. 2020;46(1):1–13. doi:10.1186/s13052-020-0781-0.
  • Shtossel O, Turjeman S, Riumin A, Goldberg MR, Elizur A, Mor H, Koren O, Louzoun Y. Recipient independent high accuracy FMT prediction and optimization in mice and humans. 2022.
  • Pinto Y, Frishman S, Turjeman S, Eshel A, Nuriel-Ohayon M, Shrossel O, Ziv O, Walters W, Parsonnet J, Ley C, et al. Gestational diabetes is driven by microbiota-induced inflammation months before diagnosis. Gut. 2023;72(5):918–928. doi:10.1136/gutjnl-2022-328406.
  • Falcon W, Pytorch lightning. GitHub. 3 2019; Note. https://github.com/PyTorchLightning/pytorch-lightning
  • Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825–2830.
  • Steve Lawrence CLG, Chung Tsoi A, Andrew DB. Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw. 1997;8(1):98–113. doi:10.1109/72.554195.
  • Vangay P, Hillmann BM, Knights D. Microbiome learning repo ([ml repo]): a public repository of microbiome regression and classification tasks. Gigascience. 2019;8(5):giz042. doi:10.1093/gigascience/giz042.
  • Qin N, Yang F, Li A, Prifti E, Chen Y, Shao L, Guo J, Le Chatelier E, Yao J, Wu L, et al. Alterations of the human gut microbiome in liver cirrhosis. Nature. 2014;513(7516):59–64. doi:10.1038/nature13568.
  • Vatanen T, Kostic AD, d’Hennezel E, Siljander H, Franzosa EA, Yassour M, Kolde R, Vlamakis H, Arthur TD, Hämäläinen A-M, et al. Variation in microbiome LPS immunogenicity contributes to autoimmunity in humans. Cell. 2016;165(4):842–853. doi:10.1016/j.cell.2016.04.007.
  • DiGiulio DB, Callahan BJ, McMurdie PJ, Costello EK, Lyell DJ, Robaczewska A, Sun CL, Goltsman DSA, Wong RJ, Shaw G, et al. Temporal and spatial variation of the human microbiota during pregnancy. Proc Natl Acad Sci USA. 2015;112(35):11060–11065. doi:10.1073/pnas.1502875112.
  • Fushiki T. Estimation of prediction error by using k-fold cross-validation. Stat Comput. 2011;21(2):137–146. doi:10.1007/s11222-009-9153-8.