Abstract
Machine learning models have made great strides in many fields of research, including bioinformatics and animal diagnostics. Recently, attention has shifted to detecting pathogens from genome sequences for disease diagnostics with computational models. While there has been tremendous progress, it has primarily been driven by large amounts of annotated data, which is expensive and hard to obtain. Hence, there is a need to develop models that can leverage low-cost, synthetic genome sequences to help tackle complex metagenome classification problems for diagnostics. In this paper, we present one of the first sim2real approaches to help multi-task deep learning models learn robust feature representations from synthetic metagenome sequences and transfer the learning to predict pathogen sequences in real data. Extensive experiments show that our model can successfully leverage synthetic and real genome sequences to obtain \(80\%\) accuracy on metagenome sequence classification. Additionally, we show that our proposed model obtains 76% accuracy, with limited real metagenome sequences.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aakur, S.N., Sarkar, S.: A perceptual prediction framework for self supervised event segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1197–1206 (2019)
Ashoor, H., et al.: Graph embedding and unsupervised learning predict genomic sub-compartments from hic chromatin interaction data. Nat. Commun. 11(1), 1–11 (2020)
Baker, B., et al.: Emergent tool use from multi-agent autocurricula. arXiv preprint arXiv:1909.07528 (2019)
Bartoszewicz, J.M., Seidel, A., Rentzsch, R., Renard, B.Y.: DeePaC: predicting pathogenic potential of novel DNA with reverse-complement neural networks. Bioinformatics 36(1), 81–89 (2020)
Fiannaca, A., et al.: Deep learning models for bacteria taxonomic classification of metagenomic data. BMC Bioinform. 19(7), 198 (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, W., Li, L., Myers, J.R., Marth, G.T.: Art: a next-generation sequencing read simulator. Bioinformatics 28(4), 593–594 (2012)
Hwang, S., Kim, C.Y., Yang, S., Kim, E., Hart, T., Marcotte, E.M., Lee, I.: Humannet v2: human gene networks for disease research. Nucleic Acids Res. 47(D1), D573–D580 (2019)
Kadian, A., et al.: Sim2real predictivity: does evaluation in simulation predict real-world performance? IEEE Robot. Autom. Lett. 5(4), 6670–6677 (2020)
Kang, U., Tong, H., Sun, J.: Fast random walk graph kernel. In: Proceedings of the 2012 SIAM International Conference on Data Mining, pp. 828–838. SIAM (2012)
Laver, T., et al.: Assessing the performance of the oxford nanopore technologies minion. Biomol. Detect. Quantif. 3, 1–8 (2015)
Li, X., et al.: Online adaptation for consistent mesh reconstruction in the wild. In: Advances in Neural Information Processing Systems, 33 (2020)
Lin, Y., Yuan, J., Kolmogorov, M., Shen, M.W., Chaisson, M., Pevzner, P.A.: Assembly of long error-prone reads using de Bruijn graphs. Proc. Nat. Acad. Sci. 113(52), E8396–E8405 (2016)
Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, 29, pp. 289–297 (2016)
Marzoev, A., Madden, S., Kaashoek, M.F., Cafarella, M., Andreas, J.: Unnatural language processing: bridging the gap between synthetic and natural language data. arXiv preprint arXiv:2004.13645 (2020)
Min, X., Zeng, W., Chen, N., Chen, T., Jiang, R.: Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding. Bioinform. 33(14), i92–i101 (2017)
Narayanan, A., Chandramohan, M., Venkatesan, R., Chen, L., Liu, Y., Jaiswal, S.: graph2vec: learning distributed representations of graphs. arXiv preprint arXiv:1707.05005 (2017)
Narayanan, S., Ramachandran, A., Aakur, S.N., Bagavathi, A.: Genome sequence classification for animal diagnostics with graph representations and deep neural networks. arXiv preprint arXiv:2007.12791 (2020)
Nguyen, T.H., Chevaleyre, Y., Prifti, E., Sokolovska, N., Zucker, J.D.: Deep learning for metagenomic data: using 2D embeddings and convolutional neural networks. arXiv preprint arXiv:1712.00244 (2017)
Perry, S.C., Beiko, R.G.: Distinguishing microbial genome fragments based on their composition: evolutionary and comparative genomic perspectives. Genome Biol. Evol. 2, 117–131 (2010)
Sadeghi, F., Toshev, A., Jang, E., Levine, S.: Sim2Real viewpoint invariant visual servoing by recurrent control. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (June 2018)
Sherry, S.T., et al.: dbSNP: the NCBI database of genetic variation. Nucleic Acids Res. 29(1), 308–311 (2001)
Stobbe, A.H., et al.: E-probe Diagnostic Nucleic acid Analysis (edna): a theoretical approach for handling of next generation sequencing data for diagnostics. J. Microbiol. Methods 94(3), 356–366 (2013)
Acknowledgement
This research was supported in part by the US Department of Agriculture (USDA) grants AP20VSD and B000C011.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Indla, V. et al. (2021). Sim2Real for Metagenomes: Accelerating Animal Diagnostics with Adversarial Co-training. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12712. Springer, Cham. https://doi.org/10.1007/978-3-030-75762-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-75762-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75761-8
Online ISBN: 978-3-030-75762-5
eBook Packages: Computer ScienceComputer Science (R0)