臺灣博碩士論文加值系統

研究背景：微生物群落對於維持這個世界的水生生態系統至關重要。波羅的海的藻 類開花威脅著海洋生態系統。尤其是藍綠色藻類的花朵會釋放毒素，對人體也有害。先前的一些研究嘗試了多種機器學習技術來預測藻華，但成功率有限。Linnaeus 海洋 天文台在 2011 年至 2013 年期間從位於 Kårehamn 海岸 11 公里處的波羅的海總共收 集了 167 個樣本，採樣間隔為 2 至 88 天（中位數為 4 天在這裡，我們分析了基於 過濾後樣品的高通量測序中觀察到的 16S rRNA 變異而定義的操作分類單位（OTU）的豐度。
研究目標：我們旨在根據過去對 OTU 成分的測量結果來預測 OTU 成分。為了實現 這一目標，我們在此報告了從過濾獲得的三個不同餾分中 OTU 組成變化的預處理和分析。
研究方法：由於測序僅提供有關每個樣品中相對豐度的信息，因此我們在這裡使用 Kendall’s Tau 比較不同分數中 OTU 的排名相關性。在選定的樣本中，我們還基於其 OTU 的相對豐度成對比較分數。
研究結果：我們的分析表明，來自同一樣品的餾分中 OTU 的存在和 OTU 的相對豐 度都存在較大差異。一個分數中有很多 OTU，而另一分數中卻很少，導致幾乎所有樣本的秩相關都低於 0.6。
研究結論：相同樣品的餾分中 OTU 組成的較大差異表明抽取的水樣品中有斑點，除非是由於樣品加工所致。無論如何，當基於過去樣本中的 OTU 組成來預測 OTU 組成時，它提出了一個重大挑戰。在評估預測結果之前，需要對其進行進一步的量化。

Background: The microbial communities are essential to maintain the aquatic ecosystems in this world. Algal bloom in the Baltic Sea threatens the sea ecosystem. In particular, blooms of blue-green algae that release toxins, which are harmful to humans too. A few previous studies have tried diverse machine learning techniques to predict algal blooms, but with limited success. The Linnaeus Marine Observatory collected a total of 167 samples from the Baltic Sea 11 km off the shore of Kårehamn in 2011-2013, with a sampling interval of 2 to 88 days (median 4 days). Here we analyse the abundance of operational taxonomic unit (OTU) defined based on variations in the 16S rRNA observed in high-throughput sequencing of the samples after filtering.
Aim: We aim to predict the OTU composition in the future based on past measurements of the OTU composition. As a step towards this aim, we here report on the pre-processing and analysis of variation in OTU composition in the three different fractions obtained from the filtering.
Method: Since the sequencing only provide information on the relative abundance within each sample, we here use Kendall’s Tau to compare the rank correlation of OTUs in different fractions. In selected samples, we also compare the fractions pairwise based on the relative abundance of their OTUs.
Results: Our analysis shows large variation in both presence of OTUs in the fractions derived from the same sample and the relative abundance of the OTUs. Many OTUs that are abundant in one fraction are rare in the other fraction, leading to rank correlations that for almost all samples are below 0.6.
Conclusion: The large variation in OTU composition in the fractions from the same sample indicate patchiness in the drawn water sample, unless it is due to the processing of the sample. Anyway, it posses a major challenge when predicting OTU composition based on the OTU composition in past samples. Further quantification of it is required before prediction results can be assessed.

Chinese abstract i
Abstract ii
Acknowledgment iv
Table of Contents v
List of Tables vii
List of Figures viii
1 Introduction 1
1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.3 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.4 Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.5 Delimitation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.6 Thesis overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2 Methods 10
2.1 Description of data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.2 Data visualization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.3 Data pre-processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
2.4 Random forest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
2.5 Artificial neural network . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3 Results and Discussion 25
3.1 Timelines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.2 Read count of OTUs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.3 Relative abundance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
3.4 90th percentile normalization . . . . . . . . . . . . . . . . . . . . . . . . . 44
3.5 Kendall’s Tau rank correlation . . . . . . . . . . . . . . . . . . . . . . . . 48
3.6 Analysis of Fraction 0.2-30 . . . . . . . . . . . . . . . . . . . . . . . . . . 63
4 Conclusion and Future works 67
4.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67
4.2 Future work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68
References 70
Appendix A Detail of the data 77
A.1 Metadata . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77

Andersson, A. F., Riemann, L., and Bertilsson, S. (2010). Pyrosequencing reveals contrasting seasonal dynamics of taxa within baltic sea bacterioplankton communities. The ISME Journal, 4(2):171.
Asgari, E., Garakani, K., McHardy, A. C., and Mofrad, M. R. K. (2018). MicroPheno: predicting environments and host phenotypes from 16S rRNA gene sequencing using a k-mer based representation of shallow sub-samples. Bioinformatics, 34(13):i32–i42.
Austin, B., Austin, D. A., Austin, B., and Austin, D. A. (2012). Bacterial fish pathogens. Springer.
Badri, M., Kurtz, Z., Muller, C., and Bonneau, R. (2018). Normalization methods for microbial abundance data strongly affect correlation estimates. bioRxiv, page 406264.
Bell, P. J. L. (2001). Viral eukaryogenesis: was the ancestor of the nucleus a complex dna virus? Journal of Molecular Evolution, 53(3):251–256.
Bessette, S., Moalic, Y., Gautey, S., Lesongeur, F., Godfroy, A., and Toffin, L. (2017). Relative abundance and diversity of bacterial methanotrophs at the oxic–anoxic interface of the congo deep-sea fan. Frontiers in microbiology, 8:715.
Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.
Brewer, C. A., Hatchard, G. W., and Harrower, M. A. (2003). Colorbrewer in print: a catalog of color schemes for maps. Cartography and geographic information science, 30(1):5–32.
Campbell, B. J., Yu, L., Heidelberg, J. F., and Kirchman, D. L. (2011). Activity of abundant and rare bacteria in a coastal ocean. Proceedings of the National Academy of Sciences, 108(31):12776–12781.
Chapin III, F. S., Matson, P. A., and Vitousek, P. (2011). Principles of terrestrial ecosystem ecology. Springer Science ＆ Business Media.
Cho, H., CHOI, U., and Park, H. (2018). Deep learning application to time-series prediction of daily chlorophyll-a concentration. WIT Transactions on Ecology and the Environment,
Croux, C. and Dehon, C. (2010). Influence functions of the spearman and kendall correlation measures. Statistical Methods ＆ Applications, 19(4):497–515.
Crump, B. C., Hopkinson, C. S., Sogin, M. L., and Hobbie, J. E. (2004). Microbial biogeography along an estuarine salinity gradient: combined influences of bacterial growth and residence time. Appl. Environ. Microbiol., 70(3):1494–1505.
Crump, B. C., Kling, G. W., Bahr, M., and Hobbie, J. E. (2003). Bacterioplankton community shifts in an arctic lake correlate with seasonal changes in organic matter source. Appl. Environ. Microbiol., 69(4):2253–2268.
Cutler, D. R., Edwards Jr, T. C., Beard, K. H., Cutler, A., Hess, K. T., Gibson, J., and Lawler, J. J. (2007). Random forests for classification in ecology. Ecology, 88(11):2783–2792.
Díaz-Uriarte, R. and De Andres, S. A. (2006). Gene selection and classification of microarray data using random forest. BMC bioinformatics, 7(1):3.
Doney, S. C., Ruckelshaus, M., Duffy, J. E., Barry, J. P., Chan, F., English, C. A., Galindo,
H. M., Grebmeier, J. M., Hollowed, A. B., Knowlton, N., et al. (2011). Climate change impacts on marine ecosystems.
Duarte, C. M. and Vaqué, D. (1992). Scale dependence of bacterioplankton patchiness. Marine Ecology Progress Series, pages 95–100.
Dvořák, P., Poulíčková, A., Hašler, P., Belli, M., Casamatta, D. A., and Papini, A. (2015). Species concepts and speciation factors in cyanobacteria, with connection to the problems of diversity and classification. Biodiversity and Conservation, 24(4):739–757.
Elkins, K. M. (2012). Forensic DNA biology: a laboratory manual. Academic Press.
Esteban, D. J., Hysa, B., and Bartow-McKenney, C. (2015). Temporal and spatial distribution of the microbial community of winogradsky columns. PloS one, 10(8):e0134588.
Feldbauer, R., Schulz, F., Horn, M., and Rattei, T. (2015). Prediction of microbial phenotypes based on comparative genomics. BMC bioinformatics, 16(14):S1.
Field, D., Amaral-Zettler, L., Cochrane, G., Cole, J. R., Dawyndt, P., Garrity, G. M., Gilbert, J., Glöckner, F. O., Hirschman, L., Karsch-Mizrachi, I., et al. (2011). The genomic standards consortium. PLoS biology, 9(6):e1001088.
Fierer, N., Leff, J. W., Adams, B. J., Nielsen, U. N., Bates, S. T., Lauber, C. L., Owens, S., Gilbert, J. A., Wall, D. H., and Caporaso, J. G. (2012). Cross-biome metagenomic analyses of soil microbial communities and their functional attributes. Proceedings of the National Academy of Sciences, 109(52):21390–21395.
Fischer, M. A., Guellert, S., Neulinger, S. C., Streit, W. R., and Schmitz, R. A. (2016). Evaluation of 16s rrna gene primer pairs for monitoring microbial community structures showed high reproducibility within and low comparability between datasets generated with multiple archaeal and bacterial primer pairs. Frontiers in microbiology, 7:1297.
Friedman, J. and Alm, E. J. (2012). Inferring correlation networks from genomic survey data. PLoS computational biology, 8(9):e1002687. Fuhrman, J. A., Cram, J. A., and Needham, D. M. (2015). Marine microbial community dynamics and their ecological interpretation. Nature Reviews Microbiology, 13(3):133.
Fuhrman, J. A., Hewson, I., Schwalbach, M. S., Steele, J. A., Brown, M. V., and Naeem, S. (2006). Annually reoccurring bacterial communities are predictable from ocean conditions. Proceedings of the National Academy of Sciences, 103(35):13104–13109.
Gibbons, S. M., Caporaso, J. G., Pirrung, M., Field, D., Knight, R., and Gilbert, J. A. (2013). Evidence for a persistent microbial seed bank throughout the global ocean. Proceedings of the National Academy of Sciences, 110(12):4651–4655.
Gibbons, S. M., Duvallet, C., and Alm, E. J. (2018). Correcting for batch effects in casecontrol microbiome studies. PLoS computational biology, 14(4):e1006102.
Gilbert, J. A., Steele, J. A., Caporaso, J. G., Steinbrück, L., Reeder, J., Temperton, B., Huse, S., McHardy, A. C., Knight, R., Joint, I., Somerfield, P., Fuhrman, J. A., and Field, D. (2012). Defining seasonal marine microbial community dynamics. ISME Journal.
Giovannoni, S. J. and Vergin, K. L. (2012). Seasonality in ocean microbial communities. Science, 335(6069):671–676.
Glibert, P. M., Anderson, D. M., Gentien, P., Granéli, E., and Sellner, K. G. (2005). The global, complex phenomena of harmful algal blooms. Oceanography, 18:136–147.
Graves, A., Wayne, G., and Danihelka, I. (2014). Neural turing machines. arXiv preprint arXiv:1410.5401.
Hanemaaijer, M., Röling, W. F., Olivier, B. G., Khandelwal, R. A., Teusink, B., and Bruggeman, F. J. (2015). Systems modeling approaches for microbial community studies: from metagenomics to inference of the community structure. Frontiers in microbiology, 6:213.
Hanson, C. A., Fuhrman, J. A., Horner-Devine, M. C., and Martiny, J. B. (2012). Beyond biogeographic patterns: processes shaping the microbial landscape. Nature Reviews Microbiology,10(7):497.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Hubbell, S. P. (2001). The unified neutral theory of biodiversity and biogeography (MPB-32). Princeton University Press.
Hugerth, L., Lindh, M., Sjöqvist, C., Carina, B., Legrand, C., Pinhassi, J., and Andersson, A. (2016). Seasonal dynamics and interactions among baltic sea prokaryoticand eukaryotic plankton assemblages.
Hugerth, L. W. and Andersson, A. F. (2017). Analysing microbial community composition through amplicon sequencing: from sampling to hypothesis testing. Frontiers in microbiology, 8:1561.
Iluz, D., Dishon, G., Capuzzo, E., Meeder, E., Astoreca, R., Montecino, V., Znachor, P., Ediger, D., and Marra, J. (2009). Short-term variability in primary productivity during a wind-driven diatom bloom in the gulf of eilat (aqaba). Aquatic microbial ecology, 56(2-3): 205–215.
Ininbergs, K., Bergman, B., Larsson, J., and Ekman, M. (2015). Microbial metagenomics in the baltic sea: recent advancements and prospects for environmental monitoring. Ambio, 44(3):439–450.
Kendall, M. G. (1938). A new measure of rank correlation. Biometrika, 30(1/2):81–93.
Knefelkamp, B., Carstens, K., and Wiltshire, K. H. (2007). Comparison of different filter types on chlorophyll-a retention and nutrient measurements. Journal of Experimental Marine Biology and Ecology, 345(1):61–70.
Konopka, A. (2009). What is microbial community ecology? The ISME journal, 3(11):1223.
Koskinen, K., Hultman, J., Paulin, L., Auvinen, P., and Kankaanpää, H. (2011). Spatially differing bacterial communities in water columns of the northern baltic sea. FEMS microbiology ecology, 75(1):99–110.
Kurtz, Z. D., Müller, C. L., Miraldi, E. R., Littman, D. R., Blaser, M. J., and Bonneau, R. A. (2015). Sparse and compositionally robust inference of microbial ecological networks. PLoS computational biology, 11(5):e1004226.
Lee, W., Evans, A., and Williams, D. R. (2016). Validation of a Smartphone Application Measuring Motor Function in Parkinson’s Disease. Journal of Parkinson’s disease, 6(2): 371–82.
Li, X., Sha, J., and Wang, Z.-L. (2018). Application of feature selection and regression models for chlorophyll-a prediction in a shallow lake. Environmental Science and Pollution Research, 25(20):19488–19498.
Liang, J.-L., Li, X.-J., Shu, H.-Y., Wang, P., Kuang, J.-L., Liu, J., Zhang, M.-M., Shu, W.-S., and Huang, L.-N. (2017). Fine-scale spatial patterns in microbial community composition in an acid mine drainage. FEMS microbiology ecology, 93(10).
Little, A. E., Robinson, C. J., Peterson, S. B., Raffa, K. F., and Handelsman, J. (2008). Rules of engagement: interspecies interactions that regulate microbial communities. Annu. Rev. Microbiol., 62:375–401.
Magurran, A. E. (2013). Measuring biological diversity. John Wiley ＆ Sons.
Maier, H. R. and Dandy, G. C. (2000). Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental modelling ＆ software, 15(1):101–124.
Marzouk, M. and Elkadi, M. (2016). Estimating water treatment plants costs using factor analysis and artificial neural networks. Journal of Cleaner Production, 112:4540–4549.
McCulluch, W. and Pitts, W. (1943). A logical calculus of the ideas imminent in nervous activity. Bulletin of Mathematical Biophysics, 5:115–133.
McMurrough, T. A., Dickson, R. J., Thibert, S. M., Gloor, G. B., and Edgell, D. R. (2014). Control of catalytic efficiency by a coevolving network of catalytic and noncatalytic residues. Proceedings of the National Academy of Sciences, 111(23):E2376–E2383.
Muttil, N. and Chau, K.-w. (2006). Neural network and genetic programming for modelling coastal algal blooms. International Journal of Environment and Pollution.
Nelsen, R. (2001). Kendall tau metric. Encyclopaedia of mathematics, 3:226–227.
Nocker, A. and Camper, A. K. (2006). Selective removal of dna from dead cells of mixed bacterial communities by use of ethidium monoazide. Appl. Environ. Microbiol., 72(3): 1997–2004.
Padilla, C. C., Ganesh, S., Gantt, S., Huhman, A., Parris, D. J., Sarode, N., and Stewart, F. J. (2015). Standard filtration practices may significantly distort planktonic microbial diversity estimates. Frontiers in microbiology, 6:547.
Panagou, E. and Kodogiannis, V. (2009). Application of neural networks as a non-linear modelling technique in food mycology. Expert Systems with Applications, 36(1):121–131.
Pinel-Alloul, B. and Ghadouani, A. (2007). Spatial heterogeneity of planktonic microorganisms in aquatic systems. In The spatial distribution of microbes in the environment, pages 203–310. Springer.
Poole, D. L. and Mackworth, A. K. (2010). Artificial Intelligence: foundations of computational agents. Cambridge University Press.
Riemann, L., Leitet, C., Pommier, T., Simu, K., Holmfeldt, K., Larsson, U., and Hagström, Å. (2008). The native bacterioplankton community in the central baltic sea is influenced by freshwater bacterial species. Appl. Environ. Microbiol., 74(2):503–515.
Rönnberg, C. and Bonsdorff, E. (2004). Baltic sea eutrophication: area-specific ecological consequences. Hydrobiologia, 514(1-3):227–241.
Scornet, E. (2017). Tuning parameters in random forests. ESAIM: Proceedings and Surveys, 60:144–162.
Sellner, K. G., Doucette, G. J., and Kirkpatrick, G. J. (2003). Harmful algal blooms: causes, impacts and detection. Journal of Industrial Microbiology and Biotechnology, 30(7):383–406.
Seymour, J. R., Mitchell, J. G., Pearson, L., and Waters, R. L. (2000). Heterogeneity in bacterioplankton abundance from 4.5 millimetre resolution sampling. Aquatic Microbial Ecology, 22(2):143–153.
Singh, K. P., Gupta, S., and Rai, P. (2013). Identifying pollution sources and predicting urban air quality using ensemble learning methods. Atmospheric Environment, 80:426–437.
Sneath, P. H., Sokal, R. R., et al. (1973). Numerical taxonomy. The principles and practice of numerical classification. W.H. Freeman and Company.
Sokal, R. R., Sneath, P. H., et al. (1963). Principles of numerical taxonomy. Journal of Mammalogy, 46:111–112.
Song, Y.-Y. and Ying, L. (2015). Decision tree methods: applications for classification and prediction. Shanghai archives of psychiatry, 27(2):130.
Spearman, C. (1961). The proof and measurement of association between two things.
Stocker, R. (2012). Marine microbes see a sea of gradients. science, 338(6107):628–633.
Stocker, R., Seymour, J. R., Samadani, A., Hunt, D. E., and Polz, M. F. (2008). Rapid chemotactic response enables marine bacteria to exploit ephemeral microscale nutrient patches. Proceedings of the National Academy of Sciences, 105(11):4209–4214.
Sulakvelidze, A., Alavidze, Z., and Morris, J. G. (2001). Bacteriophage therapy. Antimicrobial agents and chemotherapy, 45(3):649–659.
Svetnik, V., Liaw, A., Tong, C., Culberson, J. C., Sheridan, R. P., and Feuston, B. P. (2003). Random forest: a classification and regression tool for compound classification and qsar modeling. Journal of chemical information and computer sciences, 43(6):1947–1958.
Taguchi, S. and Laws, E. A. (1988). On the microparticles which pass through glass fiber filter type gf/f in coastal and open waters. Journal of Plankton Research, 10(5):999–1008.
Vilas, L. G., Spyrakos, E., Palenzuela, J. M. T., and Pazos, Y. (2014). Support vector machinebased method for predicting pseudo-nitzschia spp. blooms in coastal waters (galician rias, nw spain). Progress in Oceanography, 124:66–77.
Ward, C. S., Yung, C.-M., Davis, K. M., Blinebry, S. K., Williams, T. C., Johnson, Z. I., and Hunt, D. E. (2017). Annual community patterns are driven by seasonal switching between closely related marine bacteria. The ISME journal, 11(6):1412.
Weiss, S., Xu, Z. Z., Peddada, S., Amir, A., Bittinger, K., Gonzalez, A., Lozupone, C., Zaneveld, J. R., Vázquez-Baeza, Y., Birmingham, A., et al. (2017). Normalization and microbial differential abundance strategies depend upon data characteristics. Microbiome, 5(1): 27.
Whitaker, J., Ostle, N., Nottingham, A. T., Ccahuana, A., Salinas, N., Bardgett, R. D., Meir, P., and McNamara, N. P. (2014). Microbial community composition explains soil respiration responses to changing carbon inputs along an a ndes-to-a mazon elevation gradient. Journal of Ecology, 102(4):1058–1071.
Wilhelm, S. W., LeCleir, G. R., Bullerjahn, G. S., McKay, R. M., Saxton, M. A., Twiss, M. R., and Bourbonniere, R. A. (2014). Seasonal changes in microbial community structure and activity imply winter production is linked to summer hypoxia in a large lake. FEMS microbiology ecology, 87(2):475–485.
Willmott, C. J. and Matsuura, K. (2005). Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Climate research, 30(1):79–82.
Wu, S., Wang, G., Angert, E. R., Wang, W., Li, W., and Zou, H. (2012). Composition, diversity, and origin of the bacterial community in grass carp intestine. PloS one, 7(2):e30440.
Yajima, H. and Derot, J. (2018). Application of the random forest model for chlorophylla forecasts in fresh and brackish water bodies in japan, using multivariate long-term databases. Journal of Hydroinformatics, 20(1):206–220.
Young, I. M., Crawford, J. W., Nunan, N., Otten, W., and Spiers, A. (2008). Microbial distribution in soils: physics and scaling. Advances in agronomy, 100:81–121.
Zhang, F., Wang, Y., Cao, M., Sun, X., Du, Z., Liu, R., and Ye, X. (2016). Deep-learningbased approach for prediction of algal blooms. Sustainability, 8(10):1060.
Zhang, X., Cheng, W., Listgarten, J., Kadie, C., Huang, S., Wang, W., and Heckerman, D. (2012). Learning transcriptional regulatory relationships using sparse graphical models. PloS one, 7(5):e35762.
Zhang, Z. X., Chen, H., Chen, S. D., Shao, M., Sun, S. G., Qu, Q. M., Zhang, B. R., Liu, Y. M., Xu, Q., Wan, X., Li, L., Wen, H. B., Chen, X., Chen, H. B., Liu, Z. G., Wang, J., and Wang, G. (2014). Chinese culture permeation in the treatment of Parkinson disease: A cross-sectional study in four regions of China. BMC Res. Notes, 7(1):2–9.
Zilouchian, A. and Jafar, M. (2001). Automation and process control of reverse osmosis plants using soft computing methodologies. Desalination, 135(1-3):51–59.