Unsupervised Extraction of Stable Expression Signatures from Public Compendia with an Ensemble of Neural Networks

Cell Systems

Volumn 5, Issue 1, 2017, Pages 63-71.e6

  Tan, Jie ^a   Doing, Georgia ^a   Lewis, Kimberley A ^a   Price, Courtney E ^a   Chen, Kathleen M ^b   Cady, Kyle C ^c,d   Perchuk, Barret ^c,d   Laub, Michael T ^c,d   Hogan, Deborah A ^a   Greene, Casey S ^b  

^a DARTMOUTH MEDICAL SCHOOL   (United States)

^b UNIVERSITY OF PENNSYLVANIA   (United States)

^c MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^d HOWARD HUGHES MEDICAL INSTITUTE   (United States)

Author keywords

crosstalk; denoising autoencoders; ensemble modeling; gene expression; neural networks; phosphate starvation; Pseudomonas aeruginosa

Indexed keywords

BETAINE; CHOLINE; KINB PROTEIN; PHOSPHATE; PHOSPHATIDYLCHOLINE; PROTEIN HISTIDINE KINASE; PROTEIN KINASE; UNCLASSIFIED DRUG; BACTERIAL PROTEIN; PHOB PROTEIN, BACTERIA; TRANSCRIPTOME;

ARTICLE; BIOLOGICAL ACTIVITY; COMPARATIVE STUDY; CONTROLLED STUDY; ENZYME ACTIVATION; GENE EXPRESSION; GENE EXPRESSION PROFILING; GENETIC ANALYSIS; NERVE CELL NETWORK; NONHUMAN; PRIORITY JOURNAL; PROTEIN ANALYSIS; PSEUDOMONAS AERUGINOSA; REGULATORY MECHANISM; STABLE EXPRESSION; ARTIFICIAL NEURAL NETWORK; ATTITUDE TO HEALTH; GENE EXPRESSION REGULATION; HUMAN; INFORMATION RETRIEVAL; METABOLISM; PHYSIOLOGY; PUBLIC SECTOR; STARVATION; SYSTEM ANALYSIS; TRENDS;

BACTERIAL PROTEINS; GENE EXPRESSION PROFILING; GENE EXPRESSION REGULATION; HEALTH KNOWLEDGE, ATTITUDES, PRACTICE; HUMANS; INFORMATION STORAGE AND RETRIEVAL; NEURAL NETWORKS (COMPUTER); PSEUDOMONAS AERUGINOSA; PUBLIC SECTOR; STARVATION; SYSTEMS INTEGRATION; TRANSCRIPTOME;

EID: 85023158178     PISSN: 24054712     EISSN: 24054720     Source Type: Journal    
DOI: 10.1016/j.cels.2017.06.003     Document Type: Article

References (55)

1. Alter, O., Brown, P.O., Botstein, D., Singular value decomposition for genome-wide expression data processing and modeling. Proc. Natl. Acad. Sci. USA 97 (2000), 10101–10106.
2. Ashburner, M., Ball, C.A., Blake, J.A., Botstein, D., Butler, H., Cherry, J.M., Davis, A.P., Dolinski, K., Dwight, S.S., Eppig, J.T., et al. Gene ontology: tool for the unification of biology. Nat. Genet. 25 (2000), 25–29.
3. Beaulieu-Jones, B.K., Moore, J.H., Missing data imputation in the electronic health record using deeply learned autoencoders. Pac. Symp. Biocomput. 22 (2017), 207–218.
4. Beaulieu-Jones, B.K., Greene, C.S., Pooled Resource Open-Access ALS Clinical Trials Consortium. Semi-supervised learning of the electronic health record for phenotype stratification. J. Biomed. Inform. 64 (2016), 168–178.
5. Bengio, Y., Courville, A., Vincent, P., Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35 (2013), 1798–1828.
6. Bertani, G., Lysogeny at mid-twentieth century: P1, P2, and other experimental systems. J. Bacteriol. 186 (2004), 595–600.
7. Bielecki, P., Jensen, V., Schulze, W., Gödeke, J., Strehmel, J., Eckweiler, D., Nicolai, T., Bielecka, A., Wille, T., Gerlach, R.G., et al. Cross talk between the response regulators PhoB and TctD allows for the integration of diverse environmental signals in Pseudomonas aeruginosa. Nucleic Acids Res. 43 (2015), 6413–6425.
8. Blus-Kadosh, I., Zilka, A., Yerushalmi, G., Banin, E., The effect of pstS and phoB on quorum sensing and swarming motility in Pseudomonas aeruginosa. PLoS One, 8, 2013, e74444.
9. Chen, L., Xuan, J., Wang, C., Shih, I.-M., Wang, Y., Zhang, Z., Hoffman, E., Clarke, R., Devore, J., Peck, R., et al. Knowledge-guided multi-scale independent component analysis for biomarker identification. BMC Bioinformatics, 9, 2008, 416.
10. Damron, F.H., Owings, J.P., Okkotsu, Y., Varga, J.J., Schurr, J.R., Goldberg, J.B., Schurr, M.J., Yu, H.D., Analysis of the Pseudomonas aeruginosa regulon controlled by the sensor kinase KinB and sigma factor RpoN. J. Bacteriol. 194 (2012), 1317–1330.
11. Damron, F.H., Barbier, M., McKenney, E.S., Schurr, M.J., Goldberg, J.B., Genes required for and effects of alginate overproduction induced by growth of Pseudomonas aeruginosa on Pseudomonas isolation agar supplemented with ammonium metavanadate. J. Bacteriol. 195 (2013), 4020–4036.
12. Donato, M., Xu, Z., Tomoiaga, A., Granneman, J.G., Mackenzie, R.G., Bao, R., Than, N.G., Westfall, P.H., Romero, R., Draghici, S., Analysis and correction of crosstalk effects in pathway analysis. Genome Res. 23 (2013), 1885–1893.
13. Edgar, R., Gene Expression Omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Res. 30 (2002), 207–210.
14. Engreitz, J.M., Daigle, B.J., Marshall, J.J., Altman, R.B., Independent component analysis: mining microarray data for fundamental human gene expression modules. J. Biomed. Inform. 43 (2010), 932–944.
15. Fisher, S.L., Jiang, W., Wanner, B.L., Walsh, C.T., Cross-talk between the histidine protein kinase VanS and the response regulator PhoB. Characterization and identification of a VanS domain that inhibits activation of PhoB. J. Biol. Chem. 270 (1995), 23143–23149.
16. Frigyesi, A., Veerla, S., Lindgren, D., Höglund, M., Quackenbush, J., Jutten, C., Herault, J., Chiappetta, P., Roubaud, M., Torrésani, B., et al. Independent component analysis reveals new and biologically significant structures in microarray data. BMC Bioinformatics, 7, 2006, 290.
17. Gillis, J., Pavlidis, P., Assessing identity, redundancy and confounds in Gene Ontology annotations over time. Bioinformatics 29 (2013), 476–482.
18. Gong, T., Xuan, J., Wang, C., Li, H., Hoffman, E., Clarke, R., Wang, Y., Gene module identification from microarray data using nonnegative independent component analysis. Gene Regul. Syst. Bio. 1 (2007), 349–363.
19. Greene, C.S., Troyanskaya, O.G., Accurate evaluation and analysis of functional genomics data and methods. Ann. N. Y. Acad. Sci. 1260 (2012), 95–100.
20. Greene, C.S., Foster, J.A., Stanton, B.A., Hogan, D.A., Bromberg, Y., Computational approaches to study microbes and microbiomes. Pac. Symp. Biocomput. 21 (2016), 557–567.
21. Hampel, K.J., LaBauve, A.E., Meadows, J.A., Fitzsimmons, L.F., Nock, A.M., Wargo, M.J., Characterization of the GbdR regulon in Pseudomonas aeruginosa. J. Bacteriol. 196 (2014), 7–15.
22. Himberg, J., Hyvärinen, A., Esposito, F., Validating the independent components of neuroimaging time series via clustering and visualization. Neuroimage 22 (2004), 1214–1222.
23. Jensen, V., Lons, D., Zaoui, C., Bredenbruch, F., Meissner, A., Dieterich, G., Munch, R., Haussler, S., RhlR Expression in Pseudomonas aeruginosa is modulated by the Pseudomonas quinolone signal via PhoB-dependent and -independent pathways. J. Bacteriol. 188 (2006), 8601–8606.
24. Jiang, Y., Oron, T.R., Clark, W.T., Bankapur, A.R., D'Andrea, D., Lepore, R., Funk, C.S., Kahanda, I., Verspoor, K.M., Ben-Hur, A., et al. An expanded evaluation of protein function prediction methods shows an improvement in accuracy. Genome Biol., 17, 2016, 184.
25. Kanehisa, M., Goto, S., KEGG: kyoto encyclopedia of genes and genomes. Nucleic Acids Res. 28 (2000), 27–30.
26. King, E.O., Ward, M.K., Raney, D.E., Two simple media for the demonstration of pyocyanin and fluorescein. J. Lab. Clin. Med. 44 (1954), 301–307.
27. Lundgren, B.R., Thornton, W., Dornan, M.H., Villegas-Peñaranda, L.R., Boddy, C.N., Nomura, C.T., Gene PA2449 is essential for glycine metabolism and pyocyanin biosynthesis in Pseudomonas aeruginosa PAO1. J. Bacteriol. 195 (2013), 2087–2100.
28. Lutter, D., Langmann, T., Ugocsai, P., Moehle, C., Seibold, E., Splettstoesser, W.D., Gruber, P., Lang, E.W., Schmitz, G., Analyzing time-dependent microarray data using independent component analysis derived expression modes from human macrophages infected with F. tularensis holartica. J. Biomed. Inform. 42 (2009), 605–611.
29. Ma, S., Kosorok, M.R., Identification of differential gene pathways with principal component analysis. Bioinformatics 25 (2009), 882–889.
30. Miller, J.H., Experiments in Molecular Genetics. 1972, Cold Spring Harbor Laboratory.
31. Miotto, R., Li, L., Kidd, B.A., Dudley, J.T., Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Sci. Rep., 6, 2016, 26094.
32. Monti, S., Tamayo, P., Mesirov, J., Golub, T., Consensus clustering: a resampling-based method for class discovery and visualization of gene expression microarray data. Mach. Learn. 52 (2003), 91–118.
33. Neidhardt, F.C., Bloch, P.L., Smith, D.F., Culture medium for enterobacteria. J. Bacteriol. 119 (1974), 736–747.
34. Park, H.-S., Jun, C.-H., A simple and fast algorithm for K-medoids clustering. Expert Syst. Appl. 36 (2009), 3336–3341.
35. Piotrowski, M., Forster, T., Dobrezelecki, B., Sloan, T.M., Mitchell, L., Ghazal, P., Mewsissen, M., Petrou, S., Trew, A., and Hill, J. (2011). Optimisation and parallelisation of the partitioning around medoids function in R, in: 2011 HPCS. IEEE, pp. 707–713.
36. Podgornaia, A.I., Laub, M.T., Determinants of specificity in two-component signal transduction. Curr. Opin. Microbiol. 16 (2013), 156–162.
37. Rahme, L.G., Stevens, E.J., Wolfort, S.F., Shao, J., Tompkins, R.G., Ausubel, F.M., Common virulence factors for bacterial pathogenicity in plants and animals. Science 268 (1995), 1899–1902.
38. Raychaudhuri, S., Stuart, J.M., Altman, R.B., Principal components analysis to summarize microarray experiments: application to sporulation time series. Pac. Symp. Biocomput., 2000, 455–466.
39. Roden, J.C., King, B.W., Trout, D., Mortazavi, A., Wold, B.J., Hart, C.E., Tavazoie, S., Hughes, J., Campbell, M., Cho, R., et al. Mining gene expression data by interpreting principal components. BMC Bioinformatics, 7, 2006, 194.
40. Rustici, G., Kolesnikov, N., Brandizi, M., Burdett, T., Dylag, M., Emam, I., Farne, A., Hastings, E., Ison, J., Keays, M., et al. ArrayExpress update—trends in database growth and links to data analysis tools. Nucleic Acids Res. 41 (2013), D987–D990.
41. Santos-Beneit, F., The Pho regulon: a huge regulatory network in bacteria. Front. Microbiol., 6, 2015, 402.
42. Schnoes, A.M., Ream, D.C., Thorman, A.W., Babbitt, P.C., Friedberg, I., Biases in the experimental annotations of protein function and their effect on our understanding of protein function space. PLoS Comput. Biol., 9, 2013, e1003063.
43. Tan, J., Ung, M., Cheng, C., Greene, C.S., Unsupervised feature construction and knowledge extraction from genome-wide assays of breast cancer with denoising autoencoders. Pac. Symp. Biocomput. 20 (2015), 132–143.
44. Tan, J., Hammond, J.H., Hogan, D.A., Greene, C.S., ADAGE-based integration of publicly available Pseudomonas aeruginosa gene expression data with denoising autoencoders illuminates microbe-host interactions. mSystems, 1, 2016 e00025–15.
45. Tan, J., Doing, G., Lewis, K.A., Price, C.E., Chen, K.M., Cady, K.C., Perchuk, B., Laub, M.T., Hogan, D.A., and Greene, C.S. (2017). eADAGE-1.0.0. Zenodo. 10.5281/zenodo.580093.
46. Thompson, J.A., Tan, J., Greene, C.S., Cross-platform normalization of microarray and RNA-seq data for machine learning applications. PeerJ, 4, 2016, e1621.
47. Verhamme, D.T., Arents, J.C., Postma, P.W., Crielaard, W., Hellingwerf, K.J., Investigation of in vivo cross-talk between key two-component systems of Escherichia coli. Microbiology 148 (2002), 69–78.
48. Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A., Extracting and Composing Robust Features with Denoising Autoencoders, in: ICML ’08. 2008, ACM Press, 1096–1103.
49. Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A., Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11 (2010), 3371–3408.
50. Wanner, B.L., Chang, B.D., The phoBR operon in Escherichia coli K-12. J. Bacteriol. 169 (1987), 5569–5574.
51. Wargo, M.J., Ho, T.C., Gross, M.J., Whittaker, L.A., Hogan, D.A., GbdR regulates Pseudomonas aeruginosa plcH and pchP transcription in response to choline catabolites. Infect. Immun. 77 (2009), 1103–1111.
52. Wargo, M.J., Gross, M.J., Rajamani, S., Allard, J.L., Lundblad, L.K.A., Allen, G.B., Vasil, M.L., Leclair, L.W., Hogan, D.A., Hemolytic phospholipase C inhibition protects lung function during Pseudomonas aeruginosa infection. Am. J. Respir. Crit. Care Med. 184 (2011), 345–354.
53. Wilkerson, M.D., Hayes, D.N., ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking. Bioinformatics 26 (2010), 1572–1573.
54. Yu, B., Stability. Bernoulli 19 (2013), 1484–1500.
55. Zaborin, A., Romanowski, K., Gerdes, S., Holbrook, C., Lepine, F., Long, J., Poroyko, V., Diggle, S.P., Wilke, A., Righetti, K., et al. Red death in Caenorhabditis elegans caused by Pseudomonas aeruginosa PAO1. Proc. Natl. Acad. Sci. USA 106 (2009), 6327–6332.