1932

Abstract

Since the 1980s, deep learning and biomedical data have been coevolving and feeding each other. The breadth, complexity, and rapidly expanding size of biomedical data have stimulated the development of novel deep learning methods, and application of these methods to biomedical data have led to scientific discoveries and practical solutions. This overview provides technical and historical pointers to the field, and surveys current applications of deep learning to biomedical data organized around five subareas, roughly of increasing spatial scale: chemoinformatics, proteomics, genomics and transcriptomics, biomedical imaging, and health care. The black box problem of deep learning methods is also briefly discussed.

Loading

Article metrics loading...

/content/journals/10.1146/annurev-biodatasci-080917-013343
2018-07-20
2024-06-25
Loading full text...

Full text loading...

/deliver/fulltext/biodatasci/1/1/annurev-biodatasci-080917-013343.html?itemId=/content/journals/10.1146/annurev-biodatasci-080917-013343&mimeType=html&fmt=ahah

Literature Cited

  1. 1.  McCulloch W, Pitts W 1943. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 7:115–33
    [Google Scholar]
  2. 2.  Rosenblatt F 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65:6386–408
    [Google Scholar]
  3. 3.  Schmidhuber J 2015. Deep learning in neural networks: an overview. Neural Netw 61:85–117
    [Google Scholar]
  4. 4.  Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R 2014. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learning Res. 15:11929–58
    [Google Scholar]
  5. 5.  Baldi P, Sadowski P 2014. The dropout learning algorithm. Artif. Intell. 210:78–122
    [Google Scholar]
  6. 6.  Hochreiter S, Schmidhuber J 1997. Long short-term memory. Neural Comput 9:81735–80
    [Google Scholar]
  7. 7.  Greff K, Srivastava RK, Koutnk J, Steunebrink BR, Schmidhuber J 2017. LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learning Syst. 28:102222–32
    [Google Scholar]
  8. 8.  Cybenko G 1989. Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2:4303–14
    [Google Scholar]
  9. 9.  Hornik K, Stinchcombe M, White H 1990. Universal approximation of an unknown function and its derivatives using multilayer feedforward networks. Neural Netw 3:551–60
    [Google Scholar]
  10. 10.  Krogh A, Brown M, Mian IS, Sjölander K, Haussler D 1994. Hidden Markov models in computational biology: applications to protein modeling. J. Mol. Biol. 235:1501–31
    [Google Scholar]
  11. 11.  Baldi P, Chauvin Y, Hunkapillar T, McClure M 1994. Hidden Markov models of biological primary sequence information. PNAS 91:31059–63
    [Google Scholar]
  12. 12.  Baldi P, Chauvin Y 1996. Hybrid modeling, HMM/NN architectures, and protein applications. Neural Comput 8:71541–65
    [Google Scholar]
  13. 13.  Baldi P 2018. The inner and outer approaches for the design of recursive neural networks architectures. Data Min. Knowl. Discov. 32:1218–30
    [Google Scholar]
  14. 14.  Koller D, Friedman N 2009. Probabilistic Graphical Models: Principles and Techniques Cambridge, MA: MIT Press
    [Google Scholar]
  15. 15.  Murphy KP 2012. Machine Learning: A Probabilistic Perspective Cambridge, MA: MIT Press
    [Google Scholar]
  16. 16.  Baldi P, Brunak S, Frasconi P, Pollastri G, Soda G 1999. Exploiting the past and the future in protein secondary structure prediction. Bioinformatics 15:937–46
    [Google Scholar]
  17. 17.  Duvenaud DK, Maclaurin D, Iparraguirre J, Bombarell R, Hirzel T et al. 2015. Convolutional networks on graphs for learning molecular fingerprints. Proc. Int. Conf. Neural Inf. Process. Syst., 28th, Montreal, Can., 7–12 Dec C Cortes, DD Lee, M Sugiyama, R Garnett 2224–32 Cambridge, MA: MIT Press
    [Google Scholar]
  18. 18.  Lusci A, Pollastri G, Baldi P 2013. Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. J. Chem. Inf. Model. 53:71563–75
    [Google Scholar]
  19. 19.  Schütt KT, Arbabzadah F, Chmiela S, Müller KR, Tkatchenko A 2017. Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8:13890
    [Google Scholar]
  20. 20.  Chmiela S, Tkatchenko A, Sauceda HE, Poltavsky I, Schütt KT Müller K-R 2017. Machine learning of accurate energy-conserving molecular force fields. Sci. Adv. 3:5e1603015
    [Google Scholar]
  21. 21.  Kayala MA, Azencott CA, Chen JH, Baldi P 2011. Learning to predict chemical reactions. J. Chem. Inf. Model. 51:92209–22
    [Google Scholar]
  22. 22.  Kayala MA, Baldi P 2012. Reactionpredictor: prediction of complex chemical reactions at the mechanistic level using machine learning. J. Chem. Inf. Model. 52:102526–40
    [Google Scholar]
  23. 23.  Randall A, Cheng J, Sweredoski M, Baldi P 2008. TMBpro: secondary structure, β-contact and tertiary structure prediction of transmembrane β-barrel proteins. Bioinformatics 24:4513–20
    [Google Scholar]
  24. 24.  Baker D, Sali A 2001. Protein structure prediction and structural genomics. Science 294:93–96
    [Google Scholar]
  25. 25.  Baldi P, Pollastri G 2002. A machine learning strategy for protein analysis. IEEE Intell. Syst. 17:228–35
    [Google Scholar]
  26. 26.  Baldi P, Pollastri G 2003. The principled design of large-scale recursive neural network architectures—DAG-RNNs and the protein structure prediction problem. J. Mach. Learn. Res. 4:575–602
    [Google Scholar]
  27. 27.  Cheng J, Randall AZ, Sweredoski M, Baldi P 2005. Scratch: a protein structure and structural feature prediction server. Nucleic Acids Res 33:W72–76
    [Google Scholar]
  28. 28.  Cheng J, Tegge AN, Baldi P 2008. Machine learning methods for protein structure prediction. IEEE Rev. Biomed. Eng. 1:41–49
    [Google Scholar]
  29. 29.  Baldi P, Brunak S 2001. Bioinformatics: The Machine Learning Approach Cambridge, MA: MIT Press. , 2nd ed..
    [Google Scholar]
  30. 30.  Pollastri G, Baldi P, Fariselli P, Casadio R 2001. Prediction of coordination number and relative solvent accessibility in proteins. Proteins 47:142–53
    [Google Scholar]
  31. 31.  Pollastri G, Przybylski D, Rost B, Baldi P 2001. Improving the prediction of protein secondary strucure in three and eight classes using recurrent neural networks and profiles. Proteins 47:228–35
    [Google Scholar]
  32. 32.  Nilges M, Clore GM, Gronenborn AM 1988. Determination of three-dimensional structures of proteins from interproton distance data by dynamical simulated annealing from a random array of atoms. FEBS Lett 239:129–36
    [Google Scholar]
  33. 33.  Nilges M, Clore GM, Gronenborn AM 1988. Determination of three-dimensional structures of proteins from interproton distance data by hybrid distance geometry-dynamical simulated annealing calculations. FEBS Lett 229:317–24
    [Google Scholar]
  34. 34.  Vendruscolo M, Kussell E, Domany E 1997. Recovery of protein structure from contact maps. Fold. Des. 2:295–306
    [Google Scholar]
  35. 35.  Vassura M, Margara L, Di Lena P, Medri F, Fariselli P, Casadio R 2008. FT-COMAR: fault tolerant three-dimensional structure reconstruction from protein contact maps. Bioinformatics 24:101313–15
    [Google Scholar]
  36. 36.  Chou PY, Fasman GD 1974. Conformational parameters for amino acids in helical, β-sheet, and random coil regions calculated from proteins. Biochemistry 13:2211–22
    [Google Scholar]
  37. 37.  Chou PY, Fasman GD 1974. Prediction of protein conformation. Biochemistry 13:2222–45
    [Google Scholar]
  38. 38.  Qian N, Sejnowski TJ 1988. Predicting the secondary structure of globular proteins using neural network models. J. Mol. Biol. 202:865–84
    [Google Scholar]
  39. 39.  Bohr H, Bohr J, Brunak S, Cotterill RMJ, Lautrup B et al. 1988. Protein secondary structure and homology by neural networks. The α-helices in rhodopsin. FEBS Lett 241:1–2223–28
    [Google Scholar]
  40. 40.  Holley LH, Karplus M 1989. Protein secondary structure prediction with a neural network. PNAS 86:1152–56
    [Google Scholar]
  41. 41.  Rost B, Sander C 1997. Prediction of protein secondary structure at better than 70% accuracy. J. Mol. Biol. 232:584–99
    [Google Scholar]
  42. 42.  Rost B, Sander C 1994. Combining evolutionary information and neural networks to predict protein secondary structure. Proteins 19:55–72
    [Google Scholar]
  43. 43.  Riis SK, Krogh A 1996. Improving prediction of protein secondary structure using structured neural networks and multiple sequence alignments. J. Comput. Biol. 3:163–83
    [Google Scholar]
  44. 44.  Petersen TN, Lundegaard C, Nielsen M, Bohr H, Bohr J et al. 2000. Prediction of protein secondary structure at 80% accuracy. Proteins 41:117–20
    [Google Scholar]
  45. 45.  Mooney C, Pollastri G 2009. Beyond the twilight zone: automated prediction of structural properties of proteins by recursive neural networks and remote homology information. Proteins 77:1181–90
    [Google Scholar]
  46. 46.  Mirabello C, Pollastri G 2013. Porter, PaleAle 4.0: high-accuracy prediction of protein secondary structure and relative solvent accessibility. Bioinformatics 29:162056–58
    [Google Scholar]
  47. 47.  Magnan CN, Baldi P 2014. SSpro/ACCpro 5: almost perfect prediction of protein secondary structure and relative solvent accessibility using profiles, machine learning, and structural similarity. Bioinformatics 30:182592–97
    [Google Scholar]
  48. 48.  Shindyalov IN, Kolchanov NA, Sander C 1994. Can three-dimensional contacts of proteins be predicted by analysis of correlated mutations?. Protein Eng 7:349–58
    [Google Scholar]
  49. 49.  Olmea O, Valencia A 1997. Improving contact predictions by the combination of correlated mutations and other sources of sequence information. Fold. Des. 2:S25–32
    [Google Scholar]
  50. 50.  Fariselli P, Casadio R 1999. Neural network based predictor of residue contacts in proteins. Protein Eng 12:15–21
    [Google Scholar]
  51. 51.  Fariselli P, Casadio R 2000. Prediction of the number of residue contacts in proteins. Proc. Conf. Intell. Syst. Mol. Biol., 8th, La Jolla, Calif., 16–23 Aug R Altman 146–51 Menlo Park, CA: AAAI Press
    [Google Scholar]
  52. 52.  Pollastri G, Baldi P, Fariselli P, Casadio R 2001. Improved prediction of the number of residue contacts in proteins by recurrent neural networks. Bioinformatics 17:S234–42
    [Google Scholar]
  53. 53.  Aszodi A, Gradwell MJ, Taylor WR 1995. Global fold determination from a small number of distance restraints. J. Mol. Biol. 251:308–26
    [Google Scholar]
  54. 54.  Lund O, Frimand K, Gorodkin J, Bohr H, Bohr J et al. 1997. Protein distance constraints predicted by neural networks and probability density functions. Prot. Eng. 10:111241–48
    [Google Scholar]
  55. 55.  Gorodkin J, Lund O, Andersen CA, Brunak S 1999. Using sequence motifs for enhanced neural network prediction of protein distance constraints. Proc. Conf. Intell. Syst. Mol. Biol., 7th, Heidelberg, Ger., 6–10 Aug T Lengauer, R Schneider, P Bork, D Brutlag, J Glasgow et al.95–105 Menlo Park, CA: AAAI Press
    [Google Scholar]
  56. 56.  Kukic P, Mirabello C, Tradigo G, Walsh I, Veltri P, Pollastri G 2014. Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks. BMC Bioinform 15:16
    [Google Scholar]
  57. 57.  Fariselli P, Olmea O, Valencia A, Casadio R 2001. Prediction of contact maps with neural networks and correlated mutations. Prot. Eng. 14:835–43
    [Google Scholar]
  58. 58.  Pollastri G, Baldi P 2002. Prediction of contact maps by GIOHMMs and recurrent neural networks using lateral propagation from all four cardinal corners. Bioinformatics 18:S62–70
    [Google Scholar]
  59. 59.  Pollastri G, Vullo A, Frasconi P, Baldi P 2006. Modular DAG-RNN architectures for assembling coarse protein structures. J. Comput. Biol. 13:3631–50
    [Google Scholar]
  60. 60.  Cheng J, Baldi P 2007. Improved residue contact prediction using support vector machines and a large feature set. BMC Bioinform 8:1113
    [Google Scholar]
  61. 61.  Wang S, Sun S, Li Z, Zhang R, Xu J 2017. Accurate de novo prediction of protein contact map by ultra-deep learning model. PLOS Comput. Biol. 13:1e1005324
    [Google Scholar]
  62. 62.  Cheng J, Saigo H, Baldi P 2006. Large-scale prediction of disulphide bridges using kernel methods two-dimensional recursive neural networks, and weighted graph matching. Proteins 62:3617–29
    [Google Scholar]
  63. 63.  Di Lena P, Nagata K, Baldi P 2012. Deep architectures for protein contact map prediction. Bioinformatics 28:2449–57
    [Google Scholar]
  64. 64.  Lyons J, Dehzangi A, Heffernan R, Sharma A, Paliwal K et al. 2014. Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network. J. Comput. Chem. 35:282040–46
    [Google Scholar]
  65. 65.  Nagata K, Randall A, Baldi P 2012. SIDEpro: a novel machine learning approach for the fast and accurate prediction of side-chain conformations. Proteins 80:142–53
    [Google Scholar]
  66. 66.  Fariselli P, Pazos F, Valencia A, Casadio R 2002. Prediction of protein–protein interaction sites in heterocomplexes with neural networks. FEBS J 269:51356–61
    [Google Scholar]
  67. 67.  Jones DT, Buchan DWA, Cozzetto D, Pontil M 2011. PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments. Bioinformatics 28:2184–90
    [Google Scholar]
  68. 68.  Marks DS, Hopf TA, Sander C 2012. Protein structure prediction from sequence variation. Nat. Biotechnol. 30:111072–80
    [Google Scholar]
  69. 69.  Liu Y, Palmedo P, Ye Q, Berger B, Peng J 2017. Enhancing evolutionary couplings with deep convolutional neural networks. Cell Syst 6:165–74.e3
    [Google Scholar]
  70. 70.  Cheng J, Randall A, Baldi P 2006. Prediction of protein stability changes for single-site mutations using support vector machines. Proteins 62:41125–32
    [Google Scholar]
  71. 71.  Magnan CN, Randall A, Baldi P 2009. SOLpro: accurate sequence-based prediction of protein solubility. Bioinformatics 25:172200–7
    [Google Scholar]
  72. 72.  Cheng J, Sweredoski M, Baldi P 2005. Acurate prediction of protein disordered regions by mining protein structure data. Data Min. Knowl. Discov. 11:3213–22
    [Google Scholar]
  73. 73.  Volpato V, Alshomrani B, Pollastri G 2015. Accurate ab initio and template-based prediction of short intrinsically-disordered regions by bidirectional recurrent neural networks trained on large-scale datasets. Int. J. Mol. Sci. 16:819868–85
    [Google Scholar]
  74. 74.  Cheng J, Sweredoski MJ, Baldi P 2006. DOMpro: protein domain prediction using profiles, secondary structure, relative solvent accessibility, and recursive neural networks. Data Min. Knowl. Discov. 13:11–10
    [Google Scholar]
  75. 75.  Cheng J, Baldi P 2006. A machine learning information retrieval approach to protein fold recognition. Bioinformatics 22:121456–63
    [Google Scholar]
  76. 76.  Hou J, Adhikari B, Cheng J 2017. DeepSF: deep convolutional neural network for mapping protein sequences to folds. arXiv:1706.01010 [cs.LG]
  77. 77.  Mooney C, Pollastri G, Shields DC, Haslam NJ 2012. Prediction of short linear protein binding regions. J. Mol. Biol. 415:1193–204
    [Google Scholar]
  78. 78.  Khan W, Duffy F, Pollastri G, Shields DC, Mooney C 2013. Predicting binding within disordered protein regions to structurally characterised peptide-binding domains. PLOS ONE 8:9e72838
    [Google Scholar]
  79. 79.  Mooney C, Haslam NJ, Holton TA, Pollastri G, Shields DC 2013. Peptidelocator: prediction of bioactive peptides in protein sequences. Bioinformatics 29:91120–26
    [Google Scholar]
  80. 80.  Eickholt J, Cheng J 2012. Predicting protein residue–residue contacts using deep networks and boosting. Bioinformatics 28:233066–72
    [Google Scholar]
  81. 81.  Eickholt J, Cheng J 2013. DNdisorder: predicting protein disorder using boosting and deep networks. BMC Bioinform 14:188
    [Google Scholar]
  82. 82.  Spencer M, Eickholt J, Cheng J 2015. A deep learning network approach to ab initio protein secondary structure prediction. IEEE/ACM Trans. Comput. Biol. Bioinform. 12:1103–12
    [Google Scholar]
  83. 83.  Jo T, Hou J, Eickholt J, Cheng J 2015. Improving protein fold recognition by deep learning networks. Sci. Rep. 5:17573
    [Google Scholar]
  84. 84.  Cao R, Bhattacharya D, Hou J, Cheng J 2016. DeepQA: improving the estimation of single protein model quality with deep belief networks. BMC Bioinform 17:1495
    [Google Scholar]
  85. 85.  Nielsen H, Engelbrecht J, Brunak S, von Heijne G 1997. Identification of prokaryotic and eukaryotic signal peptides and prediction of their cleavage sites. Prot. Eng. 10:11–6
    [Google Scholar]
  86. 86.  Blom N, Sicheritz-Pontén T, Gupta R, Gammeltoft S, Brunak S 2004. Prediction of post-translational glycosylation and phosphorylation of proteins from the amino acid sequence. Proteomics 4:61633–49
    [Google Scholar]
  87. 87.  Jensen LJ, Gupta R, Blom N, Devos D, Tamames J et al. 2002. Prediction of human protein function from post-translational modifications and localization features. J. Mol. Biol. 319:51257–65
    [Google Scholar]
  88. 88.  Mooney C, Wang Y-H, Pollastri G 2011. SCLpred: protein subcellular localization prediction by N-to-1 neural networks. Bioinformatics 27:202812–19
    [Google Scholar]
  89. 89.  Mooney C, Haslam NJ, Pollastri G, Shields DC 2012. Towards the improved discovery and design of functional peptides: Common features of diverse classes permit generalized prediction of bioactivity. PLOS ONE 7:10e45012
    [Google Scholar]
  90. 90.  Holton TA, Pollastri G, Shields DC, Mooney C 2013. CPPpred: prediction of cell penetrating peptides. Bioinformatics 29:233094–96
    [Google Scholar]
  91. 91.  Volpato V, Adelfio A, Pollastri G 2013. Accurate prediction of protein enzymatic class by N-to-1 neural networks. BMC Bioinform 14:1S11
    [Google Scholar]
  92. 92.  Asgari E, Mofrad MRK 2015. Continuous distributed representation of biological sequences for deep proteomics and genomics. PLOS ONE 10:11e0141287
    [Google Scholar]
  93. 93.  Lund O, Nielsen M, Lundegaard C, Kesmir C, Brunak S 2005. Immunological Bioinformatics Cambridge, MA: MIT Press
    [Google Scholar]
  94. 94.  Nielsen M, Lundegaard C, Worning P, Lauemøller SL, Lamberth K et al. 2003. Reliable prediction of T-cell epitopes using neural networks with novel sequence representations. Prot. Sci. 12:51007–17
    [Google Scholar]
  95. 95.  Sweredoski MJ, Baldi P 2008. PEPITO: improved discontinuous B-cell epitope prediction using multiple distance thresholds and half-sphere exposure. Bioinformatics 24:121459–60
    [Google Scholar]
  96. 96.  Sweredoski MJ, Baldi P 2009. COBEpro: a novel system for predicting continuous B-cell epitopes. Prot. Eng. Des. Sel. 22:3113–20
    [Google Scholar]
  97. 97.  Magnan CN, Zeller M, Kayala MA, Vigil A, Randall A et al. 2010. High-throughput prediction of protein antigenicity using protein microarray data. Bioinformatics 26:232936–43
    [Google Scholar]
  98. 98.  Vang YS, Xie X 2017. HLA class I binding prediction via convolutional neural networks. Bioinformatics 33:172658–65
    [Google Scholar]
  99. 99.  Stormo GD, Schneider TD, Gold L, Ehrenfeucht A 1982. Use of the ‘Perceptron’ algorithm to distinguish translational initiation sites in E. coli. . Nucleic Acids Res 10:92997–3011
    [Google Scholar]
  100. 100.  Brunak S, Engelbrecht J, Knudsen S 1991. Prediction of human mRNA donor and acceptor sites from the DNA sequence. J. Mol. Biol. 220:149–65
    [Google Scholar]
  101. 101.  Hebsgaard SM, Korning PG, Tolstrup N, Engelbrecht J, Rouzé P, Brunak S 1996. Splice site prediction in Arabidopsis thaliana pre-mRNA by combining local and global sequence information. Nucleic Acids Res 24:173439–52
    [Google Scholar]
  102. 102.  Uberbacher EC, Mural RJ 1991. Locating protein-coding regions in human DNA sequences by a multiple sensor-neural network approach. PNAS 88:2411261–65
    [Google Scholar]
  103. 103.  Brunak S, Engelbrecht J, Knudsen S 1990. Neural network detects errors in the assignment of mRNA splice sites. Nucleic Acids Res 18:164797–801
    [Google Scholar]
  104. 104.  Golden J, Garcia E, Tibbetts C 1995. Evolutionary optimization of a neural network-based signal processor for photometric data from an automated DNA sequencer. Proc. Annu. Conf. Evol. Progr., 4th, San Diego, Calif., 1–3 March JR McDonnell, RG Reynolds, DB Fogel 579–601 Cambridge, MA: MIT Press
    [Google Scholar]
  105. 105.  Ewing B, Hillier L, Wendl MC, Green P 1998. Base-calling of automated sequencer traces using phred. I. Accuracy assessment. Genome Res 8:3175–85
    [Google Scholar]
  106. 106.  Boža V, Brejová B, Vinař T 2017. DeepNano: deep recurrent neural networks for base calling in MinION nanopore reads. PLOS ONE 12:6e0178751
    [Google Scholar]
  107. 107.  Alipanahi B, Delong A, Weirauch MT, Frey BJ 2015. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol. 33:8831–38
    [Google Scholar]
  108. 108.  Wang MD, Hassanzadeh HR 2017. DeeperBind: enhancing prediction of sequence specificities of DNA binding proteins. bioRxiv 099754. https://doi.org/10.1101/099754
    [Crossref]
  109. 109.  Qin Q, Feng J 2017. Imputation for transcription factor binding predictions based on deep learning. PLOS Comput. Biol. 13:2e1005403
    [Google Scholar]
  110. 110.  Quang D, Xie X 2017. Factornet: a deep learning framework for predicting cell type specific transcription factor binding from nucleotide-resolution sequential data. bioRxiv 151274. https://doi.org/10.1101/151274
    [Crossref]
  111. 111.  Zhou J, Troyanskaya OG 2015. Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods 12:10931–34
    [Google Scholar]
  112. 112.  Quang D, Chen Y, Xie X 2015. DANN: a deep learning approach for annotating the pathogenicity of genetic variants. Bioinformatics 31:5761–63
    [Google Scholar]
  113. 113.  Quang D, Xie X 2016. DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences. Nucleic Acids Res 44:11e107
    [Google Scholar]
  114. 114.  Kelley DR, Snoek J, Rinn JL 2016. Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res 26:7990–99
    [Google Scholar]
  115. 115.  Angermueller C, Lee HJ, Reik W, Stegle O 2017. DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. Genome Biol 18:167
    [Google Scholar]
  116. 116.  Li Y, Quang D, Xie X 2017. Understanding sequence conservation with deep learning. bioRxiv 103929. https://doi.org/10.1101/103929
    [Crossref]
  117. 117.  Liu F, Ren C, Li H, Zhou P, Bo X, Shu W 2015. De novo identification of replication-timing domains in the human genome by deep learning. Bioinformatics 32:5641–49
    [Google Scholar]
  118. 118.  Zhang S, Zhou J, Hu H, Gong H, Chen L et al. 2015. A deep learning framework for modeling structural features of RNA-binding protein targets. Nucleic Acids Res 44:4e32
    [Google Scholar]
  119. 119.  Herrero J, Valencia A, Dopazo J 2001. A hierarchical unsupervised growing neural network for clustering gene expression patterns. Bioinformatics 17:2126–36
    [Google Scholar]
  120. 120.  Chicco D, Sadowski P, Baldi P 2014. Deep autoencoder neural networks for gene ontology annotation predictions. Proc. ACM Conf. Bioinform. Comput. Biol. Health Inform., Newport Beach, Calif., 20–23 Sept.533–40 New York: Assoc. Comput. Mach.
    [Google Scholar]
  121. 121.  Leung MKK, Xiong HY, Lee LJ, Frey BJ 2014. Deep learning of the tissue-regulated splicing code. Bioinformatics 30:12i121–29
    [Google Scholar]
  122. 122.  Xiong HY, Alipanahi B, Lee LJ, Bretschneider H, Merico D et al. 2015. The human splicing code reveals new insights into the genetic determinants of disease. Science 347:62181254806
    [Google Scholar]
  123. 123.  Chen Y, Li Y, Narayan R, Subramanian A, Xie X 2016. Gene expression inference with deep learning. Bioinformatics 32:121832–39
    [Google Scholar]
  124. 124.  Agostinelli F, Ceglia N, Shahbaba B, Sassone-Corsi P, Baldi P 2016. What time is it? Deep learning approaches for circadian rhythms. Bioinformatics 32:12i8–17
    [Google Scholar]
  125. 125.  Baldi P, Chauvin Y 1993. Neural networks for fingerprint recognition. Neural Comput 5:3402–18
    [Google Scholar]
  126. 126.  Cireşan DC, Meier U, Schmidhuber J 2012. Multi-column deep neural networks for image classification. Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 25th, Providence, R.I., 16–21 June3642–49 New York: Inst. Electr. Electr. Eng.
    [Google Scholar]
  127. 127.  Cireşan DC, Giusti A, Gambardella LM, Schmidhuber J 2012. Deep neural networks segment neuronal membranes in electron microscopy images. Proc. Int. Conf. Neural Inf. Process. Syst., 25th, Lake Tahoe, Calif., 3–6 Dec F Pereira, CJC Burges, L Bottou, KQ Weinberger 2843–51 Red Hook, NY: Curran Assoc.
    [Google Scholar]
  128. 128.  Cireşan DC, Giusti A, Gambardella LM, Schmidhuber J 2013. Mitosis detection in breast cancer histology images with deep neural networks. Med. Image Comput. Comput.-Assist. Interv., 16th, Nagoya, Jap., 22–26 Sept K Mori, I Sakuma, Y Sato, C Barillot, N Navab 411–18 Berlin: Springer-Verlag
    [Google Scholar]
  129. 129.  Roth HR, Yao J, Lu L, Stieger J, Burns JE, Summers RM 2015. Detection of sclerotic spine metastases via random aggregation of deep convolutional neural network classifications. Recent Advances in Computational Methods and Clinical Applications for Spine Imaging J Yao, B Glocker, T Klinder, S Li 3–12 Cham, Switz: Springer Int.
    [Google Scholar]
  130. 130.  Shen W, Zhou M, Yang F, Yang C, Tian J 2015. Multi-scale convolutional neural networks for lung nodule classification. Int. Conf. Inf. Process. Med. Imaging S Ourselin, D Alexander, CF Westin, M Cardoso 588–99 Cham, Switz: Springer Int.
    [Google Scholar]
  131. 131.  Wang D, Khosla A, Gargeya R, Irshad H, Beck AH 2016. Deep learning for identifying metastatic breast cancer. arXiv:1606.05718 [q-bio.QM]
  132. 132.  Wang J, Fang Z, Lang N, Yuan H, Su M-Y, Baldi P 2017. A multi-resolution approach for spinal metastasis detection using deep siamese neural networks. Comput. Biol. Med. 84:137–46
    [Google Scholar]
  133. 133.  Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM et al. 2017. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:7639115–18
    [Google Scholar]
  134. 134.  Gulshan V, Peng L, Coram M, Stumpe MC, Wu D et al. 2016. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316:222402–10
    [Google Scholar]
  135. 135.  Wang J, Ding H, Azamian F, Zhou B, Iribarren C et al. 2017. Detecting cardiovascular disease from mammograms with deep learning. IEEE Trans. Med. Imaging 36:51172–81
    [Google Scholar]
  136. 136.  Bucilua C, Caruana R, Niculescu-Mizil A 2006. Model compression. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 12th, Phila., Pa., 20–23 Aug L Ungar, M Craven, D Gunopulos, T Eliassi-Rad 535–41 New York: Assoc. Comput. Mach.
    [Google Scholar]
  137. 137.  Sadowski P, Collado J, Whiteson D, Baldi P 2015. Deep learning, dark knowledge, and dark matter. Proc. Mach. Learn. Res. 42:81–97
    [Google Scholar]
  138. 138.  Redmon J, Divvala S, Girshick R, Farhadi A 2016. You only look once: unified, real-time object detection. Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 29th, Las Vegas, Nev., 26 June–1 July779–88 New York: Inst. Electr. Electr. Eng.
    [Google Scholar]
  139. 139.  Masci J, Giusti A, Ciresan DC, Fricout G, Schmidhuber J 2013. A fast learning algorithm for image segmentation with max-pooling convolutional networks. IEEE Int. Conf. Image Process., 20th, Melb., Aust., 15–18 Sept.2713–17 New York: Inst. Electr. Electr. Eng.
    [Google Scholar]
  140. 140.  Stollenga M, Beyon W, Liwicki M, Schmidhuber J 2015. Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. Proc. Int. Conf. Neural Inf. Process. Syst., 28th, Montreal, Can., 7–12 Dec C Cortes, DD Lee, M Sugiyama, R Garnett 2998–3006 Cambridge, MA: MIT Press
    [Google Scholar]
  141. 141.  Urban G, Tripathi P, Alkayali T, Mittal M, Jalali F et al. 2017. Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy. Gastroenterology In press
    [Google Scholar]
  142. 142.  Obermeyer Z, Emanuel EJ 2016. Predicting the future—big data, machine learning, and clinical medicine. New Engl. J. Med. 375:131216–19
    [Google Scholar]
  143. 143.  Ching T, Himmelstein DS, Beaulieu-Jones BK, Kalinin AA, Do BT et al. 2017. Opportunities and obstacles for deep learning in biology and medicine. bioRxiv 142760. https://doi.org/10.1101/142760
    [Crossref]
  144. 144.  Cabitza F, Rasoini R, Gensini GF 2017. Unintended consequences of machine learning in medicine. JAMA 318:6517–18
    [Google Scholar]
  145. 145.  Rajpurkar P, Hannun AY, Haghpanahi M, Bourn C, Ng AY 2017. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv:1707.01836 [cs.CV]
  146. 146.  Lee CK, Hofer I, Gabel E, Baldi P, Cannesson M 2018. Development and validation of a deep neural network model for prediction of postoperative in-hospital mortality. Anesthesiology In press
    [Google Scholar]
  147. 147.  Lasko TA, Denny JC, Levy MA 2013. Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data. PLOS ONE 8:6e66341
    [Google Scholar]
  148. 148.  Miotto R, Li L, Kidd BA, Dudley JT 2016. Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Sci. Rep. 6:26094
    [Google Scholar]
  149. 149.  Beaulieu-Jones BK, Greene CS et al. 2016. Semi-supervised learning of the electronic health record for phenotype stratification. J. Biomed. Inform. 64:168–78
    [Google Scholar]
  150. 150.  Jensen AB, Moseley PL, Oprea TI, Ellesøe SG, Eriksson R et al. 2014. Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients. Nat. Commun. 5:4022
    [Google Scholar]
  151. 151.  Pham T, Tran T, Phung D, Venkatesh S 2017. Predicting healthcare trajectories from medical records: a deep learning approach. J. Biomed. Inform. 69:218–229
    [Google Scholar]
  152. 152.  Choi E, Bahadori MT, Schuetz A, Stewart WF, Sun J 2016. Doctor AI: predicting clinical events via recurrent neural networks. Proc. Mach. Learn. Res. 56:301–18
    [Google Scholar]
  153. 153.  Zipser D, Andersen RA 1988. A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature 331:6158679–84
    [Google Scholar]
  154. 154.  Yamins DLK, DiCarlo JJ 2016. Using goal-driven deep learning models to understand sensory cortex. Nat. Neurosci. 19:3356–65
    [Google Scholar]
  155. 155.  Baldi P, Sadowski P 2016. A theory of local learning, the learning channel, and the optimality of backpropagation. Neural Netw 83:61–74
    [Google Scholar]
  156. 156.  Baldi P, Lu Z, Sadowski P 2017. Learning in the machine: the symmetries of the deep learning channel. Neural Netw 95:110–33
    [Google Scholar]
  157. 157.  Bach S, Binder A, Montavon G, Klauschen F, Müller K-R, Samek W 2015. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLOS ONE 10:7e0130140
    [Google Scholar]
  158. 158.  Ribeiro MT, Singh S, Guestrin C 2016. “Why should I trust you?”: Explaining the predictions of any classifier. Proc. Conf. Knowl. Discov. Data Min., 22nd, San Franc., Calif., 13–17 Aug. New York: Assoc. Comput. Mach.
    [Google Scholar]
  159. 159.  Sherrington CS 1951. Man on His Nature Cambridge, UK: Cambridge Univ. Press. , 2nd ed..
    [Google Scholar]
/content/journals/10.1146/annurev-biodatasci-080917-013343
Loading
/content/journals/10.1146/annurev-biodatasci-080917-013343
Loading

Data & Media loading...

  • Article Type: Review Article
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error