A deep learning approach for predicting antidepressant response in major depression using clinical and genetic biomarkers

Frontiers in Psychiatry

Volumn 9, Issue JUL, 2018, Pages

  Lin, Eugene ^a,b   Kuo, Po Hsiu ^c   Liu, Yu Li ^d   Yu, Younger W Y ^e   Yang, Albert C ^f,g,h   Tsai, Shih Jen ^f,g  

^a University of Washington   (United States)

^b CHINA MEDICAL UNIVERSITY   (Taiwan)

^c NATIONAL TAIWAN UNIVERSITY   (Taiwan)

^d NATIONAL HEALTH RESEARCH INSTITUTES   (Taiwan)

^e Yu's Psychiatric Clinic   (Taiwan)

^f TAIPEI VETERANS GENERAL HOSPITAL   (Taiwan)

^g NATIONAL YANG MING UNIVERSITY   (Taiwan)

^h BETH ISRAEL DEACONESS MEDICAL CENTER   (United States)

Author keywords

Antidepressant; Deep learning; Genome wide association studies; Major depressive disorder; Multilayer feedforward neural networks; Personalized medicine; Single nucleotide polymorphisms

Indexed keywords

BIOLOGICAL MARKER; CITALOPRAM; ESCITALOPRAM; FLUOXETINE; PAROXETINE;

ABCA13 GENE; ADULT; AGE; ARNTL GENE; ARTICLE; BNIP3 GENE; CACNA1E GENE; CAMK1D GENE; COHORT ANALYSIS; EXOC4 GENE; FEMALE; GABRB3 GENE; GENE; GENE LOCUS; GENETIC SUSCEPTIBILITY; GENOME-WIDE ASSOCIATION STUDY; GRIN2B GENE; GRM8 GENE; HAMILTON DEPRESSION RATING SCALE; HUMAN; LHFPL3 GENE; MACHINE LEARNING; MAJOR CLINICAL STUDY; MAJOR DEPRESSION; MALE; MOLECULAR GENETICS; NAALADL2 GENE; NCALD GENE; NELL1 GENE; NUAK1 GENE; PLA2G4A GENE; PREX1 GENE; PROK2 GENE; RBFOX1 GENE; REMISSION; SEX DIFFERENCE; SINGLE NUCLEOTIDE POLYMORPHISM; SLIT3 GENE; SOCIAL STATUS; SUICIDE ATTEMPT; TREATMENT RESPONSE; ZNF536 GENE;

EID: 85049845461     PISSN: None     EISSN: 16640640     Source Type: Journal    
DOI: 10.3389/fpsyt.2018.00290     Document Type: Article

References (57)

1. Katsanis SH, Javitt G, Hudson K. Public health. A case study of personalized medicine. Science (2008) 320:53-4. doi: 10.1126/science.1156604
2. Snyderman R. Personalized health care: from theory to practice. Biotechnol J. (2012) 7:973-9. doi: 10.1002/biot.201100297
3. Sadee W, Dai Z. Pharmacogenetics/genomics and personalized medicine. Hum Mol Genet. (2005) 14 Spec No. 2:R207-14. doi: 10.1093/hmg/ddi261
4. Lane HY, Tsai GE, Lin E. Assessing gene-gene interactions in pharmacogenomics. Mol Diagn Ther. (2012) 16:15-27. doi: 10.2165/11597270-000000000-00000
5. Lin E, Chen PS. Pharmacogenomics with antidepressants in the STAR*D study. Pharmacogenomics (2008) 9:935-46. doi: 10.2217/14622416.9.7.935
6. Lin E, Lane HY. Genome-wide association studies in pharmacogenomics of antidepressants. Pharmacogenomics (2015) 16:555-66. doi: 10.2217/pgs.15.5
7. Hamburg MA, Collins FS. The path to personalized medicine. N Engl J Med. (2010) 363:301-4. doi: 10.1056/NEJMp1006304
8. Lin E, Tsai SJ. Genome-wide microarray analysis of gene expression profiling in major depression and antidepressant therapy. Prog Neuropsychopharmacol Biol Psychiatry (2016) 64:334-40. doi: 10.1016/j.pnpbp.2015.02.008
9. Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell. (2013) 35:1798-828. doi: 10.1109/TPAMI.2013.50
10. Witten IHFE. Data Mining: Practical Machine Learning Tools and Techniques. Francisco, CA: Morgan Kaufmann Publishers (2005)
11. Chen Y, Li Y, Narayan R, Subramanian A, Xie X. Gene expression inference with deep learning. Bioinformatics (2016) 32:1832-9. doi: 10.1093/bioinformatics/btw074
12. Pham T, Tran T, Phung D, Venkatesh S. Predicting healthcare trajectories from medical records: a deep learning approach. J Biomed Inform. (2017) 69:218-29. doi: 10.1016/j.jbi.2017.04.001
13. Lin E, Lane HY. Machine learning and systems genomics approaches for multi-omics data. Biomark Res (2017) 5:2. doi: 10.1186/s40364-017-0082-y
14. Kautzky A, Baldinger P, Souery D, Montgomery S, Mendlewicz J, Zohar J, et al. The combined effect of genetic polymorphisms and clinical parameters on treatment outcome in treatment-resistant depression. Eur Neuropsychopharmacol. (2015) 25:441-53. doi: 10.1016/j.euroneuro.2015.01.001
15. Patel MJ, Andreescu C, Price JC, Edelman KL, Reynolds CF III, Aizenstein HJ. Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction. Int J Geriatr Psychiatry (2015) 30:1056-67. doi: 10.1002/gps.4262
16. Chekroud AM, Zotti RJ, Shehzad Z, Gueorguieva R, Johnson MK, Trivedi MH, et al. Cross-trial prediction of treatment outcome in depression: a machine learning approach. Lancet Psychiatry (2016) 3:243-50. doi: 10.1016/S2215-0366(15)00471-X
17. Iniesta R, Malki K, Maier W, Rietschel M, Mors O, Hauser J, et al. Combining clinical variables to optimize prediction of antidepressant treatment outcomes. J Psychiatr Res. (2016) 78:94-102. doi: 10.1016/j.jpsychires.2016.03.016
18. Maciukiewicz M, Marshe VS, Hauschild AC, Foster JA, Rotzinger S, Kennedy JL, et al. GWAS-based machine learning approach to predict duloxetine response in major depressive disorder. J Psychiatr Res. (2018) 99:62-8. doi: 10.1016/j.jpsychires.2017.12.009
19. Kung SY. Neural networks for intelligent multimedia processing. Proceed IEEE (1998) 86:1244-72
20. Lin E, Hwang Y, Wang SC, Gu ZJ, Chen EY. An artificial neural network approach to the drug efficacy of interferon treatments. Pharmacogenomics (2006) 7:1017-24. doi: 10.2217/14622416.7.7.1017
21. Biernacka JM, Sangkuhl K, Jenkins G, Whaley RM, Barman P, Batzler A, et al. The International SSRI Pharmacogenomics Consortium (ISPC): a genome-wide association study of antidepressant treatment response. Transl Psychiatry (2015) 5:e553. doi: 10.1038/tp.2015.47
22. Lin KM, Tsou HH, Tsai IJ, Hsiao MC, Hsiao CF, Liu CY, et al. CYP1A2 genetic polymorphisms are associated with treatment response to the antidepressant paroxetine. Pharmacogenomics (2010) 11:1535-43. doi: 10.2217/pgs.10.128
23. Lin E, Kuo PH, Liu YL, Yang AC, Tsai SJ. Transforming growth factor-beta signaling pathway-associated genes SMAD2 and TGFBR2 are implicated in metabolic syndrome in a Taiwanese population. Sci Rep. (2017) 7:13589. doi: 10.1038/s41598-017-14025-4
24. Lin E, Tsai SJ, Kuo PH, Liu YL, Yang AC, Kao CF, et al. The rs1277306 variant of the REST gene confers susceptibility to cognitive aging in an elderly taiwanese population. Dement Geriatr Cogn Disord. (2017) 43:119-27. doi: 10.1159/000455833
25. Howie BN, Donnelly P, Marchini J. A flexible and accurate genotype imputation method for the next generation of genome-wide association studies. PLoS Genet. (2009) 5:e1000529. doi: 10.1371/journal.pgen.1000529
26. Lin E, Kuo PH, Liu YL, Yang AC, Kao CF, Tsai SJ. Effects of circadian clock genes and health-related behavior on metabolic syndrome in a Taiwanese population: Evidence from association and interaction analysis. PLoS ONE (2017) 12:e0173861. doi: 10.1371/journal.pone.0173861
27. Lou XY, Chen GB, Yan L, Ma JZ, Zhu J, Elston RC, et al. A generalized combinatorial approach for detecting gene-by-gene and gene-by-environment interactions with application to nicotine dependence. Am J Hum Genet. (2007) 80:1125-37. doi: 10.1086/518312
28. Bishop CM. Neural Networks for Pattern Recognition. Oxford: Clarendon Press (1995)
29. Rumelhart DE, Hinton GE, William RJ. Learning internal representation by error propagation. In: Parallel Distributed Processing: Explorations. The Micro-Structure of Cognition. 1. Cambridge, MA: MIT Press (1996). p. 318-62
30. Huang LC, Hsu SY, Lin E. A comparison of classification methods for predicting Chronic Fatigue Syndrome based on genetic data. J Transl Med. (2009) 7:81. doi: 10.1186/1479-5876-7-81
31. Lin E, Hwang Y. A support vector machine approach to assess drug efficacy of interferon-alpha and ribavirin combination therapy. Mol Diagn Ther. (2008) 12:219-23. doi: 10.1007/BF03256287
32. Linden A. Measuring diagnostic and predictive accuracy in disease management: an introduction to receiver operating characteristic (ROC) analysis. J Eval Clin Pract. (2006) 12:132-9. doi: 10.1111/j.1365-2753.2005.00598.x
33. Lin E, Hsu SY. A Bayesian approach to gene-gene and gene-environment interactions in chronic fatigue syndrome. Pharmacogenomics (2009) 10:35-42. doi: 10.2217/14622416.10.1.35
34. Tohda M, Hayashi H, Sukma M, Tanaka K. BNIP-3: a novel candidate for an intrinsic depression-related factor found in NG108-15 cells treated with Hochu-ekki-to, a traditional oriental medicine, or typical antidepressants. Neurosci Res. (2008) 62:1-8. doi: 10.1016/j.neures.2008.05.007
35. Chen J, Khan RAW, Wang M, He K, Wang Q, Li Z, et al. Association between the variability of the ABCA13 gene and the risk of major depressive disorder and schizophrenia in the Han Chinese population. World J Biol Psychiatry (2017) 18:550-6. doi: 10.1080/15622975.2016.1245442
36. Glessner JT, Wang K, Sleiman PM, Zhang H, Kim CE, Flory JH, et al. Duplication of the SLIT3 locus on 5q35.1 predisposes to major depressive disorder. PLoS ONE (2010) 5:e15463. doi: 10.1371/journal.pone.0015463
37. Li J, Chai A, Wang L, Ma Y, Wu Z, Yu H, et al. Synaptic P-Rex1 signaling regulates hippocampal long-term depression and autism-like social behavior. Proc Natl Acad Sci USA. (2015) 112:E6964-72. doi: 10.1073/pnas.1512913112
38. Jan WC, Yang SY, Chuang LC, Lu RB, Lu MK, Sun HS, et al. Exploring the associations between genetic variants in genes encoding for subunits of calcium channel and subtypes of bipolar disorder. J Affect Disord. (2014) 157:80-6. doi: 10.1016/j.jad.2013.12.044
39. Guo Z, Niu W, Bi Y, Zhang R, Ren D, Hu J, et al. A study of single nucleotide polymorphisms of GRIN2B in schizophrenia from Chinese Han population. Neurosci Lett. (2016) 630:132-5. doi: 10.1016/j.neulet.2016.07.038
40. Merico D, Zarrei M, Costain G, Ogura L, Alipanahi B, Gazzellone MJ, et al. Whole-genome sequencing suggests schizophrenia risk mechanisms in humans with 22q11.2 deletion syndrome. G3 (Bethesda) (2015) 5:2453-61. doi: 10.1534/g3.115.021345
41. Alemany S, Ribases M, Vilor-Tejedor N, Bustamante M, Sanchez-Mora C, Bosch R, et al. New suggestive genetic loci and biological pathways for attention function in adult attention-deficit/hyperactivity disorder. Am J Med Genet B Neuropsychiatr Genet. (2015) 168:459-70. doi: 10.1002/ajmg.b.32341
42. Dateki S, Watanabe S, Kinoshita F, Yoshiura KI, Moriuchi H. Identification of 11p14.1-p15.3 deletion probably associated with short stature, relative macrocephaly, and delayed closure of the fontanelles. Am J Med Genet A. (2017) 173:217-20. doi: 10.1002/ajmg.a.37978
43. Davenport EC, Pendolino V, Kontou G, McGee TP, Sheehan DF, Lopez-Domenech G, et al. An essential role for the tetraspanin LHFPL4 in the cell-type-specific targeting and clustering of synaptic GABAA receptors. Cell Rep. (2017) 21:70-83. doi: 10.1016/j.celrep.2017.09.025
44. Manev H, Uz T. Clock genes: influencing and being influenced by psychoactive drugs. Trends Pharmacol Sci. (2006) 27:186-9. doi: 10.1016/j.tips.2006.02.003
45. Dmitrzak-Weglarz MP, Pawlak JM, Maciukiewicz M, Moczko J, Wilkosc M, Leszczynska-Rodziewicz A, et al. Clock gene variants differentiate mood disorders. Mol Biol Rep. (2015) 42:277-88. doi: 10.1007/s11033-014-3770-9
46. Pawlak J, Dmitrzak-Weglarz M, Maciukiewicz M, Wilkosc M, Leszczynska-Rodziewicz A, Zaremba D, et al. Suicidal behavior in the context of disrupted rhythmicity in bipolar disorder-data from an association study of suicide attempts with clock genes. Psychiatry Res. (2015) 226:517-20. doi: 10.1016/j.psychres.2015.01.010
47. Pae CU, Yu HS, Kim JJ, Lee CU, Lee SJ, Lee KU, et al. BanI polymorphism of the cytosolic phospholipase A2 gene and mood disorders in the Korean population. Neuropsychobiology (2004) 49:185-8. doi: 10.1159/000077364
48. Spijker S, Van Zanten JS, De Jong S, Penninx BW, van Dyck R, Zitman FG, et al. Stimulated gene expression profiles as a blood marker of major depressive disorder. Biol Psychiatry (2010) 68:179-86. doi: 10.1016/j.biopsych.2010.03.017
49. Terracciano A, Tanaka T, Sutin AR, Sanna S, Deiana B, Lai S, et al. Genome-wide association scan of trait depression. Biol Psychiatry (2010) 68:811-7. doi: 10.1016/j.biopsych.2010.06.030
50. Winham SJ, Cuellar-Barboza AB, McElroy SL, Oliveros A, Crow S, Colby CL, et al. Bipolar disorder with comorbid binge eating history: a genome-wide association study implicates APOB. J Affect Disord. (2014) 165:151-8. doi: 10.1016/j.jad.2014.04.026
51. Xu W, Cohen-Woods S, Chen Q, Noor A, Knight J, Hosang G, et al. Genome-wide association study of bipolar disorder in Canadian and UK populations corroborates disease loci including SYNE1 and CSMD1. BMC Med Genet. (2014) 15:2. doi: 10.1186/1471-2350-15-2
52. Gadelha A, Coleman J, Breen G, Mazzoti DR, Yonamine CM, Pellegrino R, et al. Genome-wide investigation of schizophrenia associated plasma Ndel1 enzyme activity. Schizophr Res. (2016) 172:60-7. doi: 10.1016/j.schres.2016.01.043
53. Li J, Yoshikawa A, Brennan MD, Ramsey TL, Meltzer HY. Genetic predictors of antipsychotic response to lurasidone identified in a genome wide association study and by schizophrenia risk genes. Schizophr Res. (2018) 192:194-204. doi: 10.1016/j.schres.2017.04.009
54. Sun J, Jayathilake K, Zhao Z, Meltzer HY. Investigating association of four gene regions (GABRB3, MAOB, PAH, and SLC6A4) with five symptoms in schizophrenia. Psychiatry Res. (2012) 198:202-6. doi: 10.1016/j.psychres.2011.12.035
55. Kuo PH, Chuang LC, Su MH, Chen CH, Chen CH, Wu JY, et al. Genome-wide association study for autism spectrum disorder in taiwanese han population. PLoS ONE (2015) 10:e0138695. doi: 10.1371/journal.pone.0138695
56. Perlis RH. A clinical risk stratification tool for predicting treatment resistance in major depressive disorder. Biol Psychiatry (2013) 74:7-14. doi: 10.1016/j.biopsych.2012.12.007
57. Lin E, Kuo PH, Liu YL, Yang AC, Kao CF, Tsai SJ. Association and interaction of APOA5, BUD13, CETP, LIPA and health-related behavior with metabolic syndrome in a Taiwanese population. Sci Rep. (2016) 6:36830. doi: 10.1038/srep36830