https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=30906311&retmode=xml&tool=Litmetric&email=readroberts32@gmail.com&api_key=61f08fa0b96a73de8c900d749fcb997acc09 3090631120200928
1664-8021102019Frontiers in geneticsFront GenetSALMON: Survival Analysis Learning With Multi-Omics Neural Networks on Breast Cancer.16616616610.3389/fgene.2019.00166Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.HuangZhiZSchool of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, United States.Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.Department of Electrical and Computer Engineering, Indiana University-Purdue University Indianapolis, Indianapolis, IN, United States.ZhanXiaohuiXDepartment of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China.XiangShunianSNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China.Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, United States.JohnsonTravis STSDepartment of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.Department of Biomedical Informatics, The Ohio State University, Columbus, OH, United States.HelmBryanBDepartment of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.YuChristina YCYDepartment of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.Department of Biomedical Informatics, The Ohio State University, Columbus, OH, United States.ZhangJieJDepartment of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, United States.SalamaPaulPDepartment of Electrical and Computer Engineering, Indiana University-Purdue University Indianapolis, Indianapolis, IN, United States.RizkallaMaherMDepartment of Electrical and Computer Engineering, Indiana University-Purdue University Indianapolis, Indianapolis, IN, United States.HanZhiZDepartment of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.Regenstrief Institute, Indianapolis, IN, United States.HuangKunKDepartment of Medicine, Indiana University School of Medicine, Indianapolis, IN, United States.Department of Electrical and Computer Engineering, Indiana University-Purdue University Indianapolis, Indianapolis, IN, United States.Regenstrief Institute, Indianapolis, IN, United States.engF31 LM013056LMNLM NIH HHSUnited StatesU01 CA188547CANCI NIH HHSUnited StatesJournal Article20190308
SwitzerlandFront Genet1015606211664-8021breast cancerco-expression analysiscox regressiondeep Learningmulti-omicsneural networkssurvival prognosis20181212019214201932660201932560201932561201938epublish30906311PMC641952610.3389/fgene.2019.00166Adami H. O., Malker B., Holmberg L., Persson I., Stone B. (1986). The relation between survival and age at diagnosis in breast cancer. N. Engl. J. Med. 315, 559–563. 10.1056/NEJM19860828315090610.1056/NEJM1986082831509063736639Arash E. H., Shiban A., Song S. Y., Attisano L. (2017). MARK4 inhibits Hippo signaling to promote proliferation and migration of breast cancer cells. EMBO Rep. 18, 420–436. 10.15252/embr.20164245510.15252/embr.201642455PMC533126428183853Barry W. T., Kernagis D. N., Dressman H. K., Griffis R. J., Hunter J. D., Olson J. A., et al. . (2010). Intratumor heterogeneity and precision of microarray-based predictors of breast cancer biology and clinical outcome. J. Clin. Oncol. 28, 2198–2206. 10.1200/JCO.2009.26.724510.1200/JCO.2009.26.7245PMC286043720368555Bassiouni R., Nemec K. N., Iketani A., Flores O., Showalter A., Khaled A. S., et al. . (2016). Chaperonin containing TCP-1 protein level in breast cancer cells predicts therapeutic application of a cytotoxic peptide. Clin. Cancer Res. 22, 4366–4379. 10.1158/1078-0432.CCR-15-250210.1158/1078-0432.CCR-15-2502PMC501052227012814Bauer K. R., Brown M., Cress R. D., Parise C. A., Caggiano V. (2007). Descriptive analysis of estrogen receptor (ER)negative, progesterone receptor (PR)-negative, and HER2-negative invasive breast cancer, the so-called triple-negative phenotype - a population-based study from the California Cancer Registry. Cancer 109, 1721–1728. 10.1002/cncr.2261810.1002/cncr.2261817387718Birkbak N. J., Kochupurakkal B., Izarzugaza J. M., Eklund A. C., Li Y., Liu J., et al. (2013). Tumor mutation burden forecasts outcome in ovarian cancer with BRCA1 or BRCA2 mutations. PLoS ONE 8:e80023 10.1371/journal.pone.008002310.1371/journal.pone.0080023PMC382714124265793Boyd N. F., Byng J. W., Jong R. A., Fishell E. K., Little L. E., Miller A. B., et al. . (1995). Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study. J. Natl. Cancer Inst. 87, 670–675. 10.1093/jnci/87.9.67010.1093/jnci/87.9.6707752271Bradley A. P. (1997). The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 1145–1159. 10.1016/S0031-3203(96)00142-210.1016/S0031-3203(96)00142-2Broude E. V., Gyorffy B., Chumanevich A. A., Chen M. Q., McDermott M. S. J., Shtutman M., et al. . (2015). Expression of CDK8 and CDK8-interacting genes as potential biomarkers in breast cancer. Curr. Cancer Drug Targets 15, 739–749. 10.2174/15680096150815100110581410.2174/156800961508151001105814PMC475530626452386Burwinkel B., Wirtenberger M., Klaes R., Schmutzler R. K., Grzybowska E., Forsti A., et al. . (2005). Association of NCOA3 polymorphisms with breast cancer risk. Clin. Cancer Res. 11, 2169–2174. 10.1158/1078-0432.CCR-04-162110.1158/1078-0432.CCR-04-162115788663Caruana R., Lawrence S., Giles L. (2001). Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping, in Advances in Neural Information Processing Systems 13, Papers from Neural Information Processing Systems (NIPS) 2000 (Denver, CO: ), 402–408.Chalmers Z. R., Connelly C. F., Fabrizio D., Gay L., Ali S. M., Ennis R., et al. . (2017). Analysis of 100,000 human cancer genomes reveals the landscape of tumor mutational burden. Genome Med. 9:34. 10.1186/s13073-017-0424-210.1186/s13073-017-0424-2PMC539571928420421Chandran V., Coppola G., Nawabi H., Omura T., Versano R., Huebner E. A., et al. . (2016). A systems-level analysis of the peripheral nerve intrinsic axonal growth program. Neuron 89, 956–970. 10.1016/j.neuron.2016.01.03410.1016/j.neuron.2016.01.034PMC479009526898779Chaudhary K., Poirion O. B., Lu L., Garmire L. X. (2018). Deep learning-based multi-omics integration robustly predicts survival in liver cancer. Clin. Cancer Res. 24, 1248–1259. 10.1158/1078-0432.CCR-17-085310.1158/1078-0432.CCR-17-0853PMC605017128982688Chen J., Bardes E. E., Aronow B. J., Jegga A. G. (2009). ToppGene suite for gene list enrichment analysis and candidate gene prioritization. Nucleic Acids Res. 37, W305–W311. 10.1093/nar/gkp42710.1093/nar/gkp427PMC270397819465376Cheng J., Zhang J., Han Y., Wang X., Ye X., Meng Y., et al. . (2017). Integrative analysis of histopathological images and genomic data predicts clear cell renal cell carcinoma prognosis. Cancer Res. 77, e91–e100. 10.1158/0008-5472.CAN-17-031310.1158/0008-5472.CAN-17-0313PMC726257629092949Chin S. F., Teschendorff A. E., Marioni J. C., Wang Y., Barbosa-Morais N. L., Thorne N. P., et al. . (2007). High-resolution aCGH and expression profiling identifies a novel genomic subtype of ER negative breast cancer. Genome Biol. 8:R215. 10.1186/gb-2007-8-10-r21510.1186/gb-2007-8-10-r215PMC224628917925008Ching T., Zhu X., Garmire L. X. (2018). Cox-nnet: an artificial neural network method for prognosis prediction of high-throughput omics data. PLoS Comput. Biol. 14:e1006076. 10.1371/journal.pcbi.100607610.1371/journal.pcbi.1006076PMC590992429634719Cox D. G., Hankinson S. E., Hunter D. J. (2006). Polymorphisms of the AURKA (STK15/Aurora Kinase) gene and breast cancer risk (United States). Cancer Causes Control 17, 81–83. 10.1007/s10552-005-0429-910.1007/s10552-005-0429-916411056Ercolani C., Di Benedetto A., Terrenato I., Pizzuti L., Di Lauro L., Sergi D., et al. . (2017). Expression of phosphorylated Hippo pathway kinases (MST1/2 and LATS1/2) in HER2-positive and triple-negative breast cancer patients treated with neoadjuvant therapy. Cancer Biol. Ther. 18, 339–346. 10.1080/15384047.2017.131223010.1080/15384047.2017.1312230PMC549975328387539Feng Y., Chen M. H., Moskowitz I. P., Mendonza A. M., Vidali L., Nakamura F., et al. . (2006). Filamin A (FLNA) is required for cell-cell contact in vascular development and cardiac morphogenesis. Proc. Natl. Acad. Sci. U.S.A. 103, 19836–19841. 10.1073/pnas.060962810410.1073/pnas.0609628104PMC170253017172441Friedman J., Hastie T., Tibshirani R. (2010). Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33, 1–22. 10.18637/jss.v033.i0110.18637/jss.v033.i01PMC292988020808728Geman S., Bienenstock E., Doursat R. (1992). Neural networks and the bias variance dilemma. Neural Comput. 4, 1–58. 10.1162/neco.1992.4.1.110.1162/neco.1992.4.1.1Golub G. H., Reinsch C. (1970). Singular value decomposition and least squares solutions. Numerische Math. 14, 403–420. 10.1007/BF0216302710.1007/BF02163027Goodman A. M., Kato S., Bazhenova L., Patel S. P., Frampton G. M., Miller V., et al. . (2017). Tumor mutational burden as an independent predictor of response to immunotherapy in diverse cancers. Mol. Cancer Ther. 16, 2598–2608. 10.1158/1535-7163.MCT-17-038610.1158/1535-7163.MCT-17-0386PMC567000928835386Gupta A., Mutebi M., Bardia A. (2015). Gene-expression-based predictors for breast cancer. Ann. Surg. Oncol. 22, 3418–3432. 10.1245/s10434-015-4703-010.1245/s10434-015-4703-026215189Gyorffy B., Lanczky A., Eklund A. C., Denkert C., Budczies J., Li Q., et al. . (2010). An online survival analysis tool to rapidly assess the effect of 22,277 genes on breast cancer prognosis using microarray data of 1,809 patients. Breast Cancer Res. Treat. 123, 725–731. 10.1007/s10549-009-0674-910.1007/s10549-009-0674-920020197Hadrup S., Donia M., Thor Straten P. (2013). Effector CD4 and CD8 T cells and their role in the tumor microenvironment. Cancer Microenviron. 6, 123–133. 10.1007/s12307-012-0127-610.1007/s12307-012-0127-6PMC371705923242673Han W., Han M. R., Kang J. J., Bae J. Y., Lee J. H., Bae Y. J., et al. . (2006). Genomic alterations identified by array comparative genomic hybridization as prognostic markers in tamoxifen-treated estrogen receptor-positive breast cancer. BMC Cancer 6:92. 10.1186/1471-2407-6-9210.1186/1471-2407-6-92PMC145918216608533Han Z., Johnson T., Zhang J., Zhang X., Huang K. (2017). Functional virtual flow cytometry: a visual analytic approach for characterizing single-cell gene expression patterns. Biomed. Res. Int. 2017:3035481 10.1155/2017/30354810.1155/2017/303548PMC553613428798928Han Z., Zhang J., Sun G., Liu G., Huang K. (2016). A matrix rank based concordance index for evaluating and detecting conditional specific co-expressed gene modules. BMC Genomics 17(Suppl. 7):519. 10.1186/s12864-016-2912-y10.1186/s12864-016-2912-yPMC500123127556416Horvath S., Zhang Y., Langfelder P., Kahn R. S., Boks M. P., van Eijk K., et al. . (2012). Aging effects on DNA methylation modules in human brain and blood tissue. Genome Biol. 13:R97. 10.1186/gb-2012-13-10-r9710.1186/gb-2012-13-10-r97PMC405373323034122Huang S., Chaudhary K., Garmire L. X. (2017). More is better: recent progress in multi-omics data integration methods. Front. Genet. 8:84. 10.3389/fgene.2017.0008410.3389/fgene.2017.00084PMC547269628670325Huang W. Y., Newman B., Millikan R. C., Schell M. J., Hulka B. S., Moorman P. G. (2000). Hormone-related factors and risk of breast cancer in relation to estrogen receptor and progesterone receptor status. Am. J. Epidemiol. 151, 703–714. 10.1093/oxfordjournals.aje.a01026510.1093/oxfordjournals.aje.a01026510752798Hung K., Hayashi R., Lafond-Walker A., Lowenstein C., Pardoll D., Levitsky H. (1998). The central role of CD4(+) T cells in the antitumor immune response. J. Exp. Med. 188, 2357–2368. 10.1084/jem.188.12.235710.1084/jem.188.12.2357PMC22124349858522Ishwaran H., Kogalur U. B., Blackstone E. H., Lauer M. S. (2008). Random survival forests. Ann. Appl. Stat. 2, 841–860. 10.1214/08-AOAS16910.1214/08-AOAS169Kastan M. B., Bartek J. (2004). Cell-cycle checkpoints and cancer. Nature 432, 316–323. 10.1038/nature0309710.1038/nature0309715549093Katzman J. L., Shaham U., Cloninger A., Bates J., Jiang T. T., Kluger Y. (2018). DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med. Res. Methodol. 18:24. 10.1186/s12874-018-0482-110.1186/s12874-018-0482-1PMC582843329482517Kingma D., Ba J. (2015). Adam: a method for stochastic optimization, in Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015).Kuleshov M. V., Jones M. R., Rouillard A. D., Fernandez N. F., Duan Q., Wang Z., et al. . (2016). Enrichr: a comprehensive gene set enrichment analysis web server 2016 update. Nucleic Acids Res. 44, W90–W97. 10.1093/nar/gkw37710.1093/nar/gkw377PMC498792427141961Langfelder P., Horvath S. (2008). WGCNA: an R package for weighted correlation network analysis. BMC Bioinformatics 9:559. 10.1186/1471-2105-9-55910.1186/1471-2105-9-559PMC263148819114008Liu G., Dong C., Liu L. (2016). Integrated multiple “-omics” data reveal subtypes of hepatocellular carcinoma. PLoS ONE 11:e0165457. 10.1371/journal.pone.016545710.1371/journal.pone.0165457PMC509187527806083Ma T., Zhang A. (2018). Multi-view factorization AutoEncoder with network constraints for multi-omic integrative analysis, in IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (IEEE: ). 10.1109/BIBM.2018.862137910.1109/BIBM.2018.8621379Mantel N. (1966). Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemother. Rep. 50, 163–170.5910392Marshall C. R., Howrigan D. P., Merico D., Thiruvahindrapuram B., Wu W., Greer D. S., et al. . (2017). Contribution of copy number variants to schizophrenia from a genome-wide study of 41,321 subjects. Nat. Genet. 49, 27–35. 10.1038/ng.372510.1038/ng.3725PMC573777227869829Meyer K. B., Carroll J. S. (2012). FOXA1 and breast cancer risk. Nat. Genet. 44, 1176–1177. 10.1038/ng.244910.1038/ng.244923104063Miller L. D., Smeds J., George J., Vega V. B., Vergara L., Ploner A., et al. . (2005). An expression signature for p53 status in human breast cancer predicts mutation status, transcriptional effects, and patient survival. Proc. Natl. Acad. Sci. U.S.A. 102, 13550–13555. 10.1073/pnas.050623010210.1073/pnas.0506230102PMC119727316141321Moh M. C., Shen S. L. (2009). The roles of cell adhesion molecules in tumor suppression and cell migration a new paradox. Cell Adh. Migr. 3, 334–336. 10.4161/cam.3.4.924610.4161/cam.3.4.9246PMC280274119949308Mukaka M. M. (2012). Statistics corner: a guide to appropriate use of correlation coefficient in medical research. Malawi Med. J. 24, 69–71.PMC357683023638278Muleris M., Almeida A., Gerbault-Seureau M., Malfoy B., Dutrillaux B. (1995). Identification of amplified DNA sequences in breast cancer and their organization within homogeneously staining regions. Genes Chromosomes Cancer 14, 155–163. 10.1002/gcc.287014030210.1002/gcc.28701403028589031Nagini S. (2017). Breast cancer: current molecular therapeutic targets and new players. Anticancer. Agents Med. Chem. 17, 152–163. 10.2174/187152061666616050212272410.2174/187152061666616050212272427137076Nassar F. J., Nasr R., Talhouk R. (2017). MicroRNAs as biomarkers for early breast cancer diagnosis, prognosis and therapy prediction. Pharmacol. Ther. 172, 34–49. 10.1016/j.pharmthera.2016.11.01210.1016/j.pharmthera.2016.11.01227916656Ng A. Y., Jordan M. I., Weiss Y. (2002). On spectral clustering: analysis and an algorithm, in Advances in Neural Information Processing Systems (MIT Press: ), 849–856.Pereira B., Chin S. F., Rueda O. M., Vollan H. K., Provenzano E., Bardwell H. A., et al. . (2016). The somatic mutation profiles of 2,433 breast cancers refines their genomic and transcriptomic landscapes. Nat. Commun. 7:11479. 10.1038/ncomms1147910.1038/ncomms11479PMC486604727161491Poirion O. B., Chaudhary K., Garmire L. X. (2018). Deep learning data integration for better risk stratification models of bladder cancer. AMIA Jt. Summits Transl. Sci. Proc. 2017, 197–206.PMC596179929888072Pujana M. A., Han J. D., Starita L. M., Stevens K. N., Tewari M., Ahn J. S., et al. . (2007). Network modeling links breast cancer susceptibility and centrosome dysfunction. Nat. Genet. 39, 1338–1349. 10.1038/ng.2007.210.1038/ng.2007.217922014Quail D. F., Joyce J. A. (2013). Microenvironmental regulation of tumor progression and metastasis. Nat. Med. 19, 1423–1437. 10.1038/nm.339410.1038/nm.3394PMC395470724202395Ramazzotti D., Lal A., Wang B., Batzoglou S., Sidow A. (2018). Multi-omic tumor data reveal diversity of molecular mechanisms that correlate with survival. Nat. Commun. 9:4453. 10.1038/s41467-018-06921-810.1038/s41467-018-06921-8PMC620371930367051Rangel N., Fortunati N., Osella-Abate S., Annaratone L., Isella C., Catalano M. G., et al. . (2018). FOXA1 and AR in invasive breast cancer: new findings on their co-expression and impact on prognosis in ER-positive patients. BMC Cancer 18:703. 10.1186/s12885-018-4624-y10.1186/s12885-018-4624-yPMC602937029970021Ren T., Zhang W., Liu X., Zhao H., Zhang J., Zhang J., et al. . (2014). Discoidin domain receptor 2 (DDR2) promotes breast cancer cell metastasis and the mechanism implicates epithelial-mesenchymal transition programme under hypoxia. J. Pathol. 234, 526–537. 10.1002/path.441510.1002/path.441525130389Robertson C. (2016). The extracellular matrix in breast cancer predicts prognosis through composition, splicing, and crosslinking. Exp. Cell Res. 343, 73–81. 10.1016/j.yexcr.2015.11.00910.1016/j.yexcr.2015.11.00926597760Rouault A., Banneau G., MacGrogan G., Jones N., Elarouci N., Barouk-Simonet E., et al. . (2012). Deletion of chromosomes 13q and 14q is a common feature of tumors with BRCA2 mutations. PLoS ONE 7:e52079. 10.1371/journal.pone.005207910.1371/journal.pone.0052079PMC352876523284877Ruiz de Garibay G., Mateo F., Stradella A., Valdes-Mas R., Palomero L., Serra-Musach J., et al. . (2018). Tumor xenograft modeling identifies an association between TCF4 loss and breast cancer chemoresistance. Dis. Model. Mech. 11:dmm032292. 10.1242/dmm.03229210.1242/dmm.032292PMC599260929666142Saadatmand S., de Kruijf E. M., Sajet A., Dekker-Ensink N. G., van Nes J. G. H., Putter H., et al. . (2013). Expression of cell adhesion molecules and prognosis in breast cancer. Br. J. Surg. 100, 252–260. 10.1002/bjs.898010.1002/bjs.898023175431Santosa F., Symes W. W. (1986). Linear inversion of band-limited reflection seismograms. SIAM J. Sci. Stat. Comput. 7, 1307–1330. 10.1137/090708710.1137/0907087Sato N., Maeda M., Sugiyama M., Ito S., Hyodo T., Masuda A., et al. . (2015). Inhibition of SNW1 association with spliceosomal proteins promotes apoptosis in breast cancer cells. Cancer Med. 4, 268–277. 10.1002/cam4.36610.1002/cam4.366PMC432901025450007Schmidhuber J. (2015). Deep learning in neural networks: an overview. Neural Netw. 61, 85–117. 10.1016/j.neunet.2014.09.00310.1016/j.neunet.2014.09.00325462637Setiono R., Liu H. (1997). Neural-network feature selector. IEEE Trans. Neural Netw. 8, 654–662. 10.1109/72.57210410.1109/72.57210418255668Shadeo A., Lam W. L. (2006). Comprehensive copy number profiles of breast cancer cell model genomes. Breast Cancer Res. 8:R9. 10.1186/bcr137010.1186/bcr1370PMC141399416417655Shan W., Jiang Y., Yu H., Huang Q., Liu L., Guo X., et al. . (2017). HDAC2 overexpression correlates with aggressive clinicopathological features and DNA-damage response pathway of breast cancer. Am. J. Cancer Res. 7, 1213–1226.PMC544648528560068Shao W., Cheng J., Sun L., Han Z., Feng Q., Zhang D., et al. (2018). Ordinal multi-modal feature selection for survival analysis of early-stage renal cancer, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Granada: Springer; ), 648–656.Shroff S., Zhang J., Huang K. (2016). Gene co-expression analysis predicts genetic variants associated with drug responsiveness in lung cancer. AMIA Jt Summits Transl. Sci. Proc. 2016, 32–41.PMC500175727570645Steck H., Krishnapuram B., Dehing-oberije C., Lambin P., Raykar V. C. (2007). On ranking in survival analysis: bounds on the concordance index, in Advances in Neural Information Processing Systems (Vancouver, BC: ), 1209–1216.Sun D., Wang M., Li A. (2018). A multimodal deep neural network for human breast cancer prognosis prediction by integrating multi-dimensional data. IEEE/ACM Trans. Comput. Biol. Bioinform. 99:1 10.1109/TCBB.2018.280643810.1109/TCBB.2018.280643829994639Sung A. H., Mukkamala S. (2003). Identifying important features for intrusion detection using support vector machines and neural networks, in 2003 Symposium on Applications and the Internet, Proceedings (Orlando, FL: ), 209–216. 10.1109/SAINT.2003.118305010.1109/SAINT.2003.1183050Thomas A., Routh E. D., Pullikuth A., Jin G., Su J., Chou J. W., et al. . (2018). Tumor mutational burden is a determinant of immune-mediated survival in breast cancer. Oncoimmunology 7:e1490854. 10.1080/2162402X.2018.149085410.1080/2162402X.2018.1490854PMC620742030386679Tian H. M., Liu X. H., Han W., Zhao L. L., Yuan B., Yuan C. J. (2013). Differential expression of filamin A and its clinical significance in breast cancer. Oncol. Lett. 6, 681–686. 10.3892/ol.2013.145410.3892/ol.2013.1454PMC378903524137390Ton C., Guenthoer J., Porter P. L. (2009). Somatic alterations and implications in breast cancer, in Role of Genetics in Breast and Productive Cancers, ed Welcsh P. (Seattle, WA: Springer; ), 183–213. 10.1007/978-1-4419-0477-5_910.1007/978-1-4419-0477-5_9Totzke J., Gurbani D., Raphemot R., Hughes P. F., Bodoor K., Carlson D. A., et al. . (2017). Takinib, a selective TAK1 inhibitor, broadens the therapeutic efficacy of TNF-alpha inhibition for cancer and autoimmune disease. Cell Chem. Biol. 24, 1029–1039 e1027. 10.1016/j.chembiol.2017.07.01110.1016/j.chembiol.2017.07.011PMC557657028820959Vincent-Salomon A., Thiery J. P. (2003). Host microenvironment in breast cancer development: epithelial-mesenchymal transition in breast cancer development. Breast Cancer Res. 5, 101–106. 10.1186/bcr57810.1186/bcr578PMC15415612631389Wang T., Fahrmann J. F., Lee H., Li Y. J., Tripathi S. C., Yue C., et al. (2018). JAK/STAT3-regulated fatty acid beta-oxidation is critical for breast cancer stem cell self-renewal and chemoresistance. Cell Metab. 27, 136–150 e135. 10.1016/j.cmet.2018.04.01810.1016/j.cmet.2018.04.018PMC577733829249690Weigend A. S., Rumelhart D. E., Huberman B. A. (1990). Generalization by weight-elimination with application to forecasting, in Advances in Neural Information Processing Systems (Denver, CO: ), 875–882Wu X. F., Ye Y. Q., Barcenas C. H., Chow W. H., Meng Q. H., Chavez-MacGregor M., et al. . (2017). Personalized prognostic prediction models for breast cancer recurrence and survival incorporating multidimensional data. J. Natl. Cancer Inst. 109. 10.1093/jnci/djw31410.1093/jnci/djw314PMC627931128376179Xiang S., Huang Z., Wang T., Han Z., Yu C. Y., Ni D., et al. . (2018). Condition-specific gene co-expression network mining identifies key pathways and regulators in the brain tissue of Alzheimer's disease patients. 11:115. 10.1186/s12920-018-0431-110.1186/s12920-018-0431-1PMC631192730598117Xiang Y., Zhang C. Q., Huang K. (2012). Predicting glioblastoma prognosis networks using weighted gene co-expression network analysis on TCGA data. BMC Bioinformatics 13:S12. 10.1186/1471-2105-13-S2-S1210.1186/1471-2105-13-S2-S12PMC330574822536863Yaffe M. B., Farr G. W., Miklos D., Horwich A. L., Sternlicht M. L., Sternlicht H. (1992). TCP1 complex is a molecular chaperone in tubulin biogenesis. Nature 358, 245–248. 10.1038/358245a010.1038/358245a01630491Zhang G. Q. P. (2000). Neural networks for classification: a survey. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 30, 451–462. 10.1109/5326.89707210.1109/5326.897072Zhang J., Abrams Z., Parvin J. D., Huang K. (2016). Integrative analysis of somatic mutations and transcriptomic data to functionally stratify breast cancer patients. BMC Genomics 17(Suppl. 7):513. 10.1186/s12864-016-2902-010.1186/s12864-016-2902-0PMC500123527556157Zhang J., Huang K. (2014). Normalized lmQCM: an algorithm for detecting weak quasi-cliques in weighted graph with applications in gene co-expression module discovery in cancers. Cancer Inform. 13(Suppl. 3), 137–146. 10.4137/CIN.S1402110.4137/CIN.S14021PMC496295927486298Zhang J., Huang K. (2017). Pan-cancer analysis of frequent DNA co-methylation patterns reveals consistent epigenetic landscape changes in multiple cancers. BMC Genomics 18(Suppl. 1):1045. 10.1186/s12864-016-3259-010.1186/s12864-016-3259-0PMC531028328198667Zhang J., Lu K. W., Xiang Y., Islam M., Kotian S., Kais Z., et al. . (2012). Weighted frequent gene co-expression network mining to identify genes involved in genome stability. PLoS Comput. Biol. 8:e1002656. 10.1371/journal.pcbi.100265610.1371/journal.pcbi.1002656PMC343129322956898Zhang J., Ni S., Xiang Y., Parvin J. D., Yang Y., Zhou Y., et al. . (2013). Gene co-expression analysis predicts genetic aberration loci associated with colon cancer metastasis. Int. J. Comput. Biol. Drug Des. 6, 60–71. 10.1504/IJCBDD.2013.05220210.1504/IJCBDD.2013.05220223428474Zhang L., Lv C., Jin Y., Cheng G., Fu Y., Yuan D., et al. . (2018a). Deep learning-based multi-omics data integration reveals two prognostic subtypes in high-risk neuroblastoma. Front. Genet. 9:477. 10.3389/fgene.2018.0047710.3389/fgene.2018.00477PMC620170930405689Zhang Z., Zhao Y., Liao X., Shi W., Li K., Zou Q., et al. (2018b). Deep learning in omics: a survey and guideline. Brief. Funct. Genomics. 18, 41–57. 10.1093/bfgp/ely03010.1093/bfgp/ely03030265280