In what way to efficiently and accurately look for the causal genes related to the corresponding diseases becomes a hot spot in searching. When no control experiment can be applied, we usually use causal discovery method to detect causal genes. However, the traditional independence tests in high-dimensional data have high time complexity and low accuracy. To alleviate this problem, we propose a residual independence test algorithm that combines partial correlation test and linear residuals independence test to compress the search space of the conditional set of CI(conditional independence) test, and improve the accuracy. Next, we design a causal discovery algorithm based on residual independence test, which can distinguish Markov equivalence classes by V-structure and causal functional model, we apply it to real cancer datasets in the detection of pathogenic genes. The results show that proposed algorithm is significantly better than existing algorithms in many aspects.
MOLLAM, WADDELLM, PAGED, et al. Using machine learning to design and interpret gene-expression microarrays[J]. AI Magazine, 2004, 25(1): 23-44.
[3]
NOBLED. Genes and causation[J]. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2008, 366(1878): 3001-3015. DOI: 10.1098/rsta.2008.0086 .
[4]
COOKSONW, LIANGL M, ABECASISG, et al. Mapping complex disease traits with global gene expression[J]. Nature Reviews Genetics, 2009, 10(3): 184-194. DOI: 10.1038/nrg2537 .
[5]
DINGC, PENGH. Minimum redundancy feature selection from microarray gene expression data[J]. Journal of Bioinformatics & Computational Biology, 2008,3(2): 185-205.
[6]
BLEULERS, PRELICA, ZITZLERE. An EA framework for biclustering of gene expression data[C]//Proceedings of the 2004 Congress on Evolutionary Computation. New York: IEEE Press, 2004: 166-173. DOI: 10.1109/CEC.2004.1330853 .
[7]
CHAIL E, MOHAMADM S, DERISS, et al. Inferring gene regulatory networks from gene expression data by a dynamic bayesian network-based model[C]//Distributed Computing and Artificial Intelligence: 9th International Conference. Heidelberg:Springer, 2012: 379-386. DOI: 10.1007/978-3-642-28765-7_45 .
[8]
GUYONI, ELISSEEFFA. An introduction to variable and feature selection[J]. Journal of Machine Learning Research, 2003, 3: 1157-1182. DOI:10.1162/153244303322753616 .
[9]
CAIJ, LUOJ W, WANGS L, et al. Feature selection in machine learning: A new perspective[J]. Neurocomputing, 2018, 300: 70-79. DOI: 10.1016/j.neucom.2017.11.077 .
[10]
WANGH, LINGZ, YUK, et al. Towards efficient and effective discovery of Markov blankets for feature selection[J]. Information Sciences, 2020, 509: 227-242. DOI: 10.1016/j.ins.2019.09.010 .
GONGJ, MEIH B, DINGY, et al. Multi-feature correlation redundance elimination of intrusion event[J]. Journal of Southeast University (Natural Science Edition), 2005, 35(3): 366-371. DOI: 10.3321/j.issn: 1001-0505.2005.03.010(Ch ).
[13]
HAOZ F, ZHANGH, CAIR C, et al. Causal discovery on high dimensional data[J]. Applied Intelligence, 2015, 42(3): 594-607. DOI: 10.1007/s10489-014-0607-0 .
[14]
PEARLJ. Causality[M]. Cambridge:Cambridge University Press, 2009. DOI: 10.1017/cbo9780511803161 .
[15]
EDWARDSD. Introduction to Graphical Modelling[M]. Berlin:Springer Science & Business Media, 2012.
[16]
GAOT, JIQ. Local causal discovery of direct causes and effects[J]. Advances in Neural Information Processing Systems, 2015, 2: 2512–2520. DOI: 10.5555/2969442.2969520 .
ZHANGH, ZHOUS G, GUANJ H, et al. Measuring conditional independence by independent residuals for causal discovery[J]. ACM Transactions on Intelligent Systems and Technology, 2019, 10(5): 1-19. DOI: 10.1145/3325708 .
[21]
PELLETJ P, ELISSEEFFA. Using Markov Blankets for causal structure learning[J]. Journal of Machine Learning Research, 2008, 9(7): 1295–1342. DOI: 10.1145/1390681.1442776 .
[22]
ZHANGH, ZHOUS G, YANC X, et al. Recursively learning causal structures using regression-based conditional independence test[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 3108-3115. DOI: 10.1609/aaai.v33i01.33013108 .
[23]
ZHANGH, ZHOUS G, GUANJ H. Measuring conditional independence by independent residuals: Theoretical results and application in causal discovery[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 2029 -2036. DOI: 10.1609/aaai.v32i1.11555 .
[24]
ZHANGH, ZHOUS G, ZHANGK, et al. Causal discovery using regression-based conditional independence tests[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2017, 31(1): 1250-125. DOI: 10.1609/aaai.v31i1.10698 .
[25]
ZHANGK, HYVÄRINENA. On the identifiability of the post-nonlinear causal model[C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. New York: ACM, 2009: 647-655. DOI: 10.5555/1795114.1795190 .
[26]
PETERSJ, JANZINGD, SCHÖLKOPFB. Causal inference on discrete data using additive noise models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2436-2450. DOI: 10.1109/TPAMI.2011.71 .
[27]
ZHANGH, ZHANGK, ZHOUS G, et al. Testing independence between linear combinations for causal discovery[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(7): 6538-6546. DOI: 10.1609/aaai.v35i7.16810 .
[28]
GROSSE-WENTRUPM, JANZINGD, SIEGELM, et al. Identification of causal relations in neuroimaging data with latent confounders: An instrumental variable approach[J]. NeuroImage, 2016, 125: 825-833. DOI: 10.1016/j.neuroimage.2015.10.062 .
[29]
RAMSEYJ D. A scalable conditional independence test for nonlinear, non-Gaussian data[EB/OL]. 2014: arXiv: 1401.5031.
[30]
FLAXMANS R, NEILLD B, SMOLAA J. Gaussian processes for independence tests with non-iid data in causal inference[J]. ACM Transactions on Intelligent Systems and Technology, 2016, 7(2): 1-23. DOI: 10.1145/2806892 .
[31]
PDAUDINJ J. Partial association measures and an application to qualitative regression[J]. Biometrika, 1980, 67(3): 581-590. DOI: 10.1093/biomet/67.3.581 .
[32]
PENGJ, WANGP, ZHOUN F, et al. Partial correlation estimation by joint sparse regression models[J]. Journal of the American Statistical Association, 2009, 104(486): 735-746. DOI: 10.1198/jasa.2009.0126 .
[33]
GOLUBT R, SLONIMD K, TAMAYOP, et al. Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring[J]. Science, 1999, 286(5439): 531-537. DOI: 10.1126/science.286.5439.531 .
[34]
CHENA H, TSAUY W, LINC H. Novel methods to identify biologically relevant genes for leukemia and prostate cancer from gene expression profiles[J]. BMC Genomics, 2010, 11: 274. DOI: 10.1186/1471-2164-11-274 .
[35]
JANZINGD, STEUDELB, SHAJARISALESN, et al. Justifying information-geometric causal inference[M]//Measures of Complexity. Cham: Springer International Publishing, 2015: 253-265. DOI: 10.1007/978-3-319-21852-6_18 .
[36]
KAGERL, LIONT, ATTARBASCHIA, et al. Incidence and outcome of TCF3-PBX1-positive acute lymphoblastic leukemia in Austrian children[J]. Haematologica, 2007, 92(11): 1561-1564. DOI: 10.3324/haematol.11239 .
[37]
KEIMD, HAILATN, MELHEMR, et al. Proliferation-related expression of p19/nm23 nucleoside diphosphate kinase[J]. The Journal of Clinical Investigation, 1992, 89(3): 919-924. DOI: 10.1172/JCI115672 .
[38]
YANGP, ZHOUB B, ZHANGZ, et al. A multi-filter enhanced genetic ensemble system for gene selection and sample classification of microarray data[J]. BMC bioinformatics, 2010, 11(1): 1-12. DOI: 10.1186/1471-2105-11-S1-S5 .
[39]
GRISOLANOJ L, WESSELSCHMIDTR L, PELICCIP G, et al. Altered myeloid development and acute leukemia in transgenic mice expressing PML-RARα under control of cathepsin G regulatory sequences[J]. Blood, 1997, 89(2): 376-387. DOI: 10.1006/bcmd.1997.0116 .
[40]
BERTOLIS, PAUBELLEE, BÉRARDE, et al. Ferritin heavy/light chain (FTH1/FTL) expression, serum ferritin levels, and their functional as well as prognostic roles in acute myeloid leukemia[J]. European journal of haematology, 2019, 102(2): 131-142. DOI: 10.1111/ejh.13183 .
[41]
STORRJ, DOLANG, COUSTAN-SMITHE, et al. Value of monoclonal anti-myeloperoxidase (MPO7) for diagnosing acute leukaemia[J]. Journal of clinical pathology, 1990, 43(10): 847-849. DOI: 10.1136/jcp.43.10.847 .
[42]
LINENBERGERM L. CD33-directed therapy with gemtuzumab ozogamicin in acute myeloid leukemia: Progress in understanding cytotoxicity and potential mechanisms of drug resistance[J]. Leukemia, 2005, 19(2): 176-182. DOI: 10.1038/sj.leu.2403598 .
[43]
HATFIELDK J, OLSNESA M, GJERTSENB T, et al. Antiangiogenic therapy in acute myelogenous leukemia: Targeting of vascular endothelial growth factor and interleukin 8 as possible antileukemic strategies[J]. Current Cancer Drug Targets, 2005, 5(4): 229-248. DOI: 10.2174/1568009054064651 .
[44]
ZAGHLOULA, KAMALH, ISMAILM M, et al. Soluble carcinoembryonic antigen cell adhesion molecule 1, 6 and 8 in acute myeloid leukemia: Their relation to survival and prognosis[J]. Life Science Journal, 2018, 15(4):1-11. DOI: 10.7537/marslsj150418.01 .
[45]
SELLINM E, HOLMFELDTP, STENMARKS, et al. Op18/Stathmin counteracts the activity of overexpressed tubulin-disrupting proteins in a human leukemia cell line[J]. Experimental Cell Research, 2008, 314(6): 1367-1377. DOI: 10.1016/j.yexcr.2007.12.018 .
[46]
JANOWSKA-WIECZOREKA, BELCHA R, JACOBSA, et al. Increased circulating colony-stimulating factor-1 in patients with preleukemia, leukemia, and lymphoid malignancies[J]. Blood, 1991, 77(8): 1796-1803. DOI: 10.1182/blood.v77.8.1796.bloodjournal7781796 .
[47]
CHENGC L, HOUH A, LEEM C, et al. Higher bone marrow LGALS3 expression is an independent unfavorable prognostic factor for overall survival in patients with acute myeloid leukemia[J]. Blood, 2013, 121(16): 3172-3180. DOI: 10.1182/blood-2012-07-443762 .
[48]
NAGAIT, HARIGAEH, ISHIHARAH, et al. Transcription factor GATA-2 is expressed in erythroid, early myeloid, and CD34+ human leukemia-derived cell lines[J]. Blood, 1994, 84(4):1074-84. DOI: 10.1016/0955-3886(94)90139-2 .
[49]
HOYOSV, SAVOLDOB, QUINTARELLIC, et al. Engineering CD19-specific T lymphocytes with interleukin-15 and a suicide gene to enhance their anti-lymphoma/leukemia effects and safety[J]. Leukemia, 2010, 24(6): 1160-1170. DOI: 10.1038/leu.2010.60 .
[50]
RUSINIAKM E, YUM, ROSSD T, et al. Identification of B94 (TNFAIP2) as a potential retinoic acid target gene in acute promyelocytic leukemia[J]. Cancer Research, 2000, 60(7): 1824-1829. DOI: 10.1097/00002820-200004000-00012 .
[51]
RUTELLAS, RUMIC, PUGGIONIP, et al. Expression of thrombospondin receptor (CD36) in B-cell chronic lymphocytic leukemia as an indicator of tumor cell dissemination[J]. Haematologica, 1999, 84(5): 419-424. DOI: 10.1016/S0268-9499(99)90103-0 .
[52]
SEIKIM, INOUEJ, TAKEDAT, et al. Direct evidence that p40x of human T-cell leukemia virus type I is a trans-acting transcriptional activator[J]. The EMBO Journal, 1986, 5(3): 561-565. DOI: 10.1002/j.1460-2075.1986.tb04247.x .
[53]
TANAKAH, ITOT, KYO T, et al. Treatment with IFN? in vivo up-regulates serum-soluble TNF-related apoptosis inducing ligand (sTRAIL) levels and TRAIL mRNA expressions in neutrophils in chronic myelogenous leukemia patients[J]. European Journal of Haematology, 2007, 78(5): 389-398. DOI: 10.1111/j.1600-0609.2007.00834.x .
[54]
HUX L, YANGD F, ZIMMERMANM, et al. IRF8 regulates acid ceramidase expression to mediate apoptosis and suppresses myelogeneous leukemia[J]. Cancer Research, 2011, 71(8): 2882-2891. DOI: 10.1158/0008-5472.CAN-10-2493 .
[55]
KIDSONC. Two leukocyte enzymes with catalase activity in acute leukemia[J]. Biochemical and Biophysical Research Communications, 1962, 9(1/2): 138-141. DOI: 10.1016/0006-291X(62)90102-X .
CHENL. Study on the Expression of Intercellular Adhesion Molecule⁃3 in Bone Marrow of Patients with Acute Leukemia and its Clinical Relationship [D]. Jinan: Shandong University, 2008(Ch).
LIUJ M, ZENGH L, ZHANGY,et al. Study on the expression of interleukin-8 and its receptors in acute leukemia[J]. Chinese Journal of Hematology, 1999, 20(1): 24-26 (Ch). DOI: 10.3760/j:issn:0253-2727.1999.01.007 .
[60]
KONOPLEVAM, MIKHAILA, ESTROVZ, et al. Expression and function of leptin receptor isoforms in myeloid leukemia and myelodysplastic syndromes: Proliferative and anti-apoptotic activities[J]. Blood, 1999, 93(5): 1668-1676. DOI: 10.1182/blood.v93.5.1668.405a15_1668_1676 .