计算机科学技术学报 ›› 2021,Vol. 36 ›› Issue (2): 361-374.doi: 10.1007/s11390-021-0801-6

所属专题： Emerging Areas

• • 上一篇    下一篇

基于影像遗传学数据的发现帕金森症的危险基因和异常脑区的有效WRF框架

Xia-An Bi, Member, CCF, IEEE, Zhao-Xu Xing, Rui-Hui Xu, and Xi Hu   

  1. College of Information Science and Engineering, Hunan Normal University, Changsha 410006, China;Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University, Changsha 410006, China
  • 收稿日期:2020-07-14 修回日期:2021-02-28 出版日期:2021-03-05 发布日期:2021-04-01
  • 作者简介:Xia-An Bi received his Ph.D. degree in computer applications from Hunan University, Changsha, in 2012. He is currently a professor in the Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, and College of Information Science and Engineering in Hunan Normal University, Changsha. His current research interests include machine learning, brain science, and artificial intelligence. He is the author or coauthor of several technical papers including several ESI Highly Cited Papers according to 2020 Clarivate Analytics ESI report, and also a very active reviewer for many international journals and conferences. He is a member of CCF and IEEE.
  • 基金资助:
    This work was supported by the National Natural Science Foundation of China under Grant No. 62072173, the Natural Science Foundation of Hunan Province of China under Grant No. 2020JJ4432, the Key Scientific Research Projects of Department of Education of Hunan Province under Grant No. 20A296, the Degree and Postgraduate Education Reform Project of Hunan Province under Grant No. 2019JGYB091, Hunan Provincial Science and Technology Project Foundation under Grant No. 2018TP1018, and the Innovation and Entrepreneurship Training Program of Hunan Xiangjiang Artificial Intelligence Academy.

An Efficient WRF Framework for Discovering Risk Genes and Abnormal Brain Regions in Parkinson's Disease Based on Imaging Genetics Data

Xia-An Bi, Member, CCF, IEEE, Zhao-Xu Xing, Rui-Hui Xu, and Xi Hu        

  1. College of Information Science and Engineering, Hunan Normal University, Changsha 410006, China;Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University, Changsha 410006, China
  • Received:2020-07-14 Revised:2021-02-28 Online:2021-03-05 Published:2021-04-01
  • About author:Xia-An Bi received his Ph.D. degree in computer applications from Hunan University, Changsha, in 2012. He is currently a professor in the Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, and College of Information Science and Engineering in Hunan Normal University, Changsha. His current research interests include machine learning, brain science, and artificial intelligence. He is the author or coauthor of several technical papers including several ESI Highly Cited Papers according to 2020 Clarivate Analytics ESI report, and also a very active reviewer for many international journals and conferences. He is a member of CCF and IEEE.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China under Grant No. 62072173, the Natural Science Foundation of Hunan Province of China under Grant No. 2020JJ4432, the Key Scientific Research Projects of Department of Education of Hunan Province under Grant No. 20A296, the Degree and Postgraduate Education Reform Project of Hunan Province under Grant No. 2019JGYB091, Hunan Provincial Science and Technology Project Foundation under Grant No. 2018TP1018, and the Innovation and Entrepreneurship Training Program of Hunan Xiangjiang Artificial Intelligence Academy.

PDF (PC)

47

补充材料

1

1、研究背景
作为脑科学的一个新兴研究领域，多模态数据融合分析在帕金森病等复杂脑疾病的研究中引起了广泛的关注。越来越多的研究者不局限于单一模态数据的探索，而是将焦点放在不同模态数据之间的融合上，致力于从多个层面来揭发疾病的致病机制。然而，目前的研究主要集中在不同模态数据之间的关联性检测和数据属性的约简上，忽略了数据融合后的整体挖掘框架和方法。
2、目的
我们的研究目标是通过开发一个集特征构建、特征选择和样本分类为一体的整体挖掘框架来实现对帕金森症的全面分析。
3、方法
我们提出一个加权随机森林模型作为特征筛选分类器。用相关分析方法检测基因与脑区的相互作用作为输入多模态融合特征。我们在加权随机森林的基础上实现了样本分类和最优特征选择，并构建了一个用于探索帕金森症致病因素的多模态分析框架。
4、结果
在Parkinson's Progression Markers Initiative数据库中的实验结果表明，加权随机森林比一些先进的方法表现出更好的性能，并且检测到了与帕金森症相关的脑区和基因。另外，我们还表明加权随机森林是一种非常有潜力的工具，可以对其他类似的脑部疾病进行多模态数据融合分析。
5、结论
本研究利用静息态fMRI数据和遗传数据进行多模态融合，并引入加权随机森林模型来准确区分帕金森患者和正常人，最后检测出帕金森症的病变脑区和危险基因。我们的工作可以改善帕金森患者的分类，更全面地检测出病因，为脑疾病的诊断和研究提供了一个有价值的新视角。在之后的工作中，有以下几个可以进一步研究的问题。首先，可以使用其他大脑模板来匹配图像，比如Broadman。其次，可能有比基因与功能磁共振成像这两组数据融合更好的组合。最后，我们通过大量已有的研究证实了大多数典型致病因素的合理性，证明了该方法的有效性。对于少数非典型致病因素，由于目前相关研究的缺乏，我们将在后续的研究工作中收集更多的数据，设计新的算法进行深入分析，更好地说明其在帕金森病发病机制中的作用。

关键词: 多模态融合特征, 帕金森症, 致病因素检测, 样本分类, 加权随机森林模型

Abstract: As an emerging research field of brain science, multimodal data fusion analysis has attracted broader attention in the study of complex brain diseases such as Parkinson's disease (PD). However, current studies primarily lie with detecting the association among different modal data and reducing data attributes. The data mining method after fusion and the overall analysis framework are neglected. In this study, we propose a weighted random forest (WRF) model as the feature screening classifier. The interactions between genes and brain regions are detected as input multimodal fusion features by the correlation analysis method. We implement sample classification and optimal feature selection based on WRF, and construct a multimodal analysis framework for exploring the pathogenic factors of PD. The experimental results in Parkinson's Progression Markers Initiative (PPMI) database show that WRF performs better compared with some advanced methods, and the brain regions and genes related to PD are detected. The fusion of multi-modal data can improve the classification of PD patients and detect the pathogenic factors more comprehensively, which provides a novel perspective for the diagnosis and research of PD. We also show the great potential of WRF to perform the multimodal data fusion analysis of other brain diseases.

Key words: multimodal fusion feature, Parkinson's disease, pathogenic factor detection, sample classification, weighted random forest model

[1] Arkinson C, Walden H. Parkin function in Parkinson's disease. Science, 2018, 360(6386):267-268. DOI:10.1126/science.aar6606.
[2] Lv D J, Li L X, Chen J, Wei S Z, Wang F, Hu H, Xie A M, Liu C F. Sleep deprivation caused a memory defects and emotional changes in a rotenone-based zebrafish model of Parkinson's disease. Behavioural Brain Research, 2019, 372:Article No. 112031. DOI:10.1016/j.bbr.2019.112031.
[3] Koros C, Simitsi A, Stefanis L. Genetics of Parkinson's disease:Genotype-phenotype correlations. International Review of Neurobiology, 2017, 132:197-231. DOI:10.1016/bs.irn.2017.01.009.
[4] Kim M, Kim J, Lee S H, Park H. Imaging genetics approach to Parkinson's disease and its correlation with clinical score. Scientific Reports, 2017, 7:Article No. 46700. DOI:10.1038/srep46700.
[5] Won J H, Kim M, Park B Y, Youn J, Park H. Effectiveness of imaging genetics analysis to explain degree of depression in Parkinson's disease. PLoS ONE, 2019, 14(2):Article No. e0211699. DOI:10.1371/journal.pone.0211699.
[6] Wang X, Yan J, Yao X et al. Longitudinal genotypephenotype association study through temporal structure auto-learning predictive model. Journal of Computational Biology, 2018, 25(7):809-824. DOI:10.1089/cmb.2018.0008.
[7] Hao X, Li C, Yan J, Yao X, Risacher S L, Saykin A J, Shen L, Zhang D, Alzheimer's Disease Neuroimaging Initiative. Identification of associations between genotypes and longitudinal phenotypes via temporally-constrained group sparse canonical correlation analysis. Bioinformatics, 2017, 33(14):i341-i349. DOI:10.1093/bioinformatics/btx245.
[8] Min W, Liu J, Zhang S. Edge-group sparse PCA for network-guided high dimensional data analysis. Bioinformatics, 2018, 34(20):3479-3487. DOI:10.1093/bioinformatics/bty362.
[9] Hua K, Zhang X. Estimating the total genome length of a metagenomic sample using k-mers. BMC Genomics, 2019, 20(2):Article No. 183. DOI:10.1186/s12864-019-5467-x.
[10] Calhoun V D, Liu J, AdalıT. A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data. NeuroImage, 2009, 45(1, Supplement 1):S163-S172. DOI:10.1016/j.neuroimage.2008.10.057.
[11] Hamza T H, Zabetian C P, Tenesa A et al. Common genetic variation in the HLA region is associated with late-onset sporadic Parkinson's disease. Nature Genetics, 2010, 42(9):781-785. DOI:10.1038/ng.642.
[12] Peng J, Guan J, Shang X. Predicting Parkinson's disease genes based on Node2vec and autoencoder. Frontiers in Genetics, 2019, 10:Article No. 226. DOI:10.3389/fgene.2019.00226.
[13] Mohammed A, Zamani M, Bayford R, Demosthenous A. Toward on-demand deep brain stimulation using online Parkinson's disease prediction driven by dynamic detection. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017, 25(12):2441-2452. DOI:10.1109/TNSRE.2017.2722986.
[14] Rana B, Juneja A, Saxena M, Gudwani S, Kumaran S S, Behari M, Agrawal R K. Relevant 3D local binary pattern based features from fused feature descriptor for differential diagnosis of Parkinson's disease using structural MRI. Biomedical Signal Processing and Control, 2017, 34:134-143. DOI:10.1016/j.bspc.2017.01.007.
[15] Gupta D, Julka A, Jain S, Aggarwal T, Khanna A, Arunkumar N, De Albuquerque V H C. Optimized cuttlefish algorithm for diagnosis of Parkinson's disease. Cognitive Systems Research, 2018, 52:36-48. DOI:10.1016/j.cogsys.2018.06.006.
[16] Zeng W, Liu F, Wang Q, Wang Y, Ma L, Zhang Y. Parkinson's disease classification using gait analysis via deterministic learning. Neuroscience Letters, 2016, 633:268-278. DOI:10.1016/j.neulet.2016.09.043.
[17] Huang Y A, Huang Z A, You Z H, Hu P, Li L P, Li Z W, Wang L. Precise prediction of pathogenic microorganisms using 16S rRNA gene sequences. In Proc. the 15th International Conference on Intelligent Computing, August 2019, pp.138-150. DOI:10.1007/978-3-030-26969-213.
[18] Du L, Liu K, Zhang T, Yao X, Yan J, Risacher S L, Han J, Guo L, Saykin A J, Shen L, Alzheimer's Disease Neuroimaging Initiative. A novel SCCA approach via truncated l1-norm and truncated group lasso for brain imaging genetics. Bioinformatics, 2017, 34(2):278-285. DOI:10.1093/bioinformatics/btx594.
[19] Du L, Liu K, Zhu L, Yao X, Risacher S L, Guo L, Saykin A J, Shen L, Alzheimer's Disease Neuroimaging Initiative. Identifying progressive imaging genetic patterns via multitask sparse canonical correlation analysis:A longitudinal study of the ADNI cohort. Bioinformatics, 2019, 35(14):i474-i483. DOI:10.1093/bioinformatics/btz320.
[20] Du L, Liu K, Yao X, Risacher S L, Shen L. Detecting genetic associations with brain imaging phenotypes in Alzheimer's disease via a novel structured SCCA approach. Medical Image Analysis, 2020, 61:Article No. 101656. DOI:10.1016/j.media.2020.101656.
[21] Wei L, Su R, Luan S, Liao Z, Manavalan B, Zou Q, Shi X. Iterative feature representations improve N4-methylcytosine site prediction. Bioinformatics, 2019, 35(23):4930-4937. DOI:10.1093/bioinformatics/btz408.
[22] Chen F X, Kang D Z, Chen F Y, Liu Y, Wu G, Li X, Yu L H, Lin Y X, Lin Z Y. Gray matter atrophy associated with mild cognitive impairment in Parkinson's disease. Neuroscience Letters, 2016, 617:160-165. DOI:10.1016/j.neulet.2015.12.055.
[23] Guimarães R P, Arci Santos M C, Dagher A et al. Pattern of reduced functional connectivity and structural abnormalities in Parkinson's disease:An exploratory study. Frontiers in Neurology, 2017, 7:243. DOI:10.3389/fneur.2016.00243.
[24] Hou Y, Wei Q, Ou R, Yang J, Song W, Gong Q, Shang H. Impaired topographic organization in cognitively unimpaired drug-naïve patients with rigidity-dominant Parkinson's disease. Parkinsonism & Related Disorders, 2018, 56:52-57. DOI:10.1016/j.parkreldis.2018.06.021.
[25] Zhao L, Wang E, Zhang X et al. Cortical structural connectivity alterations in primary insomnia:Insights from MRI-based morphometric correlation analysis. BioMed Research International, 2015, 2015:Article No. 817595. DOI:10.1155/2015/817595.
[26] Meunier D, Stamatakis E A, Tyler L K. Age-related functional reorganization, structural changes, and preserved cognition. Neurobiology of Aging, 2014, 35(1):42-54. DOI:10.1016/j.neurobiolaging.2013.07.003.
[27] Li H F, Yang L, Yin D, Chen W J, Liu G L, Ni W, Wang N, Yu W, Wu Z Y, Wang Z. Associations between neuroanatomical abnormality and motor symptoms in paroxysmal kinesigenic dyskinesia. Parkinsonism & Related Disorders, 2019, 62:134-140. DOI:10.1016/j.parkreldis.2018.12.029.
[28] Reijnders J S A M, Scholtissen B, Weber W E J, Aalten P, Verhey F R J, Leentjens A F G. Neuroanatomical correlates of apathy in Parkinson's disease:A magnetic resonance imaging study using voxel-based morphometry. Movement Disorders, 2010, 25(14):2318-2325. DOI:10.1002/mds.23268.
[29] Melzer T R, Watts R, MacAskill M R, Pitcher T L, Livingston L, Keenan R J, Dalrymple-Alford J C, Anderson T J. Grey matter atrophy in cognitively impaired Parkinson's disease. Journal of Neurology, Neurosurgery, and Psychiatry, 2012, 83(2):188-194. DOI:10.1136/jnnp-2011-300828.
[30] De Schipper L J, Hafkemeijer A, van der Grond J, Marinus J, Henselmans J M L, van Hilten J J. Altered whole-brain and network-based functional connectivity in Parkinson's disease. Frontiers in Neurology, 2018, 9:Article No. 419. DOI:10.3389/fneur.2018.00419.
[31] Evangelisti S, Pittau F, Testa C et al. L-dopa modulation of brain connectivity in Parkinson's disease patients:A pilot EEG-fMRI study. Frontiers in Neuroscience, 2019, 13:Article No. 611. DOI:10.3389/fnins.2019.00611.
[32] Wang Q, Li W X, Dai S X, Guo Y C, Han F F, Zheng J J, Li G H, Huang J F. Meta-analysis of Parkinson's disease and Alzheimer's disease revealed commonly impaired pathways and dysregulation of NRF2-dependent genes. Journal of Alzheimer's Disease, 2017, 56(4):1525-1539. DOI:10.3233/JAD-161032.
[33] International Parkinson Disease Genomics Consortium. Imputation of sequence variants for identification of genetic risks for Parkinson's disease:A meta-analysis of genomewide association studies. The Lancet, 2011, 377(9766):641-649. DOI:10.1016/S0140-6736(10)62345-8.
[34] Ahmed I, Tamouza R, Delord M et al. Association between Parkinson's disease and the HLA-DRB1 locus. Movement Disorders, 2012, 27(9):1104-1110. DOI:10.1002/mds.25035.
[35] Bao W, Jiang Z, Huang D S. Novel human microbe-disease association prediction using network consistency projection. BMC Bioinformatics, 2017, 18(16):Article No. 543. DOI:10.1186/s12859-017-1968-2.
[36] Sivaranjini S, Sujatha C M. Deep learning based diagnosis of Parkinson's disease using convolutional neural network. Multimedia Tools and Applications, 2019, 79(3):15467-15479. DOI:10.1007/s11042-019-7469-8.
[37] Martinez-Murcia F J, Ortiz A, Gorriz J M, Ramirez J, Castillo-Barnes D, Salas-Gonzalez D, Segovia F. Deep convolutional autoencoders vs PCA in a highly-unbalanced Parkinson's disease dataset:A DaTSCAN study. In Proc. the 13th International Conference on Soft Computing Models in Industrial and Environmental Applications, June 2018, pp. 47-56. DOI:10.1007/978-3-319-94120-25.
[38] Gao C, Sun H, Wang T et al. Model-based and modelfree machine learning techniques for diagnostic prediction and classification of clinical outcomes in Parkinson's disease. Scientific Reports, 2018, 8(1):Article No. 7129. DOI:10.1038/s41598-018-24783-4.
[39] Abós A, Baggio H C, Segura B, García-Díaz A I, Compta Y, Martí M J, Valldeoriola F, Junqué C. Discriminating cognitive status in Parkinson's disease through functional connectomics and machine learning. Scientific Reports, 2017, 7:Article No. 45347. DOI:10.1038/srep45347.
[40] Niu Y W, Wang G H, Yan G Y, Chen X. Integrating random walk and binary regression to identify novel miRNAdisease association. BMC Bioinformatics, 2019, 20(1):Article No. 59. DOI:10.1186/s12859-019-2640-9.
[41] Zhao Y, Chen X, Yin J. Adaptive boosting-based computational model for predicting potential miRNA-disease associations. Bioinformatics, 2019, 35(22):4730-4738. DOI:10.1093/bioinformatics/btz297.
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 李万学;. Almost Optimal Dynamic 2-3 Trees[J]. , 1986, 1(2): 60 -71 .
[2] C.Y.Chung; 华宣仁;. A Chinese Information Processing System[J]. , 1986, 1(2): 15 -24 .
[3] 高庆狮; 张祥; 杨树范; 陈树清;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[4] 章萃; 赵沁平; 徐家福;. Kernel Language KLND[J]. , 1986, 1(3): 65 -79 .
[5] 黄学东; 蔡莲红; 方棣棠; 迟边进; 周立; 蒋力;. A Computer System for Chinese Character Speech Input[J]. , 1986, 1(4): 75 -83 .
[6] 史忠植;. Knowledge-Based Decision Support System[J]. , 1987, 2(1): 22 -29 .
[7] 唐同诰; 招兆铿;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[8] 闵应骅;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[9] 夏培肃; 方信我; 王玉祥; 严开明; 张廷军; 刘玉兰; 赵春英; 孙继忠;. Design of Array Processor Systems[J]. , 1987, 2(3): 163 -173 .
[10] 孙永强; 陆汝占; 黄小戎;. Termination Preserving Problem in the Transformation of Applicative Programs[J]. , 1987, 2(3): 191 -201 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
总访问量：