Human Microbe-Disease Association Prediction Based on Adaptive Boosting

There are countless microbes in the human body, and they play various roles in the physiological process. There is growing evidence that microbes are closely associated with human diseases. Researching disease-related microbes helps us understand the mechanisms of diseases and provides new strategies for diseases diagnosis and treatment. Many computational models have been proposed to predict disease-related microbes, in this paper, we developed a model of Adaptive Boosting for Human Microbe-Disease Association prediction (ABHMDA) to reveal the associations between diseases and microbes by calculating the relation probability of disease-microbe pair using a strong classifier. Our model could be applied to new diseases without any known related microbes. In order to assess the prediction power of the model, global and local leave-one-out cross validation (LOOCV) were implemented. As shown in the results, the global and local LOOCV values reached 0.8869 and 0.7910, respectively. What’s more, 10, 10, and 8 out of the top 10 microbes predicted to be most likely to be associated with Asthma, Colorectal carcinoma and Type 1 diabetes were all verified by relevant literatures or database HMDAD, respectively. The above results verify the superior predictive performance of ABHMDA.

[1]  Herman Goossens,et al.  Denaturing gradient gel electrophoresis of neonatal intestinal microbiota in relation to the development of asthma , 2011, BMC Microbiology.

[2]  John F. Cryan,et al.  Brain–Gut–Microbe Communication in Health and Disease , 2011, Front. Physio..

[3]  Xing Chen,et al.  NLLSS: Predicting Synergistic Drug Combinations Based on Semi-supervised Learning , 2016, PLoS Comput. Biol..

[4]  Xing Chen,et al.  MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction , 2018, PLoS Comput. Biol..

[5]  B. Wilson,et al.  Gut Microbial Metabolism Drives Transformation of Msh2-Deficient Colon Epithelial Cells , 2014, Cell.

[6]  L. See,et al.  Higher rate of colorectal cancer among patients with pyogenic liver abscess with Klebsiella pneumoniae than those without: an 11‐year follow‐up study , 2012, Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland.

[7]  P. Cole,et al.  Host-microbe relationships in chronic respiratory infection. , 1989, Respiration; international review of thoracic diseases.

[8]  Peter G Gibson,et al.  Inhibition of allergic airways disease by immunomodulatory therapy with whole killed Streptococcus pneumoniae. , 2007, Vaccine.

[9]  Zhu-Hong You,et al.  A novel approach based on KATZ measure to predict associations of human microbiota with non‐infectious diseases , 2016, Bioinform..

[10]  Xing Chen,et al.  Novel human lncRNA-disease association inference based on lncRNA expression profiles , 2013, Bioinform..

[11]  M. Craig,et al.  Environmental determinants of type 1 diabetes: A role for overweight and insulin resistance , 2014, Journal of paediatrics and child health.

[12]  Hui Zhang,et al.  HLPI-Ensemble: Prediction of human lncRNA-protein interactions based on ensemble strategy , 2018, RNA biology.

[13]  Xing Chen,et al.  Long non-coding RNAs and complex diseases: from experimental results to computational models , 2016, Briefings Bioinform..

[14]  M. Pop,et al.  Metagenomic Analysis of the Human Distal Gut Microbiome , 2006, Science.

[15]  X. Qin,et al.  Advances in the cellular immunological pathogenesis of type 1 diabetes , 2014, Journal of cellular and molecular medicine.

[16]  C. Xiang,et al.  Human Intestinal Lumen and Mucosa-Associated Microbiota in Patients with Colorectal Cancer , 2012, PloS one.

[17]  F. Tinahones,et al.  Gut microbiota in children with type 1 diabetes differs from that in healthy children: a case-control study , 2013, BMC Medicine.

[18]  Yongdong Zhang,et al.  Drug-target interaction prediction: databases, web servers and computational models , 2016, Briefings Bioinform..

[19]  Yi Feng,et al.  Long Non-Coding RNAs , 2016, Methods in Molecular Biology.

[20]  Zhu-Hong You,et al.  PBHMDA: Path-Based Human Microbe-Disease Association Prediction , 2017, Front. Microbiol..

[21]  F. Bäckhed,et al.  The gut microbiota — masters of host development and physiology , 2013, Nature Reviews Microbiology.

[22]  Hans Bisgaard,et al.  Childhood asthma after bacterial colonization of the airway in neonates. , 2007, The New England journal of medicine.

[23]  Abdollah Dehzangi,et al.  iDTI-ESBoost: Identification of Drug Target Interaction Using Evolutionary and Structural Features with Boosting , 2017, Scientific Reports.

[24]  Katherine H. Huang,et al.  A framework for human microbiome research , 2012, Nature.

[25]  Lei Wang,et al.  BNPMDA: Bipartite Network Projection for MiRNA–Disease Association prediction , 2018, Bioinform..

[26]  Dean Billheimer,et al.  Asthma-associated differences in microbial composition of induced sputum. , 2013, The Journal of allergy and clinical immunology.

[27]  Wei Wang,et al.  MicroRNA-221 inhibits CDKN1C/p57 expression in human colorectal carcinoma , 2011, Acta Pharmacologica Sinica.

[28]  Elena Marchiori,et al.  Gaussian interaction profile kernels for predicting drug-target interaction , 2011, Bioinform..

[29]  Qi Zhao,et al.  IRWNRLPI: Integrating Random Walk and Neighborhood Regularized Logistic Matrix Factorization for lncRNA-Protein Interaction Prediction , 2018, Front. Genet..

[30]  D. Fredricks,et al.  Microbial ecology of human skin in health and disease. , 2001, The journal of investigative dermatology. Symposium proceedings.

[31]  Na-Na Guan,et al.  Predicting miRNA‐disease association based on inductive matrix completion , 2018, Bioinform..

[32]  Hai-Jun Deng,et al.  miRNA-338-3p suppresses cell growth of human colorectal carcinoma by targeting smoothened. , 2013, World journal of gastroenterology.

[33]  Rui Gao,et al.  PRWHMDA: Human Microbe-Disease Association Prediction by Random Walk on the Heterogeneous Network with PSO , 2018, International journal of biological sciences.

[34]  Xing Chen,et al.  PBMDA: A novel and effective path-based computational model for miRNA-disease association prediction , 2017, PLoS Comput. Biol..

[35]  Gert Folkerts,et al.  Bifidobacterium breve and Lactobacillus rhamnosus treatment is as effective as budesonide at reducing inflammation in a murine model for chronic asthma , 2014, Respiratory Research.

[36]  Zexuan Zhu,et al.  LRLSHMDA: Laplacian Regularized Least Squares for Human Microbe–Disease Association prediction , 2017, Scientific Reports.

[37]  A. Aydın,et al.  Differences in the gut microbiota of healthy children and those with type 1 diabetes , 2014, Pediatrics international : official journal of the Japan Pediatric Society.

[38]  Xing Chen,et al.  MicroRNAs and complex diseases: from experimental results to computational models , 2019, Briefings Bioinform..

[39]  J. Goedert,et al.  Human gut microbiome and risk for colorectal cancer. , 2013, Journal of the National Cancer Institute.

[40]  R. Milo,et al.  Revised Estimates for the Number of Human and Bacteria Cells in the Body , 2016, bioRxiv.

[41]  Xing Chen,et al.  LRSSLMDA: Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction , 2017, PLoS Comput. Biol..

[42]  Willem M. de Vos,et al.  Aberrant gut microbiota composition at the onset of type 1 diabetes in young children , 2014, Diabetologia.

[43]  Skov,et al.  Bacterial superantigens and inflammatory skin diseases , 2000, Clinical and experimental dermatology.

[44]  Jong-Wook Shin,et al.  Lung Microbiome Analysis in Steroid-Naїve Asthma Patients by Using Whole Sputum , 2016, Tuberculosis and respiratory diseases.

[45]  Anthony A. Fodor,et al.  Microbial genomic analysis reveals the essential role of inflammation in bacteria-induced colorectal cancer , 2014, Nature Communications.

[46]  Qi Xue,et al.  MicroRNA-338-3p inhibits colorectal carcinoma cell invasion and migration by targeting smoothened. , 2014, Japanese journal of clinical oncology.

[47]  Xing Chen,et al.  Prediction of microbe–disease association from the integration of neighbor and graph with collaborative recommendation model , 2017, Journal of Translational Medicine.

[48]  S. Sørensen,et al.  Gut Microbiota in Human Adults with Type 2 Diabetes Differs from Non-Diabetic Adults , 2010, PloS one.

[49]  Shao Li,et al.  Dynamic microbe and molecule networks in a mouse model of colitis-associated colorectal cancer , 2014, Scientific Reports.

[50]  A. Barabasi,et al.  Human symptoms–disease network , 2014, Nature Communications.

[51]  Tobias Kollmann,et al.  Early infancy microbial and metabolic alterations affect risk of childhood asthma , 2015, Science Translational Medicine.