BMCMDA: a novel model for predicting human microbe-disease associations via binary matrix completion

BackgroundHuman Microbiome Project reveals the significant mutualistic influence between human body and microbes living in it. Such an influence lead to an interesting phenomenon that many noninfectious diseases are closely associated with diverse microbes. However, the identification of microbe-noninfectious disease associations (MDAs) is still a challenging task, because of both the high cost and the limitation of microbe cultivation. Thus, there is a need to develop fast approaches to screen potential MDAs. The growing number of validated MDAs enables us to meet the demand in a new insight. Computational approaches, especially machine learning, are promising to predict MDA candidates rapidly among a large number of microbe-disease pairs with the advantage of no limitation on microbe cultivation. Nevertheless, a few computational efforts at predicting MDAs are made so far.ResultsIn this paper, grouping a set of MDAs into a binary MDA matrix, we propose a novel predictive approach (BMCMDA) based on Binary Matrix Completion to predict potential MDAs. The proposed BMCMDA assumes that the incomplete observed MDA matrix is the summation of a latent parameterizing matrix and a noising matrix. It also assumes that the independently occurring subscripts of observed entries in the MDA matrix follows a binomial model. Adopting a standard mean-zero Gaussian distribution for the nosing matrix, we model the relationship between the parameterizing matrix and the MDA matrix under the observed microbe-disease pairs as a probit regression. With the recovered parameterizing matrix, BMCMDA deduces how likely a microbe would be associated with a particular disease. In the experiment under leave-one-out cross-validation, it exhibits the inspiring performance (AUC = 0.906, AUPR =0.526) and demonstrates its superiority by ~ 7% and ~ 5% improvements in terms of AUC and AUPR respectively in the comparison with the pioneering approach KATZHMDA.ConclusionsOur BMCMDA provides an effective approach for predicting MDAs and can be also extended to other similar predicting tasks of binary relationship (e.g. protein-protein interaction, drug-target interaction).

[1]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

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

[3]  Siu-Ming Yiu,et al.  Predicting and understanding comprehensive drug-drug interactions via semi-nonnegative matrix factorization , 2018, BMC Systems Biology.

[4]  Shareef M Dabdoub,et al.  The subgingival microbiome of clinically healthy current and never smokers , 2014, The ISME Journal.

[5]  Jian-Yu Shi,et al.  Predicting binary, discrete and continued lncRNA-disease associations via a unified framework based on graph regression , 2017, BMC Medical Genomics.

[6]  Olli Simell,et al.  Gut Microbiome Metagenomics Analysis Suggests a Functional Model for the Development of Autoimmunity for Type 1 Diabetes , 2011, PloS one.

[7]  Jennifer C. Drew,et al.  Toward defining the autoimmune microbiome for type 1 diabetes , 2011, The ISME Journal.

[8]  Siu-Ming Yiu,et al.  Predicting combinative drug pairs towards realistic screening via integrating heterogeneous features , 2017, BMC Bioinformatics.

[9]  Hui Yu,et al.  Predicting Drug-Target Interactions via Within-Score and Between-Score , 2015, BioMed research international.

[10]  E. Stewart.  Growing Unculturable Bacteria , 2012, Journal of bacteriology.

[11]  Emily R. Davenport,et al.  Seasonal Variation in Human Gut Microbiome Composition , 2014, PloS one.

[12]  José Mario Martínez,et al.  Nonmonotone Spectral Projected Gradient Methods on Convex Sets , 1999, SIAM J. Optim..

[13]  Lawrence A. David,et al.  Diet rapidly and reproducibly alters the human gut microbiome , 2013, Nature.

[14]  Peter Cimermancic,et al.  A Systematic Analysis of Biosynthetic Gene Clusters in the Human Microbiome Reveals a Common Family of Antibiotics , 2014, Cell.

[15]  Yasen Jiao,et al.  Performance measures in evaluating machine learning based bioinformatics predictors for classifications , 2016, Quantitative Biology.

[16]  BMC Medical Genetics BioMed Central , 2003 .

[17]  J. Petrosino,et al.  Microbiota Modulate Behavioral and Physiological Abnormalities Associated with Neurodevelopmental Disorders , 2013, Cell.

[18]  Siu-Ming Yiu,et al.  Predicting Comprehensive Drug-Drug Interactions for New Drugs via Triple Matrix Factorization , 2017, IWBBIO.

[19]  Carl Nathan,et al.  Fresh Approaches to Anti-Infective Therapies , 2012, Science Translational Medicine.

[20]  W E Moore,et al.  Intestinal floras of populations that have a high risk of colon cancer , 1995, Applied and environmental microbiology.

[21]  M. Crowell,et al.  Human gut microbiota in obesity and after gastric bypass , 2009, Proceedings of the National Academy of Sciences.

[22]  Zhixun Su,et al.  Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation , 2011, NIPS.

[23]  Marcus J. Claesson,et al.  Genome-scale analyses of health-promoting bacteria: probiogenomics , 2009, Nature Reviews Microbiology.

[24]  Katherine H. Huang,et al.  Structure, Function and Diversity of the Healthy Human Microbiome , 2012, Nature.

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

[26]  Jianyu Shi,et al.  Predicting existing targets for new drugs base on strategies for missing interactions , 2016, BMC Bioinformatics.

[27]  Ewout van den Berg,et al.  1-Bit Matrix Completion , 2012, ArXiv.

[28]  D. Theriaque,et al.  Intestinal microbial ecology in premature infants assessed with non-culture-based techniques. , 2010, The Journal of pediatrics.

[29]  F. Bäckhed,et al.  Obesity alters gut microbial ecology. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[30]  Xing Chen,et al.  RKNNMDA: Ranking-based KNN for MiRNA-Disease Association prediction , 2017, RNA biology.

[31]  Pierre Cochat,et al.  Efficacy and safety of Oxalobacter formigenes to reduce urinary oxalate in primary hyperoxaluria. , 2011, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.