Identifying Disease-Gene Associations With Graph-Regularized Manifold Learning

Abstract

Complex diseases are known to be associated with disease genes. Uncovering disease-gene associations is critical for diagnosis, treatment, and prevention of diseases. Computational algorithms which effectively predict candidate disease-gene associations prior to experimental proof can greatly reduce the associated cost and time. Most existing methods are disease-specific which can only predict genes associated with a specific disease at a time. Similarities among diseases are not used during the prediction. Meanwhile, most methods predict new disease genes based on known associations, making them unable to predict disease genes for diseases without known associated genes.In this study, a manifold learning-based method is proposed for predicting disease-gene associations by assuming that the geodesic distance between any disease and its associated genes should be shorter than that of other non-associated disease-gene pairs. The model maps the diseases and genes into a lower dimensional manifold based on the known disease-gene associations, disease similarity and gene similarity to predict new associations in terms of the geodesic distance between disease-gene pairs. In the 3-fold cross-validation experiments, our method achieves scores of 0.882 and 0.854 in terms of the area under of the receiver operating characteristic (ROC) curve (AUC) for diseases with more than one known associated genes and diseases with only one known associated gene, respectively. Further de novo studies on Lung Cancer and Bladder Cancer also show that our model is capable of identifying new disease-gene associations.

Integrated Analysis of Tissue-specific Gene Expression in Diabetes by Tensor Decomposition Can Identify Possible Associated Diseases

“…Therefore, we were not surprised that the integrated analysis using the proposed method was able to identify disease associations. To our knowledge, few studies have attempted to predict the association between diseases using gene expression, although many studies have focused on the associations between genes and disease [19][20][21] and between drugs and disease association [22][23][24]. Our proposed strategy would be useful for such studies.…”

Integrated Analysis of Tissue-Specific Gene Expression in Diabetes by Tensor Decomposition Can Identify Possible Associated Diseases

“…Therefore, we were not surprised that the integrated analysis using the proposed method was able to identify disease associations. To our knowledge, few studies have attempted to predict the association between diseases using gene expression, although many studies have focused on the associations between genes and disease [ 20 , 21 , 22 ] and between drugs and disease association [ 23 , 24 , 25 ]. Our proposed strategy would be useful for such studies.…”

Protein network analysis to prioritize key genes in amyotrophic lateral sclerosis

“…We showed the Gene Ontology classifications like molecular activity, biological process, cellular components of modules using filtering domain size set to “only annotated”, default g:SCS method for multiple testing correction for p-values, maximum p-value set to 0.05, numeric IDs as prefix ENTERZGENE_ACC. Further, we identifying disease-gene correlations for each module because it helps in the understanding of disease mechanisms, which have several applications including disease diagnosis, therapy, and prevention ( Luo et al, 2019 ). The gene-disease class association is identified by the versatile platform “disgenet2r” an R package ( Pinero et al, 2020 ).…”