Heterogeneous Network-Based Inductive Matrix Methods for Predicting Biomedical Gene Disease

Abstract

Prediction of gene-disease associations has grown in popularity in recent biomedical research. However, positive and unlabeled (PU) issues and limited gene-disease association data are common concerns with present association prediction algorithms. A gene-disease association prediction approach based on Katz-enhanced inductive matrix completion is suggested in light of the abovementioned flaws. Preestimate based on the Katz technique and refined estimation based on the inductive matrix completion approach makes the model. The Katz technique is utilized to preestimate the gene-disease association on the basis of gene-disease heterogeneous network to mitigate the effects of association data-sparse and PU issues. The Katz technique, however, necessarily introduces some noise when predicting gene-disease connections due to the similarity network’s quality limitations. Therefore, the elastic net regularization approach is utilized to increase the resilience of the conventional inductive matrix completion model. As a result, the prediction effect of gene-disease connections is increased using robustness and a better inductive matrix completion model. The experimental findings demonstrate that the proposed model has dramatically increased recall and precision compared to widely used gene-disease association prediction approaches. It can also resolve the typical cold-start issue in association prediction. The proposed KIMC method may consider integrating more diverse biological data sources in the future and also aid in the effective extraction of the feature data of genes and diseases with higher correlation from this biological data to improve the prediction effect.