Weighted matrix factorization based data fusion for predicting lncRNA-disease associations

Increasing biomedical studies have demonstrated important associations between lncRNAs and various human complex diseases. Developing data integrative models can boost the performance of lncRNA-disease association identification. However, existing models generally have to transform heterogenous data into homologous networks, and then sum up these networks into a composite network for integrative prediction. The transformation may conceal the intrinsic structure of the heterogeneous data, and the summation process may suffer from noisy networks. Both these issues compromise the performance. In this paper, we introduce a Weighted Matrix Factorization based data fusion solution to predict LncRNA-Disease Associations (WMFLDA). WMFLDA first directly encodes the inter-associations between different types of biological entities (such as genes, lncRNAs, and Disease Ontology terms) via a heterogeneous network, which also encodes multiple intra-association networks of entities of the same type. Next, it assigns weights to these inter-association and intra-association matrices, and performs collaborative low-rank matrix factorization to explore the latent relationships between entities. After that, it simultaneously optimizes these weights and low-rank matrices. In the end, it uses the optimized low-rank matrices and weights to reconstruct the lncRNA-disease association matrix and accomplish the prediction. WMFLDA achieves a larger area under the receiver operating curve (by at least 7.61%), and a larger area under the precision-recall curve (by at least 5.49%) than competitive data fusion approaches in different experimental scenarios. WMFLDA can not only maintain the intrinsic structure of the association matrices, but can also selectively and differentially combine them. The codes and datasets are available at http://mlda.swu.edu.cn/codes.php?name=WMFLDA