Sparse regularized joint projection model for identifying associations of non-coding RNAs and human diseases

Current human biomedical research shows that diseases are closely related to non-coding RNAs, so it is of great significance for medicine study the relationship between and RNAs. has found associations RNAs through a variety effective methods, but most methods complex targeted at single RNA or disease. Therefore, we urgently need an simple method discover diseases. In this paper, propose sparse regularized joint projection model (SRJP) identify First, extract information series ncRNA similarity matrices disease assign average weights two sides. Then decompose spaces into low-rank put them SRJP. SRJP, innovatively use matrix combine side ncRNAs Finally, regularization term in SRJP effectively improves robustness generalization ability model. We test our on different datasets involving three types ncRNAs: circRNA, microRNA long RNA. The experimental results show superior predict