Predicting Pseudogene–miRNA Associations Based on Feature Fusion and Graph Auto-Encoder

Abstract

Pseudogenes were originally regarded as non-functional components scattered in the genome during evolution. Recent studies have shown that pseudogenes can be transcribed into long non-coding RNA and play a key role at multiple functional levels in different physiological and pathological processes. microRNAs (miRNAs) are a type of non-coding RNA, which plays important regulatory roles in cells. Numerous studies have shown that pseudogenes and miRNAs have interactions and form a ceRNA network with mRNA to regulate biological processes and involve diseases. Exploring the associations of pseudogenes and miRNAs will facilitate the clinical diagnosis of some diseases. Here, we propose a prediction model PMGAE (Pseudogene–MiRNA association prediction based on the Graph Auto-Encoder), which incorporates feature fusion, graph auto-encoder (GAE), and eXtreme Gradient Boosting (XGBoost). First, we calculated three types of similarities including Jaccard similarity, cosine similarity, and Pearson similarity between nodes based on the biological characteristics of pseudogenes and miRNAs. Subsequently, we fused the above similarities to construct a similarity profile as the initial representation features for nodes. Then, we aggregated the similarity profiles and associations of nodes to obtain the low-dimensional representation vector of nodes through a GAE. In the last step, we fed these representation vectors into an XGBoost classifier to predict new pseudogene–miRNA associations (PMAs). The results of five-fold cross validation show that PMGAE achieves a mean AUC of 0.8634 and mean AUPR of 0.8966. Case studies further substantiated the reliability of PMGAE for mining PMAs and the study of endogenous RNA networks in relation to diseases.

MIFAM-DTI: a drug-target interactions predicting model based on multi-source information fusion and attention mechanism

“…One notable advantage of cosine similarity is its resilience to the dimensionality of the vectors, rendering it suitable for assessing similarity even when dealing with highly sparse vectors. Moreover, the simplicity and efficiency of cosine similarity calculations make it well-suited for large datasets ( Zhou et al, 2021 ).…”

Inferring pseudogene–MiRNA associations based on an ensemble learning framework with similarity kernel fusion

“…Besides, a large number of computational models are also developed to forecast other ncRNA associations and disease-biomolecule associations, for example, predicting the lncRNA–miRNA 11 , 12 , circRNA–miRNA 13 , 14 , lncRNA–disease 15 , 16 , circRNA–disease 17 – 19 , drug–disease 20 interactions. Motived by these ncRNA interaction prediction, Zhou et al 21 incorporates feature fusion and graph auto-encoder to predict pseudogene–miRNA associations. In the model, various perspective attribute information for pseudogenes and miRNAs is obtained as their similarity features, and graph auto-encoder is used to obtain the low-dimensional representation of nodes.…”