2lpiRNApred: a two-layered integrated algorithm for identifying piRNAs and their functions based on LFE-GM feature selection

Abstract

Piwi-interacting RNAs (piRNAs) are indispensable in the transposon silencing, including in germ cell formation, germline stem cell maintenance, spermatogenesis, and oogenesis. piRNA pathways are amongst the major genome defence mechanisms, which maintain genome integrity. They also have important functions in tumorigenesis, as indicated by aberrantly expressed piRNAs being recently shown to play roles in the process of cancer development. A number of computational methods for this have recently been proposed, but they still have not yielded satisfactory predictive performance. Moreover, only one computational method that identifies whether piRNAs function in inducting target mRNA deadenylation been reported in the literature. In this study, we developed a two-layered integrated classifier algorithm, 2lpiRNApred. It identifies piRNAs in the first layer and determines whether they function in inducting target mRNA deadenylation in the second layer. A new feature selection algorithm, which was based on Luca fuzzy entropy and Gaussian membership function (LFE-GM), was proposed to reduce the dimensionality of the features. Five feature extraction strategies, namely, Kmer, General parallel correlation pseudo-dinucleotide composition, General series correlation pseudo-dinucleotide composition, Normalized Moreau-Broto autocorrelation, and Geary autocorrelation, and two types of classifier, Sparse Representation Classifier (SRC) and support vector machine with Mahalanobis distancebased radial basis function (SVMMDRBF), were used to construct a two-layered integrated classifier algorithm, 2lpiRNApred. The results indicate that 2lpiRNApred performs significantly better than six other existing prediction tools.

Unraveling mitochondrial piRNAs in mouse embryonic gonadal cells

“…However, nowadays the presence of piRNAs in multiple somatic cells and species and functional roles, in addition to those related to TE interference, is well established 13 – 18 , including modulation of gene expression at the transcriptional or post-transcriptional level 19 by interactions with different RNAs, such as mRNAs, transcribed pseudogenes, or long noncoding RNAs having, in part, similar mechanisms to those of miRNAs. Some approaches based on computational algorithms to identify sequences corresponding to piRNAs and potential specific functions, such as deadenylation of mRNAs, have been recently reported 20 , 21 . Dysfunctions of gene regulation piRNA-mediated interactions can lead to pathological consequences, including cancer 22 – 24 .…”

Identifying N7‐methylguanosine sites by integrating multiple features

“…Currently, physicochemical properties are an important feature descriptor, which has been successfully used in investigating protein, [ 21,22 ] DNA [ 23–25 ] and RNA. [ 26 ] Hence, in this work, we employed 22 kinds of PC properties to denote RNA sequences. [ 27 ] Accordingly, a RNA sequence can be formulated as: where denote the i th PC value of the j th dinucleotide in the RNA sequence, and L is the length of the RNA sequence.…”

A Review of Discovery Profiling of PIWI-Interacting RNAs and Their Diverse Functions in Metazoans

“…Several methods have been developed to predict individual piRNAs based on their type. For example, Pinao [ 56 ], a genetic algorithm-based weighted ensemble (GA-WE) [ 57 ], and accurate piRNA prediction [ 58 ] have been used for transposon-related piRNA prediction, and two-layer integrated programs for identifying piRNAs (2L-piRNA) [ 59 ], such as 2L-piRNAPred [ 60 ], 2lpiRNApred [ 61 ], and 2L-piRNADNN [ 62 ], have been developed for mRNA-related piRNA prediction, while piRNAPredictor [ 2 ], PiRPred [ 3 ], piRNAdetect [ 63 ], IpiRId [ 64 ], piRNN [ 65 ], and piRNApred [ 66 ] have been employed for total piRNA prediction. miRanda [ 17 ], pirnaPre [ 67 ], and pirScan [ 18 ] have been used for piRNA target prediction, and three algorithms have been proposed for predicting piRNA clusters from sRNA-seq data: proTRAC [ 54 ], piClust [ 68 ], and PILFER [ 69 ].…”