LncLocation: Efficient Subcellular Location Prediction of Long Non-Coding RNA-Based Multi-Source Heterogeneous Feature Fusion

Abstract

Recent studies uncover that subcellular location of long non-coding RNAs (lncRNAs) can provide significant information on its function. Due to the lack of experimental data, the number of lncRNAs is very limited, experimentally verified subcellular localization, and the numbers of lncRNAs located in different organelle are wildly imbalanced. The prediction of subcellular location of lncRNAs is actually a multi-classification small sample imbalance problem. The imbalance of data results in the poor recognition effect of machine learning models on small data subsets, which is a puzzling and challenging problem in the existing research. In this study, we integrate multi-source features to construct a sequence-based computational tool, lncLocation, to predict the subcellular location of lncRNAs. Autoencoder is used to enhance part of the features, and the binomial distribution-based filtering method and recursive feature elimination (RFE) are used to filter some of the features. It improves the representation ability of data and reduces the problem of unbalanced multi-classification data. By comprehensive experiments on different feature combinations and machine learning models, we select the optimal features and classifier model scheme to construct a subcellular location prediction tool, lncLocation. LncLocation can obtain an 87.78% accuracy using 5-fold cross validation on the benchmark data, which is higher than the state-of-the-art tools, and the classification performance, especially for small class sets, is improved significantly.

MSLP: mRNA subcellular localization predictor based on machine learning techniques

“…For generating these features from the DNA sequence of the corresponding mRNA, we used the iLearnPlus [ 26 ] tool. Pseudo Electron-ion interaction pseudopotentials (PseEIIP): EIIP represents the energy of delocalized electrons in nucleotides or amino acids as proposed in [ 27 , 28 ]. As an illustration of how to generate the EIIP indicator sequence, consider the following EIIP values of nucleotides: A , C , G , and T as 0.1260, 0.1340, 0.0806, and 0.1335, respectively.…”

Exploring the landscape of tools and resources for the analysis of long non-coding RNAs

“…Here, the authors have classified the transcripts into three fundamental localization types (nucleus, cytoplasm, and nucleus/cytoplasm) based on the accumulated regions of lncRNAs. Because of the scarcity of experimental data, various algorithms have also been developed to predict and annotate the subcellular localization of lncRNAs, including lncLocation [46] , GM-lncLoc [47] , and GraphLncLoc [48] . In perspective, standardization of both annotation and nomenclature, will improve the lncRNA knowledge and will advantage the integration of large volumes of lncRNA data from different sources.…”

LncRNA GACAT2 binds with protein PKM1/2 to regulate cell mitochondrial function and cementogenesis in an inflammatory environment

“…Identification and validation of pyruvate kinase M1/2 (PKM1/2) as a direct binding protein of GACAT2 that influences mitochondrial function Given that the functions of lncRNAs are closely linked to their subcellular localization, 42,43 the subcellular localization of GACAT2 in PDLSCs was determined. RNA extracted from nuclear and cytoplasmic fractions was successfully identified using a nuclear marker (U6) and cytoplasmic marker (β-actin), and the nuclear and cytoplasmic expression of GACAT2 in the PDLSCs from the Nor, EMD and Infla-EMD groups was then detected by qRT-PCR.…”