NCResNet: Noncoding Ribonucleic Acid Prediction Based on a Deep Resident Network of Ribonucleic Acid Sequences

Abstract

Noncoding RNA (ncRNA) is a kind of RNA that plays an important role in many biological processes, diseases, and cancers, while cannot translate into proteins. With the development of next-generation sequence technology, thousands of novel RNAs with long open reading frames (ORFs, longest ORF length > 303 nt) and short ORFs (longest ORF length ≤ 303 nt) have been discovered in a short time. How to identify ncRNAs more precisely from novel unannotated RNAs is an important step for RNA functional analysis, RNA regulation, etc. However, most previous methods only utilize the information of sequence features. Meanwhile, most of them have focused on long-ORF RNA sequences, but not adapted to short-ORF RNA sequences. In this paper, we propose a new reliable method called NCResNet. NCResNet employs 57 hybrid features of four categories as inputs, including sequence, protein, RNA structure, and RNA physicochemical properties, and introduces feature enhancement and deep feature learning policies in a neural net model to adapt to this problem. The experiments on benchmark datasets of 8 species shows NCResNet has higher accuracy and higher Matthews correlation coefficient (MCC) compared with other state-of-the-art methods. Particularly, on four short-ORF RNA sequence datasets, specifically mouse, Saccharomyces cerevisiae, zebrafish, and cow, NCResNet achieves greater than 10 and 15% improvements over other state-of-the-art methods in terms of accuracy and MCC. Meanwhile, for long-ORF RNA sequence datasets, NCResNet also has better accuracy and MCC than other state-of-the-art methods on most test datasets. Codes and data are available at https://github.com/abcair/NCResNet.

LncMirNet: Predicting LncRNA–miRNA Interaction Based on Deep Learning of Ribonucleic Acid Sequences

“…Composition transition distribution (CTD) [ 1 ] is primarily proposed for predicting the protein folding class, which is a global protein sequence descriptor established by Dubchak’s work [ 24 ]. Lately, CTD features are found to relate to RNA structure and are seldom used to predict the interactions between lncRNAs and miRNAs.…”

“…Likewise, Ts, Gs, and Cs were 0.1, 0.3, 0.45, 0.6, 0.85, 0.25, 0.5, 0.65, 0.8, 0.95, 0.2, 0.4, 0.55, 0.75, and 1. We used A0, A1, A2, A3, A4, T0, T1, T2, T3, T4, G0, G1, G2, G3, G4, C0, C1, C2, C3, and C4 to represent the 20 features [ 1 ].…”

“…Although noncoding RNAs (ncRNAs) [ 1 ] cannot encode proteins, they play indispensable roles in numerous life processes [ 2 , 3 , 4 , 5 , 6 , 7 ]. Accumulated studies show that many ncRNAs are involved in various life regulation processes [ 8 , 9 ].…”

The computational approaches of lncRNA identification based on coding potential: Status quo and challenges

“… [37] , [134] , [148] . In addition, the process of a deep neural network operation likes a black box, from which it is hard and difficult to interpret the performance and evaluate the importance of every input feature [149] . Such methods include LncRNA-MFDL, DeepLNC, LNCAdeep, NCResNet and so on [37] , [134] , [148] , [149] .…”

“…During the process of developing NCResNet, Yang and his colleagues estimated the running time of six models and got similar results. All six tools, NCResNet, CPC2, CPAT, IRSOM, LncFinder, and CPPred, are capable of large-scale (thousands to tens of thousands of sequences) lncRNA identification tasks [149] .…”