PLIT: An alignment-free computational tool for identification of long non-coding RNAs in plant transcriptomic datasets

Abstract

Long non-coding RNAs (lncRNAs) are a class of non-coding RNAs which play a significant role in several biological processes. RNA-seq based transcriptome sequencing has been extensively used for identification of lncRNAs. However, accurate identification of lncRNAs in RNA-seq datasets is crucial for exploring their characteristic functions in the genome as most coding potential computation (CPC) tools fail to accurately identify them in transcriptomic data. Well-known CPC tools such as CPC2, lncScore, CPAT are primarily designed for prediction of lncRNAs based on the GENCODE, NONCODE and CANTATAdb databases. The prediction accuracy of these tools often drops when tested on transcriptomic datasets. This leads to higher false positive results and inaccuracy in the function annotation process. In this study, we present a novel tool, PLIT, for the identification of lncRNAs in plants RNA-seq datasets. PLIT implements a feature selection method based on L 1 regularization and iterative Random Forests (iRF) classification for selection of optimal features. Based on sequence and codon-bias features, it classifies the RNA-seq derived FASTA sequences into coding or long non-coding transcripts. Using L 1 regularization, 31 optimal features were obtained based on lncRNA and protein-coding transcripts from 8 plant species. The performance of the tool was evaluated on 7 plant RNA-seq datasets using 10-fold cross-validation. The analysis exhibited supe- *

Long non-coding RNAs: emerging players regulating plant abiotic stress response and adaptation

“…A detailed list of plant lncRNA databases is in Table 3. Several important tools, such as CPPred [158], REPTree [159], Pfamscan [160], COME [161], PLIT [156], and CPC2 [162], are available to distinguish lncRNAs from mRNAs. Advances in bioinformatics tools and new algorithms could further boost our efforts in discovering novel lncRNAs and their accurate functional annotations.…”

“… CRISPRlnc Database for validated CRISPR/Cas9 sgRNAs for lncRNAs from variousspecies including plants 305 lncRNAs and 2102 validated sgRNAs on eight species including plant [ 154 ] http://www.crisprlnc.org or http://crisprlnc.xtbg.ac.cn CANTATAdb 2.0 It provides information on annotation of plant lncRNAs Covers information on lnc RNA on 39 plant species [ 155 ] http://cantata.amu.edu.pl , http://yeti.amu.edu.pl/CANTATA/ PLIT Used for investigating of plant lncRNAs from RNA seq data. Provides information on lncRNA from 8 plant species [ 156 ] PLncDB Detail information on plant lncRNAs Provides plant lincRNAs and lncNATs information [ 157 ] – The table is updated version of [ 17 , 61 , 143 ] …”

ItLnc-BXE: A Bagging-XGBoost-Ensemble Method With Comprehensive Sequence Features for Identification of Plant lncRNAs

“…There are two types of commonly used feature selection methods: filter methods and wrapper methods. However, filter methods ignore dependencies among features, whereas wrapper methods are inefficient in time cost [14].…”

sefOri: selecting the best-engineered sequence features to predict DNA replication origins

“…Feature selection algorithms may not only improve the model prediction accuracy (Chatterjee, et al, 2018;Deshpande, et al, 2019), but also find the biologically essential genes for a better understanding of the investigated biological process (Guo, et al, 2014). This study calculated 550 features from each given DNA sequence.…”

“…T-test based feature ranking algorithm was widely used to evaluate the phenotype-association of each feature, and usually the incremental feature selection (IFS) was utilized to find the best number of top-ranked features (Gharbali, et al, 2018;Ye, et al, 2017). The Lasso algorithm evaluated the features by minimizing the L1-penalty and assigned a weight to each feature (Deshpande, et al, 2019;Kumar, et al, 2017).…”