PLEK: a tool for predicting long non-coding RNAs and messenger RNAs based on an improved k-mer scheme

Abstract

Background: High-throughput transcriptome sequencing (RNA-seq) technology promises to discover novel protein-coding and non-coding transcripts, particularly the identification of long non-coding RNAs (lncRNAs) from de novo sequencing data. This requires tools that are not restricted by prior gene annotations, genomic sequences and high-quality sequencing.

Results: We present an alignment-free tool called PLEK (predictor of long non-coding RNAs and messenger RNAs based on an improved k-mer scheme), which uses a computational pipeline based on an improved k-mer scheme and a support vector machine (SVM) algorithm to distinguish lncRNAs from messenger RNAs (mRNAs), in the absence of genomic sequences or annotations. The performance of PLEK was evaluated on well-annotated mRNA and lncRNA transcripts. 10-fold cross-validation tests on human RefSeq mRNAs and GENCODE lncRNAs indicated that our tool could achieve accuracy of up to 95.6%. We demonstrated the utility of PLEK on transcripts from other vertebrates using the model built from human datasets. PLEK attained >90% accuracy on most of these datasets. PLEK also performed well using a simulated dataset and two real de novo assembled transcriptome datasets (sequenced by PacBio and 454 platforms) with relatively high indel sequencing errors. In addition, PLEK is approximately eightfold faster than a newly developed alignment-free tool, named Coding-Non-Coding Index (CNCI), and 244 times faster than the most popular alignment-based tool, Coding Potential Calculator (CPC), in a single-threading running manner.

Conclusions: PLEK is an efficient alignment-free computational tool to distinguish lncRNAs from mRNAs in RNA-seq transcriptomes of species lacking reference genomes. PLEK is especially suitable for PacBio or 454 sequencing data and large-scale transcriptome data. Its open-source software can be freely downloaded from https://sourceforge.net/projects/plek/files/.

Figure 1

Comparison of robustness towards indel sequencing errors. The x-axis is the indel numbers per 100 bases (indel sequencing error rates). Performance (accuracy) of CNCI declines significantly as the indel error rate increases.

Figure 2

Results of PLEK, CPC, CNCI and PhyloCSF on mouse datasets. (A) The fraction of protein-coding transcripts classified as coding or non-coding. (B) The fraction of non-coding transcripts classified as coding or non-coding. Data were collected from RefSeq mouse protein-coding transcripts (release 60) and GENCODE mouse long non-coding transcripts (vM2). Shown is the fraction of transcripts classified as coding or non-coding by each tool. All these tools performed well on protein-coding transcripts. PLEK and CNCI outperformed CPC and PhyloCSF on long non-coding transcripts.

Figure 3

Performance comparison of various ranges of k. On the x-axis, ‘5’ means that k ranged from 1 to 5. Training data comprised 22,389 human RefSeq mRNA transcripts and 22,389 GENCODE lncRNA transcripts. SVM classifiers were trained using 10-fold cross-validation on the training datasets. The figure indicates that the computation load rises and the accuracy increases along as k increases.