To build a comprehensive catalogue of lncRNA transcripts from available plant transcriptomes, RNA-sequencing libraries generated from leaf samples of 11 selected monocot/dicot plant species, including Arabidopsis thaliana, Brachypodium distachyon, Glycine max (soybean), Hordeum vulgare (barley), Medicago truncatula, Oryza sativa (rice), Populus trichocarpa (poplar), Sorghum bicolor, Solanum lycopersicum (tomato), Triticum aestivum (wheat), and Zea mays (maize), were downloaded from Sequence Read Archive (SRA) of National Center for Biotechnology Information (NCBI) [29] by SRA Tool Kit v.2.7.0. Consequently, a total of 21 transcriptome libraries produced by the Illumina sequencing platform were included in the study (S1 Table).

The quality graphs of each library were visually examined through SRA browser, and sequence files were converted to FASTQ files using fastq-dump utility of SRA Tool Kit with—skip-technical,—clip and—split-files (for paired end libraries only) options. Sequencing reads in FASTQ files were mapped to the corresponding reference genomes using STAR aligner v2.5.1 [30] with default parameters, and the mean mapping rate of total 21 libraries was found 88.50% (min: 43.64%, max: 94.04%), indicating that the libraries were suitable for performing ab initio transcriptome assembly (S2 Table). To build STAR aligner indexes, the corresponding reference genome assemblies in multi-FASTA format were downloaded from the ftp site of Ensembl Plants database release 31 [31]. The ab inito transcriptome assembly for each plant species was performed with Cufflinks v2.2.1 [32] to generate a comprehensive catalog of novel lncRNA transcripts. Subsequently, the transcript.gtf files generated in each Cufflinks run were merged with Cuffmerge tool of the Cufflinks suite. To identify novel intergenic transcripts, each merged GTF file was then compared to the corresponding Ensembl v.31 reference annotation using cuffcompare tool. Coding potential of novel transcripts were examined using Transdecoder v.1 (http://transdecoder.github.io/), and sequences longer than 200 nucleotides and containing Open Reading Frame (ORF) < 100 amino acids were classified as novel lncRNAs. We also manually retrieved and included known lncRNA species, annotated by GReeNC [25] and PNRD [27] plant non-coding RNA databases, to generate a complete list of lncRNAs for further analyses. A schematic diagram on the workflow of our study is shown in Fig 1.

A total of 4,323 mature miRNA sequences of 11 plant species were retrieved from miRBase release 21 [33]. To determine putative plant eTMs, possible miRNA target mimic sites were scanned within lncRNA sequences, and marked where they were identified through a custom script written in R programming language [34] as per the following rules previously described in [17]: (i) the 2^nd to 8^th positions at the 5’ end of a miRNA sequence must perfectly match to target lncRNA sequence, (ii) three unpaired nucleotides (bulges) are allowed between the 9th to 12th positions at the 5’ end of the miRNA sequence, and (iii) at most 3 nucleotide mismatch (excluding bulge region) can be between miRNA and lncRNA sequences. Fig 2A shows an example of pairing Z. mays eTM, zma_eTM_miR528b-5p-19, and its potential target miRNA, zma-miR528b-5p. Consequently, a large number of lncRNA sequences meeting the binding rules described above were classified as eTMs. Using this approach, several conserved target mimic sites within eTM sequences were discovered among the selected plant species particularly, A. thaliana, O. sativa, S. bicolor, T. aestivum, and Z. mays (Fig 2B).

To provide a unique and searchable resource of plant eTMs, and to bring currently discovered miRNA mimicry molecules, we established an online database called PeTMbase. Computational analysis of the plant lncRNA sequences from a variety of data sources led to the identification of several novel eTMs in multiple species. Therefore, we have assigned a unique PeTMbase ID for each predicted eTM as follows: (i) the source of eTM sequence is represented by the first three letters of PeTMbase ID. For instance, it is given “zma” prefix if eTM is discovered in Zea mays, (ii) the following three letters are “eTM”, and (iii) the rest of PeTMbase ID comprise miRBase ID of target miRNA. In case multiple eTM sequences targeting the same miRNA, incremental integer starting from 1 is suffixed to corresponding PeTMbase ID. The database stores individual information including, PeTMbase ID, sequence, miRNA target(s), transcript properties, and associated external links (if available), for each eTM into the underlying MySQL v5.7 database (https://www.mysql.com/). The user interfaces were developed with Hyper Text Markup Language (HTML) 5.0, and database search operations of PeTMbase were coded in PHP v7.1 (http://www.php.net/). The communication between the user interface of PeTMbase and MySQL database was implemented with PHP scripts. To offer a simple and an easy-to-use searching experience for the users, it was utilized JQuery (https://jquery.com/) AJAX (asynchronous HTTP) methods.

A database of 2,728 eTMs (411 A. thaliana, 16 B. distachyon, 487 G. max, 18 H. vulgare, 268 M. truncatula, 431 O. sativa, 211 P. trichocarpa, 107 S. bicolor, 16 S. lycopersicum, 291 T. aestivum, and 472 Z. mays) was developed from both manually retrieved and novel long non-coding RNA transcripts. Using any miRNA name, it is possible to search and retrieve the potential eTM within the lncRNA sequence, which contains miRNA-binding site. Once miRNA name is queried in the database, possible putative eTM entries associated with the miRNA of interest are listed and potential binding site(s) can be visualized by clicking on the PeTMbase IDs. Furthermore, the full cDNA sequence of eTM(s), along with its target miRNA sequence is provided within results window (Fig 3). Additional information regarding transcript properties such as, genomic coordinates and assembly information, and the corresponding miRNA are also supplied. If eTM sequence is retrieved from an external database, PeTMbase directs the user to original data source so that one can view and explore eTM features in-depth.

PeTMbase also enables a highly flexible user interface to retrieve eTM sequences by choosing the plant species. A certain species can be selected from the drop down menu provided in the interactive interface of the database and all available eTM information is listed in the species selection. Moreover, the user can save detailed search results in comma separated values file (.csv) format, which allows incorporating provided information with other bioinformatics tools such as blast.