PLncFire: A Scalable Pipeline for Transcriptome-wide Discovery of Plant lncRNAs

PLncFire: A Scalable Pipeline for Transcriptome-wide Discovery of Plant lncRNAs | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results PLncFire: A Scalable Pipeline for Transcriptome-wide Discovery of Plant lncRNAs Surbhi Mistry , Shivani Saxena , Dhaval Patel , Ahsan Z Rizvi doi: https://doi.org/10.1101/2025.10.13.682253 Surbhi Mistry 1 School of Computing and Technology, Institute of Advanced Research , Gandhinagar, 382426, Gujarat, India Find this author on Google Scholar Find this author on PubMed Search for this author on this site Shivani Saxena 1 School of Computing and Technology, Institute of Advanced Research , Gandhinagar, 382426, Gujarat, India Find this author on Google Scholar Find this author on PubMed Search for this author on this site Dhaval Patel 2 Gujarat Biotechnology University , Gandhinagar, 382355, Gujarat, India Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ahsan Z Rizvi 1 School of Computing and Technology, Institute of Advanced Research , Gandhinagar, 382426, Gujarat, India 3 Department of Forest Genetics and Plant Physiology, Swedish University of Agricultural Sciences , Umea, 90183, Sweden Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: ahsan.zaigam.rizvi{at}slu.se Abstract Full Text Info/History Metrics Preview PDF Abstract Long non-coding RNAs (lncRNAs) are key regulators of plant biology, yet their discovery is hindered by low sequence conservation and a lack of comprehensive annotations. To overcome these challenges, we developed PLncFire, a modular computational pipeline that automates the genome-wide identification and annotation of lncRNAs from standard RNA-seq data. PLncFire integrates quality control, transcript assembly, and a robust consensus coding-potential assessment using CPC2, PlantLncPipe, and FEELnc to generate high-confidence predictions. It classifies lncRNAs as known or novel, facilitates their prioritisation through differential expression analysis, and is designed for scalability and reproducibility across diverse plant species. PLncFire provides a standardised framework to empower large-scale lncRNA discovery and advance comparative functional genomics. The source code is available at https://github.com/ahsan-rizvi/PLncFire.git . 1 Introduction Long non-coding RNAs (lncRNAs) are transcripts longer than 200 nucleotides that do not encode proteins, yet play vital roles in regulating gene expression ( Zhang et al., 2019 ; Budak et al., 2020 ; PSVV et al., 2025 ). In plants, lncRNAs have been associated with key biological processes, including flowering time control, tissue differentiation, stress adaptation, and epigenetic regulation ( Jha et al., 2020 ). The growing catalogue of plant lncRNAs uncovered through high-throughput sequencing highlights their abundance and functional diversity but also underscores a challenge: unlike protein-coding genes, lncRNAs show poor sequence conservation, variable structures, and highly context-specific expression patterns ( Shukla et al., 2021 ; Zhang et al., 2023 ). These characteristics make their genome-wide discovery and annotation far from straightforward ( Chi et al., 2019 ; Karmakar et al., 2019 ). While numerous computational pipelines for lncRNA discovery exist, most have been designed with animal genomes in mind, lack plant-specific optimizations, or depend on a single prediction algorithm, leading to incomplete or error-prone results (Ramakrishnaiah et al., 2020). Furthermore, many approaches stop at identifying putative lncRNAs without integrating downstream classification into known and novel categories or linking them to functional prioritization steps such as differential expression analysis ( Zhang et al., 2023 ; Huang et al., 2025). The absence of a standardized, modular, and reproducible workflow tailored to plant systems has limited cross-species comparisons and slowed progress in functional genomics. For instance, PlantLncPipe ( Tian et al., 2024 ) offered one of the first end-to-end work-flows for plants, but its reliance on a single coding-potential predictor limited both its accuracy and generalizability. FEELnc ( Wucher et al., 2017 ), widely adopted across species, was originally optimized for animal genomes and often misclassifies plant transcripts due to their repetitive structures and incomplete annotations. CNIT (Guo et al., 2019) applied alignment-free features to improve speed but struggled with interpretability and cross-species reproducibility. PLncPRO (Singh et al., 2017) introduced a random forest framework, yet its predictions varied widely depending on input annotation quality. More recently, deep learning–based models such as DeepPlnc (Ritu et al., 2022) demonstrated improved sensitivity but at the cost of high false-positive rates when applied to complex plant transcriptomes. The latest entrant, PlantLncBoost ( Tian et al., 2025 ), was marketed as a breakthrough; however, an initial version misclassified chromosome identifiers as lncRNAs, and the tool continues to suffer from severe overprediction and an unstable precision-recall balance despite updates. Collectively, these advances highlight the growing interest in computational lncRNA discovery, but they also underscore a persistent gap: the absence of a modular, statistically robust, and biologically interpretable pipeline tailored specifically to the complexities of plant genomes. To address this, we introduce PLncFire, a comprehensive and specialized computational pipeline designed for the robust identification and annotation of long non-coding RNAs (lncRNAs) in plant transcriptomes. To overcome the critical challenges of high false-positive rates and poor cross-species conservation, PLncFire integrates a multifaceted strategy. It begins with stringent pre-processing of sequencing data to ensure a high-quality foundation, followed by a robust consensus prediction phase that leverages the complementary strengths of three distinct tools: CPC2 ( Kang et al., 2017 ), PlantLncPipe ( Tian et al., 2024 ), and FEELnc ( Wucher et al., 2017 ). This ensemble method significantly enhances prediction reliability by minimizing the biases and limitations inherent to any single algorithm. Subsequently, each putative lncRNA is annotated through meticulous searches against curated databases, classifying them into known or novel categories. Architecturally, this pipeline is designed to be modular and scalable, ensuring it can be readily adapted to diverse plant species with varying genomic complexities and to data from different sequencing platforms. Most importantly, PLncFire moves beyond mere identification by seamlessly integrating downstream functional prioritization, such as differential expression analysis, directly into its workflow. Consequently, PLncFire does not merely generate a catalogue of candidates; it provides a powerful, standardized framework for the functional exploration of lncRNAs, thereby accelerating research into their roles in plant development, stress response, and evolutionary biology. What sets PLncFire apart is its combination of thoughtful design and statistical robustness. Unlike existing pipelines that either miss a substantial fraction of reference lncRNAs or inflate predictions with false positives, PLncFire achieves a critical balance, consistently recovering annotated transcripts while maintaining high precision, recall, and F1 scores. These results are not isolated observations but are statistically consistent across independent datasets, underscoring the method’s reproducibility and reliability. By uniting methodological stringency with statistical power, PLncFire ensures confidence in the accuracy of predicted lncRNAs, guaranteeing that downstream biological interpretations are built on a solid foundation. The pipeline’s scope extends well beyond initial discovery: its modular framework supports comparative analyses, cross-species studies, and integration with functional genomics data, making it a versatile tool for advancing both basic and applied plant science. 2 Materials and Methods The PLncFire pipeline was developed as a modular, transcriptome-based framework for the systematic identification and annotation of plant lncRNAs. The workflow begins with rigorous data pre-processing to ensure that only high-quality reads enter downstream analyses. Raw RNA-seq reads were first subjected to quality assessment with FastQC ( Brown et al., 2017 ) to evaluate sequencing integrity, adapter contamination, and base composition. Low-quality bases and adapters were removed using Trimmomatic-0.39 ( Bolger et al., 2014 ) with default parameters. Genomes were indexed with HISAT2-build ( Guo et al., 2022 ), and quality-trimmed RNA-seq reads were aligned to the reference genome. The resulting alignment files were sorted and indexed with SAMtools ( Li et al., 2009 ; Danecek et al., 2021 ),to provide a stable and reproducible basis for transcript reconstruction. Transcriptome assembly was performed using StringTie ( Shumate et al., 2022 ) in reference-guided mode, enabling the recovery of both annotated and potentially novel transcripts. Assemblies from multiple samples were merged to generate a comprehensive, non-redundant transcript catalogue. To refine this set, transcripts shorter than 200 nucleotides or those containing fewer than two exons were removed, and overlaps with annotated protein-coding genes were excluded using Gffcompare ( Pertea and Pertea, 2020 ), thereby enriching the dataset for putative non-coding candidates. To achieve reliable lncRNA identification, the workflow combines several prediction tools, mitigating the elevated false-positive rates ( Tian et al., 2025 ) associated with individual methods. PLncFire scalable pipeline implements a consensus-based strategy for coding potential assessment. Candidate transcripts were evaluated using three complementary tools: CPC2 ( Kang et al., 2017 ), which relies on sequence-intrinsic features; PlantLncPipe ( Tian et al., 2024 ), which applies plant-optimised classifiers; and FEELnc ( Wucher et al., 2017 ), which incorporates machine learning and comparative annotation. Only transcripts classified as non-coding by at least two of these three tools were retained, substantially reducing false positives while capturing genuine lncRNAs. This consensus approach represents a central innovation of PLncFire, setting it apart from existing plant-specific pipelines. Following identification, the retained candidates were annotated by homology searches against curated plant lncRNA databases, including RNAcentral ( Sweeney et al., 2019 ), CANTATAdb ( Szcześniak and Wanowska, 2024 ), and PLncDB ( Jin et al., 2021 ), using BLASTn ( Camacho et al., 2009 ). Transcripts with significant matches were assigned as known lncRNAs, while unmatched candidates were considered novel, thus establishing a reproducible framework for distinguishing conserved regulators from lineage- or condition-specific transcripts. PLncFire scalable schematic is summarised in Figure 1 , follows a modular design comprising three stages: pre-processing, identification, and annotation with prioritisation. Each stage is fully containerised, ensuring reproducibility across platforms and compatibility with both local workstations and high-performance computing environments. In addition, the modularity of PLncFire allows substitution of individual tools; for instance, HISAT2 ( Guo et al., 2022 ) can be replaced by STAR ( Dobin et al., 2013 ) for alignment, or new databases can be integrated as plant-specific resources expand without altering the over-all structure of the workflow. This flexibility enables seamless adaptation to new genomes, sequencing platforms, and research questions, while maintaining reproducibility and scalability for large-scale analyses. Download figure Open in new tab Fig. 1: The PLncFire scalable pipeline for the identification and annotation of plant lncR-NAs from transcriptomic data. Key stages include: (1) Pre-processing: quality control, adapter trimming, and read alignment; (2) lncRNA Identification: transcript assembly, filtering, and consensus coding-potential assessment using CPC2, PlantLncPipe, and FEELnc; and later classification into known/novel lncRNAs. Performance evaluation of PLncFire was conducted by benchmarking against existing pipelines using publicly available transcriptomic datasets from NCBI ( Schoch et al., 2020 ). Since PLncFire produces binary predictions based on a consensus of three independent coding-potential tools, the prediction quality was assessed using standard classification metrics, including accuracy, precision, recall, and F1 score, which were calculated by comparing predicted lncRNAs with reference annotations. This ensured that evaluation focused on both recovery of annotated transcripts and minimisation of false positives, providing a balanced measure of performance. By integrating sequential steps of quality control ( Bolger et al., 2014 ; Brown et al., 2017 ), reference-guided transcript assembly ( Shumate et al., 2022 ), stringent transcript filtering, consensus-based coding potential prediction ( Kang et al., 2017 ; Wucher et al., 2017 ; Tian et al., 2024 ), and database-driven classification, PLncFire systematically progresses from raw sequencing reads to high-confidence lncRNA catalogues. This structured workflow ensures that candidate transcripts are rigorously evaluated, classified into known and novel categories, and quantified for expression profiling, providing a complete pipeline ready for downstream analyses. 3 Results and Discussion We benchmarked PLncFire against CPC2 ( Kang et al., 2017 ), PlantLncPipe ( Tian et al., 2024 ), FEELnc ( Wucher et al., 2017 ), PlantLncBoost ( Tian et al., 2025 ) using transcriptomic datasets from NCBI of Arachis duranensis (NCBI Accession: PRJNA258023)( Zhang et al., 2020 ) and Glycine max (NCBI Accession: PRJNA48389) ( Chang et al., 2013 ). Evaluation was based on recovery of annotated lncRNAs, novel predictions, and standard statistical metrics. LncRNA prediction statistics are summarized in Figure 2 , which breaks down recovered (overlapping with annotated lncRNAs), novel, other biotype, and missed lncRNAs across pipelines. In A. duranensis ( Figure 2a ), PLncFire predicted 10,155 lncRNAs, recovering all 8017 annotated transcripts (100%) and identifying 2138 novel candidates, without mis-classification into unrelated biotypes. FEELnc predicted 8017 lncRNAs, recovering 7045 (88%) but missing 972. CPC2 recovered 3563 (44%) and PlantLncPipe only 182 (2%). By contrast, PlantLncBoost generated 28,509 predictions, recovering 6053 annotated lncR-NAs (76%) but misclassifying more than 18,000 as other biotypes, reflecting substantial overprediction. A similar pattern was observed in G. max ( Figure 2b ), PLncFire predicted 4196 lncRNAs, recovering all 4181 annotated transcripts (100%) and reporting only 15 novel candidates. FEELnc recovered 3547 annotated lncRNAs (85%) but missed 634. CPC2 recovered 2821 (67%) and PlantLncPipe only 220 (5%). PlantLncBoost recovered just 552 annotated lncRNAs (13%) despite predicting 795 in total, with most being misassigned or spurious. Download figure Open in new tab Fig. 2: LncRNA Prediction statistics across pipelines. (a) Arachis duranensis and (b) Glycine max. Each embedded bar represents the distribution of recovered (overlap with annotated lncRNAs), novel candidates, transcripts classified as other biotypes, and missed lncRNAs, allowing direct comparison of pipeline performance. Figure 3 further illustrates benchmarking accuracy in terms of recovery rates. PLnc-Fire consistently outperformed all pipelines, achieving complete recovery in both species. FEELnc performed second best, but its recall remained incomplete. CPC2 and PlantL-ncPipe systematically underpredicted, whereas PlantLncBoost recovered a moderate fraction but suffered from instability and inflated false positives. Download figure Open in new tab Fig. 3: Benchmarking accuracy of lncRNA recovery in Arachis duranensis and Glycine max: comparison of PLncFire with existing pipelines. To capture performance in terms of classification quality, we compared pipelines across accuracy, precision, recall, and F1 score, summarized in radar charts ( Figure 4a , b). In A. duranensis, PLncFire achieved perfect scores across all metrics (accuracy, precision, recall, and F1 = 1.00). FEELnc showed strong but imperfect balance (accuracy = 0.97, precision = 0.95, recall = 0.88, F1 = 0.91). CPC2 achieved accuracy of 0.84 but low recall (0.44), while PlantLncPipe performed poorly across all metrics (F1 = 0.04). PlantLncBoost displayed high recall (0.76) but very low precision (0.23), resulting in an unstable F1 score of 0.35. The same trend was evident in G. max. PLncFire once again achieved perfect performance across all metrics, followed by FEELnc (accuracy = 0.99, precision = 1.00, recall = 0.85, F1 = 0.92). CPC2 balanced moderate performance (accuracy = 0.97, precision = 0.84, recall = 0.67, F1 = 0.75), whereas PlantLncPipe remained the weakest (F1 = 0.09). PlantL-ncBoost showed modest precision (0.70) but extremely low recall (0.13), yielding a poor F1 score of 0.22. Taken together, these benchmarks demonstrate that PLncFire consistently delivers complete recovery of annotated lncRNAs while maintaining high precision and balanced recall, a combination not achieved by any other pipeline tested. Earlier methods such as CPC2 and PlantLncPipe suffer from systematic underprediction, missing large fractions of genuine lncRNAs, whereas PlantLncBoost, despite being introduced as a machine learning–based advance, continues to display instability and excessive false positives even after recent updates. By avoiding both under and overprediction, PLnc-Fire establishes itself as a stable, reproducible, and biologically reliable framework for large-scale lncRNA discovery in plants. Download figure Open in new tab Fig. 4: Radar charts summarizing statistical performance metrics (Recall value, Precision, F1 Score, Accuracy) for (a) Arachis duranensis and (b) Glycine max. 4 Conclusion Long non-coding RNAs are key regulators of plant development, stress responses, and genome evolution, yet their discovery is often limited by inconsistent methods. PLncFire provides a modular, reproducible workflow that combines stringent filtering, consensus based coding potential assessment, and comprehensive annotation. Benchmarking against PlantLncBoost demonstrates that PLncFire identifies a larger and more biologically plausible set of lncRNAs, minimizes false positives, and enables functional prioritization through classification and expression profiling. Its consensus-driven design ensures robustness, interpretability, and scalability across species and sequencing platforms. By standardizing lncRNA discovery, PLncFire offers a reliable platform for advancing plant functional genomics and uncovering regulatory complexity. Declarations The authors declare that they have received no funding for this work and have no financial or non-financial competing interests to disclose. Conflicts of interests The authors declare no conflicts of interests. Acknowledgment The results presented in this paper were obtained using HPC facilities under ICE-BRAF, CDAC, Pune, India. References 1. ↵ Bolger , A. M. , Lohse , M. , and Usadel , B. ( 2014 ). Trimmomatic: A flexible trimmer for Illumina sequence data . Bioinformatics 30 , 2114 – 2120 . doi: 10.1093/bioinformatic-s/btu170 OpenUrl CrossRef PubMed Web of Science 2. ↵ Brown , J. , Pirrung , M. , and Mccue , L. A. ( 2017 ). FQC Dashboard: Integrates FastQC results into a web-based, interactive, and extensible FASTQ quality control tool . Bioinformatics 33 , 3137 – 3139 . doi: 10.1093/bioinformatics/btx373 OpenUrl CrossRef PubMed 3. ↵ Budak , H. , Kaya , S. B. , and Cagirici , H. B. ( 2020 ). Long Non-coding RNA in Plants in the Era of Reference Sequences . Front Plant Sci 11 . doi: 10.3389/fpls.2020.00276 OpenUrl CrossRef 4. ↵ Camacho , C. , Coulouris , G. , Avagyan , V. , Ma , N. , Papadopoulos , J. , Bealer , K. , et al. ( 2009 ). BLAST+: Architecture and applications . BMC Bioinformatics 10 . doi: 10.1186/1471-2105-10-421 OpenUrl CrossRef PubMed 5. ↵ Chang , S. , Wang , Y. , Lu , J. , Gai , J. , Li , J. , Chu , P. , et al. ( 2013 ). The Mitochondrial Genome of Soybean Reveals Complex Genome Structures and Gene Evolution at Intercellular and Phylogenetic Levels . PLoS One 8 . doi: 10.1371/journal.pone.0056502 OpenUrl CrossRef PubMed 6. ↵ Chi , Y. , Wang , D. , Wang , J. , Yu , W. , and Yang , J. ( 2019 ). Long non-coding RNA in the pathogenesis of cancers . Cells 8 . doi: 10.3390/cells8091015 OpenUrl CrossRef PubMed 7. ↵ Danecek , P. , Bonfield , J. K. , Liddle , J. , Marshall , J. , Ohan , V. , Pollard , M. O. , et al. ( 2021 ). Twelve years of SAMtools and BCFtools . Gigascience 10 . doi: 10.1093/gigascience/-giab008 OpenUrl CrossRef 8. ↵ Dobin , A. , Davis , C. A. , Schlesinger , F. , Drenkow , J. , Zaleski , C. , Jha , S. , et al. ( 2013 ). STAR: Ultrafast universal RNA-seq aligner . Bioinformatics 29 , 15 – 21 . doi: 10.1093/bioinformatics/bts635 OpenUrl CrossRef PubMed Web of Science 9. ↵ Guo , J. , Gao , J. , and Liu , Z. ( 2022 ). HISAT2 Parallelization Method Based on Spark Cluster ., in Journal of Physics: Conference Series , ( IOP Publishing Ltd ). doi: 10.1088/17426596/2179/1/012038 OpenUrl CrossRef 10. ↵ Jha , U. C. , Nayyar , H. , Jha , R. , Khurshid , M. , Zhou , M. , Mantri , N. , et al. ( 2020 ). Long non-coding RNAs: Emerging players regulating plant abiotic stress response and adaptation . BMC Plant Biol 20 . doi: 10.1186/s12870-020-02595-x OpenUrl CrossRef 11. ↵ Jin , J. , Lu , P. , Xu , Y. , Li , Z. , Yu , S. , Liu , J. , et al. ( 2021 ). PLncDB V2.0: A comprehensive encyclopedia of plant long noncoding RNAs . Nucleic Acids Res 49 , D1489 – D1495 . doi: 10.1093/nar/gkaa910 OpenUrl CrossRef 12. ↵ Kang , Y. J. , Yang , D. C. , Kong , L. , Hou , M. , Meng , Y. Q. , Wei , L. , et al. ( 2017 ). CPC2: A fast and accurate coding potential calculator based on sequence intrinsic features . Nucleic Acids Res 45 , W12 – W16 . doi: 10.1093/nar/gkx428 OpenUrl CrossRef PubMed 13. ↵ Karmakar , K. , Kundu , A. , Rizvi , A. Z. , Dubois , E. , Severac , D. , Czernic , P. , et al. ( 2019 ). Transcriptomic analysis with the progress of symbiosis in “Crack-Entry” legume arachis hypogaea highlights its contrast with “Infection Thread” adapted legumes . Molecular Plant-Microbe Interactions 32 , 271 – 285 . doi: 10.1094/MPMI-06-18-0174-R OpenUrl CrossRef PubMed 14. ↵ Li , H. , Handsaker , B. , Wysoker , A. , Fennell , T. , Ruan , J. , Homer , N. , et al. ( 2009 ). The Sequence Alignment/Map format and SAMtools . Bioinformatics 25 , 2078 – 2079 . doi: 10.1093/bioinformatics/btp352 OpenUrl CrossRef PubMed Web of Science 15. ↵ Pertea , M. , and Pertea , G. ( 2020 ). GFF Utilities: GffRead and GffCompare . F1000Res 9 . doi: 10.12688/f1000research.23297.1 OpenUrl CrossRef PubMed 16. ↵ PSVV, C. , Joseph , A. , Ebenezer , P. , Sankar , V. , Suravajhala , R. , Rao , R. S. P. , et al. ( 2025 ). An introduction to non-coding RNAs . Prog Mol Biol Transl Sci 214 , 1 – 17 . doi: 10.1016/BS.PMBTS.2025.01.006 OpenUrl CrossRef PubMed 17. ↵ Schoch , C. L. , Ciufo , S. , Domrachev , M. , Hotton , C. L. , Kannan , S. , Khovanskaya , R. , et al. ( 2020 ). NCBI Taxonomy: A comprehensive update on curation, resources and tools . Database 2020 . doi: 10.1093/database/baaa062 OpenUrl CrossRef PubMed 18. ↵ Shukla , B. , Gupta , S. , Srivastava , G. , Sharma , A. , Shukla , A. K. , and Shasany , A. K. ( 2021 ). lncRNADetector: a bioinformatics pipeline for long non-coding RNA identification and MAPslnc: a repository of medicinal and aromatic plant lncRNAs . RNA Biol 18 , 2290 – 2295 . doi: 10.1080/15476286.2021.1899673 OpenUrl CrossRef PubMed 19. ↵ Shumate , A. , Wong , B. , Pertea , G. , and Pertea , M. ( 2022 ). Improved transcriptome assembly using a hybrid of long and short reads with StringTie . PLoS Comput Biol 18 . doi: 10.1371/journal.pcbi.1009730 OpenUrl CrossRef PubMed 20. ↵ Sweeney , B. A. , Petrov , A. I. , Burkov , B. , Finn , R. D. , Bateman , A. , Szymanski , M. , et al. ( 2019 ). RNAcentral: A hub of information for non-coding RNA sequences . Nucleic Acids Res 47 , D221 – D229 . doi: 10.1093/nar/gky1034 OpenUrl CrossRef PubMed 21. ↵ Szcześniak , M. W. , and Wanowska , E. ( 2024 ). CANTATAdb 3.0: An Updated Repository of Plant Long Non-Coding RNAs . Plant Cell Physiol 65 , 1486 – 1493 . doi: 10.1093/pcp/p-cae081 OpenUrl CrossRef PubMed 22. ↵ Tian , X. C. , Chen , Z. Y. , Nie , S. , Shi, T. Le , Yan , X. M. , Bao , Y. T. , et al. ( 2024 ). Plant-LncPipe: a computational pipeline providing significant improvement in plant lncRNA identification . Hortic Res 11 . doi: 10.1093/hr/uhae041 OpenUrl CrossRef 23. ↵ Tian , X. C. , Nie , S. , Domingues , D. , Rossi Paschoal , A. , Jiang , L. B. , and Mao , J. F. ( 2025 ). PlantLncBoost: key features for plant lncRNA identification and significant improvement in accuracy and generalization . New Phytologist 247 , 1538 – 1549 . doi: 10.1111/nph.70211 OpenUrl CrossRef PubMed 24. ↵ Wucher , V. , Legeai , F. , Hédan , B. , Rizk , G. , Lagoutte , L. , Leeb , T. , et al. ( 2017 ). FEELnc: A tool for long non-coding RNA annotation and its application to the dog transcriptome . Nucleic Acids Res 45 . doi: 10.1093/nar/gkw1306 OpenUrl CrossRef PubMed 25. ↵ Zhang , L. , Lin , T. , Zhu , G. , Wu , B. , Zhang , C. , and Zhu , H. ( 2023 ). LncRNAs exert indispensable roles in orchestrating the interaction among diverse noncoding RNAs and enrich the regulatory network of plant growth and its adaptive environmental stress response . Hortic Res 10 . doi: 10.1093/hr/uhad234 OpenUrl CrossRef 26. ↵ Zhang , R. , Wang , Y. H. , Jin , J. J. , Stull , G. W. , Bruneau , A. , Cardoso , D. , et al. ( 2020 ). Exploration of Plastid Phylogenomic Conflict Yields New Insights into the Deep Relationships of Leguminosae . Syst Biol 69 , 613 – 622 . doi: 10.1093/sysbio/syaa013 OpenUrl CrossRef PubMed 27. ↵ Zhang , X. , Wang , W. , Zhu , W. , Dong , J. , Cheng , Y. , Yin , Z. , et al. ( 2019 ). Mechanisms and functions of long non-coding RNAs at multiple regulatory levels . Int J Mol Sci 20 . doi: 10.3390/ijms20225573 OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted October 15, 2025. Download PDF Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following PLncFire: A Scalable Pipeline for Transcriptome-wide Discovery of Plant lncRNAs Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share PLncFire: A Scalable Pipeline for Transcriptome-wide Discovery of Plant lncRNAs Surbhi Mistry , Shivani Saxena , Dhaval Patel , Ahsan Z Rizvi bioRxiv 2025.10.13.682253; doi: https://doi.org/10.1101/2025.10.13.682253 Share This Article: Copy Citation Tools PLncFire: A Scalable Pipeline for Transcriptome-wide Discovery of Plant lncRNAs Surbhi Mistry , Shivani Saxena , Dhaval Patel , Ahsan Z Rizvi bioRxiv 2025.10.13.682253; doi: https://doi.org/10.1101/2025.10.13.682253 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Bioinformatics Subject Areas All Articles Animal Behavior and Cognition (7642) Biochemistry (17715) Bioengineering (13907) Bioinformatics (42003) Biophysics (21470) Cancer Biology (18624) Cell Biology (25533) Clinical Trials (138) Developmental Biology (13390) Ecology (19935) Epidemiology (2067) Evolutionary Biology (24356) Genetics (15617) Genomics (22529) Immunology (17753) Microbiology (40432) Molecular Biology (17200) Neuroscience (88681) Paleontology (667) Pathology (2840) Pharmacology and Toxicology (4828) Physiology (7653) Plant Biology (15161) Scientific Communication and Education (2046) Synthetic Biology (4304) Systems Biology (9826) Zoology (2271)