Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data
Long noncoding RNAs (lncRNAs) play critical regulatory roles in human development and disease. Although there are over 100,000 samples with available RNA sequencing (RNA-seq) data, many lncRNAs have yet to be annotated. The conventional approach to identifying novel lncRNAs from RNA-seq data is to f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Non-Coding RNA |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-553X/8/5/70 |
| _version_ | 1797470654362025984 |
|---|---|
| author | Zixiu Li Peng Zhou Euijin Kwon Katherine A. Fitzgerald Zhiping Weng Chan Zhou |
| author_facet | Zixiu Li Peng Zhou Euijin Kwon Katherine A. Fitzgerald Zhiping Weng Chan Zhou |
| author_sort | Zixiu Li |
| collection | DOAJ |
| description | Long noncoding RNAs (lncRNAs) play critical regulatory roles in human development and disease. Although there are over 100,000 samples with available RNA sequencing (RNA-seq) data, many lncRNAs have yet to be annotated. The conventional approach to identifying novel lncRNAs from RNA-seq data is to find transcripts without coding potential but this approach has a false discovery rate of 30–75%. Other existing methods either identify only multi-exon lncRNAs, missing single-exon lncRNAs, or require transcriptional initiation profiling data (such as H3K4me3 ChIP-seq data), which is unavailable for many samples with RNA-seq data. Because of these limitations, current methods cannot accurately identify novel lncRNAs from existing RNA-seq data. To address this problem, we have developed software, <i>Flnc</i>, to accurately identify both novel and annotated full-length lncRNAs, including single-exon lncRNAs, directly from RNA-seq data without requiring transcriptional initiation profiles. <i>Flnc</i> integrates machine learning models built by incorporating four types of features: transcript length, promoter signature, multiple exons, and genomic location. <i>Flnc</i> achieves state-of-the-art prediction power with an AUROC score over 0.92. <i>Flnc</i> significantly improves the prediction accuracy from less than 50% using the conventional approach to over 85%. <i>Flnc</i> is available via GitHub platform. |
| first_indexed | 2024-03-09T19:39:05Z |
| format | Article |
| id | doaj.art-04db2740038f4ab382fc7794fc41cf29 |
| institution | Directory Open Access Journal |
| issn | 2311-553X |
| language | English |
| last_indexed | 2024-03-09T19:39:05Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Non-Coding RNA |
| spelling | doaj.art-04db2740038f4ab382fc7794fc41cf292023-11-24T01:42:31ZengMDPI AGNon-Coding RNA2311-553X2022-10-01857010.3390/ncrna8050070Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq DataZixiu Li0Peng Zhou1Euijin Kwon2Katherine A. Fitzgerald3Zhiping Weng4Chan Zhou5Division of Biostatistics and Health Services Research, Department of Population and Quantitative Health Sciences, University of Massachusetts Chan Medical School, Worcester, MA 01605, USADivision of Biostatistics and Health Services Research, Department of Population and Quantitative Health Sciences, University of Massachusetts Chan Medical School, Worcester, MA 01605, USADivision of Biostatistics and Health Services Research, Department of Population and Quantitative Health Sciences, University of Massachusetts Chan Medical School, Worcester, MA 01605, USAProgram in Innate Immunity, Division of Infectious Disease and Immunology, Department of Medicine, University of Massachusetts Chan Medical School, Worcester, MA 01605, USAProgram in Bioinformatics and Integrative Biology, University of Massachusetts Chan Medical School, Worcester, MA 01605, USADivision of Biostatistics and Health Services Research, Department of Population and Quantitative Health Sciences, University of Massachusetts Chan Medical School, Worcester, MA 01605, USALong noncoding RNAs (lncRNAs) play critical regulatory roles in human development and disease. Although there are over 100,000 samples with available RNA sequencing (RNA-seq) data, many lncRNAs have yet to be annotated. The conventional approach to identifying novel lncRNAs from RNA-seq data is to find transcripts without coding potential but this approach has a false discovery rate of 30–75%. Other existing methods either identify only multi-exon lncRNAs, missing single-exon lncRNAs, or require transcriptional initiation profiling data (such as H3K4me3 ChIP-seq data), which is unavailable for many samples with RNA-seq data. Because of these limitations, current methods cannot accurately identify novel lncRNAs from existing RNA-seq data. To address this problem, we have developed software, <i>Flnc</i>, to accurately identify both novel and annotated full-length lncRNAs, including single-exon lncRNAs, directly from RNA-seq data without requiring transcriptional initiation profiles. <i>Flnc</i> integrates machine learning models built by incorporating four types of features: transcript length, promoter signature, multiple exons, and genomic location. <i>Flnc</i> achieves state-of-the-art prediction power with an AUROC score over 0.92. <i>Flnc</i> significantly improves the prediction accuracy from less than 50% using the conventional approach to over 85%. <i>Flnc</i> is available via GitHub platform.https://www.mdpi.com/2311-553X/8/5/70lncRNAmachine learningRNA-seqtoolunannotated |
| spellingShingle | Zixiu Li Peng Zhou Euijin Kwon Katherine A. Fitzgerald Zhiping Weng Chan Zhou Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data Non-Coding RNA lncRNA machine learning RNA-seq tool unannotated |
| title | Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data |
| title_full | Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data |
| title_fullStr | Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data |
| title_full_unstemmed | Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data |
| title_short | Flnc: Machine Learning Improves the Identification of Novel Long Noncoding RNAs from Stand-Alone RNA-Seq Data |
| title_sort | flnc machine learning improves the identification of novel long noncoding rnas from stand alone rna seq data |
| topic | lncRNA machine learning RNA-seq tool unannotated |
| url | https://www.mdpi.com/2311-553X/8/5/70 |
| work_keys_str_mv | AT zixiuli flncmachinelearningimprovestheidentificationofnovellongnoncodingrnasfromstandalonernaseqdata AT pengzhou flncmachinelearningimprovestheidentificationofnovellongnoncodingrnasfromstandalonernaseqdata AT euijinkwon flncmachinelearningimprovestheidentificationofnovellongnoncodingrnasfromstandalonernaseqdata AT katherineafitzgerald flncmachinelearningimprovestheidentificationofnovellongnoncodingrnasfromstandalonernaseqdata AT zhipingweng flncmachinelearningimprovestheidentificationofnovellongnoncodingrnasfromstandalonernaseqdata AT chanzhou flncmachinelearningimprovestheidentificationofnovellongnoncodingrnasfromstandalonernaseqdata |