Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Distinguishing protein-coding from non-coding RNAs through support vector machines.

Jinfeng Liu1, Julian Gough, Burkhard Rost

  • 1Columbia University Bioinformatics Center, Department of Biochemistry and Molecular Biophysics, Columbia University, New York, New York, United States of America. JL840@columbia.edu

Plos Genetics
|May 10, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

Advances in Protein Function Prediction from the Fifth CAFA Challenge.

bioRxiv : the preprint server for biology·2026
Same author

Whole-genome prediction of bacterial pathogenic capacity on novel bacteria using protein language models with PathogenFinder2.

Bioinformatics (Oxford, England)·2026
Same author

Biocentral: Embedding-based Protein Predictions.

Journal of molecular biology·2026
Same author

Toxin data quality: a critical examination of bacterial exotoxins and animal toxins.

BMC research notes·2025
Same author

FlatProt: 2D visualization eases protein structure comparison.

BMC bioinformatics·2025
Same journal

Genetic survey of biomarkers at early and mid-pregnancy identifies pregnancy-specialized immune regulation.

PLoS genetics·2026
Same journal

Argonaute proteins orchestrate Meiotic Sex Chromosome Inactivation and timing of the spermatogenic transcriptional program.

PLoS genetics·2026
Same journal

Genome wide association study meta-analysis of neuropathologic lesions of Alzheimer's disease and related dementias in a multi-site autopsy cohort.

PLoS genetics·2026
Same journal

Microtubule stiffening by the doublecortin-domain protein ZYG-8 contributes to mitotic spindle orientation during zygote division in Caenorhabditis elegans.

PLoS genetics·2026
Same journal

Multiple instance fine-mapping: Predicting causal regulatory variants with a deep sequence model.

PLoS genetics·2026
Same journal

Nuclear ubiquitin-conjugating enzyme TrUbc4 and F-box protein TrFwd1-mediated modification of Cre1 in Trichoderma reesei establishes a regulatory mechanism for carbon catabolite repression.

PLoS genetics·2026
See all related articles

A new computational method, CONC, accurately distinguishes protein-coding RNA from non-coding RNA (ncRNA). This tool is crucial for understanding the transcriptome and identifying novel ncRNAs, with applications in transcript annotation.

Area of Science:

  • Genomics
  • Bioinformatics
  • Molecular Biology

Background:

  • Transcriptome studies, including RIKEN's FANTOM project, have identified numerous novel coding and non-coding RNA (ncRNA) sequences.
  • ncRNAs play critical cellular roles, making their accurate identification essential for transcriptome annotation.
  • Existing in silico methods for distinguishing coding from non-coding transcripts are limited.

Purpose of the Study:

  • To develop and validate a novel computational method for classifying RNA transcripts as either coding or non-coding.
  • To accurately differentiate protein-coding RNA from ncRNA using sequence and feature-based analysis.

Main Methods:

  • Introduction of CONC (coding or non-coding), a support vector machine-based method.
  • Classification based on features of potential protein products: peptide length, amino acid composition, secondary structure, exposed residues, entropy, homology, and alignment entropy.

Related Experiment Videos

  • Incorporation of nucleotide frequencies.
  • Training and validation using confirmed coding cDNAs from Swiss-Prot and ncRNAs from RNAdb and NONCODE.

    • Main Results:

    • CONC achieved high performance in distinguishing coding from non-coding RNAs, with 97% specificity and 98% sensitivity via ten-fold cross-validation.
    • Application to the FANTOM3 dataset (102,801 mouse cDNAs) identified over 14,000 ncRNAs.
    • Estimation of the total number of ncRNAs in the FANTOM3 dataset to be approximately 28,000.

    Conclusions:

    • CONC is a reliable and accurate computational tool for classifying RNA transcripts.
    • The method significantly aids in the identification and annotation of non-coding RNAs within large transcriptomic datasets.
    • This work contributes to a deeper understanding of the complexity and functional landscape of the transcriptome.