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

CONTRAfold: RNA secondary structure prediction without physics-based models.

Chuong B Do1, Daniel A Woods, Serafim Batzoglou

  • 1Computer Science Department, Stanford University, Stanford, CA 94305, USA. chuongdo@cs.stanford.edu

Bioinformatics (Oxford, England)
|July 29, 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

A genome-wide association study of mass spectrometry proteomics using a nanoparticle enrichment platform.

Nature genetics·2025
Same author

Multi-omics analysis of a pig-to-human decedent kidney xenotransplant.

Nature·2025
Same author

Multiplexed Nanoparticle Protein Corona Enables Accurate and Precise Deep Plasma Proteomics.

Journal of proteome research·2025
Same author

Cloud-Enabled Scalable Analysis of Large Proteomics Cohorts.

Journal of proteome research·2025
Same author

Deep, Unbiased, and Quantitative Mass Spectrometry-Based Plasma Proteome Analysis of Individual Responses to mRNA COVID-19 Vaccine.

Journal of proteome research·2025
Same author

A Scaled Proteomic Discovery Study for Prostate Cancer Diagnostic Markers Using Proteograph<sup>TM</sup> and Trapped Ion Mobility Mass Spectrometry.

International journal of molecular sciences·2024
Same journal

Cross-Domain Transfer Learning from Peptides to Metabolites Using a Multi-Property Fine-Tuned LLM.

Bioinformatics (Oxford, England)·2026
Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026
Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026
Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026
Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026
See all related articles

CONTRAfold, a new RNA secondary structure prediction method, uses conditional log-linear models (CLLMs) to achieve state-of-the-art accuracy. This approach outperforms both physics-based and existing probabilistic methods, demonstrating the power of statistical learning.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Structural Biology

Background:

  • Traditional RNA secondary structure prediction relies on free energy minimization and thermodynamic parameters.
  • Stochastic context-free grammars (SCFGs) offer a probabilistic alternative using statistical learning but have lagged in accuracy.
  • A gap exists between the predictive power of physics-based and probabilistic RNA structure modeling methods.

Purpose of the Study:

  • To introduce CONTRAfold, a novel RNA secondary structure prediction method.
  • To demonstrate the superiority of conditional log-linear models (CLLMs) over SCFGs for RNA structure prediction.
  • To achieve state-of-the-art prediction accuracy using a statistical learning approach.

Main Methods:

  • Development of CONTRAfold, a method based on conditional log-linear models (CLLMs).

Related Experiment Videos

  • Utilizing discriminative training and feature-rich scoring within the CLLM framework.
  • Cross-validation experiments to compare CONTRAfold against existing methods.

    • Main Results:

    • CONTRAfold, a CLLM, consistently outperforms SCFG analogs in grammar-based RNA structure prediction.
    • CONTRAfold achieves the highest single-sequence prediction accuracies reported to date.
    • The method surpasses both current probabilistic and physics-based RNA structure prediction techniques.

    Conclusions:

    • Conditional log-linear models (CLLMs) provide a powerful framework for RNA secondary structure prediction.
    • CONTRAfold effectively bridges the accuracy gap between probabilistic and thermodynamic models.
    • Statistical learning offers a viable alternative to empirical thermodynamic parameter measurement for RNA structure prediction.