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

Optimizing long intrinsic disorder predictors with protein evolutionary information.

Kang Peng1, Slobodan Vucetic, Predrag Radivojac

  • 1Center for Information Science and Technology, Temple University, Philadelphia, PA 19122, USA.

Journal of Bioinformatics and Computational Biology
|March 8, 2005
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

Highly Compressible Si<sub>3</sub>N<sub>4</sub> Nanowire Aerogels with Thermal Stability up to 1400 °C.

ACS applied materials & interfaces·2026
Same author

Field assessment of radon exposure in three zirconium and titanium mineral processing plants: radon concentrations, individual progeny concentrations, size distributions, etc.

Radiation protection dosimetry·2026
Same author

Causal relationship between plasma metabolites and chronic regional pain: a Mendelian randomization study.

Metabolism open·2026
Same author

Preparation of radon-free thoron sources based on <sup>228</sup>Th separated from industrial thorium nitrate.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

Targeting FAM83D triggers tumor cell senescence via cGAS-STING signaling activation and reprograms TAMs to combat glioma.

Journal of experimental & clinical cancer research : CR·2026
Same author

CXCL7/CXCR2 in the paraventricular thalamus mediates obesity-related pain.

Journal of neuroinflammation·2026

New neural network models called Predictors Of Natural Disordered Regions (PONDRs) significantly improve the prediction of intrinsically disordered proteins. These advanced PONDRs offer higher accuracy for identifying protein regions lacking specific 3-D structure.

Area of Science:

  • Biochemistry
  • Computational Biology
  • Bioinformatics

Background:

  • Intrinsically disordered proteins (IDPs) exist as an ensemble of structures and perform diverse biological functions.
  • IDPs are prevalent in nature and play crucial roles in various cellular processes.
  • Accurate prediction of disordered protein regions is essential for understanding protein function and regulation.

Purpose of the Study:

  • To develop and evaluate novel neural-network-based predictors for identifying long intrinsically disordered protein regions.
  • To improve the accuracy of sequence-based predictions for disordered protein regions compared to existing methods.
  • To provide freely accessible tools and datasets for the research community.

Main Methods:

  • Development of four new neural-network-based Predictors Of Natural Disordered Regions (PONDRs): VL3, VL3H, VL3P, and VL3E.

Related Experiment Videos

  • PONDR VL3 utilized optimized models and an improved dataset of disordered proteins.
  • PONDR VL3H incorporated homologous protein information, while PONDR VL3P used sequence profiles from PSI-BLAST.
  • PONDR VL3E combined the strengths of VL3H and VL3P.

    • Main Results:

    • The new PONDR predictors demonstrated significantly improved accuracy in predicting disordered protein regions.
    • PONDR VL3 achieved an accuracy of 83.6 +/- 1.4%.
    • PONDR VL3H and VL3P reached accuracies of 85.3 +/- 1.4% and 85.2 +/- 1.5%, respectively.
    • The combined PONDR VL3E achieved a high accuracy of 86.7 +/- 1.4%, outperforming previous PONDRs (VLXT and VL2).

    Conclusions:

    • The newly developed PONDRs, particularly VL3E, represent a substantial advancement in predicting intrinsically disordered protein regions.
    • These predictors offer enhanced accuracy for identifying protein regions lacking specific 3-D structure.
    • The predictors and datasets are available online, facilitating further research in the field of protein disorder.