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

Predicting Disordered Regions from Amino Acid Sequence: Common Themes Despite Differing Structural Characterization.

Garner, Cannon, Romero

    Genome Informatics. Workshop on Genome Informatics
    |November 10, 2000
    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

    Subtle skin changes that suggest severe disease.

    BMJ (Clinical research ed.)·2018
    Same author

    [THE REVISTA ROL CONTRIBUTION TO THE DEVELOPMENT OF SPANISH NURSING].

    Revista de enfermeria (Barcelona, Spain)·2016
    Same author

    Advances in Alliteration in Acute Myocardial Infarction: From "Time to Treatment" to "Onset to Opening"

    Journal of thrombosis and thrombolysis·2001
    Same author

    Protection Conferred by Preinfarct Angina is Manifest in the Aged Heart: Evidence from the TIMI 4 Trial.

    Journal of thrombosis and thrombolysis·2001
    Same author

    The Sequence Attribute Method for Determining Relationships Between Sequence and Protein Disorder.

    Genome informatics. Workshop on Genome Informatics·2000
    Same author

    Predicting Protein Disorder for N-, C-, and Internal Regions.

    Genome informatics. Workshop on Genome Informatics·2000
    Same journal

    MIAX: a system for assessment of macromolecular interaction. 3) A parallel hybrid GA for flexible protein docking.

    Genome informatics. Workshop on Genome Informatics·2001
    Same journal

    A gene network inference method from continuous-value gene expression data of wild-type and mutants.

    Genome informatics. Workshop on Genome Informatics·2001
    Same journal

    Two-phase partition method for simulating a biological system at an extremely high speed.

    Genome informatics. Workshop on Genome Informatics·2001
    Same journal

    Comparing predictors of disordered protein.

    Genome informatics. Workshop on Genome Informatics·2001
    Same journal

    Intrinsic protein disorder in complete genomes.

    Genome informatics. Workshop on Genome Informatics·2001
    Same journal

    Clustering and averaging of images in single-particle analysis.

    Genome informatics. Workshop on Genome Informatics·2001
    See all related articles

    Neural networks predict protein order and disorder from amino acid sequences. Both X-ray crystallography and Nuclear Magnetic Resonance (NMR) spectroscopy data yield similar predictions, suggesting disorder is sequence-dependent.

    Area of Science:

    • Protein bioinformatics
    • Computational biology
    • Structural biology

    Background:

    • Protein structure prediction is crucial for understanding function.
    • Intrinsically disordered proteins lack stable 3D structures.
    • Identifying ordered and disordered regions is key to protein analysis.

    Purpose of the Study:

    • To develop and compare neural network models for predicting protein order and disorder.
    • To assess the generalizability of models trained on different experimental data types (X-ray vs. NMR).
    • To investigate the relationship between amino acid sequence and protein structural states.

    Main Methods:

    • Training neural networks on amino acid sequences linked to ordered/disordered regions.
    • Utilizing data from X-ray crystallography and Nuclear Magnetic Resonance (NMR) spectroscopy.

    Related Experiment Videos

  • Cross-validation and out-of-sample testing between datasets.

    • Main Results:

    • Both X-ray and NMR-trained predictors achieved similar accuracies when tested on each other's data.
    • Disordered regions were consistently identified across predictors regardless of training data type.
    • NMR-trained models showed reduced accuracy on out-of-sample X-ray data compared to cross-validation.
    • X-ray trained models demonstrated consistent performance across validation and out-of-sample NMR data.

    Conclusions:

    • Disordered protein regions represent a distinct, sequence-dependent category.
    • Predictive models trained on different experimental data can be robust but may have limitations.
    • Amino acid sequence is a strong determinant of protein structural disorder.