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

Protein secondary structure prediction using logic-based machine learning.

S Muggleton1, R D King, M J Sternberg

  • 1Turing Institute, Glasgow, UK.

Protein Engineering
|October 1, 1992
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

Xanthine oxidoreductase expression is diminished in breast cancer as a response to uric acid mediated chelation of redox active iron.

Free radical biology & medicine·2025
Same author

Merits of random forests emerge in evaluation of chemometric classifiers by external validation.

Analytica chimica acta·2013
Same author

Prediction of the soluble myoglobin content of cooked burgers.

Meat science·2011
Same author

Effect of muscle type, salt and pH on cooked meat haemoprotein formation in lamb and beef.

Meat science·2011
Same author

The kinetics of cooked meat haemoprotein formation in meat and model systems.

Meat science·2011
Same author

Using a logical model to predict the growth of yeast.

BMC bioinformatics·2008
Same journal

Structure of a human Rhinovirus complexed with its receptor molecule.

Protein engineering·2024
Same journal

pH-responsive polymer-assisted refolding of urea- and organic solvent-denatured alpha-chymotrypsin.

Protein engineering·2004
Same journal

Evaluation of different linker regions for multimerization and coupling chemistry for immobilization of a proteinaceous affinity ligand.

Protein engineering·2004
Same journal

Recombinant porcine intestinal carboxylesterase: cloning from the pig liver esterase gene by site-directed mutagenesis, functional expression and characterization.

Protein engineering·2004
Same journal

Periplasmic expression of human growth hormone via plasmid vectors containing the lambdaPL promoter: use of HPLC for product quantification.

Protein engineering·2004
Same journal

Shift of fibril-forming ability of the designed alpha-helical coiled-coil peptides into the physiological pH region.

Protein engineering·2004
See all related articles

Predicting protein secondary structure is challenging. Inductive Logic Programming using the Golem program improved alpha-helix prediction accuracy to 81% for alpha/alpha domain proteins, outperforming previous methods.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning

Background:

  • Predicting protein secondary structure from primary sequences remains a significant challenge in bioinformatics.
  • Existing methods, including statistical and neural network approaches, have yielded suboptimal performance for certain protein types.

Purpose of the Study:

  • To investigate the effectiveness of Inductive Logic Programming (ILP) for improving protein secondary structure prediction.
  • To apply the Golem ILP program to learn rules for predicting alpha-helices in alpha/alpha domain proteins.

Main Methods:

  • Utilized the Inductive Logic Programming program, Golem, for rule learning.
  • Input data comprised 12 non-homologous proteins with known structures and background knowledge on residue properties.

Related Experiment Videos

  • Learned rules based on positional relationships and chemical/physical properties of amino acid residues.

    • Main Results:

    • Achieved 81% accuracy in predicting alpha-helical residues on four independent test proteins.
    • This represents a significant improvement over previous methods like PROMIS (73%) and Garnier-Osguthorpe-Robson (72%).
    • Outperformed the best reported literature result of 76% for alpha/alpha domain proteins using a neural network.

    Conclusions:

    • Inductive Logic Programming offers a promising approach for enhancing protein secondary structure prediction accuracy.
    • Golem's learned rules provide understandable insights into the factors governing alpha-helix formation.
    • ILP demonstrates a clear advantage over traditional machine learning and statistical methods in this domain.