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 experimental properties of proteins from sequence by machine learning techniques.

Pawel Smialowski1, Antonio J Martin-Galiano, Jürgen Cox

  • 1Department of Genome Oriented Bioinformatics, Technische Universität München, Wissenschaftszentrum Weihenstephan, 85350 Freising, Germany.

Current Protein & Peptide Science
|April 14, 2007
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

Proteomic analysis of dental enamel from 20 Homo naledi individuals shows no male markers.

Cell·2026
Same author

From mechanism to substratome: unraveling mysteries of γ-secretase.

The Journal of biological chemistry·2026
Same author

KpFhaB/FhaC is a virulence-associated TPS system of the globally-disseminated <i>Klebsiella pneumoniae</i> ST15 high-risk clone.

Frontiers in cellular and infection microbiology·2026
Same author

Improved Peptide Search for Identification of SUMO and Sequence-Based Modifiers, in MaxSBM.

Molecular & cellular proteomics : MCP·2026
Same author

Refractory giardiasis: Exploring the contribution of bacterial community shifts.

Travel medicine and infectious disease·2026
Same author

Bimodal Peptide Collision Cross Section Distribution Reflects Two Stable Conformations in the Gas Phase.

Journal of proteome research·2026

Predicting protein experimental success is crucial for structural genomics. Machine learning algorithms improve target selection, enhancing efficiency and reducing costs in protein structure determination.

Area of Science:

  • Structural biology
  • Bioinformatics
  • Computational biology

Background:

  • High-throughput structural genomics requires efficient target selection to maximize success rates and minimize costs.
  • Sequence-based prediction methods are essential for identifying experimentally tractable proteins and filtering difficult targets early in the pipeline.
  • Machine learning algorithms are increasingly replacing simpler empirical rules for predicting protein experimental success.

Purpose of the Study:

  • To review methods for predicting experimental success in protein cloning, expression, purification, and crystallization.
  • To highlight publicly available resources for target selection in structural genomics.
  • To discuss experimental data repositories and machine learning techniques for classification and feature selection.

Main Methods:

Related Experiment Videos

  • Review of sequence-based prediction methods, focusing on machine learning algorithms.
  • Analysis of experimental success and failure data from structural genomics consortia.
  • Description of automated feature selection techniques for improved classification.
  • Summary of publicly available resources and data repositories.

Main Results:

  • Machine learning algorithms offer superior classification power compared to simpler methods.
  • Current solubility prediction methods achieve over 70% accuracy.
  • Automated feature selection provides insights into sequence-outcome correlations.
  • A growing corpus of experimental data enhances classifier quality.

Conclusions:

  • Rigorous machine learning approaches are vital for advancing structural genomics target selection.
  • Predictive models are crucial for optimizing experimental workflows and resource allocation.
  • Continued development and application of these methods will increase the efficiency of structural biology research.