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 protein function by machine learning on amino acid sequences--a critical evaluation.

Ali Al-Shahib1, Rainer Breitling, David R Gilbert

  • 1Biomedical Informatics Signals and Systems Research Laboratory, Department of Electronic, Electrical and Computer Engineering, The University of Birmingham, Birmingham, UK. a.alshahib@bham.ac.uk

BMC Genomics
|March 22, 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

Graph neural networks can predict ketosynthase substrate specificity.

Scientific reports·2026
Same author

Exploring the biotechnological potential of terrestrial hot spring microbiomes for CO<sub>2</sub> utilisation.

Environmental microbiome·2026
Same author

Beyond nature: in vivo production of natural product analogues through programmed biosynthetic pathways.

Current opinion in biotechnology·2026
Same author

Synteny plot quality control with SyntenyQC.

Bioinformatics (Oxford, England)·2025
Same author

Engineering microbiomes for natural product discovery and production.

Natural product reports·2025
Same author

Engineering Streptomyces coelicolor for heterologous expression of the thiopeptide GE2270A-A cautionary tale.

Journal of industrial microbiology & biotechnology·2025

Machine learning can predict protein function from amino acid sequences, even for unknown proteins. Classifiers trained on known proteins generalize well across different species and proteomes.

Area of Science:

  • Computational biology
  • Bioinformatics
  • Machine learning in biology

Background:

  • Predicting protein function from amino acid sequences is a key challenge in post-genomic computational biology.
  • Machine learning classifiers can distinguish between proteins of known functional classes.
  • The transferability of these classifiers to proteins of unknown function, which may have distinct biases, was previously unclear.

Purpose of the Study:

  • To investigate the predictability of protein function using machine learning classifiers.
  • To assess the generalization capability of these classifiers across different species and proteomes.
  • To determine if classifiers trained on known proteins can accurately predict the function of uncharacterized proteins.

Main Methods:

  • Utilized machine learning classifiers to analyze protein amino acid sequences.

Related Experiment Videos

  • Compared the performance of classifiers on proteins with known versus unknown functions.
  • Evaluated the cross-species generalization ability of functional classifiers.
  • Assessed the performance of inter-species classifiers versus species-specific classifiers on specialized proteomes.

    • Main Results:

    • Proteins with known and unknown functions exhibit significant differences.
    • Proteins from different bacterial species show substantial variations, yet functional classifiers generalize across species boundaries.
    • Classifiers from a conventional species may outperform species-specific classifiers for highly specialized proteomes.

    Conclusions:

    • Machine learning classifiers trained on proteins of known function show strong potential for predicting the function of uncharacterized proteins.
    • The generalization ability of these classifiers across species suggests a robust approach to protein function prediction.
    • This study provides a promising computational strategy for advancing post-genomic functional annotation.