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

Using structural motif descriptors for sequence-based binding site prediction.

Andreas Henschel1, Christof Winter, Wan Kyu Kim

  • 1Biotechnological Center, TU Dresden, Tatzberg 47-51, Dresden, Germany. ah@biotec.tu-dresden.de

BMC Bioinformatics
|June 30, 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

Serum metabolomic signatures predict clinical outcomes in advanced non-small cell lung cancer treated with pembrolizumab plus platinum-based chemotherapy.

Frontiers in immunology·2026
Same author

Blood plasma and oral rinse liquid profiling for human papillomavirus in head and neck cancer - Unmasking false-positive p16 tissue cases and tracking disease dynamics.

Journal of translational medicine·2026
Same author

Much ado about nothing: modeling amino acid replacement with predicted protein structures.

Bioinformatics (Oxford, England)·2026
Same author

Robotic mini- or less open sublay for anterior abdominal wall hernia repair using the da Vinci single port robotic platform (SP MILOS): a preclinical feasibility study.

Hernia : the journal of hernias and abdominal wall surgery·2026
Same author

Metabolic phenotype and gender may predict treatment outcomes of atezolizumab in extensive-stage small cell lung cancer.

Translational lung cancer research·2025
Same author

The structural basis of drugs targeting protein-protein interactions uncovered with the protein-ligand interaction profiler PLIP.

Expert opinion on drug discovery·2025
Same journal

Model-based quantification of protein-protein interaction aberrations for exploring dysregulated signalling pathways through pathway maps and gene expression levels.

BMC bioinformatics·2026
Same journal

Research on multi-trait genome association study method based on Shannon information entropy.

BMC bioinformatics·2026
Same journal

A multi-view feature fusion framework with interpretable graph convolution for predicting microbe-drug associations.

BMC bioinformatics·2026
Same journal

Covariance decomposition for distance based species tree estimation.

BMC bioinformatics·2026
Same journal

SNPio: a Python interface for population genomic data processing.

BMC bioinformatics·2026
Same journal

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and multi-view contrastive learning.

BMC bioinformatics·2026
See all related articles

This study introduces a novel machine learning approach to predict protein-protein and protein-ligand interactions using sequence data. The method generates effective descriptors for identifying functional sites, complementing existing databases.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • Protein sequence annotation remains a significant challenge in bioinformatics.
  • Identifying protein-protein interactions (PPI) and protein-ligand interactions (PLI) is crucial for functional characterization.
  • Existing methods often lack the ability to predict interactions solely from sequence data.

Purpose of the Study:

  • To develop a machine learning method for predicting PPI and PLI at the sequence level.
  • To utilize 3D structural information to create sequence-based descriptors for interaction sites.
  • To enable the screening of sequence databases for predicting functional sites.

Main Methods:

  • Machine learning was employed to compile sequential segments representing structural features of interaction sites.

Related Experiment Videos

  • Profile Hidden Markov Model (HMM) descriptors were generated for both PPI and PLI.
  • Descriptors were created for 740 PPI types and over 3,000 PLI types.

    • Main Results:

    • Cross-validation indicated that two-thirds of PPI descriptors are conserved and significant for binding site recognition.
    • The method successfully identified interface residues for 230 literature-validated PPIs.
    • For ATP-binding sites, the method achieved 25% recall and 89% precision, outperforming Prosite's P-loop motif (57% precision).
    • 771 novel ATP-binding sites were identified with 96% precision, not previously detected by Prosite patterns.

    Conclusions:

    • Automatically generated descriptors serve as a valuable complement to established Prosite/InterPro motifs.
    • The method accurately predicts protein-protein and protein-ligand interactions, including binding site residues.
    • This approach is particularly useful for proteins with only sequence information available.