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

Domain-based small molecule binding site annotation.

Kevin A Snyder1, Howard J Feldman, Michel Dumontier

  • 1The Blueprint Initiative, Toronto ON, M5T 1K4, Canada. ksnyder@blueprint.org

BMC Bioinformatics
|March 21, 2006
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

Enhancing Explainable AI Stability with Realistic Synthetic Data for Cardiovascular Risk Prediction.

Studies in health technology and informatics·2026
Same author

Knowledge graph embedding and alignment of incomplete electronic health records for critical care applications.

Journal of biomedical semantics·2026
Same author

Rule-augmented constraint learning for semantic error detection in MIMIC-III knowledge graph.

International journal of medical informatics·2026
Same author

CMEO: a metadata-centric ontology for clinical studies exploration and harmonization assessment.

BMC medical informatics and decision making·2025
Same author

Privacy preservation in blockchain-based healthcare data sharing: A systematic review.

Peer-to-peer networking and applications·2025
Same author

Radiomics Quality Score 2.0: towards radiomics readiness levels and clinical translation for personalized medicine.

Nature reviews. Clinical oncology·2025
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

The Small Molecule Interaction Database (SMID) predicts small molecule binding sites on proteins using structural data. SMID-BLAST tool accurately identifies potential small molecule ligands and binding sites for any protein sequence.

Area of Science:

  • Biochemistry
  • Structural Biology
  • Bioinformatics

Background:

  • Accurate small molecule binding site information is crucial for drug discovery and protein function prediction.
  • Protein sequence annotation for small molecule binding sites is currently limited.
  • The Small Molecule Interaction Database (SMID) was developed using Protein Data Bank (PDB) structural data to address this gap.

Purpose of the Study:

  • To create a comprehensive database of protein domain-small molecule interactions.
  • To develop a tool (SMID-BLAST) for predicting small molecule binding sites on protein sequences.
  • To improve the accuracy of binding site prediction by mitigating false positives.

Main Methods:

  • Utilized co-crystallized protein-small molecule structures to identify binding domains via NCBI's Reverse Position Specific BLAST (RPS-BLAST) algorithm.

Related Experiment Videos

  • Developed the SMID-BLAST tool to predict small molecule ligands and binding sites for proteins not present in the PDB.
  • Implemented a heuristic ligand score based on E-value, residue identity, and domain entropy for confidence assessment.

    • Main Results:

    • SMID-BLAST predictions were validated against 793 experimental small molecule interactions from the PDB.
    • 60% of predicted interactions perfectly matched experimental data, with 344 showing >80% binding site residue accuracy.
    • An estimated 45% of predictions not found in the PDB validation set may represent true positives.

    Conclusions:

    • SMID effectively clusters interactions and identifies subtle binding patterns by focusing on protein domain-small molecule interactions.
    • SMID-BLAST enables prediction of small molecule targets for any protein sequence, provided the small molecule exists in the PDB.
    • SMID-BLAST demonstrates high accuracy in predicting both small molecule ligands and binding site residue positions.