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

Descriptor-based protein remote homology identification.

Ziding Zhang1, Sunil Kochhar, Martin G Grigorov

  • 1Nestlé Research Center, BioAnalyti-cal Science, CH-1000 Lausanne 26, Switzerland. Ziding. Zhang@rdls.nestle.com.

Protein Science : a Publication of the Protein Society
|January 6, 2005
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

Interpretable deep learning framework for mapping E3-substrate binding interfaces.

Nature communications·2026
Same author

Structure-guided screening of FAR-1 antagonists with multi-stage anthelmintic activity.

Antimicrobial agents and chemotherapy·2026
Same author

DeepISO: deep learning-powered prediction of protein-protein interaction rewiring generated by alternative splicing.

Genome biology·2026
Same author

OMetaNet: an efficient hybrid deep learning model based on multimodal data fusion and contrastive learning for predicting 2'-O-methylation sites in human RNA.

BMC bioinformatics·2025
Same author

PPEPFinder: A deep learning framework integrating sequence embeddings and structural graph representations for predicting fungal and oomycete effector proteins.

The Plant journal : for cell and molecular biology·2025
Same author

Multi-Omics Blood Atlas Reveals Host Immune Response Features of Immunocompromised Populations Following SARS-CoV-2 Infection.

Molecular & cellular proteomics : MCP·2025
Same journal

Macromolecular crowding inhibits degradation of alpha-synuclein amyloid fibrils induced by cathepsins and MMP9.

Protein science : a publication of the Protein Society·2026
Same journal

Sequence-encoded differences in the conformational ensembles of CITED transcriptional activation domains impact coactivator binding.

Protein science : a publication of the Protein Society·2026
Same journal

The phospholipid biosynthesis enzyme PlsB contains three distinct domains for membrane association, lysophosphatidic acid synthesis, and dimerization.

Protein science : a publication of the Protein Society·2026
Same journal

Structural basis of ligand selectivity in FAD/NAD(P)H-dependent dehydrogenases: insights from trypanothione reductase and type II NADH dehydrogenase.

Protein science : a publication of the Protein Society·2026
Same journal

Achieving protease substrate-specific inhibition by mAb dual functional selections.

Protein science : a publication of the Protein Society·2026
Same journal

How important are quantum mechanical effects in controlling biological functions: Enzymes, electron transfer and bird navigation.

Protein science : a publication of the Protein Society·2026
See all related articles

We developed DescFold, a new method for identifying remote protein homology using sequence descriptors. DescFold improves fold recognition by combining PSI-BLAST, secondary structure, and PROSITE motif data, outperforming existing techniques.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Structural Bioinformatics

Background:

  • Remote homology identification is crucial for understanding protein function and evolution.
  • Existing methods often rely on explicit structural information, limiting their applicability.
  • Developing sequence-based methods is essential for large-scale proteome analysis.

Purpose of the Study:

  • To introduce a novel protein sequence descriptor-based method for remote homology identification.
  • To infer protein fold relationships without requiring explicit structural knowledge.
  • To improve the accuracy and scope of fold recognition algorithms.

Main Methods:

  • Benchmarking 13 different descriptor types for fold identification in diverse protein sequences.

Related Experiment Videos

  • Utilizing similarity measures like cosine angle to relate descriptors to fold class membership.
  • Combining top-performing descriptors (PSI-BLAST e-values, SSEA, PROSITE motifs) into a composite method named DescFold.
  • Employing Support Vector Machine (SVM) learning for class membership prediction.

    • Main Results:

    • Identified PSI-BLAST e-values, secondary structure element alignment (SSEA), and PROSITE functional motifs as top descriptors.
    • The combined DescFold method increased remote homology identification rates from 33.7% to 46.3% compared to individual PSI-BLAST descriptors.
    • DescFold identified true remote homologs for nearly 1 in 6 sequences at 95% confidence, a ~10% improvement over single PSI-BLAST searches.
    • Benchmarking against state-of-the-art algorithms on LiveBench-8 targets showed DescFold provided confident hits for ~10% of sequences missed by other methods.

    Conclusions:

    • DescFold offers a significant advancement in sequence-based remote homology identification.
    • The method effectively infers fold relationships without explicit structural data.
    • DescFold complements existing techniques, enhancing the identification of distantly related proteins.