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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Interpretable Deep Learning Framework Leveraging RNA Foundation Model and Capsule Networks for Accurate Prediction of RNA 2'-O-Methylation Sites.

Journal of chemical information and modeling·2026
Same author

EnAcrPred: A robust ensemble machine learning framework for identifying anti-CRISPR proteins.

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

Dynamics of the SS Loop Regulates SARM1's Catalysis.

ACS chemical neuroscience·2026
Same author

DeepOTG: An effective deep learning framework for identifying human protein O-linked threonine glycosylation sites via attention-based information bottleneck.

International journal of biological macromolecules·2026
Same author

Contrastive representation learning and capsule networks enable accurate identification of ferroptosis-related proteins.

Journal of cheminformatics·2026
Same author

CrossLinker: Aligning Relational and Sequential Contexts for Drug-Target Interaction Prediction in Cold-Start and Few-Shot Scenarios.

Journal of chemical information and modeling·2026

Related Experiment Video

Updated: Jul 25, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K

StackTHPred: Identifying Tumor-Homing Peptides through GBDT-Based Feature Selection with Stacking Ensemble

Jiahui Guan1, Lantian Yao2,3, Chia-Ru Chung2

  • 1School of Medicine, The Chinese University of Hong Kong (Shenzhen) 2001 Longxiang Road, Shenzhen 518172, China.

International Journal of Molecular Sciences
|June 28, 2023
PubMed
Summary
This summary is machine-generated.

A new machine learning model, StackTHPred, accurately predicts tumor-homing peptides (THPs) for targeted cancer therapy. This computational approach accelerates the identification of THPs, improving drug specificity and reducing side effects in cancer treatment.

Keywords:
feature selectionsequence analysisstacking architecturetumor-homing peptide

More Related Videos

A Rapid Screening Workflow to Identify Potential Combination Therapy for GBM using Patient-Derived Glioma Stem Cells
05:29

A Rapid Screening Workflow to Identify Potential Combination Therapy for GBM using Patient-Derived Glioma Stem Cells

Published on: March 28, 2021

2.8K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

811

Related Experiment Videos

Last Updated: Jul 25, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K
A Rapid Screening Workflow to Identify Potential Combination Therapy for GBM using Patient-Derived Glioma Stem Cells
05:29

A Rapid Screening Workflow to Identify Potential Combination Therapy for GBM using Patient-Derived Glioma Stem Cells

Published on: March 28, 2021

2.8K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

811

Area of Science:

  • Computational biology
  • Drug discovery
  • Oncology

Background:

  • Limited targeting specificity of current anti-cancer drugs is a major challenge.
  • Tumor-homing peptides (THPs) offer improved specificity by binding to tumor tissues.
  • Experimental identification of THPs is time-consuming and complex.

Purpose of the Study:

  • To develop a novel machine learning framework, StackTHPred, for predicting tumor-homing peptides (THPs).
  • To enhance the efficiency and accuracy of THP identification for cancer therapy development.

Main Methods:

  • Proposed StackTHPred, a machine learning framework utilizing optimal features and a stacking architecture.
  • Employed an effective feature selection algorithm and three tree-based machine learning algorithms.
  • Validated performance on main and small datasets.

Main Results:

  • StackTHPred achieved high accuracy (0.915 on main, 0.883 on small dataset) and MCC scores (0.831 on main, 0.767 on small dataset).
  • Demonstrated superior performance compared to existing THP prediction methods.
  • Offered favorable interpretability for understanding THP characteristics.

Conclusions:

  • StackTHPred is a powerful computational tool for exploring and identifying THPs.
  • Facilitates the development of innovative and targeted cancer therapies.
  • Accelerates the discovery of novel peptides for improved drug delivery and efficacy.