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 Video

Updated: Oct 26, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.1K

xDeep-AcPEP: Deep Learning Method for Anticancer Peptide Activity Prediction Based on Convolutional Neural Network

Jiarui Chen1, Hong Hin Cheong1, Shirley W I Siu1,2

  • 1Department of Computer and Information Science, University of Macau, Avenida da Universidade, Taipa, Macau 999078, China.

Journal of Chemical Information and Modeling
|July 30, 2021
PubMed
Summary

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

Plant Fungal Endophytes as Sustainable Components of Insect Pest Management.

Current microbiology·2026
Same author

Allelopathic Activity of Ginseng-Cultivated Soil: Extracts on Seed Germination and Growth of Five Vegetables in China.

Plants (Basel, Switzerland)·2026
Same author

Endoscopic-Assisted Posterior Atlantoaxial Fusion: Technical Innovation and Clinical Experience.

Orthopaedic surgery·2026
Same author

Machine Learning-Based Identification and Validation of PYCR1 and PYGM as Prognostic Biomarkers for Osteosarcoma.

Clinical Medicine Insights. Oncology·2026
Same author

MEGCAM: MEta-Graph and Causal Attention Method for Drug Repurposing on Heterogeneous Drug-Target-Disease Knowledge Network.

Journal of chemical information and modeling·2026
Same author

Later Menopause Confers No Additional Protection Against Osteoporosis in Older Women.

Endocrine connections·2026

This study introduces xDeep-AcPEP, a deep learning method for predicting anticancer peptide activity against six cancer types. The model aids in designing effective peptides, offering a promising alternative to conventional cancer therapies.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Drug Discovery

Background:

  • Cancer remains a leading global cause of death, with conventional treatments like chemotherapy and radiotherapy causing significant side effects due to damage to normal cells.
  • Anticancer peptides (ACPs) show promise as targeted therapeutic agents with high efficiency and selectivity against tumor cells.

Purpose of the Study:

  • To develop a deep learning model using convolutional neural networks for predicting the biological activity of ACPs against six major cancer types (breast, colon, cervix, lung, skin, prostate).
  • To evaluate the performance of multitask learning models compared to single-task models and assess model interpretability.

Main Methods:

  • A deep learning approach employing convolutional neural networks (CNNs) was utilized for predicting biological activity (EC50, LC50, IC50, LD50).

Related Experiment Videos

Last Updated: Oct 26, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.1K
  • Multitask learning models were compared against single-task models using 5-fold cross-validation on the CancerPPD dataset.
  • Feature importance weights from convolutional layers were used to infer residue contributions to predicted activity.

    • Main Results:

    • Multitask learning models demonstrated superior performance over single-task models.
    • The best models, with defined applicability domains, achieved a mean squared error of 0.1758, Pearson's correlation coefficient of 0.8086, and Kendall's correlation coefficient of 0.6156.
    • The method, xDeep-AcPEP, provides insights into residue-level contributions to ACP activity.

    Conclusions:

    • The developed deep learning method, xDeep-AcPEP, effectively predicts ACP biological activity, aiding in the rational design of novel anticancer therapeutics.
    • This approach offers a valuable tool for identifying potent ACPs, potentially leading to more selective and less toxic cancer treatments.