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: Jul 14, 2026

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

NeuroPpred-PSCG: A Multimodal Framework Using ProtT5 and Structural Features for Neuropeptide Prediction Based on

Shengli Zhang1, Xinyi Zhang1

  • 1School of Mathematics and Statistics, Xidian University, Xi'an 710071, P. R. China.

Journal of Chemical Information and Modeling
|July 13, 2026
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

AIP-TranLAC: A Transformer-Based Method Integrating LSTM and Attention Mechanism for Predicting Anti-inflammatory Peptides.

Interdisciplinary sciences, computational life sciences·2025
Same author

AACFlow: an end-to-end model based on attention augmented convolutional neural network and flow-attention mechanism for identification of anticancer peptides.

Bioinformatics (Oxford, England)·2024
Same author

Efficient photo-driven ion pump through slightly reduced vertical graphene oxide membranes.

Dalton transactions (Cambridge, England : 2003)·2023
Same author

Efficacy and safety of XELOX combined with anlotinib and penpulimab vs XELOX as an adjuvant therapy for ctDNA-positive gastric and gastroesophageal junction adenocarcinoma: a protocol for a randomized, controlled, multicenter phase II clinical trial (EXPLORING study).

Frontiers in immunology·2023
Same author

Conjugated Polymer Composite Nanoparticles Augmenting Photosynthesis-Based Light-Triggered Hydrogel Promotes Chronic Wound Healing.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2023
Same author

Br-Doped BiOCl Nanosheet Exposed (001) Facet: Surface Oxygen Vacancy and Directed Electron Flow Boosting the Photocatalytic Performance.

Langmuir : the ACS journal of surfaces and colloids·2023

This study introduces NeuroPpred-PSCG, a deep learning tool for accurately identifying neuropeptides, which are crucial signaling molecules. The new framework significantly improves detection accuracy for neurological and metabolic disorder-related peptides.

Area of Science:

  • Biochemistry
  • Bioinformatics
  • Computational Biology

Background:

  • Neuropeptides are vital signaling molecules regulating physiological processes.
  • Aberrant neuropeptide expression is linked to neurological and metabolic disorders.
  • Accurate and rapid identification of neuropeptides is crucial for disease research.

Purpose of the Study:

  • To develop a novel multimodal deep learning framework, NeuroPpred-PSCG, for precise neuropeptide identification.
  • To integrate global semantic information from protein language models with local conformational data.
  • To enhance the accuracy and efficiency of neuropeptide detection.

Main Methods:

  • Developed NeuroPpred-PSCG, a multimodal deep learning framework.
  • Utilized a bidirectional cross-attention mechanism and gated fusion module for data integration.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jul 14, 2026

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

  • Employed a multiscale gated convolutional network for hierarchical contextual information extraction.
  • Integrated protein language model (ProtT5) insights with secondary structure data.

    • Main Results:

    • NeuroPpred-PSCG achieved high performance on an independent test set, with ACC of 94.8%, SN of 95.1%, F1-score of 94.8%, and MCC of 0.896.
    • Outperformed leading methods, including NeuroPpred-MSN, showing significant improvements in sensitivity (SN) by 2.8%.
    • Ablation studies, robustness, and interpretability analyses confirmed the framework's effectiveness and stability.

    Conclusions:

    • NeuroPpred-PSCG offers a robust and interpretable method for neuropeptide identification.
    • The framework demonstrates superior performance compared to existing methods.
    • The developed tool has significant implications for understanding and diagnosing neuropeptide-related disorders.