Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

DeepDPM: A Deep Learning Method for MoRFs Prediction Based on Wavelet Transform and Dynamic Convolutional Attention

Huaiyang Sun¹, Lun Zhu¹, Yan Wang²

¹School of Computer Science and Artificial Intelligence, Aliyun School of Big Data, School of Software, Changzhou University, Changzhou 213164, China.

Journal of Chemical Information and Modeling

|July 8, 2026

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

UniPTMs: a unified multi-type PTM site prediction model via master-slave architecture-based multi-stage fusion strategy and hierarchical contrastive loss.

BMC bioinformatics·2026

Same author

NphosNet: Predicting Protein N-Phosphorylation Sites via xLSTM and Enhanced PLM Features with a Weighted Three-Channel Cross-Attention Mechanism.

Interdisciplinary sciences, computational life sciences·2026

Same author

stMixer for Scalable Mosaic Integration and Label Transfer in Spatial Histology and Multi-Omics.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Integrated transcriptomic analysis identifies liver aging-driven fibrosis signatures and reveals therapeutic strategies based on medicine-food homology.

NPJ science of food·2026

Same author

An SE(3)-equivariant and dynamic multi-modal engine advancing from PTM site prediction to network understanding.

Communications chemistry·2026

Same author

IALA-LNN: Deep Learning for Peptide Retention Time Prediction Based on Improved Artificial Lemming Algorithm-Optimized Liquid Neural Networks.

Journal of chemical information and modeling·2026

Same journal

Graph-Based Generation and Reduction of Complex Chemical Reaction Networks.

Journal of chemical information and modeling·2026

Same journal

Modeling the Sensitivity of Large-Scale Virtual Screening to Scoring Function Accuracy, Artifacts, and Library Composition.

Journal of chemical information and modeling·2026

Same journal

Machine Learning-Driven Discovery of Indole/Oxoindole-Piperazine Scaffolds as Dual MAO-B/Sig-1R Ligands for Neurodegenerative Disorders.

Journal of chemical information and modeling·2026

Same journal

Mapping Evolution of Molecules across Biochemistry with Assembly Theory.

Journal of chemical information and modeling·2026

Same journal

Structural Proteomics-Based Deciphering of Hydrophobic Packing Fingerprints Informing Protein Thermostability in TIM Barrels.

Journal of chemical information and modeling·2026

Same journal

Bridging between Structure-Based and Data-Driven Affinity Prediction.

Journal of chemical information and modeling·2026

See all related articles

This summary is machine-generated.

DeepDPM enhances molecular recognition feature (MoRF) analysis by integrating advanced deep learning modules. This novel framework improves protein function prediction and disease association studies with superior accuracy and robustness.

Area of Science:

Computational Biology
Bioinformatics
Machine Learning

Background:

Molecular recognition features (MoRFs) are crucial in biological processes and disease.
Existing MoRF prediction methods struggle with multisource feature integration and contextual dependency.
There is a need for robust and accurate MoRF identification frameworks.

Purpose of the Study:

To introduce DeepDPM, a novel deep learning framework for enhanced MoRF prediction.
To address limitations in multisource feature modeling, contextual dependency capture, and feature fusion.
To improve the accuracy and robustness of MoRF identification for biological and disease-related studies.

Main Methods:

Utilized Prot-T5 and ESM-2 as protein sequence feature extractors.

Related Experiment Videos

Developed four novel modules: BioWaveKAN, DCAttention, BiLCrossAttention, and MultiScaleSmoothing.

Refined Focal Loss with label smoothing and temperature scaling to handle class imbalance.

Main Results:

DeepDPM achieved a Matthews Correlation Coefficient (MCC) of 0.7739 and an Area Under the Curve (AUC) of 0.9760 on the Test1 dataset.
Demonstrated relative improvements of 8.68% (MCC) and 4.75% (AUC) over the best baseline.
The framework exhibited high accuracy and robustness in MoRF prediction.

Conclusions:

DeepDPM offers a significant advancement in MoRF prediction accuracy and robustness.
The framework shows broad potential for applications in protein function analysis and disease research.
The developed methods provide a strong foundation for future MoRF identification studies.