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

Related Concept Videos

Peptide Identification Using Tandem Mass Spectrometry

Peptide Identification Using Tandem Mass Spectrometry

Tandem mass spectrometry, also known as MS/MS or MS2, is an analytical technique that employs two mass analyzers. Essentially it is a series of mass spectrometers that helps isolate a particular biomolecule and then helps study its chemical properties.
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...

You might also read

Related Articles

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

Sort by

Same author

Discovery of novel Kir4.1 inhibitors based on serdemetan with potential therapy for glioblastoma-depression comorbidity.

Pharmaceutical science advances·2026

Same author

Extreme-Thickness Meta-Membrane for Controlling Terahertz Vectorial Beams.

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

Same author

Impact of coronavirus disease 2019 nonpharmaceutical interventions on influenza epidemiology: A retrospective analysis in Hebei Province, China from 2019 to 2023.

The Journal of international medical research·2026

Same author

Impact of liuwei dihuang pills (decoction) on early diabetic nephropathy: a systematic review and meta-analysis.

Frontiers in medicine·2026

Same author

Inverting a new hydrogen map on the moon derived from Chang'E-2 gamma-ray spectrum data.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026

Same author

Prototype-Based Multi-Dimension Intensity Mapping Density Sampling Network for Corrosion Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Search research articles

Related Experiment Video

Updated: Aug 4, 2025

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

UniDL4BioPep: a universal deep learning architecture for binary classification in peptide bioactivity.

Zhenjiao Du¹, Xingjian Ding², Yixiang Xu³

¹Department of Grain Science and Industry, Kansas State University, Manhattan, KS 66506, USA.

Briefings in Bioinformatics

|April 6, 2023

Summary

UniDL4BioPep simplifies bioactive peptide discovery by using pretrained language models for efficient binary classification. This deep learning approach enhances prediction accuracy, reducing experimental workload.

Keywords:

bioactive peptide deep learning protein language model protein sequence classification universal architecture

More Related Videos

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Detection of Protein Ubiquitination Sites by Peptide Enrichment and Mass Spectrometry

Detection of Protein Ubiquitination Sites by Peptide Enrichment and Mass Spectrometry

Published on: March 23, 2020

Related Experiment Videos

Last Updated: Aug 4, 2025

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Detection of Protein Ubiquitination Sites by Peptide Enrichment and Mass Spectrometry

Detection of Protein Ubiquitination Sites by Peptide Enrichment and Mass Spectrometry

Published on: March 23, 2020

Area of Science:

Computational biology
Bioinformatics
Machine learning in drug discovery

Background:

Predicting potent peptides computationally can significantly reduce experimental efforts.
Traditional model building for peptide prediction is complex, time-consuming, and faces challenges in representation, feature selection, and hyperparameter tuning.
Recent advancements in deep learning-based language models (LMs) offer powerful protein sequence embedding for various prediction tasks.

Purpose of the Study:

To develop a universal deep-learning model architecture, UniDL4BioPep, for efficient bioactive peptide binary classification using transfer learning.
To leverage pretrained biological language models for peptide embeddings to predict bioactivities.
To provide a user-friendly tool for novel bioactive peptide discovery.

Main Methods:

Developed UniDL4BioPep, a deep learning model architecture integrating pretrained biological language models with convolutional neural networks.
Utilized transfer learning for bioactive peptide binary classification.
Evaluated model performance on large-scale bioactivity datasets and validated using uniform manifold approximation and projection analysis.

Main Results:

UniDL4BioPep achieved superior performance compared to state-of-the-art models in 15 out of 20 bioactivity prediction tasks.
Demonstrated significant improvements in accuracy (0.7-7%), Mathews correlation coefficient (1.23-26.7%), and area under the curve (0.3-25.6%).
Successfully utilized pretrained biological LMs for peptide embeddings, a novel approach for bioactivity prediction.

Conclusions:

UniDL4BioPep offers a high-performance, efficient solution for bioactive peptide discovery through advanced deep learning.
The model's architecture and transfer learning capabilities facilitate accurate binary classification of peptide bioactivities.
A web server and open-source code are available, promoting accessibility and further research in the field.