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

Protein Organization

Protein Organization

Protein Folding

Protein Folding

Protein and Protein Structure

Protein and Protein Structure

Proteins are one of the most abundant organic molecules in living systems and have the most diverse range of functions of all macromolecules. Proteins may be structural, regulatory, contractile, or protective. They may serve in transport, storage, or membranes; or they may be toxins or enzymes. Their structures, like their functions, vary greatly. They are all, however, amino acid polymers arranged in a linear sequence.
A protein's shape is critical to its function. For example, an enzyme...

RNA Structure

RNA Structure

The basic structure of RNA consists of a string of ribonucleotides attached by phosphodiester bonds. Although most RNA is single-stranded, it can form complex secondary and tertiary structures. Such structures play essential roles in the regulation of transcription and translation.
Different Types of RNA Have the Same Basic Structure
There are three main types of ribonucleic acid (RNA) involved in protein synthesis: messenger RNA (mRNA), transfer RNA (tRNA), and ribosomal RNA (rRNA). All three...

Conserved Binding Sites

Conserved Binding Sites

Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

You might also read

Related Articles

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

Sort by

Same author

The Bustelo Bolus: Caffeine Withdrawal Mimicking Status Migrainosus in a Patient With Systemic Lupus Erythematosus and Systemic Sclerosis Overlap.

Cureus·2026

Same author

Timing and Associated Factors to Formation and Detection of Sequestrum in Patients With Medication-Related Osteonecrosis of the Jaw.

Oral diseases·2026

Same author

Cryo-EM structure of the LARS1:IARS1 complex reveals a nutrient-responsive switch controlling mTORC1 signaling.

Nature communications·2026

Same author

Structural variation of the pineal gland in shift workers from neuroimaging evidence.

Chronobiology international·2026

Same author

Impact of unmet needs on health-related quality of life among cancer survivors in Ulsan, Korea.

BMC cancer·2026

Same author

Lymphoid neoplasms and benzene exposure using a revised classification scheme: systematic review and meta-analysis.

Occupational and environmental medicine·2026

Search research articles

Related Experiment Video

Updated: Jul 31, 2025

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

AttSec: protein secondary structure prediction by capturing local patterns from attention map.

Youjin Kim^1,2, Junseok Kwon³

¹Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea.

BMC Bioinformatics

|May 4, 2023

Summary

Accurate protein secondary structure prediction is crucial for understanding protein 3D structures. The novel AttSec model, using transformer architecture and pairwise features, enhances prediction accuracy by capturing local protein patterns without evolutionary information.

Keywords:

2D Convolution Computational biology Protein secondary structure Transformer

More Related Videos

RNA Secondary Structure Prediction Using High-throughput SHAPE

RNA Secondary Structure Prediction Using High-throughput SHAPE

Published on: May 31, 2013

The ITS2 Database

The ITS2 Database

Published on: March 12, 2012

Related Experiment Videos

Last Updated: Jul 31, 2025

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

RNA Secondary Structure Prediction Using High-throughput SHAPE

RNA Secondary Structure Prediction Using High-throughput SHAPE

Published on: May 31, 2013

The ITS2 Database

The ITS2 Database

Published on: March 12, 2012

Area of Science:

Computational Biology
Structural Bioinformatics
Machine Learning in Biology

Background:

Protein secondary structures are vital for describing local protein properties and predicting complex 3D structures.
Accurate prediction of protein secondary structure, defined by hydrogen bond patterns, is essential for understanding protein function.
Existing methods often rely on evolutionary information, limiting their applicability in certain contexts.

Purpose of the Study:

To develop a novel prediction model for accurate protein secondary structure determination.
To capture local protein patterns effectively using a transformer-based architecture.
To evaluate the model's performance without relying on external evolutionary information.

Main Methods:

A novel prediction model, AttSec, based on transformer architecture was developed.
AttSec extracts self-attention maps from pairwise amino acid embedding features.
2D convolution blocks are utilized to capture local patterns from the self-attention maps, using only protein embeddings as input.

Main Results:

AttSec demonstrated superior performance on the ProteinNet DSSP8 dataset, achieving 11.8% better results than other non-evolutionary models.
On the NetSurfP-2.0 DSSP8 dataset, AttSec showed an average performance improvement of 1.2%.
Significant average performance gains of 9.0% and 0.7% were observed on the ProteinNet DSSP3 and NetSurfP-2.0 DSSP3 datasets, respectively.

Conclusions:

The AttSec model accurately predicts protein secondary structures by effectively capturing local protein patterns.
The proposed pairwise feature approach shows a remarkable effect, particularly for tasks requiring finely subdivided classification, as indicated by higher improvements on DSSP8 compared to DSSP3.
The AttSec model provides a valuable tool for protein structure prediction, available at https://github.com/youjin-DDAI/AttSec.