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 Concept Videos

Conservation of Protein Domains Over Different Proteins02:26

Conservation of Protein Domains Over Different Proteins

11.1K
Protein domains are small structurally independent units that are part of a single amino acid chain.  Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
11.1K
Protein Families02:47

Protein Families

3.4K
3.4K
Protein and Protein Structure02:15

Protein and Protein Structure

80.3K
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...
80.3K
Protein and Protein Structures02:15

Protein and Protein Structures

10.7K
10.7K
Protein Networks02:26

Protein Networks

2.4K
2.4K
Protein Complex Assembly02:41

Protein Complex Assembly

10.7K
Proteins can form homomeric complexes with another unit of the same protein or heteromeric complexes with different types.  Most protein complexes self-assemble spontaneously via ordered pathways, while some proteins need assembly factors that guide their proper assembly. Despite the crowded intracellular environment, proteins usually interact with their correct partners and form functional complexes.
Many viruses self-assemble into a fully functional unit using the infected host cell to...
10.7K

You might also read

Related Articles

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

Sort by
Same author

An Episomal Clustered Regularly Interspaced Short Palindromic Repeats/Cas9 System for Transgene-Free Multiplex Gene Editing in Pig Cells.

Biology·2026
Same author

NDGA alleviates oxidative stress and supports early embryonic development in porcine oocytes.

Theriogenology·2026
Same author

Wuji Pill and <i>Akkermansia muciniphila</i> alleviates intestinal dysfunction and depression-like behavior in irritable bowel syndrome through the microbiota-gut-brain axis.

Frontiers in microbiology·2026
Same author

Wuji Wan ameliorates ulcerative colitis by restoring impaired membrane transport.

Frontiers in pharmacology·2026
Same author

Inhibition of SUV39H1 and SUV39H2 promotes zygotic genome activation and improves the developmental competence of porcine somatic cell nuclear transfer embryos.

Theriogenology·2026
Same author

Selectively Inhibition of MAPK pathway showed positive effects on Porcine embryo-derived stem cells pluripotency.

Scientific reports·2025

Related Experiment Video

Updated: Aug 22, 2025

De novo Identification of Actively Translated Open Reading Frames with Ribosome Profiling Data
08:23

De novo Identification of Actively Translated Open Reading Frames with Ribosome Profiling Data

Published on: February 18, 2022

3.7K

Collectively encoding protein properties enriches protein language models.

Jingmin An1,2, Xiaogang Weng3

  • 1School of Life Sciences, Northeast Agricultural University, Harbin, 150030, China.

BMC Bioinformatics
|November 8, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a multi-task learning approach to enhance protein language models by jointly learning protein properties. This method improves performance on downstream tasks like remote homology detection.

Keywords:
Multi-task learningProtein language modelingTransfer learning

More Related Videos

Residue-specific Incorporation of Noncanonical Amino Acids into Model Proteins Using an Escherichia coli Cell-free Transcription-translation System
11:47

Residue-specific Incorporation of Noncanonical Amino Acids into Model Proteins Using an Escherichia coli Cell-free Transcription-translation System

Published on: August 1, 2016

16.1K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

667

Related Experiment Videos

Last Updated: Aug 22, 2025

De novo Identification of Actively Translated Open Reading Frames with Ribosome Profiling Data
08:23

De novo Identification of Actively Translated Open Reading Frames with Ribosome Profiling Data

Published on: February 18, 2022

3.7K
Residue-specific Incorporation of Noncanonical Amino Acids into Model Proteins Using an Escherichia coli Cell-free Transcription-translation System
11:47

Residue-specific Incorporation of Noncanonical Amino Acids into Model Proteins Using an Escherichia coli Cell-free Transcription-translation System

Published on: August 1, 2016

16.1K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

667

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning

Background:

  • Natural language processing (NLP) models can transfer knowledge to protein domains.
  • Enriching protein language models by jointly learning correlated protein tasks is underexplored.

Purpose of the Study:

  • To design a multi-task learning (MTL) architecture for deciphering structural and evolutionary information from protein sequences.
  • To leverage BERT, pre-trained on natural language, as a backbone for protein sequence analysis.

Main Methods:

  • Developed an MTL architecture using BERT for protein sequence encoding.
  • Trained the model on three sequence-level classification tasks: protein family, superfamily, and fold.
  • Evaluated knowledge transfer to downstream tasks, including those in the TAPE benchmark.

Main Results:

  • The MTL approach effectively deciphers implicit structural and evolutionary information.
  • Encoded knowledge demonstrated strong transferability to fine-grained downstream tasks.
  • Outperformed state-of-the-art Transformer-based protein models, particularly in remote homology detection.

Conclusions:

  • The proposed MTL architecture enhances protein language models by integrating diverse protein tasks.
  • This approach offers a robust method for improving predictions in structure- and evolution-related biological applications.