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

Conservation of Protein Domains Over Different Proteins

Conservation of Protein Domains Over Different Proteins

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...

Protein Networks

Protein Networks

Improving Translational Accuracy

Improving Translational Accuracy

Protein-protein Interfaces

Protein-protein Interfaces

Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...

Proteins: From Genes to Degradation

Proteins: From Genes to Degradation

Within a biological system, the DNA encodes the RNA, and the nucleotide sequence in the RNA further defines the amino acid sequence in the protein. This is referred to as “The Central Dogma of Molecular Biology” - a term coined by Francis Crick. Central dogma is a firm principle in biology that defines the flow of genetic information within any life form. The two fundamental steps in central dogma are - transcription and translation.
Transcription is the synthesis of RNA...

Protein-Protein Interfaces

Protein-Protein Interfaces

You might also read

Related Articles

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

Sort by

Same author

Dissecting serum polyclonal antibody escape to SARS-CoV-2 variants by deep mutational learning.

Cell reports methods·2026

Same author

Protein language model pseudolikelihoods capture features of in vivo B cell selection and evolution.

Briefings in bioinformatics·2025

Same author

ClinApp: A Microservices-Based Platform for Efficient Medical Visit Scheduling.

Studies in health technology and informatics·2023

Same author

Towards the Definition of an Intelligent System for Organizing Medical Visits and Collecting Medical Data.

Studies in health technology and informatics·2023

Same author

Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning.

Nature biomedical engineering·2021

Same author

Antibody discovery and engineering by enhanced CRISPR-Cas9 integration of variable gene cassette libraries in mammalian cells.

mAbs·2019

Same journal

K-attention: a biologically informed attention operator for data-efficient sequence-based omics modeling.

Briefings in bioinformatics·2026

Same journal

Accurate prediction of asparagine deamidation in biologics using advanced machine learning models.

Briefings in bioinformatics·2026

Same journal

scImmuneCo: a compendium of cell-type-specific functional modules for decoding immune responses from single-cell RNA-seq data.

Briefings in bioinformatics·2026

Same journal

scGenoByte: a GenoByte embedding transformer with biological priors for cell type annotation.

Briefings in bioinformatics·2026

Same journal

FerroScore: a statistical approach for quantifying tumor-related ferroptosis based on omics data.

Briefings in bioinformatics·2026

Same journal

METEOR: a data-adaptive Mendelian randomization method for powerful detection of shared and specific exposures underlying multiple outcomes.

Briefings in bioinformatics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 13, 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

PLMFit: benchmarking transfer learning with protein language models for protein engineering.

Thomas Bikias^1,2, Evangelos Stamkopoulos^1,2, Sai T Reddy^1,2

¹Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland.

Briefings in Bioinformatics

|July 30, 2025

Summary

This summary is machine-generated.

Protein language models (PLMs) combined with transfer learning (TL) offer powerful protein engineering tools. Our study benchmarks different TL methods, finding fine-tuning (FT) is best for limited data and generalization needs.

Keywords:

benchmarking parameter efficient fine-tuning protein engineering protein fitness protein language models transfer learning

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

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Related Experiment Videos

Last Updated: Sep 13, 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

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

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Area of Science:

Computational biology
Protein engineering
Machine learning in bioinformatics

Background:

Protein language models (PLMs) are valuable for protein engineering.
Transfer learning (TL) enhances PLM performance through feature extraction or fine-tuning (FT).
A lack of comparative analyses hinders optimal TL strategy selection for PLMs.

Purpose of the Study:

To benchmark transfer learning (TL) methods applied to state-of-the-art protein language models (PLMs).
To identify optimal strategies for knowledge transfer in protein engineering tasks.
To determine the most suitable TL approach for specific protein engineering applications.

Main Methods:

Combined three state-of-the-art PLMs (ESM2, ProGen2, ProteinBert) with three TL methods (feature extraction, low-rank adaptation, bottleneck adapters).
Conducted >3150 in silico experiments, varying PLM sizes, layers, TL hyperparameters, and training procedures.
Evaluated performance across five diverse protein engineering datasets.

Main Results:

Utilizing partial PLMs for TL does not significantly impact performance.
The choice between feature extraction (FE) and fine-tuning (FT) depends on data amount and diversity.
FT is most effective for generalization with limited data.

Conclusions:

PLMFit provides a comprehensive benchmark for TL in PLMs.
The study offers guidance on selecting optimal FE or FT strategies for protein engineering.
PLMFit is an open-source resource to facilitate PLM application in the scientific community.