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...

You might also read

Related Articles

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

Sort by

Same author

A perspective and demonstration of an approach to screening synthetic nucleic acid orders containing short nucleic acid sequences.

Frontiers in bioengineering and biotechnology·2026

Same author

Beyond sequence similarity: toward function-based screening of nucleic acid synthesis.

Frontiers in bioengineering and biotechnology·2026

Same author

Engineering Enantiocomplementary Protoglobins for Stereoconvergent Construction of <i>N</i>-Alkylated α-Aminoketones.

Journal of the American Chemical Society·2026

Same author

A Chemoselective and Stereodivergent Platform of Heme-Nitrene Transferases to Access Chiral Aryl-β-Amino Esters and An Investigation of the Sequence-Activity Landscape.

Angewandte Chemie (International ed. in English)·2026

Same author

Verifiably stable nonlinear control with reinforcement-learned diffractive optical networks.

Optics express·2026

Same author

Sequence-based generative AI design of versatile tryptophan synthases.

Nature communications·2026

Same journal

Glycoform engineering of a mammalian platform to sculpt a humanized recombinant bioscavenger.

Cell systems·2026

Same journal

Targeted genomic editing of human gut Bacteroides species based on CRISPR-associated transposases.

Cell systems·2026

Same journal

Scalable enumeration and sampling of minimal metabolic pathways for organisms and communities.

Cell systems·2026

Same journal

Deciphering protein mutation-phenotype linkages from CRISPR-based tiling mutagenesis screens.

Cell systems·2026

Same journal

High-throughput machine learning-aided antibody discovery for cell surface antigens.

Cell systems·2026

Same journal

Quantitative cytokine profiling of primary human macrophages reveals distinct single-cell modes of trained immunity.

Cell systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 23, 2025

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

Informed training set design enables efficient machine learning-assisted directed protein evolution.

Bruce J Wittmann¹, Yisong Yue², Frances H Arnold³

¹Division of Biology and Biological Engineering, California Institute of Technology, MC 210-41, 1200 E. California Blvd., Pasadena, CA 91125, USA.

|August 20, 2021

Summary

This summary is machine-generated.

This study introduces a machine learning-assisted directed evolution (MLDE) protocol for protein engineering. The optimized MLDE protocol efficiently identifies optimal protein variants by screening full combinatorial libraries, overcoming limitations of traditional greedy methods.

Keywords:

combinatorial mutagenesis directed evolution epistasis fitness landscape machine learning protein engineering zero-shot prediction

More Related Videos

Mutagenesis and Functional Selection Protocols for Directed Evolution of Proteins in E. coli

Mutagenesis and Functional Selection Protocols for Directed Evolution of Proteins in E. coli

Published on: March 16, 2011

Directed Evolution Method in Saccharomyces cerevisiae: Mutant Library Creation and Screening

Directed Evolution Method in Saccharomyces cerevisiae: Mutant Library Creation and Screening

Published on: April 1, 2016

Related Experiment Videos

Last Updated: Oct 23, 2025

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

Mutagenesis and Functional Selection Protocols for Directed Evolution of Proteins in E. coli

Mutagenesis and Functional Selection Protocols for Directed Evolution of Proteins in E. coli

Published on: March 16, 2011

Directed Evolution Method in Saccharomyces cerevisiae: Mutant Library Creation and Screening

Directed Evolution Method in Saccharomyces cerevisiae: Mutant Library Creation and Screening

Published on: April 1, 2016

Area of Science:

Protein Engineering
Computational Biology
Machine Learning in Biochemistry

Background:

Traditional directed evolution relies on stepwise greedy optimization, which is path-dependent and can get trapped in local optima.
Identifying beneficial mutations in a specific order limits the efficiency of protein engineering.
Screening full combinatorial libraries for protein variants is computationally challenging.

Purpose of the Study:

To develop and optimize a path-independent machine learning-assisted directed evolution (MLDE) protocol.
To enable in silico screening of full combinatorial protein libraries for enhanced protein engineering.
To identify key factors influencing MLDE performance, including encoding strategies, training procedures, models, and training set design.

Main Methods:

Investigated various protein encoding strategies, machine learning models, and training procedures for MLDE.
Developed strategies to minimize the inclusion of uninformative "holes" (variants with near-zero fitness) in training data.
Evaluated the optimized MLDE protocol on an epistatic, hole-filled, four-site combinatorial fitness landscape.

Main Results:

The optimized MLDE protocol demonstrated superior performance compared to single-step greedy optimization.
Achieved the global fitness maximum up to 81-fold more frequently than traditional greedy methods.
Identified that reducing "holes" in training data is crucial for effective MLDE.

Conclusions:

Machine learning-assisted directed evolution offers a powerful, path-independent alternative to conventional greedy approaches in protein engineering.
Optimized MLDE protocols can significantly enhance the efficiency and success rate of identifying high-fitness protein variants.
Careful training data curation, specifically addressing "holes," is essential for maximizing MLDE efficacy.