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

You might also read

Related Articles

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

Sort by

Same author

Community-Based Rapid Testing for HIV in Europe and Central Asia: A Narrative Review of Models, Effectiveness, and Implementation Challenges.

Infection and drug resistance·2026

Same author

Structural insights into a conserved mechanism of choline translocation through CHT.

Science advances·2026

Same author

<i>In Silico</i> Optimization of a Bifunctional Lipase-Polyethylene Terephthalate (PET) Hydrolase for Enhanced PET and Lipid Hydrolysis.

Journal of chemical information and modeling·2026

Same author

Polyesterase activity and thermostability of carboxylesterases from Thermoleophilum album YS-3.

The FEBS journal·2026

Same author

Molecular Insights into the Activation of a Fungal Copper Radical Oxidase by Peroxidases.

Chem & bio engineering·2026

Same author

A la carte bioprospecting of substrate-selective laccases via high-throughput computational enzyme-substrate interaction profiling.

Protein science : a publication of the Protein Society·2026

Search research articles

Related Experiment Video

Updated: Aug 23, 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

EP-Pred: A Machine Learning Tool for Bioprospecting Promiscuous Ester Hydrolases.

Ruite Xiang¹, Laura Fernandez-Lopez², Ana Robles-Martín¹

¹Department of Life Sciences, Barcelona Supercomputing Center (BSC), 08034 Barcelona, Spain.

|October 27, 2022

Summary

Researchers developed EP-pred, a novel computational method, to predict enzyme substrate promiscuity from amino acid sequences alone. This accelerates the discovery of versatile industrial ester hydrolases, reducing reliance on costly structural data.

Keywords:

biocatalysts bioprospecting esterases/lipases hydrolases machine learning supervised learning

More Related Videos

The Application of Open Searching-based Approaches for the Identification of Acinetobacter baumannii O-linked Glycopeptides

The Application of Open Searching-based Approaches for the Identification of Acinetobacter baumannii O-linked Glycopeptides

Published on: November 2, 2021

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

Related Experiment Videos

Last Updated: Aug 23, 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

The Application of Open Searching-based Approaches for the Identification of Acinetobacter baumannii O-linked Glycopeptides

The Application of Open Searching-based Approaches for the Identification of Acinetobacter baumannii O-linked Glycopeptides

Published on: November 2, 2021

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

Area of Science:

Enzyme engineering and biocatalysis
Computational biology and bioinformatics
Protein science

Background:

Substrate promiscuity is a key trait for industrial enzymes, enhancing reusability and reducing costs.
Ester hydrolases are in high demand, but identifying promiscuous variants is challenging due to complex active site requirements.
Obtaining 3D protein structures for analysis is often expensive and time-consuming.

Purpose of the Study:

To develop a sequence-based method for predicting substrate promiscuity in ester hydrolases.
To overcome the limitations of structure-based analysis in enzyme discovery.
To facilitate the identification of novel, versatile industrial enzymes.

Main Methods:

Developed EP-pred, an ensemble binary classifier integrating Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and a Linear model.
Utilized machine learning algorithms to predict enzyme promiscuity directly from amino acid sequences.
Validated the method against the Lipase Engineering Database and employed a hidden Markov approach.

Main Results:

EP-pred successfully predicted ten sequences encoding promiscuous esterases.
Experimental validation confirmed that all ten predicted proteins exhibited broad substrate ambiguity.
The study demonstrates the feasibility of predicting enzyme promiscuity from sequence data alone.

Conclusions:

EP-pred offers a cost-effective and efficient approach for bioprospecting novel, substrate-promiscuous ester hydrolases.
The developed method accelerates enzyme discovery by bypassing the need for experimental 3D structure determination.
This sequence-based prediction tool has significant implications for industrial enzyme development and application.