Search research articles

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by

Same author

Identification of drug candidates against glioblastoma with machine learning and high-throughput screening of heterogeneous cellular models.

Digital discovery·2026

Same author

CRISPR-based environmental detection of Burkholderia pseudomallei identifies sanitation gaps and melioidosis risk in northeast Thailand.

Nature communications·2026

Same author

Multiobjective Design of Growth Media with Genome-Scale Metabolic Models and Bayesian Optimization.

Computational and structural biotechnology journal·2026

Same author

Nine changes needed to deliver a radical transformation in biodiversity measurement.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

From data to decisions: Toward a Biodiversity Monitoring Standards Framework.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Accurate prediction of gene deletion phenotypes with Flux Cone Learning.

Nature communications·2025

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

Search research articles

Related Experiment Video

Updated: Aug 17, 2025

Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting

Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting

Published on: April 9, 2019

Accuracy and data efficiency in deep learning models of protein expression.

Evangelos-Marios Nikolados¹, Arin Wongprommoon¹, Oisin Mac Aodha^2,3

¹School of Biological Sciences, University of Edinburgh, Edinburgh, EH9 3JH, UK.

Nature Communications

|December 14, 2022

Summary

Deep learning models for microbial strain optimization require less data than expected. Controlled sequence diversity significantly improves data efficiency, lowering barriers for biotechnology adoption.

More Related Videos

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Published on: November 15, 2017

High-throughput Protein Expression Generator Using a Microfluidic Platform

High-throughput Protein Expression Generator Using a Microfluidic Platform

Published on: August 23, 2012

Related Experiment Videos

Last Updated: Aug 17, 2025

Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting

Robust Comparison of Protein Levels Across Tissues and Throughout Development Using Standardized Quantitative Western Blotting

Published on: April 9, 2019

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Published on: November 15, 2017

High-throughput Protein Expression Generator Using a Microfluidic Platform

High-throughput Protein Expression Generator Using a Microfluidic Platform

Published on: August 23, 2012

Area of Science:

Synthetic biology
Biotechnology
Machine Learning

Background:

Synthetic biology frequently engineers microbial strains for high-value protein expression.
Deep learning (DL) models are promising for microbial strain optimization, but typically require extensive, costly training data.

Purpose of the Study:

To investigate the relationship between accuracy and data efficiency in machine learning models for sequence-to-expression prediction.
To determine if DL models can achieve high accuracy with reduced datasets and explore methods to enhance data efficiency.

Main Methods:

Trained an atlas of machine learning models on datasets with varying sizes and sequence diversity.
Utilized Explainable AI (XAI) to analyze the discriminatory capabilities of convolutional neural networks (CNNs).
Assessed prediction accuracy and data efficiency across different model configurations and training data characteristics.

Main Results:

Deep learning models can achieve significant prediction accuracy with considerably smaller datasets than previously assumed.
Controlled sequence diversity in training data substantially improves model data efficiency.
Explainable AI confirmed that CNNs can effectively discriminate between DNA sequences.

Conclusions:

DL models offer a viable path for microbial strain optimization with reduced data requirements.
Strategic design of genotype-phenotype screens, balancing data cost and quality through controlled diversity, can accelerate DL adoption in biotechnology.