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 Experiment Videos

Machine learning in computational biology to accelerate high-throughput protein expression.

Anand Sastry1, Jonathan Monk1, Hanna Tegel2

  • 1Department of Bioengineering, University of California, San Diego, CA, USA.

Bioinformatics (Oxford, England)
|April 12, 2017
PubMed
Summary

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

Systematic Review and Meta-Analysis of Studies Assessing the Safety and Efficacy of the DERIVO® 2heal® Embolization Device.

World neurosurgery·2026
Same author

Standardising mechanical thrombectomy complication reporting: A Delphi consensus study to support guidance for national audit.

Interventional neuroradiology : journal of peritherapeutic neuroradiology, surgical procedures and related neurosciences·2025
Same author

Safety and efficacy of aneurysms treated with endovascular devices (The SEATED Study).

The British journal of radiology·2025
Same author

Diagnosis and mitigation of the systemic impact of genome reduction in <i>Escherichia coli</i> DGF-298.

mBio·2024
Same author

Outcome study of the Pipeline Vantage Embolization Device (second version) in unruptured (and ruptured) aneurysms (PEDVU(R) study).

Journal of neurointerventional surgery·2023
Same author

High-resolution temporal profiling of E. coli transcriptional response.

Nature communications·2023

Machine learning predicts protein expression and solubility for the Human Protein Atlas (HPA) antibody production pipeline. This approach optimizes high-throughput experimentation by identifying key protein properties, improving success rates.

Area of Science:

  • Proteomics
  • Computational Biology
  • Machine Learning

Background:

  • The Human Protein Atlas (HPA) characterizes thousands of human proteins across tissues using transcriptomics and immunohistochemistry.
  • Over 40,000 unique human protein fragments have been expressed in E. coli for HPA.
  • Datasets enable quantitative proteome tracking and understanding of expression and solubility properties.

Purpose of the Study:

  • To identify protein properties hindering the HPA antibody production pipeline.
  • To develop a machine learning model for predicting protein expression and solubility.
  • To guide protein fragment selection for optimizing high-throughput experimentation.

Main Methods:

  • Utilized computational biology and machine learning techniques.

Related Experiment Videos

  • Developed a predictive model based on protein properties like aromaticity, hydropathy, and isoelectric point.
  • Workflow presented as IPython notebooks on GitHub for reproducibility and further analysis.

    • Main Results:

    • Identified key protein properties impacting antibody production.
    • Achieved 70% accuracy in predicting protein expression.
    • Achieved 80% accuracy in predicting protein solubility.

    Conclusions:

    • Machine learning effectively predicts protein expression and solubility.
    • Guiding fragment selection based on predicted properties enhances high-throughput experimentation.
    • The developed workflow serves as a template for future proteomic data analysis.