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

A case study where biology inspired a solution to a computer science problem

J R Koza1, D Andre

  • 1Computer Science Department, Stanford University, CA 94305, USA. Koza@CS.Stanford.Edu

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|January 1, 1996
PubMed
Summary
This summary is machine-generated.

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

[Pharmaceutical cares as means of prevention against drug iatrogenic: Case of oral anticoagulant].

Annales pharmaceutiques francaises·2021
Same author

Index of suspicion with appropriate timing of CT scan helps prevent missed diagnosis in urologic trauma.

The Medical journal of Malaysia·2018
Same author

Isolation and characterization of DNA sequences from Triticum aestivum which function as origins of replication in Saccharomyces cerevisiae.

Plant cell reports·2013
Same author

[Alzheimer's disease and anaesthesia: potential relationships and clinical implications].

Annales francaises d'anesthesie et de reanimation·2010
Same author

Determination of alpha-bisabolol and d-panthenol in cosmetic products by gas chromatography.

International journal of cosmetic science·2009
Same author

Orientational ordering in the low-temperature stable phases of deuterated thiophene.

Acta crystallographica. Section B, Structural science·2008
Same journal

Trust, Reproducibility, and Progress: The Roles of Independent Blind Prediction and Assessment and Benchmarking in Computational Biology.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

The Evolving Cyberinfrastructure at the National Institutes of Health to Support Data and AI in Biomedical Research.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

Applications of AI & ML in Biomanufacturing of Cell and Gene Therapies.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

AI for Health: Leveraging Artificial Intelligence to Revolutionize Healthcare.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

Workshop Introduction: Advances of AI Methods in Single Cell Spatial Omics.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same journal

DRIVE-KG: Enhancing variant-phenotype association discovery in understudied complex diseases using heterogeneous knowledge graphs.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
See all related articles

Inspired by gene duplication in biology, new genetic programming methods enhance automated machine learning for architecture discovery. These techniques achieved superior results in identifying transmembrane protein segments compared to human-designed algorithms.

Area of Science:

  • Evolutionary Biology
  • Computational Biology
  • Machine Learning

Background:

  • The biological theory of gene duplication, as detailed by Susumu Ohno, explains the emergence of novel biological structures and functions.
  • Automated machine learning faces challenges in architecture discovery, a critical step for developing effective models.

Purpose of the Study:

  • To apply the principles of biological gene duplication to address the problem of architecture discovery in machine learning.
  • To develop novel architecture-altering operations for genetic programming inspired by natural evolutionary processes.

Main Methods:

  • Six new architecture-altering operations for genetic programming were designed, drawing parallels with biological gene duplication mechanisms.
  • Genetic programming, incorporating these new operations, was applied to the specific problem of transmembrane protein segment identification.

Related Experiment Videos

Main Results:

  • The genetically evolved programs demonstrated effectiveness in the transmembrane protein segment identification task.
  • The best evolved program achieved an out-of-sample error rate slightly superior to existing human-written algorithms for the same problem.

Conclusions:

  • Biological gene duplication provides a valuable conceptual framework for advancing automated machine learning, particularly in architecture discovery.
  • The developed genetic programming approach offers a promising, evolution-inspired method for solving complex biological data analysis problems.