TPOT

TPOT, or the Tree-based Pipeline Optimization Tool, represents a significant advancement in the field of Automated Machine Learning (AutoML). It is designed to simplify the selection of optimal machine-learning models for various datasets. The tool is particularly beneficial for biomedical research, where it has been applied to predict angiographic diagnoses of coronary artery disease (CAD), among other uses.

TPOT stands out by representing machine learning models as expression trees optimized through a stochastic search method known as genetic programming. This approach enables the automatic selection of the most appropriate machine learning methods and their optimal parameter settings for specific predictive tasks.

Topic

Machine learning;Workflows;Metabolomics;Genotype and phenotype;Membrane and lipoproteins

Detail

  • Operation: Standardisation and normalisation

  • Software interface: Library

  • Language: Python,Shell

  • License: GNU Lesser General Public License v3.0

  • Cost: Free with restrictions

  • Version name: -

  • Credit: National Institutes of Health (NIH).

  • Input: -

  • Output: -

  • Contact: jhmoore@upenn.edu

  • Collection: -

  • Maturity: -

Publications

  • Model selection for metabolomics: predicting diagnosis of coronary artery disease using automated machine learning.
  • Orlenko A, et al. Model selection for metabolomics: predicting diagnosis of coronary artery disease using automated machine learning. Model selection for metabolomics: predicting diagnosis of coronary artery disease using automated machine learning. 2020; 36:1772-1778. doi: 10.1093/bioinformatics/btz796
  • https://doi.org/10.1093/BIOINFORMATICS/BTZ796
  • PMID: 31702773
  • PMC: PMC7703753

Download and documentation

< Back to DB search