e-infrastructure Roadmap for Open Science in Agriculture

A bibliometric study

The e-ROSA project seeks to build a shared vision of a future sustainable e-infrastructure for research and education in agriculture in order to promote Open Science in this field and as such contribute to addressing related societal challenges. In order to achieve this goal, e-ROSA’s first objective is to bring together the relevant scientific communities and stakeholders and engage them in the process of coelaboration of an ambitious, practical roadmap that provides the basis for the design and implementation of such an e-infrastructure in the years to come.

This website highlights the results of a bibliometric analysis conducted at a global scale in order to identify key scientists and associated research performing organisations (e.g. public research institutes, universities, Research & Development departments of private companies) that work in the field of agricultural data sources and services. If you have any comment or feedback on the bibliometric study, please use the online form.

You can access and play with the graphs:

Discover all records
Home page


Machine learning methods and predictive ability metrics for genome-wide prediction of complex traits


Genome-wide prediction of complex traits has become increasingly important in animal and plant breeding, and is receiving increasing attention in human genetics. Most common approaches are whole-genome regression models where phenotypes are regressed on thousands of markers concurrently, applying different prior distributions to marker effects. While use of shrinkage or regularization in SNP regression models has delivered improvements in predictive ability in genome-based evaluations, serious over-fitting problems may be encountered as the ratio between markers and available phenotypes continues increasing. Machine learning is an alternative approach for prediction and classification, capable of dealing with the dimensionality problem in a computationally flexible manner. In this article we provide an overview of non-parametric and machine learning methods used in genome wide prediction, discuss their similarities as well as their relationship to some well-known parametric approaches. Although the most suitable method is usually case dependent, we suggest the use of support vector machines and random forests for classification problems, whereas Reproducing Kernel Hilbert Spaces regression and boosting may suit better regression problems, with the former having the more consistently higher predictive ability. Neural Networks may suffer from over-fitting and may be too computationally demanded when the number of neurons is large. We further discuss on the metrics used to evaluate predictive ability in model comparison under cross-validation from a genomic selection point of view. We suggest use of predictive mean squared error as a main but not only metric for model comparison. Visual tools may greatly assist on the choice of the most accurate model. (C) 2014 Elsevier B.V. All rights reserved.

  • AU
  • US
  • Univ_Wisconsin_Madison (US)
  • Dairy_Futures_CRC (AU)
Data keywords
  • machine learning
Agriculture keywords
    Data topic
    • big data
    • modeling
    Document type

    Inappropriate format for Document type, expected simple value but got array, please use list format

    Institutions 10 co-publis
    • Univ_Wisconsin_Madison (US)
    Powered by Lodex 8.20.3
    logo commission europeenne
    e-ROSA - e-infrastructure Roadmap for Open Science in Agriculture has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 730988.
    Disclaimer: The sole responsibility of the material published in this website lies with the authors. The European Union is not responsible for any use that may be made of the information contained therein.