Predicting rice phenotypes with meta and multi-target learning
Artikel i vetenskaplig tidskrift, 2020

The features in some machine learning datasets can naturally be divided into groups. This is the case with genomic data, where features can be grouped by chromosome. In many applications it is common for these groupings to be ignored, as interactions may exist between features belonging to different groups. However, including a group that does not influence a response introduces noise when fitting a model, leading to suboptimal predictive accuracy. Here we present two general frameworks for the generation and combination of meta-features when feature groupings are present. Furthermore, we make comparisons to multi-target learning, given that one is typically interested in predicting multiple phenotypes. We evaluated the frameworks and multi-target learning approaches on a genomic rice dataset where the regression task is to predict plant phenotype. Our results demonstrate that there are use cases for both the meta and multi-target approaches, given that overall, they significantly outperform the base case.

Bioinformatics

Meta-learning

Machine learning

Multi-target learning

Rice

Författare

Oghenejokpeme I. Orhobor

University of Cambridge

Nickolai N. Alexandrov

International Rice Research Institute

Ross King

Chalmers, Biologi och bioteknik, Systembiologi

Alan Turing Institute

University of Cambridge

Machine Learning

0885-6125 (ISSN) 1573-0565 (eISSN)

Vol. In Press

Ämneskategorier

Språkteknologi (språkvetenskaplig databehandling)

Bioinformatik (beräkningsbiologi)

Datorseende och robotik (autonoma system)

DOI

10.1007/s10994-020-05881-9

Mer information

Senast uppdaterat

2020-08-28