TY  - GEN
A1  - Steinfath, Matthias
A1  - Gärtner, Tanja
A1  - Lisec, Jan
A1  - Meyer, Rhonda C.
A1  - Altmann, Thomas
A1  - Willmitzer, Lothar
A1  - Selbig, Joachim
T1  - Prediction of hybrid biomass in Arabidopsis thaliana by selected parental SNP and metabolic markers
T2  - Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe
N2  - A recombinant inbred line (RIL) population, derived from two Arabidopsis thaliana accessions, and the corresponding testcrosses with these two original accessions were used for the development and validation of machine learning models to predict the biomass of hybrids. Genetic and metabolic information of the RILs served as predictors. Feature selection reduced the number of variables (genetic and metabolic markers) in the models by more than 80% without impairing the predictive power. Thus, potential biomarkers have been revealed. Metabolites were shown to bear information on inherited macroscopic phenotypes. This proof of concept could be interesting for breeders. The example population exhibits substantial mid-parent biomass heterosis. The results of feature selection could therefore be used to shed light on the origin of heterosis. In this respect, mainly dominance effects were detected.
T3  - Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe - 1324 
KW  - Quantitative Trait Locus
KW  - feature selection
KW  - Partial Little Square
KW  - recombinant inbred line
KW  - Quantitative Trait Locus analysis
Y1  - 2009
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-431115
SN  - 1866-8372
IS  - 1324
ER  - 
TY  - JOUR
A1  - Steinfath, Matthias
A1  - Gärtner, Tanja
A1  - Lisec, Jan
A1  - Meyer, Rhonda Christiane
A1  - Altmann, Thomas
A1  - Willmitzer, Lothar
A1  - Selbig, Joachim
T1  - Prediction of hybrid biomass in Arabidopsis thaliana by selected parental SNP and metabolic markers
JF  - Theoretical and applied genetics : TAG ; international journal of plant breeding research
N2  - A recombinant inbred line (RIL) population, derived from two Arabidopsis thaliana accessions, and the corresponding testcrosses with these two original accessions were used for the development and validation of machine learning models to predict the biomass of hybrids. Genetic and metabolic information of the RILs served as predictors. Feature selection reduced the number of variables (genetic and metabolic markers) in the models by more than 80% without impairing the predictive power. Thus, potential biomarkers have been revealed. Metabolites were shown to bear information on inherited macroscopic phenotypes. This proof of concept could be interesting for breeders. The example population exhibits substantial mid-parent biomass heterosis. The results of feature selection could therefore be used to shed light on the origin of heterosis. In this respect, mainly dominance effects were detected.
KW  - Quantitative Trait Locus
KW  - feature selection
KW  - Partial Little Square
KW  - recombinant inbred line
KW  - Quantitative Trait Locus analysis
Y1  - 2009
U6  - https://doi.org/10.1007/s00122-009-1191-2
SN  - 0040-5752
SN  - 1432-2242
VL  - 120
SP  - 239
EP  - 247
PB  - Springer
CY  - Berlin
ER  -