Premium
Controlling Misclassification Rates in Identification of Haploid Seeds from Induction Crosses in Maize with High‐Oil Inducers
Author(s) -
Melchinger Albrecht E.,
Winter Markus,
Mi Xuefei,
Piepho HansPeter,
Schipprack Wolfgang,
Mirdita Vilso
Publication year - 2015
Publication title -
crop science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.76
H-Index - 147
eISSN - 1435-0653
pISSN - 0011-183X
DOI - 10.2135/cropsci2014.09.0633
Subject(s) - biology , doubled haploidy , inducer , sorting , ploidy , horticulture , botany , microbiology and biotechnology , mathematics , genetics , gene , algorithm
In vivo production of double haploid (DH) lines in maize ( Zea mays L.) requires reliable identification of haploid ( H ) seeds. A new method for achieving this goal is production of induction crosses with high‐oil (HO) inducers and sorting the resulting H and diploid crossing ( C ) seeds based on their oil content (OC). Balancing the false discovery rate (FDR) and false negative rate (FNR) by choice of a suitable proportion α of selected seeds represents an unsolved problem with this method. We investigated solutions by applying mixture distribution (MD) analysis to the OC of induction crosses for estimating the means and standard deviation (μ H , μ C , and σ) of H and C seeds and the haploid induction rate κ. Moreover, we developed formulas and software for calculating the FDR and FNR from these estimates. Using several induction crosses with HO inducer UH600, parameter estimates from (i) MD analysis in different environments and (ii) gold standard classification (GSC) of plants in the field agreed well for μ H and μ C , but only moderately for σ and κ. Parameter estimates from the MD provided meaningful guidelines for calculating the expected FDR and FNR. Selecting the α = 7.5% proportion of seeds with lowest OC was optimal for most induction crosses and balanced the FDR and FNR. In conclusion, induction crosses with HO inducers hold great promise for promoting the DH technology in maize, but an automated high‐throughput platform for sorting the seeds from the MD into several distinct classes with increasing OC is recommended to take full advantage of this novel approach.