Correction to: The application of deep learning for the classification of correct and incorrect SNP genotypes from whole
- PDF / 134,022 Bytes
- 2 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 186 Views
CORRECTION
Correction to: The application of deep learning for the classification of correct and incorrect SNP genotypes from whole-genome DNA sequencing pipelines Krzysztof Kotlarz 1 & Magda Mielczarek 1,2 & Tomasz Suchocki 1,2 & Bartosz Czech 1 & Bernt Guldbrandtsen 3 & Joanna Szyda 1,2
# Institute of Plant Genetics, Polish Academy of Sciences, Poznan 2020
Correction to: Journal of Applied Genetics (2020). https://doi.org/10.1007/s13353-020-00586-0 The original version on this paper contained an error. Figure 5 was published with the same image of figure 4. The correct figure 5 is presented here. The original article has been corrected.
The online version of the original article can be found at https://doi.org/ 10.1007/s13353-020-00586-0 * Joanna Szyda [email protected] 1
Biostatistics Group, Department of Genetics, Wroclaw University of Environmental and Life Sciences, Kozuchowska 7, 51-631, Wroclaw, Poland
2
Institute of Animal Breeding, Balice, Poland
3
Animal Breeding Group, Department of Animal Sciences, University of Bonn, Bonn, Germany
J Appl Genetics Fig. 5 Classification of validation data by the different algorithms, based on the probability cutoff thresholds estimated for the F1 or SUMSS metrics. The numbers above columns represent TP— percentages of true positive results, TN—percentages of true negative results, F1—values of the F1 metric
100
100
F1
TP
SUMSS
80 62 60 45
%
42
42
40 20 0
100
22
19
19
NAIVE
WEIGHTED
OVERSAMPLED30
97
97 87
80
OVERSAMPLED60
OVERSAMPLED100
TN
99
99
22
22
97 89
89
73
60
% 40 20 0
1 NAIVE
WEIGHTED
0.21
0.21
OVERSAMPLED30
OVERSAMPLED60
OVERSAMPLED100
0.17
0.17
0.17
OVERSAMPLED30
OVERSAMPLED60
OVERSAMPLED100
0.5
0.4
0.3
F1 0.2
0.1
0.0 NAIVE
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
WEIGHTED
Data Loading...
