Raja Ram Mehta
Research Subjects
Raja Ram Mehta has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Albrecht Serfling
Institute for Resistance Research and Stress Tolerance, Julius Kühn Institute, Federal Research Centre for Cultivated Plants, Quedlinburg, Germany
2 shared publications - Andreas Stahl
Institute for Resistance Research and Stress Tolerance, Julius Kühn Institute, Federal Research Centre for Cultivated Plants, Quedlinburg, Germany
2 shared publications - Anja Hanemann
Saatzucht Josef Breun GmbH & Co. KG, Herzogenaurach, Germany
2 shared publications - Carola Zenke-Philippi
Institute of Agronomy and Plant Breeding II, Justus Liebig University, Giessen, Germany
2 shared publications - Carsten Reinbrecht
Saatzucht Streng-Engelen GmbH & Co. KG, Uffenheim, Germany
2 shared publications - Emanuel Grosch
Institute of Agronomy and Plant Breeding II, Justus Liebig University, Giessen, Germany
2 shared publications
Latest Publications
- Open Access
- 25 October 2026
- Published by Springer Nature in Theoretical and Applied Genetics
- Vol. 139 (11) , 316
Combining different selection criteria into breeding strategies for short-term recurrent genomic selection
Each breeding program must find a balance between short-term genetic gain and the preservation of genetic variation. Different selection criteria, cross selection indices and cross-planning methods have been proposed in order to improve the trade-off between both goals compared to truncation selection and mating best with best. The relative advantage of each of these measures and methods may change depending on the duration of the breeding program because each has its particular strengths and weaknesses. We specifically focused on a short-term recurrent genomic selection program spanning five generations and used two datasets with 224 oat and 293 wheat lines, respectively, for a simulation study which evaluated genetic gain and genetic diversity for 19 different breeding strategies. Overall, we found that strategies that combined different selection criteria, cross selection indices, and/or cross-planning methods rather than relying on just one measure alone resulted in a higher genetic gain compared to truncation selection while maintaining at least the same amount of genetic diversity. We therefore conclude that combining different measures into breeding strategies can enhance breeding progress without any need for additional resources.
- 25 October 2026
- Published by Springer Nature in Theoretical and Applied Genetics
- Vol. 139 (11) , 316
Open AccessCombining different selection criteria into breeding strategies for short-term recurrent genomic selection
Each breeding program must find a balance between short-term genetic gain and the preservation of genetic variation. Different selection criteria, cross selection indices and cross-planning methods have been proposed in order to improve the trade-off between both goals compared to truncation selection and mating best with best. The relative advantage of each of these measures and methods may change depending on the duration of the breeding program because each has its particular strengths and weaknesses. We specifically focused on a short-term recurrent genomic selection program spanning five generations and used two datasets with 224 oat and 293 wheat lines, respectively, for a simulation study which evaluated genetic gain and genetic diversity for 19 different breeding strategies. Overall, we found that strategies that combined different selection criteria, cross selection indices, and/or cross-planning methods rather than relying on just one measure alone resulted in a higher genetic gain compared to truncation selection while maintaining at least the same amount of genetic diversity. We therefore conclude that combining different measures into breeding strategies can enhance breeding progress without any need for additional resources.
- Open Access
- 2 December 2025
- Published by Springer Nature in BMC Bioinformatics
- Vol. 26 (1) , 289
Haplotype-based autoencoders can reduce the dataset dimension and estimate haplotype block effects in different crop species
Background: In plant breeding, many studies currently investigate the application of machine learning (ML) to genomic prediction, hoping for an improvement in prediction accuracy compared to standard models like Genomic Best Linear Unbiased Prediction (GBLUP). However, ML algorithms require much higher computational resources. This study aims to reduce the computational requirements and speed up training time by developing a novel autoencoder architecture inspired by haplotype blocks. Our approach incorporates prior knowledge on genetic linkage, inspired by haplotype block building, into the autoencoder architecture, resulting in a new encoded variable per haplotype block. We further modified our model into a semi-supervised version by adding available yield information. We used features extracted from the autoencoder’s block layer as inputs for Random Forest and GBLUP models to predict the yield of hybrid and inbred crops. Results: Genomic prediction based on the extracted features maintained prediction accuracies equal to using the original marker data, even with a variable reduction of up to 98% and significantly reduced computation time. Prediction accuracy of the supervised component was in some cases equal to and in some lower than the prediction accuracy achieved using GBLUP. Effects estimated for haplotype block variants using our new method showed a high correlation to the blockwise sum of marker effects, which is the current standard approach for haplotype block effects. Correlation between the two block effect estimation approaches was very low for some blocks, which might indicate the incorporation of non-linear effects by the autoencoder. Conclusions: Our approach introduces a new perspective on processing haplotype blocks for genomic prediction, potentially providing more flexible modelling opportunities without the use of multiple binary dummy variables for each block variant. Additionally, training time for ML models may be significantly reduced by using the reduced feature sets generated using our method. By adding the semi-supervised component, the model is able to estimate values similar to marker effects for each block on yield. In future work, this may provide a new way of quantifying the importance of haplotype blocks for selection and breeding.
- 2 December 2025
- Published by Springer Nature in BMC Bioinformatics
- Vol. 26 (1) , 289
Open AccessHaplotype-based autoencoders can reduce the dataset dimension and estimate haplotype block effects in different crop species
Background: In plant breeding, many studies currently investigate the application of machine learning (ML) to genomic prediction, hoping for an improvement in prediction accuracy compared to standard models like Genomic Best Linear Unbiased Prediction (GBLUP). However, ML algorithms require much higher computational resources. This study aims to reduce the computational requirements and speed up training time by developing a novel autoencoder architecture inspired by haplotype blocks. Our approach incorporates prior knowledge on genetic linkage, inspired by haplotype block building, into the autoencoder architecture, resulting in a new encoded variable per haplotype block. We further modified our model into a semi-supervised version by adding available yield information. We used features extracted from the autoencoder’s block layer as inputs for Random Forest and GBLUP models to predict the yield of hybrid and inbred crops. Results: Genomic prediction based on the extracted features maintained prediction accuracies equal to using the original marker data, even with a variable reduction of up to 98% and significantly reduced computation time. Prediction accuracy of the supervised component was in some cases equal to and in some lower than the prediction accuracy achieved using GBLUP. Effects estimated for haplotype block variants using our new method showed a high correlation to the blockwise sum of marker effects, which is the current standard approach for haplotype block effects. Correlation between the two block effect estimation approaches was very low for some blocks, which might indicate the incorporation of non-linear effects by the autoencoder. Conclusions: Our approach introduces a new perspective on processing haplotype blocks for genomic prediction, potentially providing more flexible modelling opportunities without the use of multiple binary dummy variables for each block variant. Additionally, training time for ML models may be significantly reduced by using the reduced feature sets generated using our method. By adding the semi-supervised component, the model is able to estimate values similar to marker effects for each block on yield. In future work, this may provide a new way of quantifying the importance of haplotype blocks for selection and breeding.