Genome Editing and Machine Learning Models – Promising Tools for Precision Breeding in Wheat
Аутори
Kondić-Špika, AnkicaMiladinović, Dragana
Marjanović-Jeromela, Ana
Trkulja, Dragana
Glogovac, Svetlana
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Wheat is a cool season crop and its optimal daytime growing temperature during reproductive development is 15°C and for every degree Celsius above this optimum a reduction in yield has been observed. Furthermore, at different growth stages, abiotic stresses can impact different physiological processes and as a consequence different yield components that are being set at that stage, reducing yield potential. Having that in mind, we evaluated the effect of individual stresses such as: heat, drought, salt etc., as well as their combined effects (salt and N nutrition, heat and drought, etc.) on winter wheat both at cellular and plant level under controlled laboratory conditions and in a greenhouse. The genotypes, identified in these studies as potential sources of drought and other abiotic stresses tolerance (NS 40S, NS Avangarda, Subotičanka) are to be further investigated and used for the improvement of wheat production in unfavourable conditions caused by climate change. For that purpos...e combination of prediction models based on machine learning (ML), advanced molecular techniques and genome editing will be used for target gene identification and introgression. In initial steps, machine learning models will be used for prediction of future climate scenarios and to select a set of traits that wheat may need to cope with changes in the environment and enable stable food production. In genome editing experiments ML will be used to reduce need for the experimental screening of potential sites to optimise Cas9’s activity as well as for prediction of possible off-target mutations, thus increasing the efficiency of targeted wheat improvement. This combinatory approach to wheat improvement should enable more rapid gene/trait discovery and their incorporation in cultivated varieties, thus contributing to overall resilience of wheat production and related agri-food systems.
Кључне речи:
genome editing / machine learning models / wheat / abiotic stresses / physiological processes / yield components / controlled laboratory conditions / greenhouse / advanced molecular techniquesИзвор:
Book of Abstracts, 3rd PlantEd Conference, 5–7 September 2022, Düsseldorf, Germany, 2022, 58-58Издавач:
- Brussels : COST Association
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200032 (Научни институт за ратарство и повртарство, Нови Сад) (RS-MESTD-inst-2020-200032)
- COST Action CA18111: Genome editing in plants - a technology with transformative potential
- Climate Crops - Centre of Excellence for Innovations in Breeding of Climate-Resilient Crops, Institute of Field and Vegetable Crops
Колекције
Институција/група
FiVeRTY - CONF AU - Kondić-Špika, Ankica AU - Miladinović, Dragana AU - Marjanović-Jeromela, Ana AU - Trkulja, Dragana AU - Glogovac, Svetlana PY - 2022 UR - http://fiver.ifvcns.rs/handle/123456789/3263 AB - Wheat is a cool season crop and its optimal daytime growing temperature during reproductive development is 15°C and for every degree Celsius above this optimum a reduction in yield has been observed. Furthermore, at different growth stages, abiotic stresses can impact different physiological processes and as a consequence different yield components that are being set at that stage, reducing yield potential. Having that in mind, we evaluated the effect of individual stresses such as: heat, drought, salt etc., as well as their combined effects (salt and N nutrition, heat and drought, etc.) on winter wheat both at cellular and plant level under controlled laboratory conditions and in a greenhouse. The genotypes, identified in these studies as potential sources of drought and other abiotic stresses tolerance (NS 40S, NS Avangarda, Subotičanka) are to be further investigated and used for the improvement of wheat production in unfavourable conditions caused by climate change. For that purpose combination of prediction models based on machine learning (ML), advanced molecular techniques and genome editing will be used for target gene identification and introgression. In initial steps, machine learning models will be used for prediction of future climate scenarios and to select a set of traits that wheat may need to cope with changes in the environment and enable stable food production. In genome editing experiments ML will be used to reduce need for the experimental screening of potential sites to optimise Cas9’s activity as well as for prediction of possible off-target mutations, thus increasing the efficiency of targeted wheat improvement. This combinatory approach to wheat improvement should enable more rapid gene/trait discovery and their incorporation in cultivated varieties, thus contributing to overall resilience of wheat production and related agri-food systems. PB - Brussels : COST Association C3 - Book of Abstracts, 3rd PlantEd Conference, 5–7 September 2022, Düsseldorf, Germany T1 - Genome Editing and Machine Learning Models – Promising Tools for Precision Breeding in Wheat EP - 58 SP - 58 UR - https://hdl.handle.net/21.15107/rcub_fiver_3263 ER -
@conference{ author = "Kondić-Špika, Ankica and Miladinović, Dragana and Marjanović-Jeromela, Ana and Trkulja, Dragana and Glogovac, Svetlana", year = "2022", abstract = "Wheat is a cool season crop and its optimal daytime growing temperature during reproductive development is 15°C and for every degree Celsius above this optimum a reduction in yield has been observed. Furthermore, at different growth stages, abiotic stresses can impact different physiological processes and as a consequence different yield components that are being set at that stage, reducing yield potential. Having that in mind, we evaluated the effect of individual stresses such as: heat, drought, salt etc., as well as their combined effects (salt and N nutrition, heat and drought, etc.) on winter wheat both at cellular and plant level under controlled laboratory conditions and in a greenhouse. The genotypes, identified in these studies as potential sources of drought and other abiotic stresses tolerance (NS 40S, NS Avangarda, Subotičanka) are to be further investigated and used for the improvement of wheat production in unfavourable conditions caused by climate change. For that purpose combination of prediction models based on machine learning (ML), advanced molecular techniques and genome editing will be used for target gene identification and introgression. In initial steps, machine learning models will be used for prediction of future climate scenarios and to select a set of traits that wheat may need to cope with changes in the environment and enable stable food production. In genome editing experiments ML will be used to reduce need for the experimental screening of potential sites to optimise Cas9’s activity as well as for prediction of possible off-target mutations, thus increasing the efficiency of targeted wheat improvement. This combinatory approach to wheat improvement should enable more rapid gene/trait discovery and their incorporation in cultivated varieties, thus contributing to overall resilience of wheat production and related agri-food systems.", publisher = "Brussels : COST Association", journal = "Book of Abstracts, 3rd PlantEd Conference, 5–7 September 2022, Düsseldorf, Germany", title = "Genome Editing and Machine Learning Models – Promising Tools for Precision Breeding in Wheat", pages = "58-58", url = "https://hdl.handle.net/21.15107/rcub_fiver_3263" }
Kondić-Špika, A., Miladinović, D., Marjanović-Jeromela, A., Trkulja, D.,& Glogovac, S.. (2022). Genome Editing and Machine Learning Models – Promising Tools for Precision Breeding in Wheat. in Book of Abstracts, 3rd PlantEd Conference, 5–7 September 2022, Düsseldorf, Germany Brussels : COST Association., 58-58. https://hdl.handle.net/21.15107/rcub_fiver_3263
Kondić-Špika A, Miladinović D, Marjanović-Jeromela A, Trkulja D, Glogovac S. Genome Editing and Machine Learning Models – Promising Tools for Precision Breeding in Wheat. in Book of Abstracts, 3rd PlantEd Conference, 5–7 September 2022, Düsseldorf, Germany. 2022;:58-58. https://hdl.handle.net/21.15107/rcub_fiver_3263 .
Kondić-Špika, Ankica, Miladinović, Dragana, Marjanović-Jeromela, Ana, Trkulja, Dragana, Glogovac, Svetlana, "Genome Editing and Machine Learning Models – Promising Tools for Precision Breeding in Wheat" in Book of Abstracts, 3rd PlantEd Conference, 5–7 September 2022, Düsseldorf, Germany (2022):58-58, https://hdl.handle.net/21.15107/rcub_fiver_3263 .