Our era is on the wave of huge advances in the field of plant genomics and phenotyping, characterized by an explosion of high-throughput methods aimed at identifying molecular phenotypes and genotypes of interest at low costs. Examples of machine learning applications applied to plant breeding are available in the literature and include i) prediction of regulatory regions in plant genomes, ii) mRNA expression levels classification, iii) plant stress phenotyping, iv) macronutrient deficiencies recognition and v) prediction of molecular phenotypes. Here, we would propose that the machine learning framework, combined with high-throughput data (both phenotypic and genotypic), will be helpful for the next generation breeding era, in which genotypic and phenotypic data are identified and combined with unprecedented efficiency.
Cutting-edge technologies for genome sequencing and crop phenotyping, together with progress in computational science are leading a revolution in plant breeding, boosting the identification of the genetic basis of traits at a precision never reached before. In this frame, we aimed to collect the recent advances made in the next generation breeding era, in which, for example, beneficial variants are identified and combined with unprecedented efficiency by machine learning methods.
The scope of this Research Topic is to collect original articles, reviews and mini-reviews in machine learning-based approaches for plant breeding and genomics. Recent advances in SNP and structural variants prediction, Genomic Selection (GS), GWAS as well as new phenotyping mechanisms based on imaging capturing will constitute themes of this Topic too. We encourage the submission of original papers as well as review articles based on the application of machine learning methods rather than on the development of algorithms and mathematical models. The possibility of using machine learning models in synthetic biology to identify functional variants potentially valuable for crop improvement may be also discussed in this Topic.
Articles in Frontiers Research Topics are published and made available online as soon as they are accepted.
Conflict of interest statement: Dr. Ruggieri works for Biomeets Consulting, ITNIG, Barcelona, Spain. Topic Editors declare there are no other potential competing interests.
Our era is on the wave of huge advances in the field of plant genomics and phenotyping, characterized by an explosion of high-throughput methods aimed at identifying molecular phenotypes and genotypes of interest at low costs. Examples of machine learning applications applied to plant breeding are available in the literature and include i) prediction of regulatory regions in plant genomes, ii) mRNA expression levels classification, iii) plant stress phenotyping, iv) macronutrient deficiencies recognition and v) prediction of molecular phenotypes. Here, we would propose that the machine learning framework, combined with high-throughput data (both phenotypic and genotypic), will be helpful for the next generation breeding era, in which genotypic and phenotypic data are identified and combined with unprecedented efficiency.
Cutting-edge technologies for genome sequencing and crop phenotyping, together with progress in computational science are leading a revolution in plant breeding, boosting the identification of the genetic basis of traits at a precision never reached before. In this frame, we aimed to collect the recent advances made in the next generation breeding era, in which, for example, beneficial variants are identified and combined with unprecedented efficiency by machine learning methods.
The scope of this Research Topic is to collect original articles, reviews and mini-reviews in machine learning-based approaches for plant breeding and genomics. Recent advances in SNP and structural variants prediction, Genomic Selection (GS), GWAS as well as new phenotyping mechanisms based on imaging capturing will constitute themes of this Topic too. We encourage the submission of original papers as well as review articles based on the application of machine learning methods rather than on the development of algorithms and mathematical models. The possibility of using machine learning models in synthetic biology to identify functional variants potentially valuable for crop improvement may be also discussed in this Topic.
Articles in Frontiers Research Topics are published and made available online as soon as they are accepted.
Conflict of interest statement: Dr. Ruggieri works for Biomeets Consulting, ITNIG, Barcelona, Spain. Topic Editors declare there are no other potential competing interests.