Crop improvement using life cycle datasets acquired under field conditions

Abstract

Crops are exposed to various environmental stresses in the field throughout their life cycle. Modern plant science has provided remarkable insights into the molecular networks of plant stress responses in laboratory conditions, but the responses of different crops to environmental stresses in the field need to be elucidated. Recent advances in omics analytical techniques and information technology have enabled us to integrate data from a spectrum of physiological metrics of field crops. The interdisciplinary efforts of plant science and data science enable us to explore factors that affect crop productivity and identify stress tolerance-related genes and alleles. Here, we describe recent advances in technologies that are key components for data driven crop design, such as population genomics, chronological omics analyses, and computer-aided molecular network prediction. Integration of the outcomes from these technologies will accelerate our understanding of crop phenology under practical field situations and identify key characteristics to represent crop stress status. These elements would help us to genetically engineer "designed crops" to prevent yield shortfalls because of environmental fluctuations due to future climate change.

Keywords: crop phenology; epigenome; machine learning; population genomics; transcriptome.

FIGURE 1

Phenology datasets during the life cycle of a crop grown under field conditions. Time series omics data such as transcriptome, epigenome, and metabolome/hormonome data can be acquired as sequential “snapshots” throughout the crop life cycle. Parameters regarding field environment including air and soil conditions can be acquired as “streamed” datasets.

FIGURE 2

A conceptual framework for phenology data driven crop design. Phenology datasets include plant phenotypes, omics snapshots with environmental data. A genome-wide polymorphism dataset is useful to find genetic association between accessions with traits as well as with physiological state. For model building, the collected data are applied to various types of computer-aided methods. Digitized datasets can also be assessed against data on well-characterized gene functions in model plants. Machine learning-based data clustering and network prediction may help us to identify candidate genes and alleles for crop improvement.