Key research projects

1. Quantitative genetic analysis of high-throughput phenotyping data

We develop and apply statistical methods to connect data generated from high-throughput phenotyping with genetics. [YouTube 1] [YouTube 2] [YouTube 3]

2. High-Throughput Phenotyping or Phenomics

  • Wang J, Hu Y, Xiang L, Morota G, Brooks SA, Wickens CL Miller-Cushon EK, and Yu H. 2024. Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision. Journal of Animal Science. Early view. [DOI] [PubMed] [EuropePMC] [arXiv]
  • Bi Y, Campos LM, Wang J, Yu H, Hanigan MD, and Morota G. 2023. Depth video data-enabled predictions of longitudinal dairy cow body weight using thresholding and Mask R-CNN algorithms. Smart Agricultural Technology. 6:100352. [DOI] [arXiv]
  • Kadlec R, Indest S, Castro K, Waqar S, Campos LM, Amorim ST, Bi Y, Hanigan MD, and Morota G. 2022. Automated acquisition of top-view dairy cow depth image data using an RGB-D sensor camera. Translational Animal Science. 6:1-6. [DOI] [PubMed] [EuropePMC]
  • Alghamdi S, Zhao Z, Ha DS, Morota G, and Ha SS. 2022. Improved pig behavior analysis by optimizing window sizes for individual behaviors on acceleration and angular velocity data. Journal of Animal Science. 100:1-9. [DOI] [PubMed] [EuropePMC]
  • Chen CJ, Morota G, Lee K, Zhang Z, and Cheng H. 2022. VTag: a semi-supervised pipeline for tracking pig activity with a single top-view camera. Journal of Animal Science. 100:1-10. [DOI] [PubMed] [EuropePMC]
  • Yassue RM, Galli G, Borsato Junior R, Cheng H, Morota G, and Fritsche-Neto R. 2022. A low-cost greenhouse-based high-throughput phenotyping platform for genetic studies: A case study in maize under inoculation with plant growth-promoting bacteria. The Plant Phenome Journal. 5:e20043. [DOI] [bioRxiv]
  • Mota LFM, Pegolo S, Baba T, Morota G, Penagaricano F, Bittante G, and Cecchinato A. 2021. Comparison of single-breed and multi-breed training population for infrared predictions of novel phenotypes in Holstein cows. Animals. 11:1993. [DOI]
  • Mota LFM, Pegolo S, Baba T, Penagaricano F, Morota G, Bittante G, and Cecchinato A. 2021. Evaluating the performance of machine learning methods and variable selection methods for predicting difficult-to-measure traits in Holstein dairy cattle using milk infrared spectral data. 104:8107-8121. [DOI] [PubMed] [EuropePMC]
  • Morota G, Cheng H, Cook D, and Tanaka E. 2021. ASAS-NANP SYMPOSIUM: Prospects for interactive and dynamic graphics in the era of data-rich animal science. Journal of Animal Science. 99:1-17. [DOI] [PubMed] [EuropePMC]
  • Yu H, Lee K, and Morota G. 2021. Forecasting dynamic body weight of non-restrained pigs from images using an RGB-D sensor camera. Translational Animal Science. 5:1-9. [DOI] [PubMed] [EuropePMC]
  • Zhu F, Paul P, Hussain W, Wallman K, Dhatt BK, Sandhu J, Irvin L, Morota G, Yu H, and Walia H. 2021. SeedExtractor: an open-source GUI for seed image analysis. Frontiers in Plant Science. 11:581546. [DOI] [PubMed] [EuropePMC] [bioRxiv]
  • Morota G, Ventura RV, Silva FF, Koyama M, and Fernando SC. 2018. Machine learning and data mining advance predictive big data analysis in precision animal agriculture. Journal of Animal Science. 96:1540–1550. [DOI] [PubMed] [EuropePMC]

  • 3. Network analysis

    Network-based quantitative genetics offers new perspectives and approaches.

    4. Variance heterogeneity genome-wide mapping analysis

    We identified variance QTL that controll the variability of phenotypes rather than the mean of phenotypes.

    5. Genomic connectedness

    We showed that genetic connectedness can be used in the context of whole-genome prediction.

    6. Medical Subject Headings (MeSH) analysis

    We pioneered MeSH analysis in agricultural species.

    7. Biological information driven whole-genome prediction

    Annotation-based whole-genome regression methods can partition the source of genomic prediction accuracy.

    8. Machine learning and Data Science

    Application of machine learning and data science to genetics.

    9. Software development

    We are interested in developing modern interactive visualization tools in agriculture science.