scholarly journals Leveraging Precision Phenotyping Solutions within Corteva Agriscience

2021 ◽  
Author(s):  
Sara Tirado Tolosa ◽  
Nathan Coles
Author(s):  
Winnie Akinyi Nyonje ◽  
Roland Schafleitner ◽  
Mary Abukutsa-Onyango ◽  
Ray-Yu Yang ◽  
Anselimo Makokha ◽  
...  

2016 ◽  
pp. pp.00735.2016 ◽  
Author(s):  
Wenchao Qu ◽  
Christelle A.M. Robert ◽  
Matthias Erb ◽  
Bruce E. Hibbard ◽  
Maxim Paven ◽  
...  

Crop Science ◽  
2018 ◽  
Vol 58 (2) ◽  
pp. 670-678 ◽  
Author(s):  
A. E. Melchinger ◽  
J. Böhm ◽  
H. F. Utz ◽  
J. Müller ◽  
S. Munder ◽  
...  

2019 ◽  
Author(s):  
I. Adriaens ◽  
N.C. Friggens ◽  
W. Ouweltjes ◽  
H. Scott ◽  
B. Aernouts ◽  
...  

ABSTRACTA dairy cow’s lifetime resilience and her ability to re-calve gain importance on dairy farms as they affect all aspects of the sustainability of the dairy industry. Many modern farms today have milk meters and activity sensors that accurately measure yield and activity at a high frequency for monitoring purposes. We hypothesized that these same sensors can be used for precision phenotyping of complex traits such as lifetime resilience or productive lifespan. The objective of this study was to investigate if lifetime resilience and productive lifespan of dairy cows can be predicted using sensor-derived proxies of first parity sensor data. We used a data set from 27 Belgian and British dairy farms with an automated milking system containing at least 5 years of successive measurements. All of these farms had milk meter data available, and 13 of these farms were also equipped with activity sensors. This subset was used to investigate the added value of activity meters to improve the model’s prediction accuracy. To rank cows for lifetime resilience, a score was attributed to each cow based on her number of calvings, her 305-day milk yield, her age at first calving, her calving intervals and the days in milk at the moment of culling, taking her entire lifetime into account. Next, this lifetime resilience score was used to rank the cows within their herd resulting in a lifetime resilience ranking. Based on this ranking, the cows were classified in a low (last third), moderate (middle third) or high (first third) resilience category. In total 45 biologically-sound sensor features were defined from the time-series data, including measures of variability, lactation curve shape, milk yield perturbations, activity spikes indicating estrous events and activity dynamics representing health events. These features, calculated on first lactation data, were used to predict the lifetime resilience rank and thus, the classification within the herd (low/moderate/high). Using a specific linear regression model progressively including features stepwise selected at farm level (cut-off P-value of 0.2), classification performances were between 35.9% and 70.0% (46.7 ± 8.0, mean ± standard deviation) for milk yield features only and between 46.7% and 84.0% (55.5 ± 12.1, mean ± standard deviation) for lactation and activity features together. This is respectively 13.7 and 22.2% higher than what random classification would give. Moreover, using these individual farm models, only 3.5% and 2.3% of the cows were classified high while being low and vice versa, while respectively 91.8% and 94.1% of the wrongly classified animals were predicted in an adjacent category. A common equation across farms to predict this rank could not be found, which demonstrates the variability in culling and management strategies across farms and within farms over time. The lack of a common model structure across farms suggests the need to consider local (and evidence based) culling management rules when developing decision support tools for dairy farms. With this study we showed the potential of precision phenotyping of complex traits based on biologically meaningful features derived from readily available sensor data. We conclude that first lactation milk and activity sensor data have the potential to predict cows’ lifetime resilience rankings within farms but that consistency over farms is currently lacking.


2013 ◽  
pp. 341-374 ◽  
Author(s):  
Boddupalli M. Prasanna ◽  
Jose L. Araus ◽  
Jose Crossa ◽  
Jill E. Cairns ◽  
Natalia Palacios ◽  
...  

2021 ◽  
Author(s):  
Alisdair R Fernie ◽  
Saleh Alseekh ◽  
Jie Liu ◽  
Jianbing Yan

One-sentence summary: An update on the use of precision phenotyping to assess the potential of lesser cultivated species as candidates for de novo domestication or similar development for future agriculture.


2020 ◽  
Vol 13 (2) ◽  
pp. 110-116 ◽  
Author(s):  
Karthik Seetharam ◽  
Sirish Shrestha ◽  
Partho P Sengupta

Machine learning (ML), a subset of artificial intelligence, is showing promising results in cardiology, especially in cardiac imaging. ML algorithms are allowing cardiologists to explore new opportunities and make discoveries not seen with conventional approaches. This offers new opportunities to enhance patient care and open new gateways in medical decision-making. This review highlights the role of ML in cardiac imaging for precision phenotyping and prognostication of cardiac disorders.


Author(s):  
Andrew Lin ◽  
Márton Kolossváry ◽  
Sebastien Cadet ◽  
Priscilla McElhinney ◽  
Markus Goeller ◽  
...  

2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 140-140
Author(s):  
Alessio Cecchinato ◽  
Sara Pegolo ◽  
Giovanni Bittante

Abstract There is an ever-growing interest in research oriented towards the improvement of quality of animal products. In this context, one major operational bottleneck is the possibility to collect quality indicators over the meat and dairy chains and for selective breeding purposes. The use of near-infrared (NIR) and the Fourier-transformed infrared (FTIR) spectroscopy techniques have been proven to be powerful precision phenotyping tools for high-throughput meat and milk quality assessment. Such technologies allow scoring large number of animals and/or derived-products for novel (predicted) phenotypes and indicator traits to set-up potential new payment systems and boost the genetic improvement. One important step in the use of NIR and FTIR tools is the definition of the “gold standard” as the infrared-based predictions could act only as indicators traits. Indeed, the definition of a robust calibration set, the assessment of repeatability and reproducibility of the reference (i.e., gold standard) as well as the detection of random and systematic errors are crucial steps. Once the reference phenotype has been defined, different statistical methodologies could be applied to infrared spectra data. For instance, the partial least squares regression (PLS) is a multivariate regression method commonly used to build up prediction models using NIR and FTIR spectra data. However, the implementation of advanced statistical approaches, such as Bayesian approaches and machine learning methods, might allow us to achieve more robust and accurate predictions. In this talk, we will describe and discuss some of the challenges and potentials of NIR and FTIR tools for large-scale precision phenotyping. Some examples include the use of NIR and Visible-NIR (Vis-NIR) for assessing meat quality parameters (also using portable instruments able to collect spectra directly from the muscle surface at the slaughterhouse) and the use of FTIR for predicting several traits related to fine milk composition and technological traits in dairy cattle.


Sign in / Sign up

Export Citation Format

Share Document