Developing smart fitting algorithms to identify random perturbations in time-series data
Lactation curve model with explicit representation of perturbations as a phenotyping tool for dairy livestock precision farming.
Recommendation: posted 07 August 2019, validated 06 September 2019
The ability to adequately characterize the lactation curve of livestock is important not only to ensure proper nutrition of the lactating animal but, among many other benefits, it can assist in diagnosing the incidence of diseases, predicting the quantity of milk production, and comparing animals within the herd for managerial strategies such as culling. Eventually, such smart fitting algorithms can lead to improved genetic selection of more productive animals after genetic-unrelated noises are removed from the data, systematically.
The manuscript by Ben Abdelkrim et al. developed and explained an algorithm to detect perturbations in lactation curves of dairy goats. Researchers have been interested in accurately describing lactation curves since the early-1960s. Johansson  proposed a nonlinear decay function, Nelder  described an inverse polynomial, and Wood  proposed the incomplete gamma function to describe milk production of dairy cows. Unfortunately, many of the lactating animals that yielded lactation curves that did not comply with the typical, expected pattern of milk production were usually discarded and, until then, efforts to address this lack of adherence were not conducted. The recommended manuscript provides a different perspective in which rather than discarding the lactation profile, one can model the perturbations of the lactation curve as an attempt to identify possible problems (e.g., mastitis) and minimize their occurrence. Such an algorithm is important to separate females that show resilient attributes from those females that show sustainable attributes, as per existing definitions proposed by Tedeschi et al. .
The recommended manuscript proposes the Perturbed Lactation Model to explicitly account for multiple perturbations in the time-series milk production in dairy goats. When perturbations occur in biological processes, a typical negative impact is observed in the animal’s response, but on rare occasions, positive impacts can occur. In this case, the animal responds positively to the perturbation (i.e., responsive), and as a result, there is an increase in their output when compared to unperturbed animals. The recommended manuscript only considered negative impacts due to perturbations in the lactation curve of dairy goats. Future modifications should include positive responses due to perturbations. In this case, animals would be “positively responsive” to perturbations, and examples of such behavior include feed intake and growth curves.
 Johansson, I. (1961). Genetic Aspects of Dairy Cattle Breeding. University of Illinois Press, Urbana, IL.
 Nelder, J. A. (1966). Inverse polynomials, a useful group of multi-factor response functions. Biometrics. 22 (1):128-141. doi: 10.2307/2528220
 Wood, P. D. P. (1967). Algebraic model of the lactation curve in cattle. Nature. 216 (5111):164-165. doi: 10.1038/216164a0
 Tedeschi, L. O., J. P. Muir, D. G. Riley, and D. G. Fox. (2015). The role of ruminant animals in sustainable livestock intensification programs. Int. J. Sustainable Dev. World Ecol. 22 (5):452-465. doi: 10.1080/13504509.2015.1075441
Luis Tedeschi (2019) Developing smart fitting algorithms to identify random perturbations in time-series data. Peer Community in Animal Science, 100001. 10.24072/pci.animsci.100001
The recommender in charge of the evaluation of the article and the reviewers declared that they have no conflict of interest (as defined in the code of conduct of PCI) with the authors or with the content of the article. The authors declared that they comply with the PCI rule of having no financial conflicts of interest in relation to the content of the article.
Evaluation round #1
DOI or URL of the preprint: http://biorxiv.org/cgi/content/short/661249v1
Author's Reply, 05 Aug 2019
Decision by Luis Tedeschi, posted 16 Jul 2019
Dear authors; three reviewers have expressed positive feedback and important comments and suggestions on various aspects of your study. I concur that the study has merit, but before a final recommendation by the PCI ANSC can be made, I invite you to revise your manuscript based on reviewers' feedback. Please note that a reviewer provided extensive editorial corrections and suggestions to the text, and I believe you should take that into account when revising your manuscript. Please, read carefully the information provided for authors at https://animsci.peercommunityin.org/about/help_generic#For%20authors.