Elsevier

Journal of Dairy Science

Volume 102, Issue 12, December 2019, Pages 11561-11585
Journal of Dairy Science

Research
Metabolomics meets machine learning: Longitudinal metabolite profiling in serum of normal versus overconditioned cows and pathway analysis

https://doi.org/10.3168/jds.2019-17114Get rights and content
open access

ABSTRACT

This study aimed to investigate the differences in the metabolic profiles in serum of dairy cows that were normal or overconditioned when dried off for elucidating the pathophysiological reasons for the increased health disturbances commonly associated with overconditioning. Fifteen weeks antepartum, 38 multiparous Holstein cows were allocated to either a high body condition (HBCS; n = 19) group or a normal body condition (NBCS; n = 19) group and were fed different diets until dry-off to amplify the difference. The groups were also stratified for comparable milk yields (NBCS: 10,361 ± 302 kg; HBCS: 10,315 ± 437 kg; mean ± standard deviation). At dry-off, the cows in the NBCS group (parity: 2.42 ± 1.84; body weight: 665 ± 64 kg) had a body condition score (BCS) <3.5 and backfat thickness (BFT) <1.2 cm, whereas the HBCS cows (parity: 3.37 ± 1.67; body weight: 720 ± 57 kg) had BCS >3.75 and BFT >1.4 cm. During the dry period and the subsequent lactation, both groups were fed identical diets but maintained the BCS and BFT differences. A targeted metabolomics (AbsoluteIDQ p180 kit, Biocrates Life Sciences AG, Innsbruck, Austria) approach was performed in serum samples collected on d −49, +3, +21, and +84 relative to calving for identifying and quantifying up to 188 metabolites from 6 different compound classes (acylcarnitines, AA, biogenic amines, glycerophospholipids, sphingolipids, and hexoses). The concentrations of 170 metabolites were above the limit of detection and could thus be used in this study. We used various machine learning (ML) algorithms (e.g., sequential minimal optimization, random forest, alternating decision tree, and naïve Bayes–updatable) to analyze the metabolome data sets. The performance of each algorithm was evaluated by a leave-one-out cross-validation method. The accuracy of classification by the ML algorithms was lowest on d 3 compared with the other time points. Various ML methods (partial least squares discriminant analysis, random forest, information gain ranking) were then performed to identify those metabolites that were contributing most significantly to discriminating the groups. On d 21 after parturition, 12 metabolites (acetylcarnitine, hexadecanoyl-carnitine, hydroxyhexadecenoyl-carnitine, octadecanoyl-carnitine, octadecenoyl-carnitine, hydroxybutyryl-carnitine, glycine, leucine, phosphatidylcholine-diacyl-C40:3, trans-4-hydroxyproline, carnosine, and creatinine) were identified in this way. Pathway enrichment analysis showed that branched-chain AA degradation (before calving) and mitochondrial β-oxidation of long-chain fatty acids along with fatty acid metabolism, purine metabolism, and alanine metabolism (after calving) were significantly enriched in HBCS compared with NBCS cows. Our results deepen the insights into the phenotype related to overconditioning from the preceding lactation and the pathophysiological sequelae such as increased lipolysis and ketogenesis and decreased feed intake.

Key words

metabolomics
machine learning
metabolic pathway
transition cow

Cited by (0)

*

H. Sadri was a visiting scientist at the Institute of Animal Science, Physiology and Hygiene Unit, University of Bonn, 53115 Bonn, Germany, at the time the research was done.