Biology subjects

Hartung, E.

Publications and source records attributed to Hartung, E..

3 recordsLinked to original sources

bioRxiv2024

Evaluating machine learning algorithms to predict lameness in dairy cattle

Dairy cattle lameness represents one of the common concerns in intensive and commercial dairy farms. Lameness is characterized by gait-related behavioral changes in cows and multiple approaches are being utilized to associate these changes with lameness conditions including data from accelerometers, and other precision technologies. The objective was to evaluate the use of machine learning algorithms for the identification of lameness conditions in dairy cattle. In this study, 310 multiparous Holstein dairy cows from a herd in Northern Colorado were affixed with a leg-based accelerometer (Icerobotics(R) Inc, Edinburg, Scotland) to obtain the lying time (min/d), daily steps count (n/d), and daily change (n/d). Subsequently, study cows were monitored for 4 months and cows submitted for claw trimming (CT) were differentiated as receiving corrective claw trimming (CCT) or as being diagnosed with a lameness disorder and consequent therapeutic claw trimming (TCT) by a certified hoof trimmer. Cows not submitted to CT were considered healthy controls. A median filter was applied to smoothen the data by reducing inherent variability. Three different machine learning (ML) models were defined to fit each algorithm which included the conventional features (containing daily lying, daily steps, and daily change derived from the accelerometer), slope features (containing features extracted from each variable in Conventional feature), or all features (3 simple features and 3 slope features). Random forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Time series (ROCKET) were used as ML predictive approaches. For the classification of cows requiring CCT and TCT, ROCKET classifier performed better with accuracy (> 90%), ROC-AUC (> 74%), and F1 score (> 0.61) as compared to other algorithms. Slope features derived in this study increased the efficiency of algorithms as the better-performing models included All features explored. However, further classification of diseases into infectious and non-infectious events was not effective because none of the algorithms presented satisfactory model accuracy parameters. For the classification of observed cow locomotion scores into severely lame and moderately lame conditions, the ROCKET classifier demonstrated satisfactory accuracy (> 0.85), ROC-AUC (> 0.68), and F1 scores (> 0.44). We conclude that ML models using accelerometer data are helpful in the identification of lameness in cows but need further research to increase the granularity and accuracy of classification.

animal behavior and cognition↗

bioRxiv2023

Home-field advantage affects the local adaptive interaction between Andropogon gerardii ecotypes and rhizobiome

Due to climate change, drought frequencies and severities are predicted to increase across the United States. Plant responses and adaptation to stresses depend on plant genetic and environmental factors. Understanding the effect of those factors on plant performance is required to predict the species responses to environmental change. We used reciprocal gardens planted with distinct regional Andropogon gerardii ecotypes adapted to dry, mesic, and wet environments to characterize their rhizosphere communities using 16S rRNA metabarcode sequencing. Even though the local microbial pool was the main driver of these rhizosphere communities, the significant plant ecotype effect highlighted active microbial recruitment in the rhizosphere driven by ecotype or plant genetic background. Our data also suggest that ecotypes were more successful in recruiting rhizosphere community members unique to their local homesites, supporting the "home field advantage" hypothesis. These unique homesite microbes may represent microbial specialists that are linked to plant stress responses. Further, our data support ecotypic variation in the recruitment of congeneric but distinct bacterial variants, highlighting the nuanced effects of plant ecotypes on the rhizosphere microbiome recruitment. Our results should facilitate expanded studies on understanding the complexity of plant host interactions with local soil microbes and identification of functional potential of recruited microbes. Our study has the potential to aid in predicting ecosystem responses to climate change and the impact of management on restoration practices. ImportanceIn this study, we used reciprocal gardens located across a sharp precipitation gradient to characterize rhizosphere communities of distinct dry, mesic, and wet regional Andropogon gerardii ecotypes. We used16S rRNA amplicon sequencing and focused oligotyping analysis and showed that even though the location was the main driver of the microbial communities, ecotypes could potentially recruit distinct bacterial populations. We showed that different A. gerardii ecotypes were more successful in overall community recruitment and recruitment of microbes unique to the "home" environment, when growing at their "home site". We found evidence for "home field advantage" interactions between the host and associated rhizobiomes, and the capability of ecotypes to recruit specialized microbes that were potentially linked to plant stress responses. Our study provides insights into the understanding of factors effecting the plant adaptation, improving management strategies, and predicting of the future landscape under the changing climate.

microbiology↗

bioRxiv2022

Culturomics of Andropogon gerardii rhizobiome revealed nitrogen transforming capabilities of stress-tolerant Pseudomonas under drought conditions

BackgroundClimate change will result in more frequent droughts that impact soil-inhabiting microbiomes in the agriculturally vital North American perennial grasslands. In this study, we used the combination of culturomics and high-resolution genomic sequencing of microbial consortia isolated from the rhizosphere of a tallgrass prairie foundation grass, Andropogon gerardii. We cultivated the plant host-associated microbes under artificial drought-induced conditions and identified the microbe(s) that might play a significant role in the rhizobiome of Andropogon gerardii under drought conditions. ResultsPhylogenetic analysis of the non-redundant metagenome-assembled genomes (MAGs) identified the bacterial population of interest - MAG-Pseudomonas. Further metabolic pathway and pangenome analyses detected genes and pathways related to nitrogen transformation and stress responses in MAG-Pseudomonas. ConclusionsOur data indicate that the metagenome-assembled MAG-Pseudomonas has the functional potential to contribute to the plant hosts growth during stressful conditions. This study provided insights into optimizing plant productivity under drought conditions.

microbiology↗