Genes and regulatory mechanisms associated with experimentally-induced bovine respiratory disease identified using supervised machine learning methodology

AbstractBovine respiratory disease (BRD) is a multifactorial disease involving complex host immune interactions shaped by pathogenic agents and environmental factors. Advancements in RNA sequencing and associated analytical methods are improving our understanding of host response related to BRD pathophysiology. Supervised machine learning (ML) approaches present one such method for analyzing new and previously published transcriptome data to identify novel disease-associated genes and mechanisms. Our objective was to apply ML models to lung and immunological tissue datasets acquired from previous clinical BRD experiments to identify genes that classify disease with high accuracy. Raw mRNA sequencing reads from 151 bovine datasets (n = 123 BRD, n = 28 control) were downloaded from NCBI-GEO. Quality filtered reads were assembled in a HISAT2/Stringtie2 pipeline. Raw gene counts for ML analysis were normalized, transformed, and analyzed with MLSeq, utilizing six ML models. Cross-validation parameters (fivefold, repeated 10 times) were applied to 70% of the compiled datasets for ML model training and parameter tuning; optimized ML models were tested with the remaining 30%. Downstream analysis of significant genes identified by the top ML models, based on classification accuracy for each etiological association, was performed within WebGestalt and Reactome (FDR ≤ 0.05). Nearest shrunken centroid and Poisson linear discriminant analysis with power transformation models identified 154 and 195 significant genes for IBR and BRSV, respectively; from these genes, the two ML models discriminated IBR and BRSV with 100% accuracy compared to sham controls. Significant genes classified by the top ML models in IBR (154) and BRSV (195), but not BVDV (74), were related to type I interferon production and IL-8 secretion, specifically in lymphoid tissue and not homogenized lung tissue. Genes identified in Mannheimia haemolytica infections (97) were involved in activating classical and alternative pathways of complement. Novel findings, including expression of genes related to reduced mitochondrial oxygenation and ATP synthesis in consolidated lung tissue, were discovered. Genes identified in each analysis represent distinct genomic events relevant to understanding and predicting clinical BRD. Our analysis demonstrates the utility of ML with published datasets for discovering functional information to support the prediction and understanding of clinical BRD.

Download Full-text

Genes and Mechanisms Associated With Experimentally Induced Bovine Respiratory Disease Identified With Supervised Machine Learning Methodology on Integrated Transcriptomic Datasets

10.21203/rs.3.rs-789747/v1 ◽

2021 ◽

Author(s):

Matthew Scott ◽

Amelia Woolums ◽

Cyprianna Swiderski ◽

Andy Perkins ◽

Bindu Nanduri

Keyword(s):

Machine Learning ◽

Respiratory Disease ◽

Bovine Respiratory Disease ◽

Atp Synthesis ◽

Supervised Machine Learning ◽

Support Vector ◽

Type I ◽

Linear Discriminant ◽

Alternative Pathways ◽

Validation Parameters

Abstract Bovine respiratory disease (BRD) is a multifactorial disease involving complex host immune interactions shaped by pathogenic agents and environmental factors. Advancements in RNA sequencing and associated analytical methods are improving our understanding of host response related to BRD pathophysiology. Supervised machine learning (ML) approaches present one such method for analyzing new and previously published transcriptome data to identify novel genes and mechanisms. Our objective was to apply ML models to lung and immunological tissue datasets acquired from previous clinical BRD experiments to identify genes that classify disease with high accuracy. Raw mRNA sequencing reads from 151 bovine datasets (n=123 BRD, n=28 control) were downloaded from NCBI-GEO. Quality filtered reads were assembled in a HISAT2/Stringtie2 pipeline. Raw gene counts for ML analysis were normalized, transformed, and analyzed with MLSeq, utilizing six ML models. Cross-validation parameters (5-fold, repeated 10 times) were applied in a 70:30 training/testing ratio. Downstream analysis of genes identified by the top sparse classifiers for each etiological association was performed within WebGestalt and Reactome (FDR < 0.05). Support vector machines was routinely the top non-sparse classifier for predicting etiological disease versus sham control. Nearest shrunken centroid and Poisson linear discriminant analysis with power transformation could reliably classify IBR and BRSV with 100% accuracy. Genes identified in IBR and BRSV, but not BVDV, were related to type I interferon production and IL-8 secretion, specifically in lymphoid tissue and not lung. Genes identified in Mannheimia haemolytica infections were involved in activating classical and alternative pathways of complement. Novel findings, including expression of genes related to reduced mitochondrial oxygenation and ATP synthesis in consolidated lung tissue, were discovered. Genes identified in each analysis represent distinct genomic events relevant to understanding and predicting clinical BRD. The few genes shared across analyses may be reliably associated with clinical BRD. Our analysis demonstrates the utility of ML with published datasets for discovering functional information to support prediction and understanding BRD acquisition.

Download Full-text

Intelligent Image Classification for Grading Egyptian Cotton Lint

10.20944/preprints202108.0139.v1 ◽

2021 ◽

Author(s):

Oliver J. Fisher ◽

Ahmed Rady ◽

Aly A. A. El-Banna ◽

Nicholas J. Watson ◽

Haitham H. Emaish

Keyword(s):

Machine Learning ◽

Human Error ◽

Intelligent System ◽

Vision System ◽

Supervised Machine Learning ◽

Cotton Lint ◽

Linear Discriminant ◽

Ensemble Modelling ◽

Manual Inspection ◽

Egyptian Cotton

Egyptian cotton is one of the most important commodities to the Egyptian economy and is renowned globally for its quality, which is currently graded by manual inspection. This has several drawbacks including significant labour requirement, low inspection efficiency, and influence from inspection conditions such as light and human subjectivity. This current work uses a low-cost colour vision system, combined with machine learning to predict the cotton lint grade of the cultivars Giza 86, 97, 90, 94 and 96. Unsupervised and supervised machine learning approaches were explored and compared. Three different supervised learning algorithms were evaluated: linear discriminant analysis, decision trees and ensemble modelling. The highest accuracy models (77.3-98.2%) used an ensemble modelling technique to classify samples within the Egyptian cotton grades: Fully Good, Good, Fully Good Fair, Good Fair and Fully Fair. The unsupervised learning technique k-means showed that human error is more likely to occur when classifying lint belonging to the higher quality grades and underlined the need for an intelligent system to replace manual inspection.

Download Full-text

A Classification Approach for Predicting COVID-19 Patient Survival Outcome with Machine Learning Techniques

10.1101/2020.08.02.20129767 ◽

2020 ◽

Author(s):

Abdulhameed Ado Osi ◽

Hussaini Garba Dikko ◽

Mannir Abdu ◽

Auwalu Ibrahim ◽

Lawan Adamu Isma'il ◽

...

Keyword(s):

Machine Learning ◽

Survival Outcome ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Support Vector ◽

P Value ◽

Kappa Index ◽

Quality Health Care ◽

Linear Discriminant ◽

Learning Techniques

COVID-19 is an infectious disease discovered after the outbreak began in Wuhan, China, in December 2019. COVID-19 is still becoming an increasing global threat to public health. The virus has been escalated to many countries across the globe. This paper analyzed and compared the performance of three different supervised machine learning techniques; Linear Discriminant Analysis (LDA), Random Forest (RF), and Support Vector Machine (SVM) on COVID-19 dataset. The best level of accuracy between these three algorithms was determined by comparison of some metrics for assessing predictive performance such as accuracy, sensitivity, specificity, F-score, Kappa index, and ROC. From the analysis results, RF was found to be the best algorithm with 100% prediction accuracy in comparison with LDA and SVM with 95.2% and 90.9% respectively. Our analysis shows that out of these three classification models RF predicts COVID-19 patient's survival outcome with the highest accuracy. Chi-square test reveals that all the seven features except sex were significantly correlated with the COVID-19 patient's outcome (P-value < 0.005). Therefore, RF was recommended for COVID-19 patient outcome prediction that will help in early identification of possible sensitive cases for quick provision of quality health care, support and supervision.

Download Full-text

Comprehensive at-arrival transcriptomic analysis of post-weaned beef cattle uncovers type I interferon and antiviral mechanisms associated with bovine respiratory disease mortality

PLoS ONE ◽

10.1371/journal.pone.0250758 ◽

2021 ◽

Vol 16 (4) ◽

pp. e0250758

Author(s):

Matthew A. Scott ◽

Amelia R. Woolums ◽

Cyprianna E. Swiderski ◽

Andy D. Perkins ◽

Bindu Nanduri ◽

...

Keyword(s):

Beef Cattle ◽

Respiratory Disease ◽

Type I Interferon ◽

Bovine Respiratory Disease ◽

Transcriptomic Analysis ◽

Type I ◽

Antiviral Defense ◽

High Quality Research ◽

Immunological Mechanisms ◽

Unmapped Reads

Background Despite decades of extensive research, bovine respiratory disease (BRD) remains the most devastating disease in beef cattle production. Establishing a clinical diagnosis often relies upon visual detection of non-specific signs, leading to low diagnostic accuracy. Thus, post-weaned beef cattle are often metaphylactically administered antimicrobials at facility arrival, which poses concerns regarding antimicrobial stewardship and resistance. Additionally, there is a lack of high-quality research that addresses the gene-by-environment interactions that underlie why some cattle that develop BRD die while others survive. Therefore, it is necessary to decipher the underlying host genomic factors associated with BRD mortality versus survival to help determine BRD risk and severity. Using transcriptomic analysis of at-arrival whole blood samples from cattle that died of BRD, as compared to those that developed signs of BRD but lived (n = 3 DEAD, n = 3 ALIVE), we identified differentially expressed genes (DEGs) and associated pathways in cattle that died of BRD. Additionally, we evaluated unmapped reads, which are often overlooked within transcriptomic experiments. Results 69 DEGs (FDR<0.10) were identified between ALIVE and DEAD cohorts. Several DEGs possess immunological and proinflammatory function and associations with TLR4 and IL6. Biological processes, pathways, and disease phenotype associations related to type-I interferon production and antiviral defense were enriched in DEAD cattle at arrival. Unmapped reads aligned primarily to various ungulate assemblies, but failed to align to viral assemblies. Conclusion This study further revealed increased proinflammatory immunological mechanisms in cattle that develop BRD. DEGs upregulated in DEAD cattle were predominantly involved in innate immune pathways typically associated with antiviral defense, although no viral genes were identified within unmapped reads. Our findings provide genomic targets for further analysis in cattle at highest risk of BRD, suggesting that mechanisms related to type I interferons and antiviral defense may be indicative of viral respiratory disease at arrival and contribute to eventual BRD mortality.

Download Full-text

Use of nCounter mRNA Profiling to Identify at-arrival Gene Expression Patterns for Predicting Bovine Respiratory Disease in Beef Cattle

10.21203/rs.3.rs-923361/v1 ◽

2021 ◽

Author(s):

Matthew Scott ◽

Amelia Woolums ◽

Cyprianna Swiderski ◽

Alexis Thompson ◽

Andy Perkins ◽

...

Keyword(s):

Gene Expression ◽

Decision Tree ◽

Beef Cattle ◽

Respiratory Disease ◽

Type I Interferon ◽

Expression Patterns ◽

Bovine Respiratory Disease ◽

Type I ◽

Complement Factor ◽

Advanced Analysis

Abstract BackgroundTranscriptomics has identified at-arrival differentially expressed genes associated with bovine respiratory disease (BRD) development; however, their use as prediction molecules necessitates further evaluation. Therefore, we aimed to selectively analyze and corroborate at-arrival mRNA expression from multiple independent populations of beef cattle. In a nested case-control study, we evaluated the expression of 56 mRNA molecules from at-arrival blood samples of 234 cattle across seven populations via NanoString nCounter gene expression profiling. Analysis of mRNA was performed with nSolver Advanced Analysis software (p<0.05), comparing cattle groups based on the diagnosis of clinical BRD within 28 days of facility arrival (n=115 Healthy; n=119 BRD); BRD was further stratified for severity based on frequency of treatment and/or mortality (Treated_1, n=89; Treated_2+, n=30). Gene expression homogeneity of variance, receiver operator characteristic (ROC) curve, and decision tree analyses were performed between severity cohorts.ResultsIncreased expression of mRNAs involved in specialized pro-resolving mediator synthesis (ALOX15, HPGD), leukocyte differentiation (LOC100297044, GCSAML, KLF17), and antimicrobial peptide production (CATHL3, GZMB, LTF) were identified in Healthy cattle. BRD cattle possessed increased expression of CFB, and mRNA related to granulocytic processes (DSG1, LRG1, MCF2L) and type-I interferon activity (HERC6, IFI6, ISG15, MX1). Healthy and Treated_1 cattle were similar in terms of gene expression, while Treated_2+ cattle were the most distinct. ROC cutoffs were used to generate an at-arrival treatment decision tree, which classified 90% of Treated_2+ individuals. ConclusionsIncreased expression of complement factor B, pro-inflammatory, and type I interferon-associated mRNA hallmark the at-arrival expression patterns of cattle that develop severe clinical BRD. Here, we corroborate at-arrival mRNA markers identified in previous transcriptome studies and generate a prediction model to be evaluated in future studies. Further research is necessary to evaluate these expression patterns in a prospective manner.

Download Full-text

Classification of Sentiment of Reviews using Supervised Machine Learning Techniques

International Journal of Rough Sets and Data Analysis ◽

10.4018/ijrsda.2017010104 ◽

2017 ◽

Vol 4 (1) ◽

pp. 56-74 ◽

Cited By ~ 14

Author(s):

Abinash Tripathy ◽

Santanu Kumar Rath

Keyword(s):

Machine Learning ◽

Sentiment Analysis ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Support Vector ◽

Performance Parameters ◽

Linear Discriminant ◽

Learning Techniques

Sentiment analysis helps to determine hidden intention of the concerned author of any topic and provides an evaluation report on the polarity of any document. The polarity may be positive, negative or neutral. It is observed that very often the data associated with the sentiment analysis consist of the feedback given by various specialists on any topic or product. Thus, the review may be categorized properly into any sort of class based on the polarity, in order to have a good knowledge about the product. This article proposes an approach to classify the review dataset made on basis of sentiment analysis into different polarity groups. Four machine learning algorithms viz., Naive Bayes (NB), Support Vector Machine (SVM), Random Forest, and Linear Discriminant Analysis (LDA) have been considered in this paper for classification process. The obtained result on values of accuracy of the algorithms are critically examined by using different performance parameters, applied on two different datasets.

Download Full-text

PSVI-2 The effect of a recombinant Mannheimia haemolytica leukotoxoid on the health and growth performance of high-risk, newly received stocker cattle metaphylactically treated with tilmicosin

Journal of Animal Science ◽

10.1093/jas/skz258.405 ◽

2019 ◽

Vol 97 (Supplement_3) ◽

pp. 196-197

Author(s):

Autumn T Pickett ◽

Jase Ball ◽

Elizabeth Kegley ◽

Ken Blue ◽

Jacob A Hagenmaier ◽

...

Keyword(s):

Body Weight ◽

High Risk ◽

Antibody Response ◽

Growth Performance ◽

Respiratory Disease ◽

Bovine Respiratory Disease ◽

Average Daily Gain ◽

Mannheimia Haemolytica ◽

Type I ◽

Bovine Virus Diarrhea

Abstract Crossbred male beef calves (n = 259; bulls = 134, steers = 125; body weight = 250 ± 3.4 kg) approximately 6 months of age and considered high-risk for developing bovine respiratory disease arrived on 3 dates (block) and were stratified by arrival castrate status and weight to be evenly distributed across pens (8 pens/block; 9 to 12 calves/pen). The pens were randomly assigned to 1 of 2 treatments: 1) Nuplura PH (administration of a Mannheimia haemolytica leukotoxoid at processing) or 2) Control (no M. haemolytica leukotoxoid). All cattle received tilmicosin on d 0 with a 5-d post-metaphylactic interval. Body weights were recorded on d -1, 0, 14, 28, 41 and 42. Blood was collected on d -1, 14, 28, and 42 and sera were harvested to determine serum neutralization titers for bovine virus diarrhea (BVD) type I and bovine anti-M. haemolytica leukotoxin antibodies. Calves were observed daily for signs of morbidity. Body weight and average daily gain were not affected (P ≥ 0.26) by treatment. The percentage of calves administered 1, 2, or 3 antibiotic treatments for clinical bovine respiratory disease did not differ (P ≥ 0.35). There was a tendency for mortality to be greater for Control compared to Nuplura PH (1.6 vs 0.0%; P = 0.10). Calves administered Nuplura PH possessed greater antibody response against M. haemolytica leukotoxin on d 14, 28, and 42 compared to Control calves (P < 0.01). There was no treatment × day interaction for antibody titers against BVD (P = 0.98). The use of a M. haemolytica leukotoxoid had no effect on growth performance and morbidity for the 42-d following receiving in this small-pen study, but reduced the incidence of mortality and did not interfere with antibody response to BVD vaccination in high-risk, newly received calves metaphylactically treated with tilmicosin on arrival.

Download Full-text

Texture-Based Metallurgical Phase Identification in Structural Steels: A Supervised Machine Learning Approach

Metals ◽

10.3390/met9050546 ◽

2019 ◽

Vol 9 (5) ◽

pp. 546 ◽

Cited By ~ 8

Author(s):

Dayakar L. Naik ◽

Hizb Ullah Sajid ◽

Ravi Kiran

Keyword(s):

Machine Learning ◽

Visual Information ◽

Supervised Machine Learning ◽

Automatic Identification ◽

Phase Identification ◽

Textural Features ◽

K Nearest Neighbor ◽

Pixel Intensity ◽

Image Domain ◽

Linear Discriminant

Automatic identification of metallurgical phases based on thresholding methods in microstructural images may not be possible when the pixel intensities associated with the metallurgical phases overlap and, hence, are indistinguishable. To circumvent this problem, additional visual information about the metallurgical phases, referred to as textural features, are considered in this study. Mathematically, textural features are the second order statistics of an image domain and can be distinct for each metallurgical phase. Textural features are evaluated from the gray level co-occurrence matrix (GLCM) of each metallurgical phase (ferrite, pearlite, and martensite) present in heat-treated ASTM A36 steels in this study. The dataset of textural features and pixel intensities generated for the metallurgical phases is used to train supervised machine learning classifiers, which are subsequently employed to predict the metallurgical phases in the microstructure. Naïve Bayes (NB), k-nearest neighbor (K-NN), linear discriminant analysis (LDA), and decision tree (DT) classifiers are the four classifiers employed in this study. The performances of all four classifiers were assessed prior to their deployment, and the classification accuracy was found to be >97%. The proposed technique has two unique advantages: (1) unlike pixel intensity-based methods, the proposed method does not misclassify the grain boundaries as a metallurgical phase, and (2) the proposed method does not require the end-user to input the number of phases present in the microstructure.

Download Full-text

MasPA: A Machine Learning Application to Predict Risk of Mastitis in Cattle from AMS Sensor Data

AgriEngineering ◽

10.3390/agriengineering3030037 ◽

2021 ◽

Vol 3 (3) ◽

pp. 575-584

Author(s):

Naeem Abdul Ghafoor ◽

Beata Sitkowska

Keyword(s):

Machine Learning ◽

Web Application ◽

Parameter Tuning ◽

Supervised Machine Learning ◽

Sensor Data ◽

Common Disease ◽

Full Potential ◽

Learning Approaches ◽

Effective Parameters ◽

Sensory Parameters

Mastitis is a common disease that prevails in cattle owing mainly to environmental pathogens; they are also the most expensive disease for cattle in dairy farms. Several prevention and treatment methods are available, although most of these options are quite expensive, especially for small farms. In this study, we utilized a dataset of 6600 cattle along with several of their sensory parameters (collected via inexpensive sensors) and their prevalence to mastitis. Supervised machine learning approaches were deployed to determine the most effective parameters that could be utilized to predict the risk of mastitis in cattle. To achieve this goal, 26 classification models were built, among which the best performing model (the highest accuracy in the shortest time) was selected. Hyper parameter tuning and K-fold cross validation were applied to further boost the top model’s performance, while at the same time avoiding bias and overfitting of the model. The model was then utilized to build a GUI application that could be used online as a web application. The application can predict the risk of mastitis in cattle from the inhale and exhale limits of their udder and their temperature with an accuracy of 98.1% and sensitivity and specificity of 99.4% and 98.8%, respectively. The full potential of this application can be utilized via the standalone version, which can be easily integrated into an automatic milking system to detect the risk of mastitis in real time.

Download Full-text