Quantification of differences in resistance to gastrointestinal nematode infections in sheep using a multivariate blood parameter.

Breeding for resistance to gastrointestinal nematodes (GIN) in sheep relies largely on the use of worm egg counts (WEC) to identify animals that are able to resist infection. As an alternative to such measures of parasite load we aimed to develop a method to identify animals showing resistance to GIN infection based on the impact of the infection on blood parameters. We hypothesized that blood parameters may provide a measure of infection level with a blood-feeding parasite through perturbation of red blood cell parameters due to feeding behaviour of the parasite, and white blood cell parameters through the mounting of an immune response in the host animal. We measured a set of blood parameters in 390 sheep that had been exposed to an artificial regime of repeated challenges with Trichostrongylus colubriformis followed by Haemonchus contortus. A simple analysis revealed strong relationships between single blood parameters and WECs with correlation coefficients -0.54 to -0.60. We then used more complex multi-variate methods based on supervised classifier models (including Bayesian Network) as well as regression models (Lasso and Elastic Net) to study the relationships between WECs and blood parameters, and derived algorithms describing the relationships. The ability of these algorithms to classify sheep GIN resistance status was tested using the WEC and blood parameters collected from a different group of 418 sheep that had acquired natural infections of H. contortus from pasture. We identified the most resistant and most susceptible animals (10% percentiles) of this group based on WECs, and then compared the identities of these animals to the identities of animals that were predicted to be most resistant and most susceptible by our algorithms. The models showed varying abilities to predict susceptible and resistant sheep, with up to 65% of the most susceptible animals and 30% of the most resistant animals identified by the Elastic Net model algorithms. The prediction algorithms derived from female sheep data performed better than those for male sheep in some cases, with the predicted animals accounting for up to 50-60% of the actual resistant and susceptible female animals. Heritability values were calculated for blood parameters and the aggregate trait descriptions defined by the novel prediction algorithms. The aggregate trait descriptions were moderately heritable and may therefore be suitable for use in genetic selection strategies. The present study indicates that multivariate models based on blood parameter data showed some ability to predict the resistance status of sheep to infection with H. contortus.

Machine learning approach for pooled DNA sample calibration.

BACKGROUND: Despite ongoing reduction in genotyping costs, genomic studies involving large numbers of species with low economic value (such as Black Tiger prawns) remain cost prohibitive. In this scenario DNA pooling is an attractive option to reduce genotyping costs. However, genotyping of pooled samples comprising DNA from many individuals is challenging due to the presence of errors that exceed the allele frequency quantisation size and therefore cannot be simply corrected by clustering techniques. The solution to the calibration problem is a correction to the allele frequency to mitigate errors incurred in the measurement process. We highlight the limitations of the existing calibration solutions such as the fact they impose assumptions on the variation between allele frequencies 0, 0.5, and 1.0, and address a limited set of error types. We propose a novel machine learning method to address the limitations identified. RESULTS: The approach is tested on SNPs genotyped with the Sequenom iPLEX platform and compared to existing state of the art calibration methods. The new method is capable of reducing the mean square error in allele frequency to half that achievable with existing approaches. Furthermore for the first time we demonstrate the importance of carefully considering the choice of training data when using calibration approaches built from pooled data. CONCLUSION: This paper demonstrates that improvements in pooled allele frequency estimates result if the genotyping platform is characterised at allele frequencies other than the homozygous and heterozygous cases. Techniques capable of incorporating such information are described along with aspects of implementation.

Allele frequency calibration for SNP based genotyping of DNA pools: A regression based local-global error fusion method.

BACKGROUND: The costs associated with developing high density microarray technologies are prohibitive for genotyping animals when there is low economic value associated with a single animal (e.g. prawns). DNA pooling is an attempt to address this issue by combining multiple DNA samples prior to genotyping. Instead of genotyping the DNA samples of the individuals, a mixture of DNA samples (i.e. the pool) from the individuals is genotyped only once. This greatly reduces the cost of genotyping. Pooled samples are subject to greater genotyping inaccuracies than individual samples. Wrong genotyping will lead to wrong biological conclusions. It is thus required to calibrate the resulting genotypes (allele frequencies). METHODS: We present a regression based approach to translate raw array output to allele frequency. During training, few pools and the individuals that constitute the pools are genotyped. Given the genotypes of individuals that constitute the pool, we compute the true allele frequency. We then train a regression algorithm to produce a mapping between the raw array outputs to the true allele frequency. We test the algorithm using pool samples withheld from the training set. During prediction, we use this map to genotype pools with no prior knowledge of the individuals constituting the pools. RESULTS AND DISCUSSION: After data quality control we have available a dataset comprised of 912 pools. We estimate allele frequency using three approaches: the raw data, a commonly used piecewise linear transformation, and the proposed local-global learner fusion method. The resulting RMS errors for the three approaches are 0.135, 0.120, and 0.080 respectively.

Novel layered clustering-based approach for generating ensemble of classifiers.

This paper introduces a novel concept for creating an ensemble of classifiers. The concept is based on generating an ensemble of classifiers through clustering of data at multiple layers. The ensemble classifier model generates a set of alternative clustering of a dataset at different layers by randomly initializing the clustering parameters and trains a set of base classifiers on the patterns at different clusters in different layers. A test pattern is classified by first finding the appropriate cluster at each layer and then using the corresponding base classifier. The decisions obtained at different layers are fused into a final verdict using majority voting. As the base classifiers are trained on overlapping patterns at different layers, the proposed approach achieves diversity among the individual classifiers. Identification of difficult-to-classify patterns through clustering as well as achievement of diversity through layering leads to better classification results as evidenced from the experimental results.