Use of partial least squares regression to predict single nucleotide polymorphism marker genotypes when some animals are genotyped with a low-density panel

Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments

Between January and October of 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has infected more than 34 million persons in a worldwide pandemic leading to over one million deaths worldwide (data from the Johns Hopkins University). Since the virus begun to spread, emergency departments were busy with COVID-19 patients for whom a quick decision regarding in- or outpatient care was required. The virus can cause characteristic abnormalities in chest radiographs (CXR), but, due to the low sensitivity of CXR, additional variables and criteria are needed to accurately predict risk. Here, we describe a computerized system primarily aimed at extracting the most relevant radiological, clinical, and laboratory variables for improving patient risk prediction, and secondarily at presenting an explainable machine learning system, which may provide simple decision criteria to be used by clinicians as a support for assessing patient risk. To achieve robust and reliable variable selection, Boruta and Random Forest (RF) are combined in a 10-fold cross-validation scheme to produce a variable importance estimate not biased by the presence of surrogates. The most important variables are then selected to train a RF classifier, whose rules may be extracted, simplified, and pruned to finally build an associative tree, particularly appealing for its simplicity. Results show that the radiological score automatically computed through a neural network is highly correlated with the score computed by radiologists, and that laboratory variables, together with the number of comorbidities, aid risk prediction. The prediction performance of our approach was compared to that that of generalized linear models and shown to be effective and robust. The proposed machine learning-based computational system can be easily deployed and used in emergency departments for rapid and accurate risk prediction in COVID-19 patients.

Complex Data Imputation by Auto-Encoders and Convolutional Neural Networks—A Case Study on Genome Gap-Filling

Missing data imputation has been a hot topic in the past decade, and many state-of-the-art works have been presented to propose novel, interesting solutions that have been applied in a variety of fields. In the past decade, the successful results achieved by deep learning techniques have opened the way to their application for solving difficult problems where human skill is not able to provide a reliable solution. Not surprisingly, some deep learners, mainly exploiting encoder-decoder architectures, have also been designed and applied to the task of missing data imputation. However, most of the proposed imputation techniques have not been designed to tackle “complex data”, that is high dimensional data belonging to datasets with huge cardinality and describing complex problems. Precisely, they often need critical parameters to be manually set or exploit complex architecture and/or training phases that make their computational load impracticable. In this paper, after clustering the state-of-the-art imputation techniques into three broad categories, we briefly review the most representative methods and then describe our data imputation proposals, which exploit deep learning techniques specifically designed to handle complex data. Comparative tests on genome sequences show that our deep learning imputers outperform the state-of-the-art KNN-imputation method when filling gaps in human genome sequences.

Relationships among ensiling, nutritional, fermentative, microbiological traits and contamination in corn silages addressed with partial least squares regression

The objective of this work was to reduce the predictor dimensionality and to develop a model able to forecast contamination in corn silages. A survey on 33 dairy farms was performed, and samples from core, lateral, and apical parts of the feed-out face of corn silage bunkers were analyzed for chemical, biological (digestible and indigestible NDF), fermentative (pH, ammonia nitrogen, lactic acid, VFA, and ethanol), and microbiological (yeasts and molds) traits. Corn silage samples were analyzed for cell and spore counts by adoption of a molecular DNA-based method. A partial least squares (PLS) regression with a leave-one-out cross-validation method was used to reduce the dimensionality of the original predictors ( = 30) by projecting the independent variables into latent constructs. In a first step of the model development, the importance of independent variables in predicting contamination was assessed by plotting factor loadings of both dependent and independent variables on the first 2 components and by verifying for each predictor the variable influence on projection values adopting the Wold's criterion as well as the entity of standardized regression coefficients. Three ensiling characteristics (bunker type, presence of lateral wrap plastic film, and penetration resistance as a measurement of the ensiled mass density), a chemical trait (DM), 9 characterizations of the fermentative profile (pH, ammonia nitrogen, acetic acid, butyric acid, isobutyric acid, valeric acid, isovaleric acid, ethanol, and lactic acid), and 2 microbiological traits (yeasts and molds) were retained as important terms in the PLS model. Three reduced-variable PLS (rPLS) regressions-the first based on ensiling, chemical, fermentative, and microbiological retained important variables (rPLSecfm); the second based on chemical, fermentative, and microbiological retained important traits (rPLScfm); and the last based on only chemical and fermentative retained important variables (rPLScf)-were performed. The model that best fit the measurements was rPLSecfm. The rPLScfm and rPLScf models had similar regression performances but higher mean square errors of prediction than rPLSecfm. However, all tested models seemed adequate to rank corn silages for low, medium, and high risks of contamination. To avoid the visit on farm by trained people required to measure penetration resistance, the use of the rPLScf model is suggested as a useful tool to assess the risk of in corn silage.

Use of partial least squares regression to impute SNP genotypes in Italian cattle breeds

Background

The objective of the present study was to test the ability of the partial least squares regression technique to impute genotypes from low density single nucleotide polymorphisms (SNP) panels i.e. 3K or 7K to a high density panel with 50K SNP. No pedigree information was used.

Methods

Data consisted of 2093 Holstein, 749 Brown Swiss and 479 Simmental bulls genotyped with the Illumina 50K Beadchip. First, a single-breed approach was applied by using only data from Holstein animals. Then, to enlarge the training population, data from the three breeds were combined and a multi-breed analysis was performed. Accuracies of genotypes imputed using the partial least squares regression method were compared with those obtained by using the Beagle software. The impact of genotype imputation on breeding value prediction was evaluated for milk yield, fat content and protein content.

Results

In the single-breed approach, the accuracy of imputation using partial least squares regression was around 90 and 94% for the 3K and 7K platforms, respectively; corresponding accuracies obtained with Beagle were around 85% and 90%. Moreover, computing time required by the partial least squares regression method was on average around 10 times lower than computing time required by Beagle. Using the partial least squares regression method in the multi-breed resulted in lower imputation accuracies than using single-breed data. The impact of the SNP-genotype imputation on the accuracy of direct genomic breeding values was small. The correlation between estimates of genetic merit obtained by using imputed versus actual genotypes was around 0.96 for the 7K chip.

Conclusions

Results of the present work suggested that the partial least squares regression imputation method could be useful to impute SNP genotypes when pedigree information is not available.