Evaluating the performance of machine learning methods and variable selection methods for predicting difficult-to-measure traits in Holstein dairy cattle using milk infrared spectral data

Fourier-transform infrared (FTIR) spectroscopy is a powerful high-throughput phenotyping tool for predicting traits that are expensive and difficult to measure in dairy cattle. Calibration equations are often developed using standard methods, such as partial least squares (PLS) regression. Methods that employ penalization, rank-reduction, and variable selection, as well as being able to model the nonlinear relations between phenotype and FTIR, might offer improvements in predictive ability and model robustness. This study aimed to compare the predictive ability of 2 machine learning methods, namely random forest (RF) and gradient boosting machine (GBM), and penalized regression against PLS regression for predicting 3 phenotypes differing in terms of biological meaning and relationships with milk composition (i.e., phenotypes measurable directly and not directly in milk, reflecting different biological processes which can be captured using milk spectra) in Holstein-Friesian cattle under 2 cross-validation scenarios. The data set comprised phenotypic information from 471 Holstein-Friesian cows, and 3 target phenotypes were evaluated: (1) body condition score (BCS), (2) blood β-hydroxybutyrate (BHB, mmol/L), and (3) κ-casein expressed as a percentage of nitrogen (κ-CN, % N). The data set was split considering 2 cross-validation scenarios: samples-out random in which the population was randomly split into 10-folds (8-folds for training and 1-fold for validation and testing); and herd/date-out in which the population was randomly assigned to training (70% herd), validation (10%), and testing (20% herd) based on the herd and date in which the samples were collected. The random grid search was performed using the training subset for the hyperparameter optimization and the validation set was used for the generalization of prediction error. The trained model was then used to assess the final prediction in the testing subset. The grid search for penalized regression evidenced that the elastic net (EN) was the best regularization with increase in predictive ability of 5%. The performance of PLS (standard model) was compared against 2 machine learning techniques and penalized regression using 2 cross-validation scenarios. Machine learning methods showed a greater predictive ability for BCS (0.63 for GBM and 0.61 for RF), BHB (0.80 for GBM and 0.79 for RF), and κ-CN (0.81 for GBM and 0.80 for RF) in samples-out cross-validation. Considering a herd/date-out cross-validation these values were 0.58 (GBM and RF) for BCS, 0.73 (GBM and RF) for BHB, and 0.77 (GBM and RF) for κ-CN. The GBM model tended to outperform other methods in predictive ability around 4%, 1%, and 7% for EN, RF, and PLS, respectively. The prediction accuracies of the GBM and RF models were similar, and differed statistically from the PLS model in samples-out random cross-validation. Although, machine learning techniques outperformed PLS in herd/date-out cross-validation, no significant differences were observed in terms of predictive ability due to the large standard deviation observed for predictions. Overall, GBM achieved the highest accuracy of FTIR-based prediction of the different phenotypic traits across the cross-validation scenarios. These results indicate that GBM is a promising method for obtaining more accurate FTIR-based predictions for different phenotypes in dairy cattle.     

BSig: evaluating the statistical significance of biclustering solutions

Statistical evaluation of biclustering solutions is essential to guarantee the absence of spurious relations and to validate the high number of scientific statements inferred from unsupervised data analysis without a proper statistical ground. Most biclustering methods rely on merit functions to discover biclusters with specific homogeneity criteria. However, strong homogeneity does not guarantee the statistical significance of biclustering solutions. Furthermore, although some biclustering methods test the statistical significance of specific types of biclusters, there are no methods to assess the significance of flexible biclustering models. This work proposes a method to evaluate the statistical significance of biclustering solutions. It integrates state-of-the-art statistical views on the significance of local patterns and extends them with new principles to assess the significance of biclusters with additive, multiplicative, symmetric, order-preserving and plaid coherencies. The proposed statistical tests provide the unprecedented possibility to minimize the number of false positive biclusters without incurring on false negatives, and to compare state-of-the-art biclustering algorithms according to the statistical significance of their outputs. Results on synthetic and real data support the soundness and relevance of the proposed contributions, and stress the need to combine significance and homogeneity criteria to guide the search for biclusters.     

Influence of Reaction Conditions on Diacid Formation During Au-Catalyzed Oxidation of Glycerol and Hydroxymethylfurfural

The selective oxidation of glycerol and 5-hydroxymethylfurfural (HMF) to diacids over supported gold catalysts (Au/C and Au/TiO₂) in liquid water at mild temperatures was a strong function of the added base such as NaOH. Use of hydrotalcite as a solid base in place of NaOH in the HMF reaction medium facilitated the production of diacid over Au/TiO₂, but extensive leaching of magnesium suggested that hydrotalcite was consumed stoichiometrically in the reaction. Production of diacids from glycerol oxidation over supported Au catalysts was promoted by operating in a continuous flow reactor and by increasing the catalyst loading in a semi-batch reactor. Trace inhibitors formed by conversion of the product monoacid are proposed to account for the generally low selectivity to diacids over gold catalysts.     

Directed inorganic modification of bi-component polymer fibers by selective vapor reaction and atomic layer deposition

Nanocomposite organic/inorganic materials with spatially-controlled composition can be formed using vapor-phase atomic layer deposition (ALD) on bi-component polymer fibers. The ALD process promotes selective precursor infusion into the inner core of a core/shell polymer fiber, yielding nanoparticles encapsulated within the core. Likewise, choosing alternate precursors or reaction conditions yield particles or films on the outer polymer shell. In-situ infrared spectroscopy and transmission electron microscopy show that infusion yields selective dispersion of aluminum oxide in different polymer regions, forming fine nanoparticle dispersions or films. Selective inclusion of metal oxide materials during atomic layer deposition on polymers can create unique organic/inorganic composite structures for many advanced uses.     

Role of Btg2 in the Progression of a PDGF-Induced Oligodendroglioma Model

Tumor progression is a key aspect in oncology. Not even the overexpression of a powerful oncogenic stimulus such as platelet derived growth factor-B (PDGF-B) is sufficient per se to confer full malignancy to cells. In previous studies we showed that neural progenitors overexpressing PDGF-B need to undergo progression to acquire the capability to give rise to secondary tumor following transplant. By comparing the expression profile of PDGF-expressing cells before and after progression, we found that progressed tumors consistently downregulate the expression of the antiproliferative gene Btg2. We therefore tested whether the downregulation of Btg2 is sufficient and necessary for glioma progression with loss and gain of function experiments. Our results show that downregulation of Btg2 is not sufficient but is necessary for tumor progression since the re-introduction of Btg2 in fully progressed tumors dramatically impairs their gliomagenic potential. These results suggest an important role of Btg2 in glioma progression. Accordingly with this view, the analysis of public datasets of human gliomas showed that reduced level of Btg2 expression correlates with a significantly worse prognosis.     

Operator equalisation for bloat free genetic programming and a survey of bloat control methods

Bloat can be defined as an excess of code growth without a corresponding improvement in fitness. This problem has been one of the most intensively studied subjects since the beginnings of Genetic Programming. This paper begins by briefly reviewing the theories explaining bloat, and presenting a comprehensive survey and taxonomy of many of the bloat control methods published in the literature through the years. Particular attention is then given to the new Crossover Bias theory and the bloat control method it inspired, Operator Equalisation (OpEq). Two implementations of OpEq are described in detail. The results presented clearly show that Genetic Programming using OpEq is essentially bloat free. We discuss the advantages and shortcomings of each different implementation, and the unexpected effect of OpEq on overfitting. We observe the evolutionary dynamics of OpEq and address its potential to be extended and integrated into different elements of the evolutionary process.     

Multivariate Analysis of the Stability of Spray-Dried Eupenicillium javanicum Peptidases

Peptidases occupy a central position in the enzyme market because of their importance in many areas, such as for physiological processes, foods, and detergents, as well as in the pharmaceutical, leather, and biotechnology industries. Microbial production is among the major sources of peptidases because it presents many advantages when compared with other methods. In this study, the metallopeptidases produced by the fungus Eupenicillium javanicum under a solid-state fermentation bioprocess were spray-dried. The enzymatic extract was dried using drying adjuvants, and optimal conditions for preserving enzymatic activity were studied following a Box-Behnken experimental design. The spray process factors studied were the air-drying temperature, enzyme feed flow rate, and the proportion of enzyme/additive. The responses analyzed were the dry extract yield and enzymatic activity after spray drying. Additionally, the stability of the dry extracts was assessed during 180 days at 4°C and 25°C. The results revealed extract yields of up to 66.12% and good enzymatic activity for intermediate values of temperature and adjuvant proportions. Furthermore, the dried enzymatic extracts showed potential for future commercial applications because of their stability at 25°C for 180 days.