Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth

For the untargeted analysis of the metabolome of biological samples with liquid chromatography–mass spectrometry (LC-MS), high-dimensional data sets containing many different metabolites are obtained. Since the utilization of these complex data is challenging, different machine learning approaches have been developed. Those methods are usually applied as black box classification tools, and detailed information about class differences that result from the complex interplay of the metabolites are not obtained. Here, we demonstrate that this information is accessible by the application of random forest (RF) approaches and especially by surrogate minimal depth (SMD) that is applied to metabolomics data for the first time. We show this by the selection of important features and the evaluation of their mutual impact on the multi-level classification of white asparagus regarding provenance and biological identity. SMD enables the identification of multiple features from the same metabolites and reveals meaningful biological relations, proving its high potential for the comprehensive utilization of high-dimensional metabolomics data.

LR Hunting: A Random Forest Based Cell–Cell Interaction Discovery Method for Single-Cell Gene Expression Data

Cell–cell interactions (CCIs) and cell–cell communication (CCC) are critical for maintaining complex biological systems. The availability of single-cell RNA sequencing (scRNA-seq) data opens new avenues for deciphering CCIs and CCCs through identifying ligand-receptor (LR) gene interactions between cells. However, most methods were developed to examine the LR interactions of individual pairs of genes. Here, we propose a novel approach named LR hunting which first uses random forests (RFs)-based data imputation technique to link the data between different cell types. To guarantee the robustness of the data imputation procedure, we repeat the computation procedures multiple times to generate aggregated imputed minimal depth index (IMDI). Next, we identify significant LR interactions among all combinations of LR pairs simultaneously using unsupervised RFs. We demonstrated LR hunting can recover biological meaningful CCIs using a mouse cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) dataset and a triple-negative breast cancer scRNA-seq dataset.

Development of random forest model as decision support tool in water resources management of Ogun headwater catchments

Water resources cannot be effectively managed unless potential evapotranspiration is determined with high accuracy at headwater catchments. The study presents the most suitable feature combinations for building a reliable potential evapotranspiration (PET) model in the headwater catchments of Ogun River Basin, Southwest Nigeria. Using rainfall (R), wind speed (U2), sunshine hour (S), relative humidity (Rh), minimum temperature (Tmin) and maximum temperature (Tmax) as input features, a Random Forest (RF) model was developed to predict PET. Although the model yielded satisfactory results, it was subjected to the minimal depth and percentage increase in mean square error (%IncMSE). This was done to reduce the input features and to increase model accuracy. Thereafter various combinations of important input features were examined in order to establish the best combinations required to yield optimum results. The study revealed that although Tmax (%IncMSE of 652.09, p value < 0.05) and Rh (%IncMSE of 254.36, p value < 0.05) were the most important predictors of PET, a more reliable RF model was achieved when S and U2 were combined with them. Consequently, this study presents RF with a combination of four parameters (Tmax, Rh, S and U2) as an excellent computational technique for the prediction of PET in headwater catchments.

Lung Decortication With Argon Plasma Energy for the Treatment of Chronic Pleural Empyema

Lung decortication for the treatment of chronic pleural empyema remains a technically challenging procedure that is associated with bleeding and air leak. The recent advent of pure argon plasma has provided thoracic surgeons with an electrically neutral energy source for dissection and coagulation of pulmonary tissue with minimal depth of necrosis. In this article, we describe the technique of lung decortication with argon plasma energy (PlasmaJet, Plasma Surgical, Roswell, GA, USA) for the treatment of chronic pleural empyema. With appropriate application, the PlasmaJet can facilitate the removal of fibrous cortex with satisfactory hemostasis and aerostasis. Argon plasma energy can potentially be a useful adjunct in lung decortication. Controlled trials are needed to determine its role in the surgical management of advanced pleural empyema.

The topological nilpotence degree of a Noetherian unstable algebra

We investigate the topological nilpotence degree, in the sense of Henn–Lannes–Schwartz, of a connected Noetherian unstable algebra R. When R is the mod p cohomology ring of a compact Lie group, Kuhn showed how this invariant is controlled by centralizers of elementary abelian p-subgroups. By replacing centralizers of elementary abelian p-subgroups with components of Lannes’ T-functor, and utilizing the techniques of unstable algebras over the Steenrod algebra, we are able to generalize Kuhn’s result to a large class of connected Noetherian unstable algebras. We show how this generalizes Kuhn’s result to more general classes of groups, such as groups of finite virtual cohomological dimension, profinite groups, and Kac–Moody groups. In fact, our results apply much more generally, for example, we establish results for p-local compact groups in the sense of Broto–Levi–Oliver, for connected H-spaces with Noetherian mod p cohomology, and for the Borel equivariant cohomology of a compact Lie group acting on a manifold. Along the way we establish several results of independent interest. For example, we formulate and prove a version of Carlson’s depth conjecture in the case of a Noetherian unstable algebra of minimal depth.

Towards a multi-basin SWAT model for the migration of nutrients and pesticides to Puck Bay (Southern Baltic Sea)

Background This paper analyzes the impact of changes in fertilization on crop yields and the runoff of nutrients from a small agricultural catchment (176 km2) to a shallow bay, using the SWAT model. Puck Bay is part of the Gulf of Gdansk and belongs to the Baltic Sea. The whole area of Puck Bay (364 km2) is protected (Natura 2000) yet despite this it suffers from eutrophication problems due to the relatively minimal depth and difficult water exchange. Methods The paper presents a comparison of the calculated yields and the runoff of nutrients and pesticides in the SWAT model, for a small agricultural coastal catchment. Calculations were made for 13 crop scenarios with weather data from 2011 to 2019. For each crop, an agriculture calendar was made. Two variants of fertilization were considered (autofertilization mode and according to the calendar). The nutrient runoff was calculated depending on the adopted scenario. In addition, the fate of selected pesticides was simulated. Results Depending on the crop, the annual load of NO3into the stream ranged from 0.74 to 3.65 kg ha−1. The annual load of organic phosphorous into the stream was between 0.686 and 3.64 kg ha−1. This is lower than in the majority of EU or Baltic countries. The surface runoff of dissolved Glyphosate was equal to 286 mg ha−1. The annual loads of nutrients from the catchment area are equivalent in both fertilization modes. Regardless of the selected fertilization mode, in addition to the dosage, the form of nutrients is important for the model.