Feature selection becomes prominent, especially in the data sets with many variables and features. It will eliminate unimportant variables and improve the accuracy as well as the performance of classification. Random Forest has emerged as a quite useful algorithm that can handle the feature selection issue even with a higher number of variables. In this paper, we use three popular datasets with a higher number of variables (Bank Marketing, Car Evaluation Database, Human Activity Recognition Using Smartphones) to conduct the experiment. There are four main reasons why feature selection is essential. First, to simplify the model by reducing the number of parameters, next to decrease the training time, to reduce overfilling by enhancing generalization, and to avoid the curse of dimensionality. Besides, we evaluate and compare each accuracy and performance of the classification model, such as Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA). The highest accuracy of the model is the best classifier. Practically, this paper adopts Random Forest to select the important feature in classification. Our experiments clearly show the comparative study of the RF algorithm from different perspectives. Furthermore, we compare the result of the dataset with and without essential features selection by RF methods varImp(), Boruta, and Recursive Feature Elimination (RFE) to get the best percentage accuracy and kappa. Experimental results demonstrate that Random Forest achieves a better performance in all experiment groups.

/pdf/selecting-critical-features-for-data-classification-based-on-vlfz2eyf1v.pdf

Selecting critical features for data classification based on machine learning methods

The cryptic lifestyle of most fungi necessitates molecular identification of the guild in environmental studies. Over the past decades, rapid development and affordability of molecular tools have tremendously improved insights of the fungal diversity in all ecosystems and habitats. Yet, in spite of the progress of molecular methods, knowledge about functional properties of the fungal taxa is vague and interpretation of environmental studies in an ecologically meaningful manner remains challenging. In order to facilitate functional assignments and ecological interpretation of environmental studies we introduce a user friendly traits and character database FungalTraits operating at genus and species hypothesis levels. Combining the information from previous efforts such as FUNGuild and Fun(Fun) together with involvement of expert knowledge, we reannotated 10,210 and 151 fungal and Stramenopila genera, respectively. This resulted in a stand-alone spreadsheet dataset covering 17 lifestyle related traits of fungal and Stramenopila genera, designed for rapid functional assignments of environmental studies. In order to assign the trait states to fungal species hypotheses, the scientific community of experts manually categorised and assigned available trait information to 697,413 fungal ITS sequences. On the basis of those sequences we were able to summarise trait and host information into 92,623 fungal species hypotheses at 1% dissimilarity threshold.

/pdf/fungaltraits-a-user-friendly-traits-database-of-fungi-and-20rs5h5y04.pdf

FungalTraits: a user-friendly traits database of fungi and fungus-like stramenopiles

Genome-wide association studies have discovered numerous genomic loci associated with Alzheimer's disease (AD); yet the causal genes and variants are incompletely identified. We performed an updated genome-wide AD meta-analysis, which identified 37 risk loci, including new associations near CCDC6, TSPAN14, NCK2 and SPRED2. Using three SNP-level fine-mapping methods, we identified 21 SNPs with >50% probability each of being causally involved in AD risk and others strongly suggested by functional annotation. We followed this with colocalization analyses across 109 gene expression quantitative trait loci datasets and prioritization of genes by using protein interaction networks and tissue-specific expression. Combining this information into a quantitative score, we found that evidence converged on likely causal genes, including the above four genes, and those at previously discovered AD loci, including BIN1, APH1B, PTK2B, PILRA and CASS4.

Genome-wide meta-analysis, fine-mapping and integrative prioritization implicate new Alzheimer’s disease risk genes

Including cover crops within agricultural rotations may increase soil organic carbon (SOC). However, contradictory findings generated by on-site experiments make it necessary to perform a comprehensive assessment of interactions between cover crops, environmental and management factors, and changes in SOC. In this study, we collected data from studies that compared agricultural production with and without cover crops, and then analyzed those data using meta-analysis and regression. Our results showed that including cover crops into rotations significantly increased SOC, with an overall mean change of 15.5% (95% confidence interval of 13.8%–17.3%). Whereas medium-textured soils had highest SOC stocks (overall means of 39 Mg ha−1 with and 37 Mg ha−1 without cover crops), fine-textured soils showed the greatest increase in SOC after the inclusion of cover crops (mean change of 39.5%). Coarse-textured (11.4%) and medium-textured soils (10.3%) had comparatively smaller changes in SOC, while soils in temperate climates had greater changes (18.7%) than those in tropical climates (7.2%). Cover crop mixtures resulted in greater increases in SOC compared to mono-species cover crops, and using legumes caused greater SOC increases than grass species. Cover crop biomass positively affected SOC changes while carbon:nitrogen ratio of cover crop biomass was negatively correlated with SOC changes. Cover cropping was associated with significant SOC increases in shallow soils (≤30 cm), but not in subsurface soils (>30 cm). The regression analysis revealed that SOC changes from cover cropping correlated with improvements in soil quality, specifically decreased runoff and erosion and increased mineralizable carbon, mineralizable nitrogen, and soil nitrogen. Soil carbon change was also affected by annual temperature, number of years after start of cover crop usage, latitude, and initial SOC concentrations. Finally, the mean rate of carbon sequestration from cover cropping across all studies was 0.56 Mg ha−1 yr−1. If 15% of current global cropland were to adopt cover crops, this value would translate to 0.16 ± 0.06 Pg of carbon sequestered per year, which is ~1–2% of current fossil fuels emissions. Altogether, these results indicated that the inclusion of cover crops into agricultural rotations can enhance soil carbon concentrations, improve many soil quality parameters, and serve as a potential sink for atmosphere CO2.

A meta-analysis of global cropland soil carbon changes due to cover cropping

Changes of nitrogen deposition in China from 1980 to 2018.

The availability of high-quality RNA-sequencing and genotyping data of post-mortem brain collections from consortia such as CommonMind Consortium (CMC) and the Accelerating Medicines Partnership for Alzheimer’s Disease (AMP-AD) Consortium enable the generation of a large-scale brain cis-eQTL meta-analysis. Here we generate cerebral cortical eQTL from 1433 samples available from four cohorts (identifying >4.1 million significant eQTL for >18,000 genes), as well as cerebellar eQTL from 261 samples (identifying 874,836 significant eQTL for >10,000 genes). We find substantially improved power in the meta-analysis over individual cohort analyses, particularly in comparison to the Genotype-Tissue Expression (GTEx) Project eQTL. Additionally, we observed differences in eQTL patterns between cerebral and cerebellar brain regions. We provide these brain eQTL as a resource for use by the research community. As a proof of principle for their utility, we apply a colocalization analysis to identify genes underlying the GWAS association peaks for schizophrenia and identify a potentially novel gene colocalization with lncRNA RP11-677M14.2 (posterior probability of colocalization 0.975).

/pdf/large-eqtl-meta-analysis-reveals-differing-patterns-between-1hv8fbsjv0.pdf

K Brennand

Papers

Large eQTL meta-analysis reveals differing patterns between cerebral cortical and cerebellar brain regions.