Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India.

Gully erosion is a form of natural disaster and one of the land loss mechanisms causing severe problems worldwide. This study aims to delineate the areas with the most severe gully erosion susceptibility (GES) using the machine learning techniques Random Forest (RF), Gradient Boosted Regression Tree (GBRT), Naïve Bayes Tree (NBT), and Tree Ensemble (TE). The gully inventory map (GIM) consists of 120 gullies. Of the 120 gullies, 84 gullies (70%) were used for training and 36 gullies (30%) were used to validate the models. Fourteen gully conditioning factors (GCFs) were used for GES modeling and the relationships between the GCFs and gully erosion was assessed using the weight-of-evidence (WofE) model. The GES maps were prepared using RF, GBRT, NBT, and TE and were validated using area under the receiver operating characteristic(AUROC) curve, the seed cell area index (SCAI) and five statistical measures including precision (PPV), false discovery rate (FDR), accuracy, mean absolute error (MAE), and root mean squared error (RMSE). Nearly 7% of the basin has high to very high susceptibility for gully erosion. Validation results proved the excellent ability of these models to predict the GES. Of the analyzed models, the RF (AUROC = 0.96, PPV = 1.00, FDR = 0.00, accuracy = 0.87, MAE = 0.11, RMSE = 0.19 for validation dataset) is accurate enough for modeling and better suited for GES modeling than the other models. Therefore, the RF model can be used to model the GES areas not only in this river basin but also in other areas with the same geo-environmental conditions.

Argus: An open-source and flexible software application for automated quantification of behavior during social interaction in adult zebrafish.

Zebrafish show great potential for behavioral neuroscience. Promising lines of research, however, require the development and validation of software tools that will allow automated and cost-effective behavioral analysis. Building on our previous work with the RealFishTracker (in-house-developed tracking system), we present Argus, a data extraction and analysis tool built in the open-source R language for behavioral researchers without any expertise in R. Argus includes a new, user-friendly, and efficient graphical user interface, instead of a command-line interface, and offers simplicity and flexibility in measuring complex zebrafish behavior through customizable parameters. In this article, we compare Argus with Noldus EthoVision and Noldus The Observer, to validate this new system. All three software applications were originally designed to quantify the behavior of a single subject. We first also performed an analysis of the movement of individual fish and compared the performance of the three software applications. Next we computed and quantified the behavioral variables that characterize dyadic interactions between zebrafish. We found that Argus and EthoVision extract similar absolute values and patterns of changes in these values for several behavioral measures, including speed, freezing, erratic movement, and interindividual distance. In contrast, the manual coding of behavior in The Observer showed weaker correlations with the two tracking methods (EthoVision and Argus). Thus, Argus is a novel, cost-effective, and customizable method for the analysis of adult zebrafish behavior that may be utilized for the behavioral quantification of both single and dyadic interacting subjects, but further sophistication will be needed for the proper identification of complex motor patterns, measures that a human observers can easily detect.

A Bayesian estimate of the concordance correlation coefficient with skewed data.

Concordance correlation coefficient (CCC) is one of the most popular scaled indices used to evaluate agreement. Most commonly, it is used under the assumption that data is normally distributed. This assumption, however, does not apply to skewed data sets. While methods for the estimation of the CCC of skewed data sets have been introduced and studied, the Bayesian approach and its comparison with the previous methods has been lacking. In this study, we propose a Bayesian method for the estimation of the CCC of skewed data sets and compare it with the best method previously investigated. The proposed method has certain advantages. It tends to outperform the best method studied before when the variation of the data is mainly from the random subject effect instead of error. Furthermore, it allows for greater flexibility in application by enabling incorporation of missing data, confounding covariates, and replications, which was not considered previously. The superiority of this new approach is demonstrated using simulation as well as real-life biomarker data sets used in an electroencephalography clinical study. The implementation of the Bayesian method is accessible through the Comprehensive R Archive Network.

Automated machine learning with R: AutoML tools for beginners in clinical research.

Recently, interest in machine learning (ML) has increased as the application fields have expanded significantly. Although ML methods excel in many fields, establishing an ML pipeline requires considerable time and human resources. Automated ML (AutoML) tools offer a solution by automating repetitive tasks, such as data preprocessing, model selection, hyperparameter optimization, and prediction analysis. This review introduces the use of AutoML tools for general research, including clinical studies. In particular, it outlines a simple approach that is accessible to beginners using the R programming language (R Foundation for Statistical Computing). In addition, the practical code and output results for binary classification are provided to facilitate direct application by clinical researchers in future studies.

Intact cell mass spectrometry coupled with machine learning reveals minute changes induced by single gene silencing.

Intact (whole) cell MALDI TOF mass spectrometry is a commonly used tool in clinical microbiology for several decades. Recently it was introduced to analysis of eukaryotic cells, including cancer and stem cells. Besides targeted metabolomic and proteomic applications, the intact cell MALDI TOF mass spectrometry provides a sufficient sensitivity and specificity to discriminate cell types, isogenous cell lines or even the metabolic states. This makes the intact cell MALDI TOF mass spectrometry a promising tool for quality control in advanced cell cultures with a potential to reveal batch-to-batch variation, aberrant clones, or unwanted shifts in cell phenotype. However, cellular alterations induced by change in expression of a single gene has not been addressed by intact cell mass spectrometry yet. In this work we used a well-characterized human ovarian cancer cell line SKOV3 with silenced expression of a tumor suppressor candidate 3 gene (TUSC3). TUSC3 is involved in co-translational N-glycosylation of proteins with well-known global impact on cell phenotype. Altogether, this experimental design represents a highly suitable model for optimization of intact cell mass spectrometry and analysis of spectral data. Here we investigated five machine learning algorithms (k-nearest neighbors, decision tree, random forest, partial least squares discrimination, and artificial neural network) and optimized their performance either in pure populations or in two-component mixtures composed of cells with normal or silenced expression of TUSC3. All five algorithms reached accuracy over 90 % and were able to reveal even subtle changes in mass spectra corresponding to alterations of TUSC3 expression. In summary, we demonstrate that spectral fingerprints generated by intact cell MALDI-TOF mass spectrometry coupled to a machine learning classifier can reveal minute changes induced by alteration of a single gene, and therefore contribute to the portfolio of quality control applications in routine cell and tissue cultures.

End-to-End Data Automation for Pooled Sample SARS-CoV-2 Using R and Other Open-Source Tools.

BACKGROUND: Due to supply chain shortages of reagents for real-time (RT)-PCR for SARS-CoV-2 and increasing demand on technical staff, an end-to-end data automation strategy for SARS-CoV-2 sample pooling and singleton analysis became necessary in the summer of 2020. METHODS: Using entirely open source software tools-Linux, bash, R, RShiny, ShinyProxy, and Docker-we developed a modular software application stack to manage the preanalytical, analytical, and postanalytical processes for singleton and pooled testing in a 5-week time frame. RESULTS: Pooling was operationalized for 81 days, during which time 64 pooled runs were performed for a total of 5320 sample pools and approximately 21 280 patient samples in 4:1 format. A total of 17 580 negative pooled results were released in bulk. After pooling was discontinued, the application stack was used for singleton analysis and modified to release all viral RT-PCR results from our laboratory. To date, 236 109 samples have been processed avoiding over 610 000 transcriptions. CONCLUSIONS: We present an end-to-end data automation strategy connecting 11 devices, one network attached storage, 2 Linux servers, and the laboratory information system.

BaroWavelet: An R-based tool for dynamic baroreflex evaluation through wavelet analysis techniques.

BACKGROUND AND OBJECTIVE: Baroreflex sensitivity constitutes an indicator of the function of the baroreceptor control mechanism of blood pressure levels. It can be computed after estimating heart rate and blood pressure variability. We propose a novel tool for the evaluation of baroreflex sensitivity using wavelet analysis methods. This tool, known as BaroWavelet, incorporates an algorithm proposal based on the analysis methodology of the RHRV software package, as well as other conventional techniques. Our objectives are to develop and evaluate the tool, by testing its ability to detect changes in baroreflex sensitivity in humans. METHODS: The code for this tool was designed in the R programming environment and was organized into two analysis routines and a graphical interface. Simulated recordings of blood pressure and inter-beat intervals were employed for an initial evaluation of the tool in a controlled environment. Finally, similar recordings obtained during supine and orthostatic postural evaluations, from patients that belonged to the open-access EUROBAVAR data set, were analyzed. RESULTS: BaroWavelet identified the scripted changes of the baroreflex sensitivity in the simulated data. The algorithm proposal was also able to better retain additional information regarding the dynamics of the baroreflex. In the EUROBAVAR subjects, baroreflex sensitivity components were significantly smaller during orthostatism when compared with the supine position. CONCLUSIONS: BaroWavelet managed to characterize baroreflex dynamics from the recordings, which were consistent with the findings reported in the literature. This demonstrates its effectiveness to perform these analyses. We suggest that this tool may be of use in research and for the evaluation of baroreflex sensitivity with clinical and therapeutic purposes. The new tool is available at the official GitHub repository of the Autonomic Nervous System Unit of the University of Málaga (https://github.com/CIMES-USNA-UMA/BaroWavelet).

Implementation of machine learning in DNA barcoding for determining the plant family taxonomy.

The DNA barcoding approach has been used extensively in taxonomy and phylogenetics. The differences in certain DNA sequences are able to differentiate and help classify organisms into taxa. It has been used in cases of taxonomic disputes where morphology by itself is insufficient. This research aimed to utilize hierarchical clustering, an unsupervised machine learning method, to determine and resolve disputes in plant family taxonomy. We take a case study of Leguminosae that historically some classify into three families (Fabaceae, Caesalpiniaceae, and Mimosaceae) but others classify into one family (Leguminosae). This study is divided into several phases, which are: (i) data collection, (ii) data preprocessing, (iii) finding the best distance method, and (iv) determining disputed family. The data used are collected from several sources, including National Center for Biotechnology Information (NCBI), journals, and websites. The data for validation of the methods were collected from NCBI. This was used to determine the best distance method for differentiating families or genera. The data for the case study in the Leguminosae group was collected from journals and a website. From the experiment that we have conducted, we found that the Pearson method is the best distance method to do clustering ITS sequence of plants, both in accuracy and computational cost. We use the Pearson method to determine the disputed family between Leguminosae. We found that the case study of Leguminosae should be grouped into one family based on our research.

Analysis of an event study using the Fama-French five-factor model: teaching approaches including spreadsheets and the R programming language.

The current financial education framework has an increasing need to introduce tools that facilitate the application of theoretical models to real-world data and contexts. However, only a limited number of free tools are available for this purpose. Given this lack of tools, the present study provides two approaches to facilitate the implementation of an event study. The first approach consists of a set of MS Excel files based on the Fama-French five-factor model, which allows the application of the event study methodology in a semi-automatic manner. The second approach is an open-source R-programmed tool through which results can be obtained in the context of an event study without the need for programming knowledge. This tool widens the calculus possibilities provided by the first approach and offers the option to apply not only the Fama-French five-factor model but also other models that are common in the financial literature. It is a user-friendly tool that enables reproducibility of the analysis and ensures that the calculations are free of manipulation errors. Both approaches are freely available and ready-to-use.

Manipulating and Basic Analysis of Tabular Metagenomics Datasets Using R.

Handling and manipulating tabular datasets is a critical step in every metagenomics analysis pipeline. The R statistical programming language offers a variety of versatile tools for working with tabular data that allow for the development of computationally efficient and reproducible workflows. Here we outline the basics of the R programming language and showcase a number of tools for data manipulation and basic analysis of metagenomics datasets.

Metagenomics Data Visualization Using R.

Communicating key finds is a crucial part of the research process. Data visualization is the field of graphically representing data to help communicate key findings. Building on previous chapters around data manipulating using the R programming language this, chapter will explore how to use R to plot data and generate high-quality graphics. It will cover plotting using the base R plotting functionality and introduce the famous ggplot2 package [2] that is widely used for data visualization in R. After this general introduction to data visualization tools, the chapter will explore more specific data visualization techniques for metagenomics data and their use cases using these basic packages.

Personality Pathology and Suicide Risk: Examining the Relationship Between DSM-5 Alternative Model Traits and Suicidal Ideation and Behavior in College-Aged Individuals.

BACKGROUND: This study examines the link between personality pathology and suicide risk regarding the DSM-5 alternative model of personality disorders. METHOD: The study investigates the facets, domains, internalizing, and externalizing of personality pathology and their correlation and predictive significance for suicidal ideation and behavior. This study examined a diverse and balanced sample of 1,398 college students aged between 18- and 29-year-olds from nine colleges in Kafrelshiekh University, with nearly equal representation of both genders (687 males, 711 females), a mix of rural and urban residents (807 rural, 591 urban), and a wide range of socioeconomic backgrounds (15 very low SES, 84 low SES, 878 moderate SES, 364 high SES, and 57 very high SES). The Personality Inventory for the DSM-5 (PID-5) was utilized to assess personality pathology. Columbia-Suicide Severity Rating Scale (C-SSRS) was used to evaluate suicidal ideation and behavior. RESULTS AND DISCUSSION: Logistic regression reveals significant associations between personality traits and suicidal ideation (e.g., Anhedonia, Suspiciousness) and behavior (e.g., Risk Taking, Depressivity). Negative Affect and Detachment are significantly linked to suicidal ideation, while Detachment, Disinhibition, and Psychoticism are linked to suicidal behavior. Internalizing personality pathology predicts both ideation and behavior, indicating a contribution to suicidal thoughts and self-destructive acts. Externalizing is a significant predictor of suicidal behavior.

A Computational Tool for Analysis of Mass Spectrometry Data of Ubiquitin-Enriched Samples.

Mass spectrometry data on ubiquitin and ubiquitin-like modifiers are becoming increasingly more accessible, and the coverage progressively deepen as methodologies mature. This type of mass spectrometry data is linked to specific data analysis pipelines for ubiquitin. This chapter describes a computational tool to facilitate analysis of mass spectrometry data obtained on ubiquitin-enriched samples. For example, the analysis of ubiquitin branch site statistics and functional enrichment analysis against ubiquitin proteasome system protein sets are completed with a few functional calls. We foresee that the proposed computational methodology can aid in proximity drug design by, for example, elucidating the expression of E3 ligases and other factors related to the ubiquitin proteasome system.

Using Machine Learning for Predicting the Hospitalization of Emergency Department Patients.

Artificial intelligence processes are increasingly being used in emergency medicine, notably for supporting clinical decisions and potentially improving healthcare services. This study investigated demographics, coagulation tests, and biochemical markers routinely used for patients seen in the Emergency Department (ED) concerning hospitalization. This retrospective observational study included 13,991 emergency department visits of patients who had undergone biomarker testing to a tertiary public hospital in Greece during 2020. After applying five well-known classifiers of the caret package for machine learning of the R programming language in the whole data set and to each ED unit separately, the best performance regarding AUC ROC was observed in the Pulmonology ED unit. Furthermore, among the five classification techniques evaluated, a random forest classifier outperformed other models.

Tabular strategies for metadata in ecology, evolution, and the environmental sciences.

Data support knowledge development and theory advances in ecology and evolution. We are increasingly reusing data within our teams and projects and through the global, openly archived datasets of others. Metadata can be challenging to write and interpret, but it is always crucial for reuse. The value metadata cannot be overstated-even as a relatively independent research object because it describes the work that has been done in a structured format. We advance a new perspective and classify methods for metadata curation and development with tables. Tables with templates can be effectively used to capture all components of an experiment or project in a single, easy-to-read file familiar to most scientists. If coupled with the R programming language, metadata from tables can then be rapidly and reproducibly converted to publication formats including extensible markup language files suitable for data repositories. Tables can also be used to summarize existing metadata and store metadata across many datasets. A case study is provided and the added benefits of tables for metadata, a priori, are developed to ensure a more streamlined publishing process for many data repositories used in ecology, evolution, and the environmental sciences. In ecology and evolution, researchers are often highly tabular thinkers from experimental data collection in the lab and/or field, and representations of metadata as a table will provide novel research and reuse insights.

geneExpressionFromGEO: An R Package to Facilitate Data Reading from Gene Expression Omnibus (GEO).

Gene expression profiling is a useful way to measure the activity of genes in molecular biology and, because of its effectiveness, researchers have released thousands of gene expression datasets publicly in online databases and repositories, such as Gene Expression Omnibus (GEO). To read and analyze gene expression data, the computational biology community has developed several tools and platforms, including Bioconductor, an R open-source platform of software packages that can be used to analyze these data. Despite the usefulness of Bioconductor and of its packages, it is still difficult to read gene expression data from GEO, and to assign gene symbols to the probesets of datasets. To alleviate this problem, we introduce here a new R software package, geneExpressionFromGEO, which provides to the users the possibility to easily download gene expression data from GEO and to easily associate gene symbols to probesets. In this short chapter, we describe the assets of our software package, and we report an example of its usage. We believe that geneExpressionFromGEO can be very useful for the R community of bioinformaticians working on gene expression data.

MStractor: R Workflow Package for Enhancing Metabolomics Data Pre-Processing and Visualization.

Untargeted metabolomics experiments for characterizing complex biological samples, conducted with chromatography/mass spectrometry technology, generate large datasets containing very complex and highly variable information. Many data-processing options are available, however, both commercial and open-source solutions for data processing have limitations, such as vendor platform exclusivity and/or requiring familiarity with diverse programming languages. Data processing of untargeted metabolite data is a particular problem for laboratories that specialize in non-routine mass spectrometry analysis of diverse sample types across humans, animals, plants, fungi, and microorganisms. Here, we present MStractor, an R workflow package developed to streamline and enhance pre-processing of metabolomics mass spectrometry data and visualization. MStractor combines functions for molecular feature extraction with user-friendly dedicated GUIs for chromatographic and mass spectromerty (MS) parameter input, graphical quality-control outputs, and descriptive statistics. MStractor performance was evaluated through a detailed comparison with XCMS Online. The MStractor package is freely available on GitHub at the MetabolomicsSA repository.

Propensity score matching with R: conventional methods and new features.

It is increasingly important to accurately and comprehensively estimate the effects of particular clinical treatments. Although randomization is the current gold standard, randomized controlled trials (RCTs) are often limited in practice due to ethical and cost issues. Observational studies have also attracted a great deal of attention as, quite often, large historical datasets are available for these kinds of studies. However, observational studies also have their drawbacks, mainly including the systematic differences in baseline covariates, which relate to outcomes between treatment and control groups that can potentially bias results. Propensity score methods, which are a series of balancing methods in these studies, have become increasingly popular by virtue of the two major advantages of dimension reduction and design separation. Within this approach, propensity score matching (PSM) has been empirically proven, with outstanding performances across observational datasets. While PSM tutorials are available in the literature, there is still room for improvement. Some PSM tutorials provide step-by-step guidance, but only one or two packages have been covered, thereby limiting their scope and practicality. Several articles and books have expounded upon propensity scores in detail, exploring statistical principles and theories; however, the lack of explanations on function usage in programming language has made it difficult for researchers to understand and follow these materials. To this end, this tutorial was developed with a six-step PSM framework, in which we summarize the recent updates and provide step-by-step guidance to the R programming language. This tutorial offers researchers with a broad survey of PSM, ranging from data preprocessing to estimations of propensity scores, and from matching to analyses. We also explain generalized propensity scoring for multiple or continuous treatments, as well as time-dependent PSM. Lastly, we discuss the advantages and disadvantages of propensity score methods.

Applying Mixed-Effects Modeling to Behavioral Economic Demand: An Introduction.

Behavioral economic demand methodology is increasingly being used in various fields such as substance use and consumer behavior analysis. Traditional analytical techniques to fitting demand data have proven useful yet some of these approaches require preprocessing of data, ignore dependence in the data, and present statistical limitations. We term these approaches "fit to group" and "two stage" with the former interested in group or population level estimates and the latter interested in individual subject estimates. As an extension to these regression techniques, mixed-effect (or multilevel) modeling can serve as an improvement over these traditional methods. Notable benefits include providing simultaneous group (i.e., population) level estimates (with more accurate standard errors) and individual level predictions while accommodating the inclusion of "nonsystematic" response sets and covariates. These models can also accommodate complex experimental designs including repeated measures. The goal of this article is to introduce and provide a high-level overview of mixed-effects modeling techniques applied to behavioral economic demand data. We compare and contrast results from traditional techniques to that of the mixed-effects models across two datasets differing in species and experimental design. We discuss the relative benefits and drawbacks of these approaches and provide access to statistical code and data to support the analytical replicability of the comparisons. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s40614-021-00299-7.

Identification of Novel Glycolysis-Related Gene Signatures Associated With Prognosis of Patients With Clear Cell Renal Cell Carcinoma Based on TCGA.

OBJECTIVE: The purpose of the present study was to detect novel glycolysis-related gene signatures of prognostic values for patients with clear cell renal cell carcinoma (ccRCC). METHODS: Glycolysis-related gene sets were acquired from the Molecular Signatures Database (V7.0). Gene Set Enrichment Analysis (GSEA) software (4.0.3) was applied to analyze glycolysis-related gene sets. The Perl programming language (5.32.0) was used to extract glycolysis-related genes and clinical information of patients with ccRCC. The receiver operating characteristic curve (ROC) and Kaplan-Meier curve were drawn by the R programming language (3.6.3). RESULTS: The four glycolysis-related genes (B3GAT3, CENPA, AGL, and ALDH3A2) associated with prognosis were identified using Cox proportional regression analysis. A risk score staging system was established to predict the outcomes of patients with ccRCC. The patients with ccRCC were classified into the low-risk group and high-risk group. CONCLUSIONS: We have successfully constructed a risk staging model for ccRCC. The model has a better performance in predicting the prognosis of patients, which may have positive reference value for the treatment and curative effect evaluation of ccRCC.