Search

A detailed characterization of the chemical composition of complex substances, such as products of petroleum refining and environmental mixtures, is greatly needed in exposure assessment and manufacturing. The inherent complexity and variability in the composition of complex substances obfuscate the choices for their detailed analytical characterization. Yet, in lieu of exact chemical composition of complex substances, evaluation of the degree of similarity is a sensible path toward decision-making in environmental health regulations. Grouping of similar complex substances is a challenge that can be addressed via advanced analytical methods and streamlined data analysis and visualization techniques. Here, we propose a framework with unsupervised and supervised analyses to optimally group complex substances based on their analytical features. We test two data sets of complex oil-derived substances. The first data set is from gas chromatography-mass spectrometry (GC-MS) analysis of 20 Standard Reference Materials representing crude oils and oil refining products. The second data set consists of 15 samples of various gas oils analyzed using three analytical techniques: GC-MS, GC×GC-flame ionization detection (FID), and ion mobility spectrometry-mass spectrometry (IM-MS). We use hierarchical clustering using Pearson correlation as a similarity metric for the unsupervised analysis and build classification models using the Random Forest algorithm for the supervised analysis. We present a quantitative comparative assessment of clustering results via Fowlkes–Mallows index, and classification results via model accuracies in predicting the group of an unknown complex substance. We demonstrate the effect of (i) different grouping methodologies, (ii) data set size, and (iii) dimensionality reduction on the grouping quality, and (iv) different analytical techniques on the characterization of the complex substances. While the complexity and variability in chemical composition are an inherent feature of complex substances, we demonstrate how the choices of the data analysis and visualization methods can impact the communication of their characteristics to delineate sufficient similarity. [ABSTRACT FROM AUTHOR]

The mammalian neocortex is subdivided into a series of cortical areas that are functionally and anatomically distinct and are often distinguished in brain sections using histochemical stains and other markers of protein expression. We searched the Allen Mouse Brain Atlas, a database of gene expression, for novel markers of cortical areas. To screen for genes that change expression at area borders, we employed a random forest algorithm and binary region classification. Novel genetic markers were identified for 19 of 39 areas and provide code that quickly and efficiently searches the Allen Mouse Brain Atlas. Our results demonstrate the utility of the random forest algorithm for cortical area classification and we provide code that may be used to facilitate the identification of genetic markers of cortical and subcortical structures and perhaps changes in gene expression in disease states. [ABSTRACT FROM AUTHOR]

Preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. Due to the lack of effective preventive measures, its prediction is essential to its prompt management. This study aimed to develop models using machine learning to predict late-onset preeclampsia using hospital electronic medical record data. The performance of the machine learning based models and models using conventional statistical methods were also compared. A total of 11,006 pregnant women who received antenatal care at Yonsei University Hospital were included. Maternal data were retrieved from electronic medical records during the early second trimester to 34 weeks. The prediction outcome was late-onset preeclampsia occurrence after 34 weeks’ gestation. Pattern recognition and cluster analysis were used to select the parameters included in the prediction models. Logistic regression, decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, and stochastic gradient boosting method were used to construct the prediction models. C-statistics was used to assess the performance of each model. The overall preeclampsia development rate was 4.7% (474 patients). Systolic blood pressure, serum blood urea nitrogen and creatinine levels, platelet counts, serum potassium level, white blood cell count, serum calcium level, and urinary protein were the most influential variables included in the prediction models. C-statistics for the decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, stochastic gradient boosting method, and logistic regression models were 0.857, 0.776, 0.573, 0.894, 0.924, and 0.806, respectively. The stochastic gradient boosting model had the best prediction performance with an accuracy and false positive rate of 0.973 and 0.009, respectively. The combined use of maternal factors and common antenatal laboratory data of the early second trimester through early third trimester could effectively predict late-onset preeclampsia using machine learning algorithms. Future prospective studies are needed to verify the clinical applicability algorithms. [ABSTRACT FROM AUTHOR]

The internal phenotypes of netted muskmelon (Cucumis melo L. var. eticulates Naud.) are always associated with its external phenotypes. In this study, the parameters of external phenotypic traits were extracted from muskmelon images captured by machine vision, and the internal phenotypes of interest to us were measured. Pearson analysis showed that most external phenotypic traits were highly correlated with these internal phenotypes in muskmelon fruit. In this study, we used the random forest algorithm to predict muskmelon fruit internal phenotypes based on the significantly associated external parameters. Carotenoids, sucrose, and total soluble solid (TSS) were the three most accurately monitored internal phenotypes with prediction R-squared (R2) values of 0.947 (root-mean-square error (RMSE) = 0.019 mg/100 g), 0.918 (RMSE = 3.233 mg/g), and 0.916 (RMSE = 1.089%), respectively. Further, a simplified model was constructed and validated based on the top 10 external phenotypic parameters associated with each internal phenotype, and these parameters were filtered with the varImp function from the random forest package. The top 10 external phenotypic parameters correlated with each internal phenotype used in the simplified model were not identical. The results showed that the simplified models also accurately monitored the melon internal phenotypes, despite that the predicted R2 values decreased 0.3% to 7.9% compared with the original models. This study improved the efficiency and accuracy of real-time fruit quality monitoring for greenhouse muskmelon. [ABSTRACT FROM AUTHOR]

The study shows the feasibility of predicting firms’ expenditures in innovation, as reported in the Community Innovation Survey, applying a supervised machine-learning approach on a sample of Italian firms. Using an integrated dataset of administrative records and balance sheet data, designed to include all informative variables related to innovation but also easily accessible for most of the cohort, random forest algorithm is implemented to obtain a classification model aimed to identify firms that are potential innovation performers. The performance of the classifier, estimated in terms of AUC, is 0.794. Although innovation investments do not always result in patenting, the model is able to identify 71.92% of firms with patents. More encouraging results emerge from the analysis of the inner working of the model: predictors identified as most important—such as firm size, sector belonging and investment in intangible assets—confirm previous findings of literature, but in a completely different framework. The outcomes of this study are considered relevant for both economic analysts, because it demonstrates the potential of data-driven models for understanding the nature of innovation behaviour, and practitioners, such as policymakers or venture capitalists, who can benefit by evidence-based tools in the decision-making process. [ABSTRACT FROM AUTHOR]

MiRNAs and proteins play important roles in different stages of breast tumor development and serve as biomarkers for the early diagnosis of breast cancer. A new algorithm that combines machine learning algorithms and multilayer complex network analysis is hereby proposed to explore the potential diagnostic values of miRNAs and proteins. XGBoost and random forest algorithms were employed to screen the most important miRNAs and proteins. Maximal information coefficient was applied to assess intralayer and interlayer connection. A multilayer complex network was constructed to identify miRNAs and proteins that could serve as biomarkers for breast cancer. Proteins and miRNAs that are nodes in the network were subsequently categorized into two network layers considering their distinct functions. The betweenness centrality was used as the first measurement of the importance of the nodes within each single layer. The degree of the nodes was chosen as the second measurement to map their signalling pathways. By combining these two measurements into one score and comparing the difference of the same candidate between normal tissue and cancer tissue, this novel multilayer network analysis could be applied to successfully identify molecules associated with breast cancer. [ABSTRACT FROM AUTHOR]

This paper proposes a mixture regression model-based method for drug sensitivity prediction. The proposed method explicitly addresses two fundamental issues in drug sensitivity prediction, namely, population heterogeneity and feature selection pertaining to each of the subpopulations. The mixture regression model is estimated using the imputation-conditional consistency algorithm, and the resulting estimator is consistent. This paper also proposes an average-BIC criterion for determining the number of components for the mixture regression model. The proposed method is applied to the CCLE dataset, and the numerical results indicate that the proposed method can make a drastic improvement over the existing ones, such as random forest, support vector regression, and regularized linear regression, in both drug sensitivity prediction and feature selection. The p-values for the comparisons in drug sensitivity prediction can reach the order O(10−8) or lower for the drugs with heterogeneous populations. [ABSTRACT FROM AUTHOR]

Stock trend prediction is a challenging task due to the market’s noise, and machine learning techniques have recently been successful in coping with this challenge. In this research, we create a novel framework for stock prediction, Dynamic Advisor-Based Ensemble (dynABE). dynABE explores domain-specific areas based on the companies of interest, diversifies the feature set by creating different “advisors” that each handles a different area, follows an effective model ensemble procedure for each advisor, and combines the advisors together in a second-level ensemble through an online update strategy we developed. dynABE is able to adapt to price pattern changes of the market during the active trading period robustly, without needing to retrain the entire model. We test dynABE on three cobalt-related companies, and it achieves the best-case misclassification error of 31.12% and an annualized absolute return of 359.55% with zero maximum drawdown. dynABE also consistently outperforms the baseline models of support vector machine, neural network, and random forest in all case studies. [ABSTRACT FROM AUTHOR]

Objective: The rapid proliferation of machine learning research using electronic health records to classify healthcare outcomes offers an opportunity to address the pressing public health problem of adolescent suicidal behavior. We describe the development and evaluation of a machine learning algorithm using natural language processing of electronic health records to identify suicidal behavior among psychiatrically hospitalized adolescents. Methods: Adolescents hospitalized on a psychiatric inpatient unit in a community health system in the northeastern United States were surveyed for history of suicide attempt in the past 12 months. A total of 73 respondents had electronic health records available prior to the index psychiatric admission. Unstructured clinical notes were downloaded from the year preceding the index inpatient admission. Natural language processing identified phrases from the notes associated with the suicide attempt outcome. We enriched this group of phrases with a clinically focused list of terms representing known risk and protective factors for suicide attempt in adolescents. We then applied the random forest machine learning algorithm to develop a classification model. The model performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Results: The final model had a sensitivity of 0.83, specificity of 0.22, AUC of 0.68, a PPV of 0.42, NPV of 0.67, and an accuracy of 0.47. The terms mostly highly associated with suicide attempt clustered around terms related to suicide, family members, psychiatric disorders, and psychotropic medications. Conclusion: This analysis demonstrates modest success of a natural language processing and machine learning approach to identifying suicide attempt among a small sample of hospitalized adolescents in a psychiatric setting. [ABSTRACT FROM AUTHOR]

Background: Exhaled aerosols from lungs have unique patterns, and their variation can be correlated to the underlying lung structure and associated abnormities. However, it is challenging to characterize such aerosol patterns and differentiate their difference because of their complexity. This challenge is even greater for small airway diseases, where the disturbance signals are weak. Objectives and methods: The objective of this study is exploiting different feature extraction algorithms to develop a practical classifier to diagnose obstructive lung diseases using exhaled aerosol images. These include proper orthogonal decomposition (POD), principal component analysis (PCA), dynamic mode decomposition (DMD), and DMD with control (DMDC). Aerosol images were generated via physiology-based simulations in one normal and four diseased airway models in G7-9 bronchioles. The image data were classified using both the support vector machine (SVM) and random forest (RF) algorithms. The effectiveness of different features was evaluated by classification accuracy and misclassification rate. Findings: Results show a significantly higher performance using dynamic feature extractions (DMD and DMDC) than static algorithms (POD and PCA). Adding the control variables to DMD further improved classification accuracy. Comparing the classification methods, RF persistently outperformed SVM for all types of features considered. While the performance of RF constantly increased with the number of features retained, the performance of SVM peaked at 50 and decreased thereafter. The 5-class classification accuracy was 94.8% using the DMDC-RF model and 93.0% using the DMD-RF model, both of which were higher than 87.0% in the previous study that used fractal dimension features. Conclusion: Considering that disease progression is inherently a dynamic process, DMD(C)-based feature extraction preserves temporal information and is preferred over POD and PCA. Compared with hand-crafted features like fractals, feature extraction by DMD and DMDC is automatic and more accurate. [ABSTRACT FROM AUTHOR]

Understanding the drivers of large-scale vegetation change is critical to managing landscapes and key to predicting how projected climate and land use changes will affect regional vegetation patterns. This study aimed to improve our understanding of the role, magnitude, and spatial distribution of the key environmental and socioeconomic factors driving vegetation change in a southern African savanna. This research was conducted across the Kwando, Okavango and Zambezi catchments of southern Africa (Angola, Namibia, Botswana and Zambia) and explored vegetation cover change across the region from 2001–2010. A novel coupled analysis was applied to model the dynamic biophysical factors then to determine the discrete / social drivers of spatial heterogeneity on vegetation. Previous research applied Dynamic Factor Analysis (DFA), a multivariate times series dimension reduction technique, to ten years of monthly remotely sensed vegetation data (MODIS-derived normalized difference vegetation index, NDVI), and a suite of time-series (monthly) environmental covariates: precipitation, mean, minimum and maximum air temperature, soil moisture, relative humidity, fire and potential evapotranspiration. This initial research was performed at a regional scale to develop meso-scale models explaining mean regional NDVI patterns. The regional DFA predictions were compared to the fine-scale MODIS time series using Kendall’s Tau and Sen’s Slope to identify pixels where the DFA model we had developed, under or over predicted NDVI. Once identified, a Random Forest (RF) analysis using a series of static social and physical variables was applied to explain these remaining areas of under- and over- prediction to fully explore the drivers of heterogeneity in this savanna system. The RF analysis revealed the importance of protected areas, elevation, soil type, locations of higher population, roads, and settlements, in explaining fine scale differences in vegetation biomass. While the previously applied DFA generated a model of environmental variables driving NDVI, the RF work developed here highlighted human influences dominating that signal. The combined DFRFA model approach explains almost 90% of the variance in NDVI across this landscape from 2001–2010. Our methodology presents a unique coupling of dynamic and static factor analyses, yielding novel insights into savanna heterogeneity, and providing a tool of great potential for researchers and managers alike. [ABSTRACT FROM AUTHOR]

The performance of three machine learning methods (support vector regression, random forests and artificial neural network) for estimating the LAI of paddy rice was evaluated in this study. Traditional univariate regression models involving narrowband NDVI with optimized band combinations as well as linear multivariate calibration partial least squares regression models were also evaluated for comparison. A four year field-collected dataset was used to test the robustness of LAI estimation models against temporal variation. The partial least squares regression and three machine learning methods were built on the raw hyperspectral reflectance and the first derivative separately. Two different rules were used to determine the models’ key parameters. The results showed that the combination of the red edge and NIR bands (766 nm and 830 nm) as well as the combination of SWIR bands (1114 nm and 1190 nm) were optimal for producing the narrowband NDVI. The models built on the first derivative spectra yielded more accurate results than the corresponding models built on the raw spectra. Properly selected model parameters resulted in comparable accuracy and robustness with the empirical optimal parameter and significantly reduced the model complexity. The machine learning methods were more accurate and robust than the VI methods and partial least squares regression. When validating the calibrated models against the standalone validation dataset, the VI method yielded a validation RMSE value of 1.17 for NDVI(766,830) and 1.01 for NDVI(1114,1190), while the best models for the partial least squares, support vector machine and artificial neural network methods yielded validation RMSE values of 0.84, 0.82, 0.67 and 0.84, respectively. The RF models built on the first derivative spectra with mtry = 10 showed the highest potential for estimating the LAI of paddy rice. [ABSTRACT FROM AUTHOR]

Implantable-cardioverter defibrillators (ICD) detect and terminate life-threatening ventricular tachyarrhythmia with electric shocks after they occur. This puts patients at risk if they are driving or in a situation where they can fall. ICD’s shocks are also very painful and affect a patient’s quality of life. It would be ideal if ICDs can accurately predict the occurrence of ventricular tachyarrhythmia and then issue a warning or provide preventive therapy. Our study explores the use of ICD data to automatically predict ventricular arrhythmia using heart rate variability (HRV). A 5 minute and a 10 second warning system are both developed and compared. The participants for this study consist of 788 patients who were enrolled in the ICD arm of the Sudden Cardiac Death–Heart Failure Trial (SCD-HeFT). Two groups of patient rhythms, regular heart rhythms and pre-ventricular-tachyarrhythmic rhythms, are analyzed and different HRV features are extracted. Machine learning algorithms, including random forests (RF) and support vector machines (SVM), are trained on these features to classify the two groups of rhythms in a subset of the data comprising the training set. These algorithms are then used to classify rhythms in a separate test set. This performance is quantified by the area under the curve (AUC) of the ROC curve. Both RF and SVM methods achieve a mean AUC of 0.81 for 5-minute prediction and mean AUC of 0.87–0.88 for 10-second prediction; an AUC over 0.8 typically warrants further clinical investigation. Our work shows that moderate classification accuracy can be achieved to predict ventricular tachyarrhythmia with machine learning algorithms using HRV features from ICD data. These results provide a realistic view of the practical challenges facing implementation of machine learning algorithms to predict ventricular tachyarrhythmia using HRV data, motivating continued research on improved algorithms and additional features with higher predictive power. [ABSTRACT FROM AUTHOR]

Crab species are economically and ecologically important in coastal ecosystems, and their spatial distributions are pivotal for conservation and fisheries management. This study was focused on modelling the spatial distributions of three Portunidae crabs (Charybdis bimaculata, Charybdis japonica, and Portunus trituberculatus) in Haizhou Bay, China. We applied three analytical approaches (Generalized additive model (GAM), random forest (RF), and artificial neural network (ANN)) to spring and fall bottom trawl survey data (2011, 2013–2016) to develop and compare species distribution models (SDMs). Model predictability was evaluated using cross-validation based on the observed species distribution. Results showed that sea bottom temperature (SBT), sea bottom salinity (SBS), and sediment type were the most important factors affecting crab distributions. The relative importance of candidate variables was not consistent among species, season, or model. In general, we found ANNs to have less stability than both RFs and GAMs. GAMs overall yielded the least complex response curve structure. C. japonica was more pronounced in southwestern portion of Haizhou Bay, and C. bimaculata tended to stay in offshore areas. P. trituberculatus was the least region-specific and exhibited substantial annual variations in abundance. The comparison of multiple SDMs was informative to understand species responses to environmental factors and predict species distributions. This study contributes to better understanding the environmental niches of crabs and demonstrates best practices for the application of SDMs for management and conservation planning. [ABSTRACT FROM AUTHOR]

The number of images taken per patient scan has rapidly increased due to advances in software, hardware and digital imaging in the medical domain. There is the need for medical image annotation systems that are accurate as manual annotation is impractical, time-consuming and prone to errors. This paper presents modeling approaches performed to automatically classify and annotate radiographs using several classification schemes, which can be further applied for automatic content-based image retrieval (CBIR) and computer-aided diagnosis (CAD). Different image preprocessing and enhancement techniques were applied to augment grayscale radiographs by virtually adding two extra layers. The Image Retrieval in Medical Applications (IRMA) Code, a mono-hierarchical multi-axial code, served as a basis for this work. To extensively evaluate the image enhancement techniques, five classification schemes including the complete IRMA code were adopted. The deep convolutional neural network systems Inception-v3 and Inception-ResNet-v2, and Random Forest models with 1000 trees were trained using extracted Bag-of-Keypoints visual representations. The classification model performances were evaluated using the ImageCLEF 2009 Medical Annotation Task test set. The applied visual enhancement techniques proved to achieve better annotation accuracy in all classification schemes. [ABSTRACT FROM AUTHOR]

miRWalk is an open-source platform providing an intuitive interface that generates predicted and validated miRNA-binding sites of known genes of human, mouse, rat, dog and cow. The core of miRWalk is the miRNA target site prediction with the random-forest-based approach software TarPmiR searching the complete transcript sequence including the 5’-UTR, CDS and 3’-UTR. Moreover, it integrates results other databases with predicted and validated miRNA-target interactions. The focus is set on a modular design and extensibility as well as a fast update cycle. The database is available using Python, MySQL and HTML/Javascript Database URL: . [ABSTRACT FROM AUTHOR]

Humans emit numerous volatile organic compounds (VOCs) through breath and skin. The nature and rate of these emissions are affected by various factors including emotional state. Previous measurements of VOCs and CO2 in a cinema have shown that certain chemicals are reproducibly emitted by audiences reacting to events in a particular film. Using data from films with various age classifications, we have studied the relationship between the emission of multiple VOCs and CO2 and the age classifier (0, 6, 12, and 16) with a view to developing a new chemically based and objective film classification method. We apply a random forest model built with time independent features extracted from the time series of every measured compound, and test predictive capability on subsets of all data. It was found that most compounds were not able to predict all age classifiers reliably, likely reflecting the fact that current classification is based on perceived sensibilities to many factors (e.g. incidences of violence, sex, antisocial behaviour, drug use, and bad language) rather than the visceral biological responses expressed in the data. However, promising results were found for isoprene which reliably predicted 0, 6 and 12 age classifiers for a variety of film genres and audience age groups. Therefore, isoprene emission per person might in future be a valuable aid to national classification boards, or even offer an alternative, objective, metric for rating films based on the reactions of large groups of people. [ABSTRACT FROM AUTHOR]

Can structural information of proteins generate essential features for predicting the deleterious effect of a single nucleotide variant (SNV) independent of the known existence of the SNV in diseases? In this work, we answer the question by examining the performance of features generated from prior knowledge with the goal towards determining the pathogenic effect of rare variants in rare disease. We take the approach of prioritizing SNV loci focusing on protein structure-based features. The proposed structure-based features are generated from geometric, physical, chemical, and functional properties of the variant loci and structural neighbors of the loci utilizing multiple homologous structures. The performance of the structure-based features alone, trained on 80% of HumVar-HumDiv combination (HumVD-train) and tested on 20% of HumVar-HumDiv (HumVD-test), ClinVar and ClinVar rare variant rare disease (ClinVarRVRD) datasets, showed high levels of discernibility in determining the SNV’s pathogenic or benign effects on patients. Combined structure- and sequence-based features generated from prior knowledge on a random forest model further improved the F scores to 0.84 (HumVD-test), 0.75 (ClinVar), and 0.75 (ClinVarRVRD). Including features based on the difference between wild-type in addition to the features based on loci information increased the F score slightly more to 0.90 (HumVD-test), 0.78 (ClinVar), and 0.76 (ClinVarRVRD). The empirical examination and high F scores of the results based on loci information alone suggest that location of SNV plays a primary role in determining functional impact of mutation and that structure-based features can help enhance the prediction performance. [ABSTRACT FROM AUTHOR]

Coral reef systems can undergo rapid transitions from coral-dominated to macroalgae-dominated states following disturbances, and models indicate that these may sometimes represent shifts between alternative stable states. While several mechanisms may lead to alternate stable states on coral reefs, only a few have been investigated theoretically. We explore a model that illustrates that reduced vulnerability of macroalgae to herbivory as macroalgae grow and mature could be an important mechanism: when macroalgae are palatable to herbivores as juveniles, but resistant as adults, coral-dominated and algae-dominated states are bistable across a wide range of parameter space. We compare two approaches to global sensitivity analysis to rank the relative importance of the model parameters in determining the presence and magnitude of alternative stable states, and find that the two most influential parameters are the death rate of coral and the rate of maturation of algae out of the vulnerable stage. The Random Forest approach for global sensitivity analysis, recently adopted by ecologists, provides a more efficient method for ranking the relative importance of parameters than a variance-based approach that has been used frequently by computer scientists and engineers. Our results suggest that managing reefs to reduce chronic stressors that cause coral mortality and/or enhance the growth rates of algae can help prevent reefs from becoming locked in a macroalgae-dominated state. [ABSTRACT FROM AUTHOR]

Running-related overuse injuries can result from a combination of various intrinsic (e.g., gait biomechanics) and extrinsic (e.g., running surface) risk factors. However, it is unknown how changes in environmental weather conditions affect running gait biomechanical patterns since these data cannot be collected in a laboratory setting. Therefore, the purpose of this study was to develop a classification model based on subject-specific changes in biomechanical running patterns across two different environmental weather conditions using data obtained from wearable sensors in real-world environments. Running gait data were recorded during winter and spring sessions, with recorded average air temperatures of -10° C and +6° C, respectively. Classification was performed based on measurements of pelvic drop, ground contact time, braking, vertical oscillation of pelvis, pelvic rotation, and cadence obtained from 66,370 strides (~11,000/runner) from a group of recreational runners. A non-linear and ensemble machine learning algorithm, random forest (RF), was used to classify and compute a heuristic for determining the importance of each variable in the prediction model. To validate the developed subject-specific model, two cross-validation methods (one-against-another and partitioning datasets) were used to obtain experimental mean classification accuracies of 87.18% and 95.42%, respectively, indicating an excellent discriminatory ability of the RF-based model. Additionally, the ranked order of variable importance differed across the individual runners. The results from the RF-based machine-learning algorithm demonstrates that processing gait biomechanical signals from a single wearable sensor can successfully detect changes to an individual’s running patterns based on data obtained in real-world environments. [ABSTRACT FROM AUTHOR]

It is difficult to determine ages of eels via otoliths, because multiple alternating translucent and opaque zones in the otoliths are hard to identify. In this study, we developed an efficient age determination method for whitespotted conger (Conger myriaster), using random forest models with otolith weight and length, total body length, capture location and season as predictors. 409 specimens were collected from six locations in Yellow and East China Sea between October 2016 and December 2017. Overall OOB error rate was 17.36% compared with 16.26% for the external cross-validation dataset, and the error of age was within one year. Otolith weight and total length were the most important predictors, followed by otolith length, capture locations and seasons. There were no significant differences between the results derived from otolith/somatic morphometrics and otoliths annuli in the estimation of age composition and von Betalanffy Growth Functions growth curve. Our results demonstrated that random forest model with otolith and somatic morphometrics is an efficient and reliable approach for age determination of C. myriaster, which may also be applied to other eel species. [ABSTRACT FROM AUTHOR]

The ensemble method random forests has become a popular classification tool in bioinformatics and related fields. The out-of-bag error is an error estimation technique often used to evaluate the accuracy of a random forest and to select appropriate values for tuning parameters, such as the number of candidate predictors that are randomly drawn for a split, referred to as mtry. However, for binary classification problems with metric predictors it has been shown that the out-of-bag error can overestimate the true prediction error depending on the choices of random forests parameters. Based on simulated and real data this paper aims to identify settings for which this overestimation is likely. It is, moreover, questionable whether the out-of-bag error can be used in classification tasks for selecting tuning parameters like mtry, because the overestimation is seen to depend on the parameter mtry. The simulation-based and real-data based studies with metric predictor variables performed in this paper show that the overestimation is largest in balanced settings and in settings with few observations, a large number of predictor variables, small correlations between predictors and weak effects. There was hardly any impact of the overestimation on tuning parameter selection. However, although the prediction performance of random forests was not substantially affected when using the out-of-bag error for tuning parameter selection in the present studies, one cannot be sure that this applies to all future data. For settings with metric predictor variables it is therefore strongly recommended to use stratified subsampling with sampling fractions that are proportional to the class sizes for both tuning parameter selection and error estimation in random forests. This yielded less biased estimates of the true prediction error. In unbalanced settings, in which there is a strong interest in predicting observations from the smaller classes well, sampling the same number of observations from each class is a promising alternative. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel classification model for automatically identifying individuals with age-related macular degeneration (AMD) or Diabetic Macular Edema (DME) using retinal features from Spectral Domain Optical Coherence Tomography (SD-OCT) images. Our classification method uses retinal features such as the thickness of the retina and the thickness of the individual retinal layers, and the volume of the pathologies such as drusen and hyper-reflective intra-retinal spots. We extract automatically, ten clinically important retinal features by segmenting individual SD-OCT images for classification purposes. The effectiveness of the extracted features is evaluated using several classification methods such as Random Forrest on 251 (59 normal, 177 AMD and 15 DME) subjects. We have performed 15-fold cross-validation tests for three phenotypes; DME, AMD and normal cases using these data sets and achieved accuracy of more than 95% on each data set with the classification method using Random Forrest. When we trained the system as a two-class problem of normal and eye with pathology, using the Random Forrest classifier, we obtained an accuracy of more than 96%. The area under the receiver operating characteristic curve (AUC) finds a value of 0.99 for each dataset. We have also shown the performance of four state-of-the-methods for classification the eye participants and found that our proposed method showed the best accuracy. [ABSTRACT FROM AUTHOR]

Influenza A virus commonly circulating in swine (IAV-S) is characterized by large genetic and antigenic diversity and, thus, improvements in different aspects of IAV-S surveillance are needed to achieve desirable goals of surveillance such as to establish the capacity to forecast with the greatest accuracy the number of influenza cases likely to arise. Advancements in modeling approaches provide the opportunity to use different models for surveillance. However, in order to make improvements in surveillance, it is necessary to assess the predictive ability of such models. This study compares the sensitivity and predictive accuracy of the autoregressive integrated moving average (ARIMA) model, the generalized linear autoregressive moving average (GLARMA) model, and the random forest (RF) model with respect to the frequency of influenza A virus (IAV) in Ontario swine. Diagnostic data on IAV submissions in Ontario swine between 2007 and 2015 were obtained from the Animal Health Laboratory (University of Guelph, Guelph, ON, Canada). Each modeling approach was examined for predictive accuracy, evaluated by the root mean square error, the normalized root mean square error, and the model’s ability to anticipate increases and decreases in disease frequency. Likewise, we verified the magnitude of improvement offered by the ARIMA, GLARMA and RF models over a seasonal-naïve method. Using the diagnostic submissions, the occurrence of seasonality and the long-term trend in IAV infections were also investigated. The RF model had the smallest root mean square error in the prospective analysis and tended to predict increases in the number of diagnostic submissions and positive virological submissions at weekly and monthly intervals with a higher degree of sensitivity than the ARIMA and GLARMA models. The number of weekly positive virological submissions is significantly higher in the fall calendar season compared to the summer calendar season. Positive counts at weekly and monthly intervals demonstrated a significant increasing trend. Overall, this study shows that the RF model offers enhanced prediction ability over the ARIMA and GLARMA time series models for predicting the frequency of IAV infections in diagnostic submissions. [ABSTRACT FROM AUTHOR]

Drug-drug interaction (DDI) is a change in the effect of a drug when patient takes another drug. Characterizing DDIs is extremely important to avoid potential adverse drug reactions. We represent DDIs as a complex network in which nodes refer to drugs and links refer to their potential interactions. Recently, the problem of link prediction has attracted much consideration in scientific community. We represent the process of link prediction as a binary classification task on networks of potential DDIs. We use link prediction techniques for predicting unknown interactions between drugs in five arbitrary chosen large-scale DDI databases, namely DrugBank, KEGG, NDF-RT, SemMedDB, and Twosides. We estimated the performance of link prediction using a series of experiments on DDI networks. We performed link prediction using unsupervised and supervised approach including classification tree, k-nearest neighbors, support vector machine, random forest, and gradient boosting machine classifiers based on topological and semantic similarity features. Supervised approach clearly outperforms unsupervised approach. The Twosides network gained the best prediction performance regarding the area under the precision-recall curve (0.93 for both random forests and gradient boosting machine). The applied methodology can be used as a tool to help researchers to identify potential DDIs. The supervised link prediction approach proved to be promising for potential DDIs prediction and may facilitate the identification of potential DDIs in clinical research. [ABSTRACT FROM AUTHOR]

The Hereditary Spastic Paraplegias (HSP) are a group of heterogeneous disorders with a wide spectrum of underlying neural pathology, and hence HSP patients express a variety of gait abnormalities. Classification of these phenotypes may help in monitoring disease progression and personalizing therapies. This is currently managed by measuring values of some kinematic and spatio-temporal parameters at certain moments during the gait cycle, either in the doctor´s surgery room or after very precise measurements produced by instrumental gait analysis (IGA). These methods, however, do not provide information about the whole structure of the gait cycle. Classification of the similarities among time series of IGA measured values of sagittal joint positions throughout the whole gait cycle can be achieved by hierarchical clustering analysis based on multivariate dynamic time warping (DTW). Random forests can estimate which are the most important isolated parameters to predict the classification revealed by DTW, since clinicians need to refer to them in their daily practice. We acquired time series of pelvic, hip, knee, ankle and forefoot sagittal angular positions from 26 HSP and 33 healthy children with an optokinetic IGA system. DTW revealed six gait patterns with different degrees of impairment of walking speed, cadence and gait cycle distribution and related with patient’s age, sex, GMFCS stage, concurrence of polyneuropathy and abnormal visual evoked potentials or corpus callosum. The most important parameters to differentiate patterns were mean pelvic tilt and hip flexion at initial contact. Longer time of support, decreased values of hip extension and increased knee flexion at initial contact can differentiate the mildest, near to normal HSP gait phenotype and the normal healthy one. Increased values of knee flexion at initial contact and delayed peak of knee flexion are important factors to distinguish GMFCS stages I from II-III and concurrence of polyneuropathy. [ABSTRACT FROM AUTHOR]

Prediction of adverse drug reactions is an important problem in drug discovery endeavors which can be addressed with data-driven strategies. SIDER is one of the most reliable and frequently used datasets for identification of key features as well as building machine learning models for side effects prediction. The inherently unbalanced nature of this data presents with a difficult multi-label multi-class problem towards prediction of drug side effects. We highlight the intrinsic issue with SIDER data and methodological flaws in relying on performance measures such as AUC while attempting to predict side effects.We argue for the use of metrics that are robust to class imbalance for evaluation of classifiers. Importantly, we present a ‘hierarchical anatomical classification schema’ which aggregates side effects into organs, sub-systems, and systems. With the help of a weighted performance measure, using 5-fold cross-validation we show that this strategy facilitates biologically meaningful side effects prediction at different levels of anatomical hierarchy. By implementing various machine learning classifiers we show that Random Forest model yields best classification accuracy at each level of coarse-graining. The manually curated, hierarchical schema for side effects can also serve as the basis of future studies towards prediction of adverse reactions and identification of key features linked to specific organ systems. Our study provides a strategy for hierarchical classification of side effects rooted in the anatomy and can pave the way for calibrated expert systems for multi-level prediction of side effects. [ABSTRACT FROM AUTHOR]

The ability to predict what courses a student may enroll in the coming semester plays a pivotal role in the allocation of learning resources, which is a hot topic in the domain of educational data mining. In this study, we propose an innovative approach to characterize students’ cross-college course enrollments by leveraging a novel contextual graph. Specifically, different kinds of variables, such as students, courses, colleges and diplomas, as well as various types of variable relations, are utilized to depict the context of each variable, and then a representation learning algorithm node2vec is applied to extracting sophisticated graph-based features for the enrollment analysis. In this manner, the relations between any pair of variables can be measured quantitatively, which enables the variable type to transform from nominal to ratio. These graph-based features are examined by the random forest algorithm, and experiments on 24,663 students, 1,674 courses and 417,590 enrollment records demonstrate that the contextual graph can successfully improve analyzing the cross-college course enrollments, where three of the graph-based features have significantly stronger impacts on prediction accuracy than the others. Besides, the empirical results also indicate that the student’s course preference is the most important factor in predicting future course enrollments, which is consistent to the previous studies that acknowledge the course interest is a key point for course recommendations. [ABSTRACT FROM AUTHOR]

Horizontal behavior of highly migratory marine species is difficult to decipher because animals are wide-ranging, spend minimal time at the ocean surface, and utilize remote habitats. Satellite telemetry enables researchers to track individual movements, but population level inferences are rare due to data limitations that result from difficulty of capture and sporadic tag reporting. We introduce a Bayesian modeling framework to address population level questions with satellite telemetry data when data are sparse. We also outline an approach for identifying informative variables for use within the model. We tested our modeling approach using a large telemetry dataset for Shortfin Makos (Isurus oxyrinchus), which allowed us to assess the effects of various degrees of data paucity. First, a permuted Random Forest analysis is implemented to determine which variables are most informative. Next, a generalized additive mixed model is used to help define the relationship of each remaining variable with the response variable. Using jags and rjags for the analysis of Bayesian hierarchical models using Markov Chain Monte Carlo simulation, we then developed a movement model to generate parameter estimates for each of the variables of interest. By randomly reducing the tagging dataset by 25, 50, 75, and 90 percent and recalculating the parameter estimates, we demonstrate that the proposed Bayesian approach can be applied in data-limited situations. We also demonstrate how two commonly used linear mixed models with maximum likelihood estimation (MLE) can be similarly applied. Additionally, we simulate data from known parameter values to test each model’s ability to recapture those values. Despite performing similarly, we advocate using the Bayesian over the MLE approach due to the ability for later studies to easily utilize results of past study to inform working models, and the ability to use prior knowledge via informed priors in systems where such information is available. [ABSTRACT FROM AUTHOR]

Subjective well-being includes ‘affect’ and ‘satisfaction with life’ (SWL). This study proposes a unified approach to construct a profile of subjective well-being based on social media language in Facebook status updates. We apply sentiment analysis to generate users’ affect scores, and train a random forest model to predict SWL using affect scores and other language features of the status updates. Results show that: the computer-selected features resemble the key predictors of SWL as identified in early studies; the machine-predicted SWL is moderately correlated with the self-reported SWL (r = 0.36, p < 0.01), indicating that language-based assessment can constitute valid SWL measures; the machine-assessed affect scores resemble those reported in a previous experimental study; and the machine-predicted subjective well-being profile can also reflect other psychological traits like depression (r = 0.24, p < 0.01). This study provides important insights for psychological prediction using multiple, machine-assessed components and longitudinal or dense psychological assessment using social media language. [ABSTRACT FROM AUTHOR]

This study investigates signals from sustained phonation and text-dependent speech modalities for Parkinson’s disease screening. Phonation corresponds to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. Signals were recorded through two channels simultaneously, namely, acoustic cardioid (AC) and smart phone (SP) microphones. Additional modalities were obtained by splitting speech recording into voiced and unvoiced parts. Information in each modality is summarized by 18 well-known audio feature sets. Random forest (RF) is used as a machine learning algorithm, both for individual feature sets and for decision-level fusion. Detection performance is measured by the out-of-bag equal error rate (EER) and the cost of log-likelihood-ratio. Essentia audio feature set was the best using the AC speech modality and YAAFE audio feature set was the best using the SP unvoiced modality, achieving EER of 20.30% and 25.57%, respectively. Fusion of all feature sets and modalities resulted in EER of 19.27% for the AC and 23.00% for the SP channel. Non-linear projection of a RF-based proximity matrix into the 2D space enriched medical decision support by visualization. [ABSTRACT FROM AUTHOR]

In livestock industries, reliable up-to-date spatial distribution and abundance records for animals and farms are critical for governments to manage and respond to risks. Yet few, if any, countries can afford to maintain comprehensive, up-to-date agricultural census data. Statistical modelling can be used as a proxy for such data but comparative modelling studies have rarely been undertaken for livestock populations. Widespread species, including livestock, can be difficult to model effectively due to complex spatial distributions that do not respond predictably to environmental gradients. We assessed three machine learning species distribution models (SDM) for their capacity to estimate national-level farm animal population numbers within property boundaries: boosted regression trees (BRT), random forests (RF) and K-nearest neighbour (K-NN). The models were built from a commercial livestock database and environmental and socio-economic predictor data for New Zealand. We used two spatial data stratifications to test (i) support for decision making in an emergency response situation, and (ii) the ability for the models to predict to new geographic regions. The performance of the three model types varied substantially, but the best performing models showed very high accuracy. BRTs had the best performance overall, but RF performed equally well or better in many simulations; RFs were superior at predicting livestock numbers for all but very large commercial farms. K-NN performed poorly relative to both RF and BRT in all simulations. The predictions of both multi species and single species models for farms and within hypothetical quarantine zones were very close to observed data. These models are generally applicable for livestock estimation with broad applications in disease risk modelling, biosecurity, policy and planning. [ABSTRACT FROM AUTHOR]

Shortwave solar radiation is an important component of the surface energy balance and provides the principal source of energy for terrestrial ecosystems. This paper presents a machine learning approach in the form of a random forest (RF) model for estimating daily downward solar radiation flux at the land surface over complex terrain using MODIS (MODerate Resolution Imaging Spectroradiometer) remote sensing data. The model-building technique makes use of a unique network of 16 solar flux measurements in the semi-arid Reynolds Creek Experimental Watershed and Critical Zone Observatory, in southwest Idaho, USA. Based on a composite RF model built on daily observations from all 16 sites in the watershed, the model simulation of downward solar radiation matches well with the observation data (r2 = 0.96). To evaluate model performance, RF models were built from 12 of 16 sites selected at random and validated against the observations at the remaining four sites. Overall root mean square errors (RMSE), bias, and mean absolute error (MAE) are small (range: 37.17 W/m2-81.27 W/m2, -48.31 W/m2-15.67 W/m2, and 26.56 W/m2-63.77 W/m2, respectively). When extrapolated to the entire watershed, spatiotemporal patterns of solar flux are largely consistent with expected trends in this watershed. We also explored significant predictors of downward solar flux in order to reveal important properties and processes controlling downward solar radiation. Based on the composite RF model built on all 16 sites, the three most important predictors to estimate downward solar radiation include the black sky albedo (BSA) near infrared band (0.858 μm), BSA visible band (0.3–0.7 μm), and clear day coverage. This study has important implications for improving the ability to derive downward solar radiation through a fusion of multiple remote sensing datasets and can potentially capture spatiotemporally varying trends in solar radiation that is useful for land surface hydrologic and terrestrial ecosystem modeling. [ABSTRACT FROM AUTHOR]

A new head pose estimation technique based on Random Forest (RF) and texture features for facial image analysis using a monocular camera is proposed in this paper, especially about how to efficiently combine the random forest and the features. In the proposed technique a randomized tree with useful attributes is trained to improve estimation accuracy and tolerance of occlusions and illumination. Specifically, a number of features including Multi-scale Block Local Block Pattern (MB-LBP) are extracted from an image, and random features such as the MB-LBP scale parameters, a block coordinate, and a layer of an image pyramid in the feature pool are used for training the tree. The randomized tree aims to maximize the information gain at each node while random samples traverse the nodes in the tree. To this aim, a split function considering the uniform property of the LBP feature is developed to move sample blocks to the left or the right children nodes. The trees are independently trained with random inputs, yet they are grouped to form a random forest so that the results collected from the trees are used for make the final decision. Precisely, we use a Maximum-A-Posteriori criterion in the decision. It is demonstrated with experimental results that the proposed technique provides significantly enhanced classification performance in the head pose estimation in various conditions of illumination, poses, expressions, and facial occlusions. [ABSTRACT FROM AUTHOR]

In spacecraft electrical signal characteristic data, there exists a large amount of data with high-dimensional features, a high computational complexity degree, and a low rate of identification problems, which causes great difficulty in fault diagnosis of spacecraft electronic load systems. This paper proposes a feature extraction method that is based on deep belief networks (DBN) and a classification method that is based on the random forest (RF) algorithm; The proposed algorithm mainly employs a multi-layer neural network to reduce the dimension of the original data, and then, classification is applied. Firstly, we use the method of wavelet denoising, which was used to pre-process the data. Secondly, the deep belief network is used to reduce the feature dimension and improve the rate of classification for the electrical characteristics data. Finally, we used the random forest algorithm to classify the data and comparing it with other algorithms. The experimental results show that compared with other algorithms, the proposed method shows excellent performance in terms of accuracy, computational efficiency, and stability in addressing spacecraft electrical signal data. [ABSTRACT FROM AUTHOR]

This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in gathering socioeconomic information in urban settlements. We use land cover, spectral, structure and texture features extracted from a Google Earth image of Liverpool (UK) to evaluate their potential to predict Living Environment Deprivation at a small statistical area level. We also contribute to the methodological literature on the estimation of socioeconomic indices with remote-sensing data by introducing elements from modern machine learning. In addition to classical approaches such as Ordinary Least Squares (OLS) regression and a spatial lag model, we explore the potential of the Gradient Boost Regressor and Random Forests to improve predictive performance and accuracy. In addition to novel predicting methods, we also introduce tools for model interpretation and evaluation such as feature importance and partial dependence plots, or cross-validation. Our results show that Random Forest proved to be the best model with an R2 of around 0.54, followed by Gradient Boost Regressor with 0.5. Both the spatial lag model and the OLS fall behind with significantly lower performances of 0.43 and 0.3, respectively. [ABSTRACT FROM AUTHOR]

Soaring birds can balance the energetic costs of movement by switching between flapping, soaring and gliding flight. Accelerometers can allow quantification of flight behavior and thus a context to interpret these energetic costs. However, models to interpret accelerometry data are still being developed, rarely trained with supervised datasets, and difficult to apply. We collected accelerometry data at 140Hz from a trained golden eagle (Aquila chrysaetos) whose flight we recorded with video that we used to characterize behavior. We applied two forms of supervised classifications, random forest (RF) models and K-nearest neighbor (KNN) models. The KNN model was substantially easier to implement than the RF approach but both were highly accurate in classifying basic behaviors such as flapping (85.5% and 83.6% accurate, respectively), soaring (92.8% and 87.6%) and sitting (84.1% and 88.9%) with overall accuracies of 86.6% and 92.3% respectively. More detailed classification schemes, with specific behaviors such as banking and straight flights were well classified only by the KNN model (91.24% accurate; RF = 61.64% accurate). The RF model maintained its accuracy of classifying basic behavior classification accuracy of basic behaviors at sampling frequencies as low as 10Hz, the KNN at sampling frequencies as low as 20Hz. Classification of accelerometer data collected from free ranging birds demonstrated a strong dependence of predicted behavior on the type of classification model used. Our analyses demonstrate the consequence of different approaches to classification of accelerometry data, the potential to optimize classification algorithms with validated flight behaviors to improve classification accuracy, ideal sampling frequencies for different classification algorithms, and a number of ways to improve commonly used analytical techniques and best practices for classification of accelerometry data. [ABSTRACT FROM AUTHOR]

Building on developments in machine learning and prior work in the science of judicial prediction, we construct a model designed to predict the behavior of the Supreme Court of the United States in a generalized, out-of-sample context. To do so, we develop a time-evolving random forest classifier that leverages unique feature engineering to predict more than 240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015). Using only data available prior to decision, our model outperforms null (baseline) models at both the justice and case level under both parametric and non-parametric tests. Over nearly two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the justice vote level. More recently, over the past century, we outperform an in-sample optimized null model by nearly 5%. Our performance is consistent with, and improves on the general level of prediction demonstrated by prior work; however, our model is distinctive because it can be applied out-of-sample to the entire past and future of the Court, not a single term. Our results represent an important advance for the science of quantitative legal prediction and portend a range of other potential applications. [ABSTRACT FROM AUTHOR]

Purpose: In oncology, texture features extracted from positron emission tomography with 18-fluorodeoxyglucose images (FDG-PET) are of increasing interest for predictive and prognostic studies, leading to several tens of features per tumor. To select the best features, the use of a random forest (RF) classifier was investigated. Methods: Sixty-five patients with an esophageal cancer treated with a combined chemo-radiation therapy were retrospectively included. All patients underwent a pretreatment whole-body FDG-PET. The patients were followed for 3 years after the end of the treatment. The response assessment was performed 1 month after the end of the therapy. Patients were classified as complete responders and non-complete responders. Sixty-one features were extracted from medical records and PET images. First, Spearman’s analysis was performed to eliminate correlated features. Then, the best predictive and prognostic subsets of features were selected using a RF algorithm. These results were compared to those obtained by a Mann-Whitney U test (predictive study) and a univariate Kaplan-Meier analysis (prognostic study). Results: Among the 61 initial features, 28 were not correlated. From these 28 features, the best subset of complementary features found using the RF classifier to predict response was composed of 2 features: metabolic tumor volume (MTV) and homogeneity from the co-occurrence matrix. The corresponding predictive value (AUC = 0.836 ± 0.105, Se = 82 ± 9%, Sp = 91 ± 12%) was higher than the best predictive results found using the Mann-Whitney test: busyness from the gray level difference matrix (P < 0.0001, AUC = 0.810, Se = 66%, Sp = 88%). The best prognostic subset found using RF was composed of 3 features: MTV and 2 clinical features (WHO status and nutritional risk index) (AUC = 0.822 ± 0.059, Se = 79 ± 9%, Sp = 95 ± 6%), while no feature was significantly prognostic according to the Kaplan-Meier analysis. Conclusions: The RF classifier can improve predictive and prognostic values compared to the Mann-Whitney U test and the univariate Kaplan-Meier survival analysis when applied to several tens of features in a limited patient database. [ABSTRACT FROM AUTHOR]

Harvested to perilously low numbers by commercial whaling during the past century, the large scale response of Antarctic blue whales Balaenoptera musculus intermedia to environmental variability is poorly understood. This study uses acoustic data collected from 586 sonobuoys deployed in the austral summers of 1997 through 2009, south of 38°S, coupled with visual observations of blue whales during the IWC SOWER line-transect surveys. The characteristic Z-call and D-call of Antarctic blue whales were detected using an automated detection template and visual verification method. Using a random forest model, we showed the environmental preferences pattern, spatial occurrence and acoustic behaviour of Antarctic blue whales. Distance to the southern boundary of the Antarctic Circumpolar Current (SBACC), latitude and distance from the nearest Antarctic shores were the main geographic predictors of blue whale call occurrence. Satellite-derived sea surface height, sea surface temperature, and productivity (chlorophyll-a) were the most important environmental predictors of blue whale call occurrence. Call rates of D-calls were strongly predicted by the location of the SBACC, latitude and visually detected number of whales in an area while call rates of Z-call were predicted by the SBACC, latitude and longitude. Satellite-derived sea surface height, wind stress, wind direction, water depth, sea surface temperatures, chlorophyll-a and wind speed were important environmental predictors of blue whale call rates in the Southern Ocean. Blue whale call occurrence and call rates varied significantly in response to inter-annual and long term variability of those environmental predictors. Our results identify the response of Antarctic blue whales to inter-annual variability in environmental conditions and highlighted potential suitable habitats for this population. Such emerging knowledge about the acoustic behaviour, environmental and habitat preferences of Antarctic blue whales is important in improving the management and conservation of this highly depleted species. [ABSTRACT FROM AUTHOR]

Background: Present knowledge indicates a multilayered hierarchical gene regulatory network (ML-hGRN) often operates above a biological pathway. Although the ML-hGRN is very important for understanding how a pathway is regulated, there is almost no computational algorithm for directly constructing ML-hGRNs. Results: A backward elimination random forest (BWERF) algorithm was developed for constructing the ML-hGRN operating above a biological pathway. For each pathway gene, the BWERF used a random forest model to calculate the importance values of all transcription factors (TFs) to this pathway gene recursively with a portion (e.g. 1/10) of least important TFs being excluded in each round of modeling, during which, the importance values of all TFs to the pathway gene were updated and ranked until only one TF was remained in the list. The above procedure, termed BWERF. After that, the importance values of a TF to all pathway genes were aggregated and fitted to a Gaussian mixture model to determine the TF retention for the regulatory layer immediately above the pathway layer. The acquired TFs at the secondary layer were then set to be the new bottom layer to infer the next upper layer, and this process was repeated until a ML-hGRN with the expected layers was obtained. Conclusions: BWERF improved the accuracy for constructing ML-hGRNs because it used backward elimination to exclude the noise genes, and aggregated the individual importance values for determining the TFs retention. We validated the BWERF by using it for constructing ML-hGRNs operating above mouse pluripotency maintenance pathway and Arabidopsis lignocellulosic pathway. Compared to GENIE3, BWERF showed an improvement in recognizing authentic TFs regulating a pathway. Compared to the bottom-up Gaussian graphical model algorithm we developed for constructing ML-hGRNs, the BWERF can construct ML-hGRNs with significantly reduced edges that enable biologists to choose the implicit edges for experimental validation. [ABSTRACT FROM AUTHOR]

Invasive Alien Plants occur in numbers differing by orders of magnitude at subsequent invasion stages. Effective sampling and quantifying niches of rare invasive plants are quite problematic. The aim of this paper is an estimation of the influence of invasive plants frequency on the explanation of their local abundance. We attempted to achieve it through: (1) assessment of occurrence of self-regenerating invasive plants in urban woodlands, (2) comparison of Random Forest modelling results for frequent and rare species. We hypothesized that the abundance of frequent species would be explained better than that of rare ones and that both rare and frequent species share a common hierarchy of the most important determinants. We found 15 taxa in almost two thirds of 1040 plots with a total number of 1068 occurrences. There were recorded 6 taxa of high frequency–Prunus serotina, Quercus rubra, Acer negundo, Robinia pseudoacacia, Impatiens parviflora and Solidago spp.–and 9 taxa of low frequency: Acer saccharinum, Amelanchier spicata, Cornus spp., Fraxinus spp., Parthenocissus spp., Syringa vulgaris, Echinocystis lobata, Helianthus tuberosus, Reynoutria spp. Random Forest’s models’ quality grows with the number of occurrences of frequent taxa but not of the rare ones. Both frequent and rare taxa share a similar hierarchy of predictors’ importance: Land use > Tree stand > Seed source and, for frequent taxa, Forest properties as well. We conclude that there is an ‘explanation jump’ at higher species frequencies, but rare species are surprisingly similar to frequent ones in their determinant’s hierarchy, with differences conforming with their respective stages of invasion. [ABSTRACT FROM AUTHOR]

DNA-binding proteins are fundamentally important in cellular processes. Several computational-based methods have been developed to improve the prediction of DNA-binding proteins in previous years. However, insufficient work has been done on the prediction of DNA-binding proteins from protein sequence information. In this paper, a novel predictor, DNABP (DNA-binding proteins), was designed to predict DNA-binding proteins using the random forest (RF) classifier with a hybrid feature. The hybrid feature contains two types of novel sequence features, which reflect information about the conservation of physicochemical properties of the amino acids, and the binding propensity of DNA-binding residues and non-binding propensities of non-binding residues. The comparisons with each feature demonstrated that these two novel features contributed most to the improvement in predictive ability. Furthermore, to improve the prediction performance of the DNABP model, feature selection using the minimum redundancy maximum relevance (mRMR) method combined with incremental feature selection (IFS) was carried out during the model construction. The results showed that the DNABP model could achieve 86.90% accuracy, 83.76% sensitivity, 90.03% specificity and a Matthews correlation coefficient of 0.727. High prediction accuracy and performance comparisons with previous research suggested that DNABP could be a useful approach to identify DNA-binding proteins from sequence information. The DNABP web server system is freely available at . [ABSTRACT FROM AUTHOR]

Accurate predictions of crop yield are critical for developing effective agricultural and food policies at the regional and global scales. We evaluated a machine-learning method, Random Forests (RF), for its ability to predict crop yield responses to climate and biophysical variables at global and regional scales in wheat, maize, and potato in comparison with multiple linear regressions (MLR) serving as a benchmark. We used crop yield data from various sources and regions for model training and testing: 1) gridded global wheat grain yield, 2) maize grain yield from US counties over thirty years, and 3) potato tuber and maize silage yield from the northeastern seaboard region. RF was found highly capable of predicting crop yields and outperformed MLR benchmarks in all performance statistics that were compared. For example, the root mean square errors (RMSE) ranged between 6 and 14% of the average observed yield with RF models in all test cases whereas these values ranged from 14% to 49% for MLR models. Our results show that RF is an effective and versatile machine-learning method for crop yield predictions at regional and global scales for its high accuracy and precision, ease of use, and utility in data analysis. RF may result in a loss of accuracy when predicting the extreme ends or responses beyond the boundaries of the training data. [ABSTRACT FROM AUTHOR]

As a novel class of noncoding RNAs, long noncoding RNAs (lncRNAs) have been verified to be associated with various diseases. As large scale transcripts are generated every year, it is significant to accurately and quickly identify lncRNAs from thousands of assembled transcripts. To accurately discover new lncRNAs, we develop a classification tool of random forest (RF) named LncRNApred based on a new hybrid feature. This hybrid feature set includes three new proposed features, which are MaxORF, RMaxORF and SNR. LncRNApred is effective for classifying lncRNAs and protein coding transcripts accurately and quickly. Moreover,our RF model only requests the training using data on human coding and non-coding transcripts. Other species can also be predicted by using LncRNApred. The result shows that our method is more effective compared with the Coding Potential Calculate (CPC). The web server of LncRNApred is available for free at . [ABSTRACT FROM AUTHOR]

Current methods for distinguishing acute coronary syndromes such as heart attack from stable coronary artery disease, based on the kinetics of thrombin formation, have been limited to evaluating sensitivity of well-established chemical species (e.g., thrombin) using simple quantifiers of their concentration profiles (e.g., maximum level of thrombin concentration, area under the thrombin concentration versus time curve). In order to get an improved classifier, we use a 34-protein factor clotting cascade model and convert the simulation data into a high-dimensional representation (about 19000 features) using a piecewise cubic polynomial fit. Then, we systematically find plausible assays to effectively gauge changes in acute coronary syndrome/coronary artery disease populations by introducing a statistical learning technique called Random Forests. We find that differences associated with acute coronary syndromes emerge in combinations of a handful of features. For instance, concentrations of 3 chemical species, namely, active alpha-thrombin, tissue factor-factor VIIa-factor Xa ternary complex, and intrinsic tenase complex with factor X, at specific time windows, could be used to classify acute coronary syndromes to an accuracy of about 87.2%. Such a combination could be used to efficiently assay the coagulation system. [ABSTRACT FROM AUTHOR]

Large scale, high-resolution global data on farm animal distributions are essential for spatially explicit assessments of the epidemiological, environmental and socio-economic impacts of the livestock sector. This has been the major motivation behind the development of the Gridded Livestock of the World (GLW) database, which has been extensively used since its first publication in 2007. The database relies on a downscaling methodology whereby census counts of animals in sub-national administrative units are redistributed at the level of grid cells as a function of a series of spatial covariates. The recent upgrade of GLW1 to GLW2 involved automating the processing, improvement of input data, and downscaling at a spatial resolution of 1 km per cell (5 km per cell in the earlier version). The underlying statistical methodology, however, remained unchanged. In this paper, we evaluate new methods to downscale census data with a higher accuracy and increased processing efficiency. Two main factors were evaluated, based on sample census datasets of cattle in Africa and chickens in Asia. First, we implemented and evaluated Random Forest models (RF) instead of stratified regressions. Second, we investigated whether models that predicted the number of animals per rural person (per capita) could provide better downscaled estimates than the previous approach that predicted absolute densities (animals per km2). RF models consistently provided better predictions than the stratified regressions for both continents and species. The benefit of per capita over absolute density models varied according to the species and continent. In addition, different technical options were evaluated to reduce the processing time while maintaining their predictive power. Future GLW runs (GLW 3.0) will apply the new RF methodology with optimized modelling options. The potential benefit of per capita models will need to be further investigated with a better distinction between rural and agricultural populations. [ABSTRACT FROM AUTHOR]

Soil cadmium (Cd) contamination has attracted a great deal of attention because of its detrimental effects on animals and humans. This study aimed to develop and compare the performances of stepwise linear regression (SLR), classification and regression tree (CART) and random forest (RF) models in the prediction and mapping of the spatial distribution of soil Cd and to identify likely sources of Cd accumulation in Fuyang County, eastern China. Soil Cd data from 276 topsoil (0–20 cm) samples were collected and randomly divided into calibration (222 samples) and validation datasets (54 samples). Auxiliary data, including detailed land use information, soil organic matter, soil pH, and topographic data, were incorporated into the models to simulate the soil Cd concentrations and further identify the main factors influencing soil Cd variation. The predictive models for soil Cd concentration exhibited acceptable overall accuracies (72.22% for SLR, 70.37% for CART, and 75.93% for RF). The SLR model exhibited the largest predicted deviation, with a mean error (ME) of 0.074 mg/kg, a mean absolute error (MAE) of 0.160 mg/kg, and a root mean squared error (RMSE) of 0.274 mg/kg, and the RF model produced the results closest to the observed values, with an ME of 0.002 mg/kg, an MAE of 0.132 mg/kg, and an RMSE of 0.198 mg/kg. The RF model also exhibited the greatest R2 value (0.772). The CART model predictions closely followed, with ME, MAE, RMSE, and R2 values of 0.013 mg/kg, 0.154 mg/kg, 0.230 mg/kg and 0.644, respectively. The three prediction maps generally exhibited similar and realistic spatial patterns of soil Cd contamination. The heavily Cd-affected areas were primarily located in the alluvial valley plain of the Fuchun River and its tributaries because of the dramatic industrialization and urbanization processes that have occurred there. The most important variable for explaining high levels of soil Cd accumulation was the presence of metal smelting industries. The good performance of the RF model was attributable to its ability to handle the non-linear and hierarchical relationships between soil Cd and environmental variables. These results confirm that the RF approach is promising for the prediction and spatial distribution mapping of soil Cd at the regional scale. [ABSTRACT FROM AUTHOR]

The aim of this study was to elucidate the underlying biochemical processes to identify potential key molecules of meat quality traits drip loss, pH of meat 1 h post-mortem (pH1), pH in meat 24 h post-mortem (pH24) and meat color. An untargeted metabolomics approach detected the profiles of 393 annotated and 1,600 unknown metabolites in 97 Duroc × Pietrain pigs. Despite obvious differences regarding the statistical approaches, the four applied methods, namely correlation analysis, principal component analysis, weighted network analysis (WNA) and random forest regression (RFR), revealed mainly concordant results. Our findings lead to the conclusion that meat quality traits pH1, pH24 and color are strongly influenced by processes of post-mortem energy metabolism like glycolysis and pentose phosphate pathway, whereas drip loss is significantly associated with metabolites of lipid metabolism. In case of drip loss, RFR was the most suitable method to identify reliable biomarkers and to predict the phenotype based on metabolites. On the other hand, WNA provides the best parameters to investigate the metabolite interactions and to clarify the complex molecular background of meat quality traits. In summary, it was possible to attain findings on the interaction of meat quality traits and their underlying biochemical processes. The detected key metabolites might be better indicators of meat quality especially of drip loss than the measured phenotype itself and potentially might be used as bio indicators. [ABSTRACT FROM AUTHOR]

Random Forest has become a standard data analysis tool in computational biology. However, extensions to existing implementations are often necessary to handle the complexity of biological datasets and their associated research questions. The growing size of these datasets requires high performance implementations. We describe CloudForest, a Random Forest package written in Go, which is particularly well suited for large, heterogeneous, genetic and biomedical datasets. CloudForest includes several extensions, such as dealing with unbalanced classes and missing values. Its flexible design enables users to easily implement additional extensions. CloudForest achieves fast running times by effective use of the CPU cache, optimizing for different classes of features and efficiently multi-threading. . [ABSTRACT FROM AUTHOR]