Random generalized linear model: a highly accurate and interpretable ensemble predictor

Advantages of Synthetic Noise and Machine Learning for Analyzing Radioecological Data Sets

The ecological effects of accidental or malicious radioactive contamination are insufficiently understood because of the hazards and difficulties associated with conducting studies in radioactively-polluted areas. Data sets from severely contaminated locations can therefore be small. Moreover, many potentially important factors, such as soil concentrations of toxic chemicals, pH, and temperature, can be correlated with radiation levels and with each other. In such situations, commonly-used statistical techniques like generalized linear models (GLMs) may not be able to provide useful information about how radiation and/or these other variables affect the outcome (e.g. abundance of the studied organisms). Ensemble machine learning methods such as random forests offer powerful alternatives. We propose that analysis of small radioecological data sets by GLMs and/or machine learning can be made more informative by using the following techniques: (1) adding synthetic noise variables to provide benchmarks for distinguishing the performances of valuable predictors from irrelevant ones; (2) adding noise directly to the predictors and/or to the outcome to test the robustness of analysis results against random data fluctuations; (3) adding artificial effects to selected predictors to test the sensitivity of the analysis methods in detecting predictor effects; (4) running a selected machine learning method multiple times (with different random-number seeds) to test the robustness of the detected “signal”; (5) using several machine learning methods to test the “signal’s” sensitivity to differences in analysis techniques. Here, we applied these approaches to simulated data, and to two published examples of small radioecological data sets: (I) counts of fungal taxa in samples of soil contaminated by the Chernobyl nuclear power plan accident (Ukraine), and (II) bacterial abundance in soil samples under a ruptured nuclear waste storage tank (USA). We show that the proposed techniques were advantageous compared with the methodology used in the original publications where the data sets were presented. Specifically, our approach identified a negative effect of radioactive contamination in data set I, and suggested that in data set II stable chromium could have been a stronger limiting factor for bacterial abundance than the radionuclides ¹³⁷Cs and ⁹⁹Tc. This new information, which was extracted from these data sets using the proposed techniques, can potentially enhance the design of radioactive waste bioremediation.

Ensemble of One-Class Classifiers for Personal Risk Detection Based on Wearable Sensor Data

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users.

Chromatin Regulators as a Guide for Cancer Treatment Choice

The limited capacity to predict a patient's response to distinct chemotherapeutic agents is a major hurdle in cancer management. The efficiency of a large fraction of current cancer therapeutics (radio- and chemotherapies) is influenced by chromatin structure. Reciprocally, alterations in chromatin organization may affect resistance mechanisms. Here, we explore how the misexpression of chromatin regulators-factors involved in the establishment and maintenance of functional chromatin domains-can inform about the extent of docetaxel response. We exploit Affymetrix and NanoString gene expression data for a set of chromatin regulators generated from breast cancer patient-derived xenograft models and patient samples treated with docetaxel. Random Forest classification reveals specific panels of chromatin regulators, including key components of the SWI/SNF chromatin remodeler, which readily distinguish docetaxel high-responders and poor-responders. Further exploration of SWI/SNF components in the comprehensive NCI-60 dataset reveals that the expression inversely correlates with docetaxel sensitivity. Finally, we show that loss of the SWI/SNF subunit BRG1 (SMARCA4) in a model cell line leads to enhanced docetaxel sensitivity. Altogether, our findings point toward chromatin regulators as biomarkers for drug response as well as therapeutic targets to sensitize patients toward docetaxel and combat drug resistance. Mol Cancer Ther; 15(7); 1768-77. ©2016 AACR.

Individual and Familial Susceptibility to MPTP in a Common Marmoset Model for Parkinson's Disease

INTRODUCTION

Insight into susceptibility mechanisms underlying Parkinson's disease (PD) would aid the understanding of disease etiology, enable target finding and benefit the development of more refined disease-modifying strategies.

METHODS

We used intermittent low-dose MPTP (0.5 mg/kg/week) injections in marmosets and measured multiple behavioral and neurochemical parameters. Genetically diverse monkeys from different breeding families were selected to investigate inter- and intrafamily differences in susceptibility to MPTP treatment.

RESULTS

We show that such differences exist in clinical signs, in particular nonmotor PD-related behaviors, and that they are accompanied by differences in neurotransmitter levels. In line with the contribution of a genetic component, different susceptibility phenotypes could be traced back through genealogy to individuals of the different families.

CONCLUSION

Our findings show that low-dose MPTP treatment in marmosets represents a clinically relevant PD model, with a window of opportunity to examine the onset of the disease, allowing the detection of individual variability in disease susceptibility, which may be of relevance for the diagnosis and treatment of PD in humans.

Quantitative Modeling of Microbial Population Responses to Chronic Irradiation Combined with Other Stressors

Microbial population responses to combined effects of chronic irradiation and other stressors (chemical contaminants, other sub-optimal conditions) are important for ecosystem functioning and bioremediation in radionuclide-contaminated areas. Quantitative mathematical modeling can improve our understanding of these phenomena. To identify general patterns of microbial responses to multiple stressors in radioactive environments, we analyzed three data sets on: (1) bacteria isolated from soil contaminated by nuclear waste at the Hanford site (USA); (2) fungi isolated from the Chernobyl nuclear-power plant (Ukraine) buildings after the accident; (3) yeast subjected to continuous γ-irradiation in the laboratory, where radiation dose rate and cell removal rate were independently varied. We applied generalized linear mixed-effects models to describe the first two data sets, whereas the third data set was amenable to mechanistic modeling using differential equations. Machine learning and information-theoretic approaches were used to select the best-supported formalism(s) among biologically-plausible alternatives. Our analysis suggests the following: (1) Both radionuclides and co-occurring chemical contaminants (e.g. NO₂) are important for explaining microbial responses to radioactive contamination. (2) Radionuclides may produce non-monotonic dose responses: stimulation of microbial growth at low concentrations vs. inhibition at higher ones. (3) The extinction-defining critical radiation dose rate is dramatically lowered by additional stressors. (4) Reproduction suppression by radiation can be more important for determining the critical dose rate, than radiation-induced cell mortality. In conclusion, the modeling approaches used here on three diverse data sets provide insight into explaining and predicting multi-stressor effects on microbial communities: (1) the most severe effects (e.g. extinction) on microbial populations may occur when unfavorable environmental conditions (e.g. fluctuations of temperature and/or nutrient levels) coincide with radioactive contamination; (2) an organism’s radioresistance and bioremediation efficiency in rich laboratory media may be insufficient to carry out radionuclide bioremediation in the field—robustness against multiple stressors is needed.

Identifying human microRNA–disease associations by a new diffusion-based method

Identifying the microRNA–disease relationship is vital for investigating the pathogenesis of various diseases. However, experimental verification of disease-related microRNAs remains considerable challenge to many researchers, particularly for the fact that numerous new microRNAs are discovered every year. As such, development of computational methods for disease-related microRNA prediction has recently gained eminent attention. In this paper, first, we construct a miRNA functional network and a disease similarity network by integrating different information sources. Then, we further introduce a new diffusion-based method (NDBM) to explore global network similarity for miRNA–disease association inference. Even though known miRNA–disease associations in the database are rare, NDBM still achieves an area under the ROC curve (AUC) of 85.62% in the leave-one-out cross-validation in improving the prediction accuracy of previous methods significantly. Moreover, our method is applicable to diseases with no known related miRNAs as well as new miRNAs with unknown target diseases. Some associations who strongly predicted by our method are confirmed by public databases. These superior performances suggest that NDBM could be an effective and important tool for biomedical research.