On Model Evaluation Under Non-constant Class Imbalance
Ontology highlight
ABSTRACT:
SUBMITTER: Krzhizhanovskaya V
PROVIDER: S-EPMC7303692 | biostudies-literature | 2020 May
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Viscoelasticity is a fundamental property of virtually all biological materials, and proteinaceous, fibrous materials that constitute the extracellular matrix (ECM) are no exception. Viscoelasticity may be particularly important in the ECM since cells can apply mechanical stress resulting from cell contractility over very long periods of time. However, measurements of ECM fiber response to long-term constant force loading are scarce, despite the increasing recognition that mechanical strain regulates the biological function of some ECM fibers. We developed a dual micropipette system that applies constant force to single fibers for up to 8?h. We utilized this system to study the time dependent response of fibronectin (Fn) fibers to constant force, as Fn fibers exhibit tremendous extensibility before mechanical failure as well as strain dependent alterations in biological properties. These data demonstrate the Fn fibers continue to stretch under constant force loading for at least 8?h and that this long-term creep results in plastic deformation of Fn fibers, in contrast to elastic deformation of Fn fibers under short-term, but fast loading rate extension. These data demonstrate that physiologically-relevant loading may impart mechanical features to Fn fibers by switching them into an extended state that may have altered biological functions. STATEMENT OF SIGNIFICANCE: Measurements of extracellular matrix (ECM) fiber response to constant force loading are scarce, so we developed a novel technique for applying constant force to single ECM fibers. We used this technique to measure constant force creep of fibronectin fibers since these fibers have been shown to be mechanotransducers whose functions can be altered by mechanical strain. We found that fibronectin fibers creep under constant force loading for the duration of the experiment and that this creep behavior resembles a power law. Furthermore, we found that constant force creep results in plastic deformation of the fibers, which suggests that the mechanobiological switching of fibronectin can only occur once after long-term loading.
| S-EPMC6777959 | biostudies-literature
Project description:Relative potency plays an important role in toxicology. Estimates of relative potency are used to rank chemicals by their effects, to calculate equivalent doses of test chemicals compared to a standard, and to weight contributions of constituent chemicals when evaluating mixtures. Typically relative potency is characterized by a constant dilution factor, even when non-similar dose-response curves indicate that constancy is inappropriate. Improperly regarding relative potency as constant may distort conclusions and potentially mislead investigators or policymakers. We consider a more general approach that allows relative potency to vary as a function of dose, response, or response quantile. Distinct functions can be defined, each generalizing different but equivalent descriptions of constant relative potency. When two chemicals have identical response limits, these functions all carry fundamentally equivalent information; otherwise, relative potency as a function of response quantile is distinct and embodies a modified definition of relative potency. Which definition is preferable depends on whether one views any differences in response limits as intrinsic to the chemicals or as extrinsic, arising from idiosyncrasies of data sources. We illustrate these ideas with constructed examples and real data. Relative potency functions offer a unified and principled description of relative potency for non-similar dose-response curves.
| S-EPMC3134169 | biostudies-literature
Project description:Isothermal titration calorimetry (ITC) is the gold standard for accurate measurement of thermodynamic parameters in solution reactions. In the data processing of ITC, the non-constant variance of the heat requires special consideration. The variance function approach has been successfully applied in previous studies, but is found to fail under certain conditions in this work. Here, an explicit ITC measurement model consisting of main thermal effects and error components has been proposed to quantitatively evaluate and predict the non-constant variance of the heat data under various conditions. Monte Carlo simulation shows that the ITC measurement model provides higher accuracy and flexibility than variance function in high c-value reactions or with additional error components, for example, originated from the fluctuation of the concentrations or other properties of the solutions. The experimental design of basic error evaluation is optimized accordingly and verified by both Monte Carlo simulation and experiments. An easy-to-run Python source code is provided to illustrate the establishment of the ITC measurement model and the estimation of heat variances. The accurate and reliable non-constant variance of heat is helpful to the application of weighted least squares regression, the proper evaluation or selection of the reaction model.
| S-EPMC7773272 | biostudies-literature
Project description:Various definitions of fitness are essentially based on the number of descendants of an allele or a phenotype after a sufficiently long time. However, these different definitions do not explicate the continuous evolution of life histories. Herein, we focus on the eigenfunction of an age-structured population model as fitness. The function generates an equation, called the Hamilton-Jacobi-Bellman equation, that achieves adaptive control of life history in terms of both the presence and absence of the density effect. Further, we introduce a perturbation method that applies the solution of this equation to the long-term logarithmic growth rate of a stochastic structured population model. We adopt this method to realize the adaptive control of heterogeneity for an optimal foraging problem in a variable environment as the analyzable example. The result indicates that the eigenfunction is involved in adaptive strategies under all the environments listed herein. Thus, we aim to systematize adaptive life histories in the presence of density effects and variable environments using the proposed objective function as a universal fitness candidate.
| S-EPMC8437290 | biostudies-literature
Project description:Drywells are widely used as managed aquifer recharge devices to capture stormwater runoff and recharge groundwater, but little research has examined the role of subsurface heterogeneity in hydraulic properties on drywell recharge efficiency. Numerical experiments were therefore conducted on a 2D-axisymmetric domain using the HYDRUS (2D/3D) software to systematically study the influence of various homogenous soil types and subsurface heterogeneity on recharge from drywells under constant head conditions. The mean cumulative infiltration (μI) and recharge (μR) volumes increased with an increase in the saturated hydraulic conductivity (Ks ) for various homogeneous soils. Subsurface heterogeneity was described by generating ten stochastic realizations of soil hydraulic properties with selected standard deviation (σ), and horizontal (X) and vertical (Z) correlation lengths. After 365 days, values of μI, μR, and the radius of the recharge area increased with σ and X but decreased with Z. The value of μR was always smaller for a homogeneous than a heterogeneous domain. This indicates that recharge for a heterogeneous profile cannot be estimated with an equivalent homogeneous profile. The value of μR was always smaller than μI and correlations were highly non-linear due to vadose zone storage. Knowledge of only infiltration volume can, therefore, lead to misinterpretation of recharge efficiency, especially at earlier times. The arrival time of the wetting front at the bottom boundary (60 m) ranged from 21-317 days, with earlier times occurring for increasing σ and Z. The corresponding first arrival location can be 0.1-44 m away from the bottom releasing point of a drywell in the horizontal direction, with greater distances occurring for increasing σ and X. This knowledge is important to accurately assess drywell recharged performance, water quantity, and water quality.
| S-EPMC7751658 | biostudies-literature
Project description:Although over 90 oversampling approaches have been developed in the imbalance learning domain, most of the empirical study and application work are still based on the “classical” resampling techniques. In this paper, several experiments on 19 benchmark datasets are set up to study the efficiency of six powerful oversampling approaches, including both “classical” and new ones. According to our experimental results, oversampling techniques that consider the minority class distribution (new ones) perform better in most cases and RACOG gives the best performance among the six reviewed approaches. We further validate our conclusion on our real-world inspired vehicle datasets and also find applying oversampling techniques can improve the performance by around 10%. In addition, seven data complexity measures are considered for the initial purpose of investigating the relationship between data complexity measures and the choice of resampling techniques. Although no obvious relationship can be abstracted in our experiments, we find F1v value, a measure for evaluating the overlap which most researchers ignore, has a strong negative correlation with the potential AUC value (after resampling).
| S-EPMC7206329 | biostudies-literature
Project description:MicroRNAs (miRNAs) are ~20-25 nucleotides non-coding RNAs, which regulated gene expression in the post-transcriptional level. The accurate rate of identifying the start sit of mature miRNA from a given pre-miRNA remains lower. It is noting that the mature miRNA prediction is a class-imbalanced problem which also leads to the unsatisfactory performance of these methods. We improved the prediction accuracy of classifier using balanced datasets and presented MatFind which is used for identifying 5' mature miRNAs candidates from their pre-miRNA based on ensemble SVM classifiers with idea of adaboost. Firstly, the balanced-dataset was extract based on K-nearest neighbor algorithm. Secondly, the multiple SVM classifiers were trained in orderly using the balance datasets base on represented features. At last, all SVM classifiers were combined together to form the ensemble classifier. Our results on independent testing dataset show that the proposed method is more efficient than one without treating class imbalance problem. Moreover, MatFind achieves much higher classification accuracy than other three approaches. The ensemble SVM classifiers and balanced-datasets can solve the class-imbalanced problem, as well as improve performance of classifier for mature miRNA identification. MatFind is an accurate and fast method for 5' mature miRNA identification.
| S-EPMC4867574 | biostudies-literature
Project description:MiRNAs are small (~22nt long) non-coding RNA sequences; binds to the complementarity target sites in 3' Untranslated Region (UTR) of mRNA sequences but not restricted to other mRNA regions viz., 5' UTR and Coding sequences (CDS). Complementarity binding of miRNA to mRNA target sites either results in complete degradation of the mRNA itself or it may regulate the mRNA as an oncogene or as a tumor suppressor gene. However, the exact mechanism involved in identifying a miRNA to be associated with cancer is still unclear. Further, with the outburst in the number of miRNAs sequences recorded every year in miRBase, the gap is still widening mainly due to the laborious and economically unfavorable experimental procedures associated with the functional annotation. Motivated by the fact, we constructed a two-step support vector machine-based predictive model - miRSEQ and miRINT. However, the major pitfall during the construction of the model is the class imbalance problem. Hence, in order to overcome class imbalance problem, in the present study we empirically compare the effectiveness of two different methods viz., Synthetic Minority Oversampling Technique (SMOTE) and cost-senstive learning method. Performance measures were evaluated in terms of Precision and Recall. Based on our result, it was observed that for miRNA dataset with high class imbalance utilized for predicting association of cancer, cost-sensitive method outperformed the oversampling method.
| S-EPMC4349932 | biostudies-literature
Project description:Machine intelligence (MI), including machine learning and deep learning, have been regarded as promising methods to reduce the prohibitively high cost of drug development. However, a dilemma within MI has limited its wide application: machine learning models are easier to interpret but yield worse predictive performance than deep learning models. Therefore, we propose a pipeline called Class Imbalance Learning with Bayesian Optimization (CILBO) to improve the performance of machine learning models in drug discovery. To demonstrate the efficacy of the CILBO pipeline, we developed an example model to predict antibacterial candidates. Comparison of the antibacterial prediction performance between our model and a well-known deep learning model published by Stokes et al. suggests that our model can perform as well as the deep learning model in drug activity prediction. The CILBO pipeline we propose provides a simple, alternative approach to accelerate preliminary screenings and decrease the cost of drug discovery.
| S-EPMC8827090 | biostudies-literature
Project description:There is widespread evidence for a worldwide trend of insect decline, but we have much fewer data about recent temporal trends in other arthropod groups, including spiders. Spiders can be hypothesised to similarly decline because of trophic dependence on insects and being equally sensitive to local and global environmental changes. Background trends in arthropod populations can be verified if we decouple large-scale environmental transitions, such as climate change, from local factors. To provide a case study on baseline spider community trends, we observed changes in the spider community of an unsprayed alfalfa field and its margin 23 years apart under largely unchanged local conditions. We aimed to determine whether there are changes in spider abundance, species richness and mean species characteristics. Spider abundance per unit effort decreased dramatically, by 45% in alfalfa and by 59% in the margin, but species richness and most characteristics remained unchanged. Community composition in both habitats shifted and became more similar by the current study period. The population decline was especially marked in certain farmland species. We propose that in the absence of local causative factors, spider abundance decline in our study indicates a reduction of spider populations at landscape and regional scales.
| S-EPMC9911793 | biostudies-literature