Multimodal Perturbation Research Articles

Host-microbiome associations in saliva predict COVID-19 severity.

Established evidence indicates that oral microbiota plays a crucial role in modulating host immune responses to viral infection. Following severe acute respiratory syndrome coronavirus 2, there are coordinated microbiome and inflammatory responses within the mucosal and systemic compartments that are unknown. The specific roles the oral microbiota and inflammatory cytokines play in the pathogenesis of coronavirus disease 2019 (COVID-19) are yet to be explored. Here, we evaluated the relationships between the salivary microbiome and host parameters in different groups of COVID-19 severity based on their oxygen requirement. Saliva and blood samples (n = 80) were collected from COVID-19 and from noninfected individuals. We characterized the oral microbiomes using 16S ribosomal RNA gene sequencing and evaluated saliva and serum cytokines and chemokines using multiplex analysis. Alpha diversity of the salivary microbial community was negatively associated with COVID-19 severity, while diversity increased with health. Integrated cytokine evaluations of saliva and serum showed that the oral host response was distinct from the systemic response. The hierarchical classification of COVID-19 status and respiratory severity using multiple modalities separately (i.e. microbiome, salivary cytokines, and systemic cytokines) and simultaneously (i.e. multimodal perturbation analyses) revealed that the microbiome perturbation analysis was the most informative for predicting COVID-19 status and severity, followed by the multimodal. Our findings suggest that oral microbiome and salivary cytokines may be predictive of COVID-19 status and severity, whereas atypical local mucosal immune suppression and systemic hyperinflammation provide new cues to understand the pathogenesis in immunologically compromised populations.

An intelligent stock trading decision system based on ensemble classifier through multimodal perturbation

Candlesticks are widely used as an effective technical analysis tool in financial markets. Traditionally, different combinations of candlesticks have formed specific bullish/bearish patterns providing investors with increased opportunities for profitable trades. However, most patterns derived from subjective expertise without quantitative analysis. In this article, combining bullish/bearish patterns with ensemble learning, we present an intelligent system for making stock trading decisions. The Ensemble Classifier through Multimodal Perturbation (ECMP) is designed to generate a diverse set of precise base classifiers to further determine the candlestick patterns. It achieves this by: first, introducing perturbations to the sample space through bootstrap sampling; second, employing an attribute reduction algorithm based on neighborhood rough set theory to select relevant features; third, perturbing the feature space through random subspace selection. Ultimately, the trading decisions are guided by the classification outcomes of this procedure. To evaluate the proposed model, we apply it to empirical investigations within the context of the Chinese stock market. The results obtained from our experiments clearly demonstrate the effectiveness of the approach.

Multimodal Perturbation and Cluster Pruning Based Selective Ensemble Classifier and Its Iron Industrial Application

Multimodal Perturbation and Cluster Pruning Based Selective Ensemble Classifier and Its Iron Industrial Application

Multimodal perturbation analyses of cyclin-dependent kinases reveal a network of synthetic lethalities associated with cell-cycle regulation and transcriptional regulation

Cell-cycle control is accomplished by cyclin-dependent kinases (CDKs), motivating extensive research into CDK targeting small-molecule drugs as cancer therapeutics. Here we use combinatorial CRISPR/Cas9 perturbations to uncover an extensive network of functional interdependencies among CDKs and related factors, identifying 43 synthetic-lethal and 12 synergistic interactions. We dissect CDK perturbations using single-cell RNAseq, for which we develop a novel computational framework to precisely quantify cell-cycle effects and diverse cell states orchestrated by specific CDKs. While pairwise disruption of CDK4/6 is synthetic-lethal, only CDK6 is required for normal cell-cycle progression and transcriptional activation. Multiple CDKs (CDK1/7/9/12) are synthetic-lethal in combination with PRMT5, independent of cell-cycle control. In-depth analysis of mRNA expression and splicing patterns provides multiple lines of evidence that the CDK-PRMT5 dependency is due to aberrant transcriptional regulation resulting in premature termination. These inter-dependencies translate to drug–drug synergies, with therapeutic implications in cancer and other diseases.

An Optimally Selective Ensemble Classifier Based on Multimodal Perturbation and Its Application

An Optimally Selective Ensemble Classifier Based on Multimodal Perturbation and Its Application

Adaptive forecasting of wind power based on selective ensemble of offline global and online local learning

Wind power has become an important part of clean energy. Reliable wind power forecasting is the key to performing optimal scheduling of wind energy. However, it is challenging to obtain accurate wind power forecasting due to inherent intermittency and randomness of wind energy. In addition, the characteristics of wind power data will inevitably change with time, which will lead to the performance degradation of the forecasting model. To address these problems, an adaptive wind power forecasting method based on selective ensemble of offline global and online local learning (SEOGOL) is proposed. To ensure the effectiveness of the ensemble, SEOGOL employs a multi-modal perturbation mechanism to enhance the diversity of the base models, including perturbation on modeling samples through multi-resolution and multi-interval time-difference resampling, perturbation on learners, and perturbation on model hyperparameters. In addition, with defining the accuracy and diversity of base models as two optimization objectives, a multi-objective ensemble pruning approach is proposed to achieve model selection. Furthermore, the adaptive fusion of the individual models is achieved according to the Bayesian rule. Compared with traditional non-adaptive and simple adaptive forecasting methods, the proposed method successfully combines the advantages of offline global and online local learning. SEOGOL can not only mine large-scale historical wind power data, but also capture the latest wind power status information, thus effectively improving the accuracy and reliability of wind power forecasting. The effectiveness and superiority of the proposed SEOGOL method are verified using an actual wind power data set.

Semi-supervised ensemble support vector regression based soft sensor for key quality variable estimation of nonlinear industrial processes with limited labeled data

Soft sensor technique has become a promising solution to enable real-time estimations of difficult-to-measure quality variables in industrial processes. However, traditional soft sensor models cannot always function well due to two challenging issues. First, labeled data are usually expensive to obtain in many real-world applications, thus leading to unsatisfactory performance for traditional supervised soft sensors. Meanwhile, the information behind abundant unlabeled data is not fully exploited. Second, it is very common for soft sensors to encounter the modeling uncertainty resulting from the diversity of training data, model hyperparameters, and optimization parameters. Therefore, a new soft sensor method called semi-supervised ensemble support vector regression (SSESVR) is proposed by combining semi-supervised learning with ensemble learning. The SSESVR method first formulates the estimation of pseudo-labels as a multi-learner pseudo-labeling optimization problem and then solve it through evolutionary approach, thus extending the labeled training set using satisfactory pseudo-labeled data. Further, by considering multimodal perturbation mechanism, a two-level ensemble architecture is employed to enable efficient cooperation of semi-supervised and ensemble learning framework. Two case studies are conducted to verify the effectiveness and superiority of the proposed SSESVR approach.

Probabilistic wind power forecasting using selective ensemble of finite mixture Gaussian process regression models

Ensemble learning models have been widely used for wind power forecasting to facilitate efficient dispatching of power systems. However, traditional ensemble methods cannot always function well due to insufficient accuracy and diversity of base learners, ignorance of ensemble pruning, as well as the lack of adaptation capability. Therefore, a novel probabilistic wind power forecasting method is proposed based on selective ensemble of finite mixture Gaussian process regression models (SEFMGPR). First, a set of diverse local Gaussian process regression (GPR) models are constructed through multimodal perturbation mechanism, i.e., perturbing the training data and input attributes simultaneously. Then, a set of finite mixture GPR models (FMGPR) is built by integrating local GPR models through finite mixture mechanism (FMM). Next, the highly influential FMGPR models are selected using genetic algorithm (GA) based ensemble pruning. When a new test sample comes, the component predictions from the selected FMGPR models are adaptively combined by using FMM again and the probabilistic prediction results of the SEFMGPR model are obtained. Besides, an incremental adaptation mechanism is used to alleviate performance degradation of SEFMGPR. The application results from a real wind farm dataset show that SEFMGPR outperforms the traditional global and ensemble wind power prediction methods, and can maintain high prediction accuracy by effectively handling time-varying changes of wind power data.

Characterizing the molecular regulation of inhibitory immune checkpoints with multimodal single-cell screens.

The expression of inhibitory immune checkpoint molecules such as PD-L1 is frequently observed in human cancers and can lead to the suppression of T cell-mediated immune responses. Here, we apply ECCITE-seq, a technology which combines pooled CRISPR screens with single-cell mRNA and surface protein measurements, to explore the molecular networks that regulate PD-L1 expression. We also develop a computational framework, mixscape, that substantially improves the signal-to-noise ratio in single-cell perturbation screens by identifying and removing confounding sources of variation. Applying these tools, we identify and validate regulators of PD-L1, and leverage our multi-modal data to identify both transcriptional and post-transcriptional modes of regulation. Specifically, we discover that the kelch-like protein KEAP1 and the transcriptional activator NRF2, mediate levels of PD-L1 upregulation after IFNγ stimulation. Our results identify a novel mechanism for the regulation of immune checkpoints and present a powerful analytical framework for the analysis of multi-modal single-cell perturbation screens.

Ensemble learning based on random super-reduct and resampling

Ensemble learning has been widely used for improving the performance of base classifiers. Diversity among base classifiers is considered as a key issue in ensemble learning. Recently, to promote the diversity of base classifiers, ensemble methods through multi-modal perturbation have been proposed. These methods simultaneously use two or more perturbation techniques when generating base classifiers. In this paper, from the perspective of multi-modal perturbation, we propose an ensemble approach (called ‘E $$\_$$ RSRR’) based on random super-reduct and resampling. To generate a set of accurate and diverse base classifiers, E $$\_$$ RSRR adopts a new multi-modal perturbation strategy. This strategy combines two perturbation techniques together, that is, resampling and random super-reduct. First, it perturbs the sample space via the resampling technique; Second, it perturbs the feature space via the random super-reduct technique, which is a combination of RSS (random subspace selection) technique and ADEFS (approximate decision entropy-based feature selection) method in rough sets. Experimental results show that E $$\_$$ RSRR can provide competitive solutions for ensemble learning.

Ensemble Just-In-Time Learning-Based Soft Sensor for Mooney Viscosity Prediction in an Industrial Rubber Mixing Process

The lack of online sensors for Mooney viscosity measurement has posed significant challenges for enabling efficient monitoring, control, and optimization of industrial rubber mixing process. To obtain real-time and accurate estimations of Mooney viscosity, a novel soft sensor method, referred to as multimodal perturbation- (MP-) based ensemble just-in-time learning Gaussian process regression (MP-EJITGPR), is proposed by exploiting ensemble JIT learning. This method employs perturbations on similarity measure and input variables for generating the diversity of JIT learners. Furthermore, a set of accurate and diverse JIT learners are built through an evolutionary multiobjective optimization by balancing the accuracy and diversity objectives explicitly. Moreover, all base JIT learners are combined adaptively using a finite mixture mechanism. The proposed method is applied to an industrial rubber mixing process for Mooney viscosity prediction, and the experimental results demonstrate its effectiveness and superiority over traditional soft sensor methods.

Single-cell RNA-Sequencing in Neuroscience

Summary Technical innovations in the last decade have allowed to sequence transcriptomes of single cells. Single-cell RNA-sequencing (scRNA-seq) has since then opened the window to a deeper understanding of cellular identity and is becoming a widely used method in molecular biology. In neuroscience, scRNA-seq has broad applications, for example in determining cellular diversity in different brain regions and in revealing transcriptomic variations across brain disorders. The method consists of several steps: isolation and lysis of single cells, reverse transcription of RNAs, amplification of cDNAs, and next-generation sequencing. The large datasets can subsequently be analysed using different bioinformatic tools to deduce biological meaning. Current developments aim to integrate scRNA-seq into cellular network analysis through multimodal analysis, spatial localisation and perturbation experiments, in order to understand brain physiology and pathology.

Laser–matter interactions: Inhomogeneous Richtmyer–Meshkov and Rayleigh–Taylor instabilities

AbstractIn this experimental study, the ablative Richtmyer–Meshkov (RM) and the Rayleigh–Taylor (RT) instabilities were generated by the laser pulse of Gaussian-like power profile. The initial multi-modal perturbation, the inhomogeneous momentum transfer and different Atwood numbers generate different shapes of spikes and bubbles in the central region (CR) and the near-central region (NCR) of the spot. A one-dimensional Gaussian-like power profile causes the formation of the wavy-like rows of aperiodic spikes. The periodic spike segments inside the rows appear due to locally coherent flow. In the NCR, the mushroom-shape spikes tend to the organization on the isotropic square and the anisotropic rhombic lattices. The increase of the lattice periods two, three, or four times indicates formation of superstructures. The growth of sharp asymmetric RM/RT spikes in the CR is fast, uncorrelated and linear, while the growth of the symmetric mushroom-shape ones in the NCR is slow, correlated, and nonlinear.

Modal interactions between a large-wavelength inclined interface and small-wavelength multimode perturbations in a Richtmyer-Meshkov instability.

The interaction of a small-wavelength multimodal perturbation with a large-wavelength inclined interface perturbation is investigated for the reshocked Richtmyer-Meshkov instability using three-dimensional simulations. The ares code, developed at Lawrence Livermore National Laboratory, was used for these simulations and a detailed comparison of simulation results and experiments performed at the Georgia Tech Shock Tube facility is presented first for code validation. Simulation results are presented for four cases that vary in large-wavelength perturbation amplitude and the presence of secondary small-wavelength multimode perturbations. Previously developed measures of mixing and turbulence quantities are presented that highlight the large variation in perturbation length scales created by the inclined interface and the multimode complex perturbation. Measures are developed for entrainment, and turbulence anisotropy that help to identify the effects of and competition between each perturbations type. It is shown through multiple measures that before reshock the flow processes a distinct memory of the initial conditions that is present in both large-scale-driven entrainment measures and small-scale-driven mixing measures. After reshock the flow develops to a turbulentlike state that retains a memory of high-amplitude but not low-amplitude large-wavelength perturbations. It is also shown that the high-amplitude large-wavelength perturbation is capable of producing small-scale mixing and turbulent features similar to the small-wavelength multimode perturbations.

Research Note—Generating Shareable Statistical Databases for Business Value: Multiple Imputation with Multimodal Perturbation

Business organizations are generating growing volumes of data about their employees, customers, and suppliers. Much of these data cannot be exploited for business value due to privacy and confidentiality concerns. National statistical agencies share sensitive data collected from individuals and businesses by modifying the data so individuals and firms cannot be identified but statistical utility is preserved. We build on this literature to develop a hybrid approach to data masking for business organizations. We demonstrate the validity of the hybrid approach, which we call multiple imputation with multimodal perturbation (MIMP), using Monte Carlo simulation and illustrate its application in a specific business context. Results of our analysis open new areas of research for information systems scholarship and new potential revenue sources for business organizations.

About Our Authors

About Our Authors

Ensembling evidential k-nearest neighbor classifiers through multi-modal perturbation

Ensembling techniques have already been considered for improving the accuracy of k-nearest neighbor classifier. It is shown that using different feature subspaces for each member classifier, strong ensembles can be generated. Although it has a more flexible structure which is an obvious advantage from diversity point of view and is observed to provide better classification accuracies compared to voting based k-NN classifier, ensembling evidential k -NN classifier which is based on Dempster–Shafer theory of evidence is not yet fully studied. In this paper, we firstly investigate improving the performance of evidential k-NN classifier using random subspace method. Taking into account its potential to be perturbed also in parameter dimension due to its class and classifier dependent parameters, we propose ensembling evidential k-NN through multi-modal perturbation using genetic algorithms. Experimental results have shown that the improved accuracies obtained using random subspace method can be further surpassed through multi-modal perturbation.

Ensembling Local Learners Through Multimodal Perturbation

Ensemble learning algorithms train multiple component learners and then combine their predictions. In order to generate a strong ensemble, the component learners should be with high accuracy as well as high diversity. A popularly used scheme in generating accurate but diverse component learners is to perturb the training data with resampling methods, such as the bootstrap sampling used in bagging. However, such a scheme is not very effective on local learners such as nearest-neighbor classifiers because a slight change in training data can hardly result in local learners with big differences. In this paper, a new ensemble algorithm named Filtered Attribute Subspace based Bagging with Injected Randomness (FASBIR) is proposed for building ensembles of local learners, which utilizes multimodal perturbation to help generate accurate but diverse component learners. In detail, FASBIR employs the perturbation on the training data with bootstrap sampling, the perturbation on the input attributes with attribute filtering and attribute subspace selection, and the perturbation on the learning parameters with randomly configured distance metrics. A large empirical study shows that FASBIR is effective in building ensembles of nearest-neighbor classifiers, whose performance is better than that of many other ensemble algorithms.