Method For Prediction Of Response Research Articles

Configuration Optimization and Response Prediction Method of the Clamping Robot for Vibration Suppression of Cantilever Workpiece

Cantilever workpieces are widely used in the aerospace field; they produce vibrations easily and affect machining quality under the action of external forces. Enhancing the stiffness of the workpiece using a robot as a fixture is an effective means to solve this problem. However, the vibration suppression effect of the clamping system depends on the dynamics performance of different configurations of the robot. Therefore, in order to obtain the optimal clamping robot configuration, the system dynamics model composed of automated guided vehicle (AGV)-robot-gripper-workpiece (ARGW) is established based on the transfer matrix method of the multibody system (MSTMM), and the vibration responses of the workpiece under different configurations are analyzed. Then, a robot configuration optimization method based on workpiece response was proposed. Finally, the effectiveness of the optimization method is verified through simulations and experiments at different clamping robot configurations. The dynamics model and optimization method in this paper can be used to predict the workpiece vibration response and choose a reasonable clamping robot configuration, avoiding the reduction in workpiece machining quality due to the improper configuration of the clamping robot.

Benchmark of embedding-based methods for accurate and transferable prediction of drug response.

Prediction of therapy response has been a major challenge in cancer precision medicine due to the extensive tumor heterogeneity. Recently, several deep learning methods have been developed to predict drug response by utilizing various omics data. Most of them train models by using the drug-response screening data generated from cell lines and then use these models to predict response in cancer patient data. In this study, we focus on and evaluate deep learning methods using transcriptome data for the long-standing question of personalized drug-response prediction. We developed an embedding-based approach for drug-response prediction and benchmarked similar methods for their performance. For all methods, we used pretreatment transcriptome data to train models and then conducted a comprehensive evaluation and comparison of the models using cross-panels, cross-datasets and target genes. We further validated the methods using three independent datasets assessing multiple compounds for their predictive capability of drug response, survival outcome and cell line status. As a result, the methods building on gene embeddings had an overall competitive performance with reduced overfitting when we applied evaluation parameters for model fitting as well as the correlation with clinical outcomes in the validation data. We further developed an ensemble model to combine the results from the three most competitive methods for an overall prediction. Finally, we developed DrVAEN (https://bioinfo.uth.edu/drvaen), a user-friendly and easy-accessible web-server that hosts all these methods for drug-response prediction and model comparison for broad use in cancer research, method evaluation and drug development.

Comparison between two computational fluid dynamics methods for gust response predictions

Based on the open-source computational fluid dynamics (CFD) platform, OpenFOAM, two numerical simulation methods for gusty inflow characterization and gust response prediction are implemented by solving the fundamental incompressible unsteady Reynolds averaged Navier–Stokes (URANS) equations. One is the Field Velocity Method (FVM) and the other is the Oscillating Vane Method (OVM). The gust velocity field is characterized and the aerodynamic responses of some airfoils under the Sears-type sinusoidal gusts are predicted by both gust simulation methods. The results indicate that both methods are capable of obtaining satisfactory gusty inflow conditions as expected as well as the airfoil aerodynamic responses. Comparatively, from the perspective of computing cost, the FVM is more advantageous in reducing the computational resources than the OVM while simultaneously ensuring the computational accuracy.

A novel residual improved deep learning indirect measurement algorithm (RIDLA) for nonlinear dynamic responses

Accurately measuring points-of-concern in nonlinear structures is of great importance for structural optimization analysis, vibration reduction and isolation design, and structural health assessment. For complicated structures with strong nonlinear characteristics, it can be challenging to directly measure the strain, displacement, and other responses at points-of-concern, so sometimes measurements can only be indirectly deduced using data from measurable points. To address the disadvantages of traditional dynamic response analysis and prediction methods, such as their time-consumption and low accuracy, this study made full use of the ability of deep learning to capture nonlinear features. A novel residual improved deep learning indirection measurement algorithm (RIDLA) for predicting dynamic responses of nonlinear structures is proposed. The long short-term memory (LSTM) neural network with time-series feature prediction feedback was selected as the basic algorithm, and a multi-level residual improving deep learning model was constructed using interactive iterations between measurable point responses and calculated residuals, which effectively acquired the dynamic responses of the point-of-concern with improved accuracy. The performance of the RIDLA method in nonlinear response regression was evaluated using a simulation analysis of a six-degree-of-freedom mass-damping-spring nonlinear system and by using random vibration test data of a satellite structure. The results showed that the proposed RIDLA method can achieve high measurement accuracy and is suitable for indirect measurements of dynamic responses in complex nonlinear systems.

A multi-objective based radiomics feature selection method for response prediction following radiotherapy

Objective. Radiomics contains a large amount of mineable information extracted from medical images, which has important significance in treatment response prediction for personalized treatment. Radiomics analyses generally involve high dimensions and redundant features, feature selection is essential for construction of prediction models. Approach. We proposed a novel multi-objective based radiomics feature selection method (MRMOPSO), where the number of features, sensitivity, and specificity are jointly considered as optimization objectives in feature selection. The MRMOPSO innovated in the following three aspects: (1) Fisher score to initialize the population to speed up the convergence; (2) Min-redundancy particle generation operations to reduce the redundancy between radiomics features, a truncation strategy was introduced to further reduce the number of features effectively; (3) Particle selection operations guided by elitism strategies to improve local search ability of the algorithm. We evaluated the effectiveness of the MRMOPSO by using a multi-institution oropharyngeal cancer dataset from The Cancer Imaging Archive. 357 patients were used for model training and cross validation, an additional 64 patients were used for evaluation. Main results. The area under the curve (AUC) of our method achieved AUCs of 0.82 and 0.84 for cross validation and independent dataset, respectively. Compared with classical feature selection methods, the AUC of MRMOPSO is significantly higher than the Lasso (AUC = 0.74, p-value = 0.02), minimal-redundancy-maximal-relevance criterion (mRMR) (AUC = 0.73, p-value = 0.05), F-score (AUC = 0.48, p-value < 0.01), and mutual information (AUC = 0.69, p-value < 0.01) methods. Compared to single-objective methods, the AUC of MRMOPSO is 12% higher than those of the genetic algorithm (GA) (AUC = 0.68, p-value = 0.02) and particle swarm optimization algorithm (AUC = 0.72, p-value = 0.05) methods. Compared to other multi-objective feature selection methods, the AUC of MRMOPSO is 14% higher than those of multiple objective particle swarm optimization (MOPSO) (AUC = 0.68, p-value = 0.02) and nondominated sorting genetic algorithm II (NSGA2) (AUC = 0.70, p-value = 0.03). Significance. We proposed a multi-objective based radiomics feature selection method. Compared to conventional feature reduction algorithms, the proposed algorithm effectively reduced feature dimension, and achieved superior performance, with improved sensitivity and specificity, for response prediction in radiotherapy.

An improved rigid rod method for wind-induced swing response prediction of heavily iced transmission lines

Wind-induced swing of overhead transmission lines may cause flashover and line tripping, which will greatly jeopardize the normal operation of power transmission system and give rise to great economy loss. This paper analyzed a swing flashover accident on a practical high-voltage (HV) transmission line and calculated the swing angle of the suspension insulator string using the rigid rod method recommended by the Chinese standard. The aerodynamic coefficients of the iced HV transmission lines were obtained through high frequency force balance wind tunnel tests. An improved rigid rod method was then developed for predicting wind-induced swing response of heavily iced transmission lines in mountainous terrain under severe icy weather conditions. Finally, the improved rigid rod method was also extended to deal with general transmission lines with light ice accretion or regular ice shapes.

ASGARD is A Single-cell Guided Pipeline to Aid Repurposing of Drugs

Single-cell RNA sequencing technology has enabled in-depth analysis of intercellular heterogeneity in various diseases. However, its full potential for precision medicine has yet to be reached. Towards this, we propose A Single-cell Guided Pipeline to Aid Repurposing of Drugs (ASGARD) that defines a drug score to recommend drugs by considering all cell clusters to address the intercellular heterogeneity within each patient. ASGARD shows significantly better average accuracy on single-drug therapy compared to two bulk-cell-based drug repurposing methods. We also demonstrated that it performs considerably better than other cell cluster-level predicting methods. In addition, we validate ASGARD using the drug response prediction method TRANSACT with Triple-Negative-Breast-Cancer patient samples. We find that many top-ranked drugs are either approved by the Food and Drug Administration or in clinical trials treating corresponding diseases. In conclusion, ASGARD is a promising drug repurposing recommendation tool guided by single-cell RNA-seq for personalized medicine. ASGARD is free for educational use at https://github.com/lanagarmire/ASGARD.

A novel univariate dimension‐reduction based interval finite element method for static response prediction of uncertain structures

AbstractTo eliminate the errors caused by the conventional interval perturbation finite element method due to classic interval arithmetic and neglect of higher‐order terms, we propose a novel univariate dimension‐reduction based interval finite element method to predict the static response bounds of structures with uncertain but bounded parameters. First, a univariate dimension‐reduction algorithm is derived using the generalized Taylor expansion. The global stiffness matrix is expressed as the sum of the median and the univariate disturbance radius. Compared with Taylor expansion approximation, the univariate dimension‐reduction approximation has higher accuracy and does not increase the amount of calculation. Then the inverse of the interval global stiffness matrix is approximated as an improved Neumann series. Higher‐ order terms are included by summing up the geometric terms in the Neumann series. Finally, the improved interval algorithm is used to solve the upper and lower bounds of the structural displacement response and the element stress response. The dependence between the interval parameters is accounted in comparison with the classic interval algorithm. The accuracy and effectiveness of the new method are validated by numerical cases on 2D truss, 3D frame and truck frame with multiple interval parameters.

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends.

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

DROEG: a method for cancer drug response prediction based on omics and essential genes integration.

Predicting therapeutic responses in cancer patients is a major challenge in the field of precision medicine due to high inter- and intra-tumor heterogeneity. Most drug response models need to be improved in terms of accuracy, and there is limited research to assess therapeutic responses of particular tumor types. Here, we developed a novel method DROEG (Drug Response based on Omics and Essential Genes) for prediction of drug response in tumor cell lines by integrating genomic, transcriptomic and methylomic data along with CRISPR essential genes, and revealed that the incorporation of tumor proliferation essential genes can improve drug sensitivity prediction. Concisely, DROEG integrates literature-based and statistics-based methods to select features and uses Support Vector Regression for model construction. We demonstrate that DROEG outperforms most state-of-the-art algorithms by both qualitative (prediction accuracy for drug-sensitive/resistant) and quantitative (Pearson correlation coefficient between the predicted and actual IC50) evaluation in Genomics of Drug Sensitivity in Cancer and Cancer Cell Line Encyclopedia datasets. In addition, DROEG is further applied to the pan-gastrointestinal tumor with high prevalence and mortality as a case study at both cell line and clinical levels to evaluate the model efficacy and discover potential prognostic biomarkers in Cisplatin and Epirubicin treatment. Interestingly, the CRISPR essential gene information is found to be the most important contributor to enhance the accuracy of the DROEG model. To our knowledge, this is the first study to integrate essential genes with multi-omics data to improve cancer drug response prediction and provide insights into personalized precision treatment.

ScDR: Predicting Drug Response at Single-Cell Resolution.

Heterogeneity exists inter- and intratumorally, which might lead to different drug responses. Therefore, it is extremely important to clarify the drug response at single-cell resolution. Here, we propose a precise single-cell drug response (scDR) prediction method for single-cell RNA sequencing (scRNA-seq) data. We calculated a drug-response score (DRS) for each cell by integrating drug-response genes (DRGs) and gene expression in scRNA-seq data. Then, scDR was validated through internal and external transcriptomics data from bulk RNA-seq and scRNA-seq of cell lines or patient tissues. In addition, scDR could be used to predict prognoses for BLCA, PAAD, and STAD tumor samples. Next, comparison with the existing method using 53,502 cells from 198 cancer cell lines showed the higher accuracy of scDR. Finally, we identified an intrinsic resistant cell subgroup in melanoma, and explored the possible mechanisms, such as cell cycle activation, by applying scDR to time series scRNA-seq data of dabrafenib treatment. Altogether, scDR was a credible method for drug response prediction at single-cell resolution, and helpful in drug resistant mechanism exploration.

Dynamic response prediction of prototype from scale-down model for I-core sandwich panels subjected to internal explosion

Cabin scale-down model experiments are an effective approach to investigate the dynamic response of I-core sandwich panels subjected to internal explosion. However, it is difficult to guarantee the complete geometrical similarity in terms of plate thickness for I-core sandwich panels between the scale-down model and prototype due to manufacturing process restriction and thickness specifications of commercially available plates. To resolve the above issue, a new and more reasonable dynamic response prediction method with high accuracy for prototype based on scale-down model test was proposed in the present work. The feasibility and accuracy of proposed prediction method were theoretically, experimentally, and numerically verified. The effects of TNT charge mass, correction method of TNT charge mass, and quasi-static pressure load were investigated. Results show that the proposed prediction method from the energy point of view has high accuracy and good feasibility when the plate thickness of scale-down model distorts. In the proposed approach, the TNT charge mass is corrected through specific impulse correction. Higher accuracy is gained by using the proposed prediction method in the case of internal explosion with large TNT charge mass. Directly correcting the TNT charge mass on the basis of geometrical similarity still underestimates the dynamic response of incomplete scale-down model when plate thickness distorts. It is not reasonable to ignore the effect of quasi-static pressure load, because the specific impulse of quasi-static pressure load is much larger than that of shock wave load. This work can provide practicable and accurate application guidance for the design of internal explosion scale-down model experiments for I-core sandwich panels.

Pharmacogenetics of Anticancer Drugs: Clinical Response and Toxicity.

Cancer is the most challenging disease for medical professionals to treat. The factors underlying the complicated situation include anticancer drug-associated toxicity, non-specific response, low therapeutic window, variable treatment outcomes, development of drug resistance, treatment complications, and cancer recurrence. The remarkable advancement in biomedical sciences and genetics, over the past few decades, however, is changing the dire situation. The discovery of gene polymorphism, gene expression, biomarkers, particular molecular targets and pathways, and drug-metabolizing enzymes have paved the way for the development and provision of targeted and individualized anticancer treatment. Pharmacogenetics is the study of genetic factors having the potential to affect clinical responses and pharmacokinetic and pharmacodynamic behaviors of drugs. This chapter emphasizes pharmacogenetics of anticancer drugs and its applications in improving treatment outcomes, selectivity, toxicity of the drugs, and discovering and developing personalized anticancer drugs and genetic methods for prediction of drug response and toxicity.

SEISMIC RESPONSE PREDICTION METHOD BASED ON EQUIVALENT LINEARIZATION OF STUD-TYPE VISCOELASTIC DAMPERS WITH AMPLITUDE DEPENDENCIES

Equivalent linearization is an available method widely used to conveniently predict the nonlinear responses of buildings. The present study proposes a seismic response prediction method based on equivalent linearization of stud-type viscoelastic dampers with amplitude dependencies for that there is not a lot of research discussing on estimation method for such dampers. Through the present analyses, the authors found that the proposed prediction method leads the structural design process to be more effective one saving costs by comparison with former trial-and-error approach with time history numerical analysis.

A systematic assessment of deep learning methods for drug response prediction: from in vitro to clinical applications.

Drug response prediction is an important problem in personalized cancer therapy. Among various newly developed models, significant improvement in prediction performance has been reported using deep learning methods. However, systematic comparisons of deep learning methods, especially of the transferability from preclinical models to clinical cohorts, are currently lacking. To provide a more rigorous assessment, the performance of six representative deep learning methods for drug response prediction using nine evaluation metrics, including the overall prediction accuracy, predictability of each drug, potential associated factors and transferability to clinical cohorts, in multiple application scenarios was benchmarked. Most methods show promising prediction within cell line datasets, and TGSA, with its lower time cost and better performance, is recommended. Although the performance metrics decrease when applying models trained on cell lines to patients, a certain amount of power to distinguish clinical response on some drugs can be maintained using CRDNN and TGSA. With these assessments, we provide a guidance for researchers to choose appropriate methods, as well as insights into future directions for the development of more effective methods in clinical scenarios.

Drug response prediction using graph representation learning and Laplacian feature selection

Knowing the responses of a patient to drugs is essential to make personalized medicine practical. Since the current clinical drug response experiments are time-consuming and expensive, utilizing human genomic information and drug molecular characteristics to predict drug responses is of urgent importance. Although a variety of computational drug response prediction methods have been proposed, their effectiveness is still not satisfying. In this study, we propose a method called LGRDRP (Learning Graph Representation for Drug Response Prediction) to predict cell line-drug responses. At first, LGRDRP constructs a heterogeneous network integrating multiple kinds of information: cell line miRNA expression profiles, drug chemical structure similarity, gene-gene interaction, cell line-gene interaction and known cell line-drug responses. Then, for each cell line, learning graph representation and Laplacian feature selection are combined to obtain network topology features related to the cell line. The learning graph representation method learns network topology structure features, and the Laplacian feature selection method further selects out some most important ones from them. Finally, LGRDRP trains an SVM model to predict drug responses based on the selected features of the known cell line-drug responses. Our five-fold cross-validation results show that LGRDRP is significantly superior to the art-of-the-state methods in the measures of the average area under the receiver operating characteristics curve, the average area under the precision-recall curve and the recall rate of top-k predicted sensitive cell lines. Our results demonstrated that the usage of multiple types of information about cell lines and drugs, the learning graph representation method, and the Laplacian feature selection is useful to the improvement of performance in predicting drug responses. We believe that such an approach would be easily extended to similar problems such as miRNA-disease relationship inference.

Digital twin-based life-cycle seismic performance assessment of a long-span cable-stayed bridge

Long-span cable-stayed bridges often have a design service life of more than a hundred years, during which they may experience multiple earthquake events and accumulate seismic damage if they are located in seismic-prone regions. Earthquake occurrence is discretely and randomly distributed over the life cycle of a long-span cable-stayed bridge and often causes sudden drops in the structural performance instead of yearly fixed seismic performance degradation. This study thus proposes a digital twin-based life-cycle seismic performance assessment method for long-span cable-stayed bridges. The major components of this method include: (1) a seismic hazard analysis-based generation method of earthquake occurrence sequence; (2) a digital twin-based structural response prediction method considering lifetime earthquake occurrence and sequence; and (3) a service life quantification method. The proposed method is applied to a scaled long-span cable-stayed bridge with a series of shake table tests. The results show that the digital twin can closely reproduce the life-cycle seismic response of the bridge under sequential earthquakes. The proposed assessment method provides a more intuitive presentation of the life-cycle seismic damage accumulation process and a more accurate estimation of the service life of a long-span cable-stayed bridge.

ScDrug: From single-cell RNA-seq to drug response prediction

Single-cell RNA sequencing (scRNA-seq) technology allows massively parallel characterization of thousands of cells at the transcriptome level. scRNA-seq is emerging as an important tool to investigate the cellular components and their interactions in the tumor microenvironment. scRNA-seq is also used to reveal the association between tumor microenvironmental patterns and clinical outcomes and to dissect cell-specific effects of drug treatment in complex tissues. Recent advances in scRNA-seq have driven the discovery of biomarkers in diseases and therapeutic targets. Although methods for prediction of drug response using gene expression of scRNA-seq data have been proposed, an integrated tool from scRNA-seq analysis to drug discovery is required. We present scDrug as a bioinformatics workflow that includes a one-step pipeline to generate cell clustering for scRNA-seq data and two methods to predict drug treatments. The scDrug pipeline consists of three main modules: scRNA-seq analysis for identification of tumor cell subpopulations, functional annotation of cellular subclusters, and prediction of drug responses. scDrug enables the exploration of scRNA-seq data readily and facilitates the drug repurposing process. scDrug is freely available on GitHub at https://github.com/ailabstw/scDrug.

A Study on Key Disciplinary Parameters of Artificial Intelligent-Based Analysis Method for Dynamic Response Prediction of Floating Offshore Wind Turbines

Abstract The dynamic performance prediction of floating offshore wind turbines (FOWTs) is a challenging task, as the existing theories might not be fully reliable for FOWTs due to the high nonlinearities and coupling effects. The artificial intelligent (AI) method gives a promising solution for this issue, and Chen and Hu proposed a novel AI-based method, named SADA (software-in-the-loop combined artificial intelligence method for dynamic response analysis of FOWTs), to overcome these challenges. This paper addresses a further and in-depth investigation of the key technologies of the key disciplinary parameters (KDPs) in the SADA method to obtain a novel and accurate analysis method for dynamic responses prediction of FOWTs. First, the categorization of KDPs is introduced, which can be divided into three categories: environmental KDPs, disciplinary KDPs, and specific KDPs. Second, two factors, the number of KDPs and boundary adjustment of KDPs, are investigated through the reinforcement learning algorithm within the SADA method. Basin experimental data of a spar-type FOWT is used for AI training. The results show that more proper KDPs set in the SADA method can lead to higher accuracy for the prediction of FOWTs. Besides, reasonable boundary conditions will also contribute to the convergence of the algorithms efficiently. Finally, the instruction on how to better choose KDPs and how to set and adjust their boundary conditions is given in the conclusion. The application of KDPs in the SADA method not only provides a deeper understanding of the dynamic response of the entire FOWTs system but also provides a promising solution to overcome the challenges of validation.

A Rate‐Dependent Constitutive Model of HTPB Propellant Based on Parallel Rheological Framework

AbstractNumerous studies have shown that highly strain‐rate dependent behavior is present in the mechanical properties of Hydroxyl‐terminated polybutadiene(HTPB)propellants, and many experts and scholars have attempted to develop constitutive models to describe such rate‐dependent properties of propellants. From the linear viscoelastic model to the Zhu‐Wang‐Tang model, the strain‐rate dependent properties of viscoelastic materials have been described to some extent. But due to the highly nonlinear mechanical behavior exhibited in propellant materials, the nonlinear behavior of propellants at different strain rates is difficult to be captured in the above constitutive models which are all based on linear elasticity. Therefore, in this paper, a nonlinear viscoelastic constitutive model was proposed based on the parallel rheological framework, in which the hyperelastic and viscoelastic flow laws were embedded. Because of the excellent ability to capture the nonlinear behavior of the material, the parallel rheological framework was used to predict the mechanical response at six sets of experiments with different rates. Surprisingly, this constitutive structure model performed good prediction of the mechanical properties of the material by comparison between theoretical calculations and experimental data. The constitutive model was verified by finite element method with numerical simulation software, and the robustness of the constitutive model was checked by a new set of experimental data. A good foundation was established for the accurate description of the propellant constitutive model strain‐rate dependent characteristics by the results of this paper, which could provide a new method for the rapid prediction and evaluation of the propellant mechanical response.