Estimation of non-equilibrium transition rate from gene expression data.

The dynamical properties of many complex physical and biological systems can be quantified from the energy landscape theory. Previous approaches focused on estimating the transition rate from landscape reconstruction based on data. However, for general non-equilibrium systems (such as gene regulatory systems), both the energy landscape and the probability flux are important to determine the transition rate between attractors. In this work, we proposed a data-driven approach to estimate non-equilibrium transition rate, which combines the kernel density estimation and non-equilibrium transition rate theory. Our approach shows superior performance in estimating transition rate from data, compared with previous methods, due to the introduction of a nonparametric density estimation method and the new saddle point by considering the effects of flux. We demonstrate the practical validity of our approach by applying it to a simplified cell fate decision model and a high-dimensional stem cell differentiation model. Our approach can be applied to other biological and physical systems.

Community data-driven approach to identify pathogenic founder variants for pan-ethnic carrier screening panels.

BACKGROUND: The American College of Medical Genetics and Genomics (ACMG) recently published new tier-based carrier screening recommendations. While many pan-ethnic genetic disorders are well established, some genes carry pathogenic founder variants (PFVs) that are unique to specific ethnic groups. We aimed to demonstrate a community data-driven approach to creating a pan-ethnic carrier screening panel that meets the ACMG recommendations. METHODS: Exome sequencing data from 3061 Israeli individuals were analyzed. Machine learning determined ancestries. Frequencies of candidate pathogenic/likely pathogenic (P/LP) variants based on ClinVar and Franklin were calculated for each subpopulation based on the Franklin community platform and compared with existing screening panels. Candidate PFVs were manually curated through community members and the literature. RESULTS: The samples were automatically assigned to 13 ancestries. The largest number of samples was classified as Ashkenazi Jewish (n = 1011), followed by Muslim Arabs (n = 613). We detected one tier-2 and seven tier-3 variants that were not included in existing carrier screening panels for Ashkenazi Jewish or Muslim Arab ancestries. Five of these P/LP variants were supported by evidence from the Franklin community. Twenty additional variants were detected that are potentially pathogenic tier-2 or tier-3. CONCLUSIONS: The community data-driven and sharing approaches facilitate generating inclusive and equitable ethnically based carrier screening panels. This approach identified new PFVs missing from currently available panels and highlighted variants that may require reclassification.

Feed Components and Timing to Improve the Feed Conversion Ratio for Sustainable Aquaculture Using Starch.

Aquaculture contributes to the sustainable development of food security, marine resource conservation, and economy. Shifting aquaculture feed from fish meal and oil to terrestrial plant derivatives may result in cost savings. However, many carnivorous fish cannot be sustained on plant-derived materials, necessitating the need for the identification of important factors for farmed fish growth and the identification of whether components derived from terrestrial plants can be used in feed. Herein, we focused on the carnivorous fish leopard coral grouper (P. leopardus) to identify the essential growth factors and clarify their intake timing from feeds. Furthermore, we evaluated the functionality of starch, which are easily produced by terrestrial plants. Results reveal that carbohydrates, which are not considered essential for carnivorous fish, can be introduced as a major part of an artificial diet. The development of artificial feed using starch offers the possibility of increasing the growth of carnivorous fish in aquaculture.

Data-driven multivariate identification of gyrification patterns in a transdiagnostic patient cohort: A cluster analysis approach.

BACKGROUND: Multivariate data-driven statistical approaches offer the opportunity to study multi-dimensional interdependences between a large set of biological parameters, such as high-dimensional brain imaging data. For gyrification, a putative marker of early neurodevelopment, direct comparisons of patterns among multiple psychiatric disorders and investigations of potential heterogeneity of gyrification within one disorder and a transdiagnostic characterization of neuroanatomical features are lacking. METHODS: In this study we used a data-driven, multivariate statistical approach to analyze cortical gyrification in a large cohort of N = 1028 patients with major psychiatric disorders (Major depressive disorder: n = 783, bipolar disorder: n = 129, schizoaffective disorder: n = 44, schizophrenia: n = 72) to identify cluster patterns of gyrification beyond diagnostic categories. RESULTS: Cluster analysis applied on gyrification data of 68 brain regions (DK-40 atlas) identified three clusters showing difference in overall (global) gyrification and minor regional variation (regions). Newly, data-driven subgroups are further discriminative in cognition and transdiagnostic disease risk factors. CONCLUSIONS: Results indicate that gyrification is associated with transdiagnostic risk factors rather than diagnostic categories and further imply a more global role of gyrification related to mental health than a disorder specific one. Our findings support previous studies highlighting the importance of association cortices involved in psychopathology. Explorative, data-driven approaches like ours can help to elucidate if the brain imaging data on hand and its a priori applied grouping actually has the potential to find meaningful effects or if previous hypotheses about the phenotype as well as its grouping have to be revisited.

CNN-LSTM Hybrid Model to Promote Signal Processing of Ultrasonic Guided Lamb Waves for Damage Detection in Metallic Pipelines.

The ultrasonic guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects in metallic pipelines. The signal processing of guided waves is often challenging due to the complexity of the operational conditions and environment in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for the signal processing and data classification of complex systems, thus showing great potential for damage detection in critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model was utilized for decoding ultrasonic guided waves for damage detection in metallic pipelines, and twenty-nine features were extracted as input to classify different types of defects in metallic pipes. The prediction capacity of the CNN-LSTM model was assessed by comparing it to those of CNN and LSTM. The results demonstrated that the CNN-LSTM hybrid model exhibited much higher accuracy, reaching 94.8%, as compared to CNN and LSTM. Interestingly, the results also revealed that predetermined features, including the time, frequency, and time-frequency domains, could significantly improve the robustness of deep learning approaches, even though deep learning approaches are often believed to include automated feature extraction, without hand-crafted steps as in shallow learning. Furthermore, the CNN-LSTM model displayed higher performance when the noise level was relatively low (e.g., SNR = 9 or higher), as compared to the other two models, but its prediction dropped gradually with the increase of the noise.

A Fault Detection Approach Based on One-Sided Domain Adaptation and Generative Adversarial Networks for Railway Door Systems.

Fault detection using the domain adaptation technique is one of the more promising methods of solving the domain shift problem, and has therefore been intensively investigated in recent years. However, the domain adaptation method still has elements of impracticality: firstly, domain-specific decision boundaries are not taken into consideration, which often results in poor performance near the class boundary; and secondly, information on the source domain needs to be exploited with priority over information on the target domain, as the source domain can provide a rich dataset. Thus, the real-world implementations of this approach are still scarce. In order to address these issues, a novel fault detection approach based on one-sided domain adaptation for real-world railway door systems is proposed. An anomaly detector created using label-rich source domain data is used to generate distinctive source latent features, and the target domain features are then aligned toward the source latent features in a one-sided way. The performance and sensitivity analyses show that the proposed method is more accurate than alternative methods, with an F1 score of 97.9%, and is the most robust against variation in the input features. The proposed method also bridges the gap between theoretical domain adaptation research and tangible industrial applications. Furthermore, the proposed approach can be applied to conventional railway components and various electro-mechanical actuators. This is because the motor current signals used in this study are primarily obtained from the controller or motor drive, which eliminates the need for extra sensors.

Early prediction of Alzheimer's disease and related dementias using real-world electronic health records.

INTRODUCTION: This study aims to explore machine learning (ML) methods for early prediction of Alzheimer's disease (AD) and related dementias (ADRD) using the real-world electronic health records (EHRs). METHODS: A total of 23,835 ADRD and 1,038,643 control patients were identified from the OneFlorida+ Research Consortium. Two ML methods were used to develop the prediction models. Both knowledge-driven and data-driven approaches were explored. Four computable phenotyping algorithms were tested. RESULTS: The gradient boosting tree (GBT) models trained with the data-driven approach achieved the best area under the curve (AUC) scores of 0.939, 0.906, 0.884, and 0.854 for early prediction of ADRD 0, 1, 3, or 5 years before diagnosis, respectively. A number of important clinical and sociodemographic factors were identified. DISCUSSION: We tested various settings and showed the predictive ability of using ML approaches for early prediction of ADRD with EHRs. The models can help identify high-risk individuals for early informed preventive or prognostic clinical decisions.

Data-Driven Approaches Used for Compound Library Design for the Treatment of Parkinson's Disease.

Parkinson's disease (PD) is the second most common neurodegenerative disease in older individuals worldwide. Pharmacological treatment for such a disease consists of drugs such as monoamine oxidase B (MAO-B) inhibitors to increase dopamine concentration in the brain. However, such drugs have adverse reactions that limit their use for extended periods; thus, the design of less toxic and more efficient compounds may be explored. In this context, cheminformatics and computational chemistry have recently contributed to developing new drugs and the search for new therapeutic targets. Therefore, through a data-driven approach, we used cheminformatic tools to find and optimize novel compounds with pharmacological activity against MAO-B for treating PD. First, we retrieved from the literature 3316 original articles published between 2015-2021 that experimentally tested 215 natural compounds against PD. From such compounds, we built a pharmacological network that showed rosmarinic acid, chrysin, naringenin, and cordycepin as the most connected nodes of the network. From such compounds, we performed fingerprinting analysis and developed evolutionary libraries to obtain novel derived structures. We filtered these compounds through a docking test against MAO-B and obtained five derived compounds with higher affinity and lead likeness potential. Then we evaluated its antioxidant and pharmacokinetic potential through a docking analysis (NADPH oxidase and CYP450) and physiologically-based pharmacokinetic (PBPK modeling). Interestingly, only one compound showed dual activity (antioxidant and MAO-B inhibitors) and pharmacokinetic potential to be considered a possible candidate for PD treatment and further experimental analysis.

The clinical heterogeneity of subjective cognitive decline: a data-driven approach on a population-based sample.

BACKGROUND: subjective cognitive decline (SCD) refers to the subjective experience of cognitive decline in the absence of detectable cognitive impairment. SCD has been largely studied as a risk condition for cognitive decline. Empirical observations suggest that persons with SCD are heterogeneous, including individuals with early Alzheimer's disease and others with psychological vulnerabilities and/or physical comorbidity. The semiology of SCD is still in its infancy, and the features predicting cognitive decline are poorly defined. The present study aims to identify subgroups of SCD using a data-driven approach and study their clinical evolution across 8 years. METHODS: the study population is the InveCe.Ab population-based cohort, including cognitively unimpaired people aged 70-74 years and followed for 8 years. Hierarchical cluster analysis (HCA) was carried out to identify distinct SCD subgroups based on nine clinical and cognitive features. Longitudinal changes by baseline SCD status were estimated using linear mixed models for cognitive decline and Cox proportional-hazard model for all-cause dementia risk. RESULTS: out of 956 individuals, 513 were female (54%); and the mean age was 72.1 (SD = 1.3), education was 7.2 (3.3), and 370 (39%) reported cognitive complaints (SCD). The HCA resulted in two clusters (SCD1 and SCD2). SCD2 were less educated and had more comorbidities, cardiovascular risk and depressive symptoms than SCD1 and controls. SCD2 presented steeper cognitive decline (Mini-Mental State Examination; ß = -0.31) and increased all-cause dementia risk (hazard-ratio = 3.4). CONCLUSIONS: at the population level, basic clinical information can differentiate individuals with SCD at higher risk of developing dementia, underlining the heterogeneous nature of this population even in a sample selected for a narrow age range, in a specific geographic area.

A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems.

Heating, ventilation, and air conditioning (HVAC) systems are a popular research topic because buildings' energy is mostly used for heating and/or cooling. These systems heavily rely on sensory measurements and typically make an integral part of the smart building concept. As such, they require the implementation of fault detection and diagnosis (FDD) methodologies, which should assist users in maintaining comfort while consuming minimal energy. Despite the fact that FDD approaches are a well-researched subject, not just for improving the operation of HVAC systems but also for a wider range of systems in industrial processes, there is a lack of application in commercial buildings due to their complexity and low transferability. The aim of this review paper is to present and systematize cutting-edge FDD methodologies, encompassing approaches and special techniques that can be applied in HVAC systems, as well as to provide best-practice heuristics for researchers and solution developers in this domain. While the literature analysis targets the FDD perspective, the main focus is put on the data-driven approach, which covers commonly used models and data pre-processing techniques in the field. Data-driven techniques and FDD solutions based on them, which are most commonly used in recent HVAC research, form the backbone of our study, while alternative FDD approaches are also presented and classified to properly contextualize and round out the review.

Trajectory Modeling by Distributed Gaussian Processes in Multiagent Systems.

This paper considers trajectory a modeling problem for a multi-agent system by using the Gaussian processes. The Gaussian process, as the typical data-driven method, is well suited to characterize the model uncertainties and perturbations in a complex environment. To address model uncertainties and noises disturbances, a distributed Gaussian process is proposed to characterize the system model by using local information exchange among neighboring agents, in which a number of agents cooperate without central coordination to estimate a common Gaussian process function based on local measurements and datum received from neighbors. In addition, both the continuous-time system model and the discrete-time system model are considered, in which we design a control Lyapunov function to learn the continuous-time model, and a distributed model predictive control-based approach is used to learn the discrete-time model. Furthermore, we apply a Kullback-Leibler average consensus fusion algorithm to fuse the local prediction results (mean and variance) of the desired Gaussian process. The performance of the proposed distributed Gaussian process is analyzed and is verified by two trajectory tracking examples.

Deep Learning Empowered Structural Health Monitoring and Damage Diagnostics for Structures with Weldment via Decoding Ultrasonic Guided Wave.

Welding is widely used in the connection of metallic structures, including welded joints in oil/gas metallic pipelines and other structures. The welding process is vulnerable to the inclusion of different types of welding defects, such as lack of penetration and undercut. These defects often initialize early-age cracking and induced corrosion. Moreover, welding-induced defects often accompany other types of mechanical damage, thereby leading to more challenges in damage detection. As such, identification of weldment defects and interaction with other mechanical damages at their early stage is crucial to ensure structural integrity and avoid potential premature failure. The current strategies of damage identification are achieved using ultrasonic guided wave approaches that rely on a change in physical parameters of propagating waves to discriminate as to whether there exist damaged states or not. However, the inherently complex nature of weldment, the complication of damages interactions, and large-scale/long span structural components integrated with structure uncertainties pose great challenges in data interpretation and making an informed decision. Artificial intelligence and machine learning have recently become emerging methods for data fusion, with great potential for structural signal processing through decoding ultrasonic guided waves. Therefore, this study aimed to employ the deep learning method, convolutional neural network (CNN), for better characterization of damage features in terms of welding defect type, severity, locations, and interaction with other damage types. The architecture of the CNN was set up to provide an effective classifier for data representation and data fusion. A total of 16 damage states were designed for training and calibrating the accuracy of the proposed method. The results revealed that the deep learning method enables effectively and automatically extracting features of ultrasonic guided waves and yielding high precise prediction for damage detection of structures with welding defects in complex situations. In addition, the effectiveness and robustness of the proposed methods for structure uncertainties using different embedding materials, and data under noise interference, was also validated and findings demonstrated that the proposed deep learning methods still exhibited a high accuracy at high noise levels.

Building an Interdisciplinary Team for Disaster Response Research: A Data-Driven Approach.

Building an interdisciplinary team is critical to disaster response research as it often deals with acute onset events, short decision horizons, constrained resources, and uncertainties related to rapidly unfolding response environments.  This article examines three teaming mechanisms for interdisciplinary disaster response research, including ad hoc and/or grant proposal driven teams, research center or institute based teams, and teams oriented by matching expertise toward long-term collaborations. Using hurricanes as the response context, it further examines several types of critical data that require interdisciplinary collaboration on collection, integration, and analysis. Last, suggesting a data-driven approach to engaging multiple disciplines, the article advocates building interdisciplinary teams for disaster response research with a long-term goal and an integrated research protocol.

Coupling Analytical Models and Machine Learning Methods for Fast and Reliable Resolution of Effects in Multifrequency Eddy-Current Sensors.

Eddy current (EC) measurements, widely used for diagnostics of conductive materials, are highly dependent on physical properties and geometry of a sample as well as on a design of an EC-sensor. For a sensor of a given design, the conductivity and thickness of a sample as well as the gap between the sample and the sensor (lift-off) are the most influencing parameters. Estimation of these parameters, based on signals acquired from the sensor, is quite complicated in case when all three parameters are unknown and may vary. In this paper, we propose a machine learning based approach for solving this problem. The approach makes it possible to avoid time and resource-consuming computations and does not require experimental data for training of the prediction models. The approach was tested using independent sets of measurements from both simulated and real experimental data.

Modelling COVID-19 Scenarios for the States and Federal Territories of Malaysia.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes COVID-19 disease, which has become pandemic since December 2019. In the recent months, among five countries in the Southeast Asia, Malaysia has the highest per-capita daily new cases and daily new deaths. A mathematical modelling approach using a Singular Spectrum Analysis (SSA) technique was used to generate data-driven 30-days ahead forecasts for the number of daily cases in the states and federal territories in Malaysia at four consecutive time points between 27 July 2021 and 26 August 2021. Each forecast was produced using SSA prediction model of the current major trend at each time point. The objective is to understand the transition dynamics of COVID-19 in each state by analysing the direction of change of the major trends during the period of study. The states and federal territories in Malaysia were grouped in four categories based on the nature of the transition. Overall, it was found that the COVID-19 spread has progressed unevenly across states and federal territories. Major regions like Selangor, Kuala Lumpur, Putrajaya and Negeri Sembilan were in Group 3 (fast decrease in infectivity) and Labuan was in Group 4 (possible eradication of infectivity). Other states e.g. Pulau Pinang, Sabah, Sarawak, Kelantan and Johor were categorised in Group 1 (very high infectivity levels) with Perak, Kedah, Pahang, Terengganu and Melaka were classified in Group 2 (high infectivity levels). It is also cautioned that SSA provides a promising avenue for forecasting the transition dynamics of COVID-19; however, the reliability of this technique depends on the availability of good quality data.

Normal mode analysis of a relaxation process with Bayesian inference.

Measurements of relaxation processes are essential in many fields, including nonlinear optics. Relaxation processes provide many insights into atomic/molecular structures and the kinetics and mechanisms of chemical reactions. For the analysis of these processes, the extraction of modes that are specific to the phenomenon of interest (normal modes) is unavoidable. In this study we propose a framework to systematically extract normal modes from the viewpoint of model selection with Bayesian inference. Our approach consists of a well-known method called sparsity-promoting dynamic mode decomposition, which decomposes a mixture of damped oscillations, and the Bayesian model selection framework. We numerically verify the performance of our proposed method by using coherent phonon signals of a bismuth polycrystal and virtual data as typical examples of relaxation processes. Our method succeeds in extracting the normal modes even from experimental data with strong backgrounds. Moreover, the selected set of modes is robust to observation noise, and our method can estimate the level of observation noise. From these observations, our method is applicable to normal mode analysis, especially for data with strong backgrounds.

Machine Learning-Enriched Lamb Wave Approaches for Automated Damage Detection.

Lamb wave approaches have been accepted as efficiently non-destructive evaluations in structural health monitoring for identifying damage in different states. Despite significant efforts in signal process of Lamb waves, physics-based prediction is still a big challenge due to complexity nature of the Lamb wave when it propagates, scatters and disperses. Machine learning in recent years has created transformative opportunities for accelerating knowledge discovery and accurately disseminating information where conventional Lamb wave approaches cannot work. Therefore, the learning framework was proposed with a workflow from dataset generation, to sensitive feature extraction, to prediction model for lamb-wave-based damage detection. A total of 17 damage states in terms of different damage type, sizes and orientations were designed to train the feature extraction and sensitive feature selection. A machine learning method, support vector machine (SVM), was employed for the learning model. A grid searching (GS) technique was adopted to optimize the parameters of the SVM model. The results show that the machine learning-enriched Lamb wave-based damage detection method is an efficient and accuracy wave to identify the damage severity and orientation. Results demonstrated that different features generated from different domains had certain levels of sensitivity to damage, while the feature selection method revealed that time-frequency features and wavelet coefficients exhibited the highest damage-sensitivity. These features were also much more robust to noise. With increase of noise, the accuracy of the classification dramatically dropped.

A Hybrid Sensor Fault Diagnosis for Maintenance in Railway Traction Drives.

Due to the importance of sensors in railway traction drives availability, sensor fault diagnosis has become a key point in order to move from preventive maintenance to condition-based maintenance. Most research works are limited to sensor fault detection and isolation, but only a few of them analyze the types of sensor faults, such as offset or gain, with the aim of reconfiguring the sensor in order to implement a fault tolerant system. This article is based on a fusion of model-based and data-driven techniques. First, an observer-based approach, using a Sliding Mode observer, is utilized for sensor fault reconstruction in real time. Then, once the fault is detected, a time window of sensor measurements and sensor fault reconstruction is sent to the remote maintenance center for fault evaluation. Finally, an offline processing is carried out to discriminate between gain and offset sensor faults, in order to get a maintenance decision-making to reconfigure the sensor during the next train stop. Fault classification is done by means of histograms and statistics. The technique here proposed is applied to the DC-link voltage sensor in a railway traction drive and is validated in a hardware-in-the-loop platform.

Mild cognitive impairment understanding: an empirical study by data-driven approach.

BACKGROUND: Cognitive decline has emerged as a significant threat to both public health and personal welfare, and mild cognitive decline/impairment (MCI) can further develop into Dementia/Alzheimer's disease. While treatment of Dementia/Alzheimer's disease can be expensive and ineffective sometimes, the prevention of MCI by identifying modifiable risk factors is a complementary and effective strategy. RESULTS: In this study, based on the data collected by Centers for Disease Control and Prevention (CDC) through the nationwide telephone survey, we apply a data-driven approach to re-exam the previously founded risk factors and discover new risk factors. We found that depression, physical health, cigarette usage, education level, and sleep time play an important role in cognitive decline, which is consistent with the previous discovery. Besides that, the first time, we point out that other factors such as arthritis, pulmonary disease, stroke, asthma, marital status also contribute to MCI risk, which is less exploited previously. We also incorporate some machine learning and deep learning algorithms to weigh the importance of various factors contributed to MCI and predicted cognitive declined. CONCLUSION: By incorporating the data-driven approach, we can determine that risk factors significantly correlated with diseases. These correlations could also be expanded to another medical diagnosis besides MCI.

Patient scheduling based on a service-time prediction model: a data-driven study for a radiotherapy center.

With the growth of the population, access to medical care is in high demand, and queues are becoming longer. The situation is more critical when it concerns serious diseases such as cancer. The primary problem is inefficient management of patients rather than a lack of resources. In this work, we collaborate with the Centre Intégré de Cancérologie de Laval (CICL). We present a data-driven study based on a nonblock approach to patient appointment scheduling. We use data mining and regression methods to develop a prediction model for radiotherapy treatment duration. The best model is constructed by a classification and regression tree; its accuracy is 84%. Based on the predicted duration, we design new workday divisions, which are evaluated with various patient sequencing rules. The results show that with our approach, 40 additional patients are treated daily in the cancer center, and a considerable improvement is noticed in patient waiting times and technologist overtime.