Optimal Model Parameters Research Articles

Design and optimization of a planar anti-buckling compliant rotational joint with a remote center of motion

Compliant mechanisms (CMs) exhibit some excellent mechanical properties and provide numerous innovative solutions for many existing mechanical applications. Among them, planar compliant rotational joints have made substantial contributions to precision engineering. To achieve high-precision positioning with a compliant rotational joint, it is essential to study characteristics such as anti-buckling and constant stiffness. The remote center of motion (RCM) mechanism, with its compact structure and ease of precise control, is expected to enhance overall rigidity and reduce parasitic displacements. Here, we propose a planar anti-buckling compliant rotational joint with a RCM. Static modeling and model validation are conducted for different geometric configurations, including single and combined structures. A distributed configuration with bidirectional anti-buckling properties is selected for optimization. Using a global parameter optimization model, single-objective optimization studies are conducted for three distinct characteristics. Subsequently, a multi-objective optimization model for constant stiffness and high precision is established. Based on the optimization results, a compliant rotational joint with bidirectional anti-buckling, constant rotational stiffness, and high precision is designed. Finally, the effectiveness of the optimization method is validated through physical experiments.

Construction of an inflammatory, nutritional, and metabolic prognostic risk score in patients with heart failure with preserved ejection fraction: a machine learning-based approach

Abstract Background Chronic inflammation, malnutrition, and metabolic syndrome contribute to the underlying mechanisms of heart failure with preserved ejection fraction (HFpEF). Inflammatory, nutritional, and metabolic biomarkers often interact with each other and affect the prognosis of patients. Purpose We aimed to identify the most predictive indicators from a pool of 21 biomarkers encompassing inflammation, nutritional status, as well as lipid, glucose, thyroid, and uric acid metabolism. Subsequently, predictive biomarkers were used to develop a risk score to enhance risk prediction for patients with HFpEF. Methods We included patients diagnosed with HFpEF and without infective or systemic disease. The primary outcome was all-cause mortality. We employed the Least Absolute Shrinkage and Selection Operator (LASSO) regression to screen the biomarkers. A machine learning-based approach was utilized to fine-tune the optimal model parameters. Additionally, we generated 1000 bootstrapping datasets to identify biomarkers recurring above a 95% frequency in repetitions, which were then employed to formulate the biomarker risk score. The discrimination of incorporating the risk score into the basic model was evaluated using 100 iterations of 5-fold cross-validation to assess the predictive efficacy. Results Among the 1311 included patients (with a median age of 64 years and 42.6% female), 363 patients (27.7%) experienced mortality over a median follow-up period of 2.7 years. The final risk score model was derived from 5 biomarkers—albumin (ALB), red blood cell distribution width-standard deviation (RDW-SD), lymphocytes, triiodothyronine (T3), and uric acid—each selected in over 95% of 1000 bootstrapping iterations. Integration of this risk score into the basic model notably enhanced discrimination (∆C-index=0.015, 95% CI 0.005-0.023) and reclassification (IDI: 3.3%, 95% CI 1.7%-5.8%; NRI: 15.2%, 95% CI 6.5%-22.5%) for risk stratification. In time-dependent receiver operating characteristic (ROC) analysis, the mean area under the curve (AUC) of the risk score was 0.688, 0.710, and 0.738 at 1, 3, and 5 years post-discharge, respectively, in the cross-validation sets. Incorporating the risk score into the basic model significantly improved the AUC at 1, 3, and 5 years (DeLong test P-value<0.05). Furthermore, in multivariable Cox regression, the risk score demonstrated an independent association with all-cause mortality (HR: 1.81, 95% CI 1.51-2.16, P<0.001 per 1 score increase). Conclusions A risk score derived from 5 commonly used inflammatory, nutritional, thyroid and uric acid metabolic biomarkers can effectively identify high-risk patients with HFpEF. This approach supports the development of potential individualized management strategies for patients with HFpEF.Study population and model constructionPredictive performance of the risk score

Toxicokinetic model of the pyrethroid pesticide lambda-cyhalothrin, main exposure route and dose reconstruction predictions in agricultural workers.

A toxicokinetic model of the pyrethroid insecticide lambda-cyhalothrin (LCT) was developed to relate absorbed doses to urinary cis-3-(2-chloro-3,3,3-trifluoroprop-1-en-1-yl)-2,2-dimethylcyclopropanecarboxylic acid (CFMP) metabolite levels used as a biomarker of exposure. The model then served to reconstruct absorbed doses in agricultural workers and their probability of exceeding the EFSA Acceptable occupational Exposure Level (AOEL). The toxicokinetic model was able to reproduce the temporal profiles of CFMP in the urine of operators spraying pesticides using the optimized model parameters (adjusted to human volunteer data). Modeling also showed that simulation of an inadvertent oral exposure mainly was the exposure scenario giving the best fit to CFMP urinary time-course data in applicators. With the dermal model parameters optimized from data in volunteers, simulation of a dermal exposure in applicators did not allow to reproduce the observed peak excretions and urinary metabolite levels; extremely high applied dermal doses would be required but still simulated dermal penetration rate would remain too slow. Simulation of an inhalation exposure allowed to reproduce the observed time-courses, but with unrealistic air concentrations. For applicators with the highest urinary concentrations, there was a probability of exceeding the AOEL at some points during the biomonitoring period [>50% probability of exceeding for 27% of 24-h samples]; for non-applicator workers the probability of exceeding the AOEL value was very low [corresponding value of 5%]. Furthermore, the median [95% CI] estimates of 10 000 Monte Carlo simulations led to a biological reference value corresponding to the AOEL of 116 [113-119] ng/kg bw/d and 7.5 [7.3-7.7] μg/L. Overall, 7% of applicators and 1% of workers performing weeding and strawberry picking had a probability of exceeding this biological reference value. As a next step, it would be interesting to apply these methods to multiple exposure to various contaminants.

An Adaptive Parameter Optimization Deep Learning Model for Energetic Liquid Vision Recognition Based on Feedback Mechanism.

The precise detection of liquid flow and viscosity is a crucial challenge in industrial processes and environmental monitoring due to the variety of liquid samples and the complex reflective properties of energetic liquids. Traditional methods often struggle to maintain accuracy under such conditions. This study addresses the complexity arising from sample diversity and the reflective properties of energetic liquids by introducing a novel model based on computer vision and deep learning. We propose the DBN-AGS-FLSS, an integrated deep learning model for high-precision, real-time liquid surface pointer detection. The model combines Deep Belief Networks (DBN), Feedback Least-Squares SVM classifiers (FLSS), and Adaptive Genetic Selectors (AGS). Enhanced by bilateral filtering and adaptive contrast enhancement algorithms, the model significantly improves image clarity and detection accuracy. The use of a feedback mechanism for reverse judgment dynamically optimizes model parameters, enhancing system accuracy and robustness. The model achieved an accuracy, precision, F1 score, and recall of 99.37%, 99.36%, 99.16%, and 99.36%, respectively, with an inference speed of only 1.5 ms/frame. Experimental results demonstrate the model's superior performance across various complex detection scenarios, validating its practicality and reliability. This study opens new avenues for industrial applications, especially in real-time monitoring and automated systems, and provides valuable reference for future advancements in computer vision-based detection technologies.

Modelling the evolving critical state of crushable soils and parameter optimization with an improved genetic algorithm (AIS-RCGA)

The critical state line (CSL) plays an essential role in the constitutive modelling of granular soils. It serves as a reference line for the measurement of the state parameter. The critical state of crushable soils cannot accurately be determined from experimental data because of the ever-changing soil properties due to particle breakage. In this study, two new parameters eB and eb are introduced, which account for the final position and the evolution of CSL of crushable soils during shearing, respectively. To identify the optimal CSL-related parameters from experimental data, a hybrid genetic algorithm combining artificial immune system (AIS) and real-coded genetic algorithm (RCGA), namely AIS-RCGA is adopted. The fitness is defined to minimize the prediction error of both void ratio (or, pore water pressure) and deviatoric stress. We have refined the tuning methods for several hyperparameters of AIS-RCGA and proposed a novel method to assess the similarity of individuals within AIS-RCGA. Results show that the new method is more efficient in finding the global optimal for our problem. With optimized model parameters, the new constitutive model can accurately predict the response of crushable soil, outperforming other constitutive model reported in the literature.

Structural topology optimization based on deep learning

In the mechanical design of structures, traditional topology optimization methods involve numerous finite element iterative analyses, leading to a significant expenditure of computational resources. Therefore, the improved multi-scale gradient generative adversarial networks topology optimization technique is proposed. The topology optimization condition parameters are compressed into a low-dimensional latent space feature representation using the encoder, allowing the model to better extract features from these parameters. To speed up model training, the generator and discriminator networks use lightweight residual convolutional blocks. The hybrid attention mechanism extracts prominent region features from the topology optimization structure map. The model training process is guided by a multi-dimensional fusion loss function to enhance the quality of generated model samples. Finally, transferring the parameters of the low-resolution topology optimization model to the high-resolution model enables complete training on a limited amount of high-resolution topology optimization datasets. The experimental data on the low- and high-resolution topology optimization datasets demonstrate that, when compared to alternative methods, this method produces better-quality topology optimization structure maps. Additionally, it can generate high-resolution topology optimization structure maps in minimal time, enabling real-time topology optimization.

Joint torque estimation method of industrial robot by combining error compensation model based on LSTM and iterative weighted parameter identification

It is essential for human-robot interaction to accurate joint torque value estimation of industrial robots without force/torque (F/T) sensors. The most common method to estimate the value of robot joint torque is based on dynamic model parameter identification. However, no matter how elaborate the modeling methods are used, there are always uncertainty errors when robot’s joint rotation direction changes. In this paper, an identification framework is proposed to estimate optimal model parameters, and a deep learning network is proposed to compensate for the uncertainty errors caused by the unmodeled dynamics part. At first, the dynamic parameters are estimated during the Least Squares (LS) identification process considering the noise influence and data outliers, and the nonlinear friction model is unified into the identification framework. Secondly, based on Long-Short Term Memory (LSTM) network, an error compensation model (ECM) is proposed to establish the mapping relationship between the joint motion and the identification errors. Finally, a 6-DOF robot is used for parameter identification and ECM validation. Experimental results show that the proposed identification method is better than the LS method. Compared with the torque value estimated by the identification method, the proposed ECM can compensate for the uncertainty errors and improve the torque estimation accuracy.

Traffic Flow Prediction in 5G-Enabled Intelligent Transportation Systems Using Parameter Optimization and Adaptive Model Selection.

This study proposes a novel hybrid method, FVMD-WOA-GA, for enhancing traffic flow prediction in 5G-enabled intelligent transportation systems. The method integrates fast variational mode decomposition (FVMD) with optimization techniques, namely, the whale optimization algorithm (WOA) and genetic algorithm (GA), to improve the accuracy of overall traffic flow based on models tailored for each decomposed sub-sequence. The selected predictive models-long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU)-were considered to capture diverse temporal dependencies in traffic data. This research explored a multi-stage approach, where the decomposition, optimization, and selection of models are performed systematically to improve prediction performance. Experimental validation on two real-world traffic datasets further underscores the method's efficacy, achieving root mean squared errors (RMSEs) of 152.43 and 7.91 on the respective datasets, which marks improvements of 3.44% and 12.87% compared to the existing methods. These results highlight the ability of the FVMD-WOA-GA approach to improve prediction accuracy significantly, reduce inference time, enhance system adaptability, and contribute to more efficient traffic management.

Acoustic characterization of porous windscreens for sound pressure and particle velocity sensors

Acoustic measurements of ground vehicles, wind turbines or aircrafts are often performed outdoors in presence of wind. Air movement around an acoustic sensor may significantly disturb the measured signals due to flow-induced vibrations and turbulence. This is specially relevant for pressure-gradient and particle-velocity based acoustic transducers which are more sensitive to these perturbations. To attenuate this effect and improve measurement quality, the sensors are typically covered with windscreens made of porous materials. However, designing an appropriate windscreen poses a challenging task, demanding a deep understanding of sound transmission characteristics. This study works towards quantifying acoustic properties of rigid-frame porous materials through in-situ measurements and fitting a parametric fluid-equivalent model to find optimal model parameters. The parameters are subsequently investigated by comparing windscreen insertion loss through finite-element numerical simulations and measurements on a sound intensity PU probe.

Direct Identification of the Continuous Relaxation Time and Frequency Spectra of Viscoelastic Materials

Relaxation time and frequency spectra are not directly available by measurement. To determine them, an ill-posed inverse problem must be solved based on relaxation stress or oscillatory shear relaxation data. Therefore, the quality of spectra models has only been assessed indirectly by examining the fit of the experiment data to the relaxation modulus or dynamic moduli models. As the measures of data fitting, the mean sum of the moduli square errors were usually used, the minimization of which was an essential step of the identification algorithms. The aim of this paper was to determine a relaxation spectrum model that best approximates the real unknown spectrum in a direct manner. It was assumed that discrete-time noise-corrupted measurements of a relaxation modulus obtained in the stress relaxation experiment are available for identification. A modified relaxation frequency spectrum was defined as a quotient of the real relaxation spectrum and relaxation frequency and expanded into a series of linearly independent exponential functions that are known to constitute a basis of the space of square-integrable functions. The spectrum model, given by a finite series of these basis functions, was assumed. An integral-square error between the real unknown modified spectrum and the spectrum model was taken as a measure of the model quality. This index was proved to be expressed in terms of the measurable relaxation modulus at uniquely defined sampling instants. Next, an empirical identification index was introduced in which the values of the real relaxation modulus are replaced by their noisy measurements. The identification consists of determining the spectrum model that minimizes this empirical index. Tikhonov regularization was applied to guarantee model smoothness and noise robustness. A simple analytical formula was derived to calculate the optimal model parameters and expressed in terms of the singular value decomposition. A complete identification algorithm was developed. The analysis of the model smoothness and model accuracy for noisy measurements was carried out. The equivalence of the direct identification of the relaxation frequency and time spectra has been demonstrated when the time spectrum is modeled by a series of functions given by the product of the relaxation frequency and its exponential function. The direct identification concept can be applied to both viscoelastic fluids and solids; however, some limitations to its applicability have been pointed out. Numerical studies have shown that the proposed identification algorithm can be successfully used to identify Gaussian-like and Kohlrausch–Williams–Watt relaxation spectra. The applicability of this approach to determining other commonly used classes of relaxation spectra was also examined.

Optimization of an N2O Emission Flux Model Based on a Variable-Step Drosophila Algorithm

The application of intelligent process-based crop model parameter optimization algorithms can effectively improve both the model simulation accuracy and applicability. Based on measured values of soil N2O emission flux in wheat fields from 2020 to 2022, and meteorological data from 1971 to 2022, five parameters of the N2O emission flux module in the APSIM model were optimized using the variable step Fruit Fly algorithm (VSS-FOA). The optimized parameters were the soil nitrification potential, the range of concentrated KNH4 of ammonia and nitrogen at semi-maximum utilization efficiency, the proportion of nitrogen loss to N2O during the nitrification process, the denitrification coefficient, and the Power term P for calculating the denitrification water coefficient. Contrasting the optimized parameters using the VSS-FOA algorithm versus the default values supplied with the model substantially improved the goodness-of-fit to field measurements with the overall R2 increasing from 0.41 to 0.74, and a decrease in NRMSE from 17.1% to 11.4%. This work demonstrates that the VSS-FOA algorithm affords a straightforward mechanism for the optimization of parameters in models such as APSIM to enhance the accuracy of model N2O emission flux estimates.

Optimizing parameters for additive manufacturing: a study on the vibrational performance of 3D printed cantilever beams using material extrusion

Purpose This study aims to investigate the impact of different printing parameters on the free vibration characteristics of 3D printed cantilever beams. Through a comprehensive analysis of material extrusion (ME) variables such as extrusion rate, printing pattern and layer thickness, the study seeks to enhance the understanding of how these parameters influence the vibrational properties, particularly the natural frequency, of printed components. Design/methodology/approach The experimental design involves conducting a series of experiments using a central composite design approach to gather data on the vibrational response of ABS cantilever beams under diverse ME parameters. These parameters are systematically varied across different levels, facilitating a thorough exploration of their effects on the vibrational behavior of the printed specimens. The collected data are then used to develop a predictive model leveraging a hybrid artificial neural network (ANN)/ particle swarm optimization (PSO) approach, which combines the strengths of ANN in modeling complex relationships and PSO in optimizing model parameters. Findings The developed ANN/PSO hybrid model demonstrates high accuracy in predicting the natural frequency of 3D printed cantilever beams, with a correlation ratio (R) of 0.9846 when tested against experimental data. Through iterative fine-tuning with PSO, the model achieves a low mean square error (MSE) of 1.1353e-5, underscoring its precision in estimating the vibrational characteristics of printed specimens. Furthermore, the model’s transformation into a regression model enables the derivation of surface response characteristics governing the vibration properties of 3D printed objects in response to input parameters, facilitating the identification of optimal parameter configurations for maximizing vibration characteristics in 3D printed products. Originality/value This study introduces a novel predictive model that combines ANNs with PSO to analyze the vibrational behavior of 3D printed ABS cantilever beams produced under various ME parameters. By integrating these advanced methodologies, the research offers a pioneering approach to precisely estimating the natural frequency of 3D printed objects, contributing to the advancement of predictive modeling in additive manufacturing.

Accurate Oil Temperature Prediction Model and Oil Refilling Parameters Optimization for Hydraulic Closed-Circuit System

Oil temperature plays a crucial role in hydraulic closed-circuit systems (HCS), and conventional thermal equilibrium models and coupled simulation models face challenges in terms of accuracy, efficiency, and cost when calculating oil temperature. This study introduces an innovative HCS oil temperature precise prediction model and oil refilling parameter optimization method. The initial sample space was determined through a Sobol sensitivity analysis and improved Latin hypercube sampling, leading to the development of a combinatorial agent model (CAM) suitable for oil temperature prediction with superior accuracy and stability compared to other methods. Based on CAM, the optimal oil refilling flow rates under various operational conditions are computed. To validate the efficacy of the theoretical analysis, an HCS experiment platform was established. The data indicates that the temperature prediction error range of the CAM model falls between 0.30 °C and 1.05 °C, and optimizing the oil refilling flow rate can effectively enhance system efficiency while ensuring that the oil temperature remains within permissible limits. The research methodology and findings are applicable in engineering practice and can be extended to optimize the design of other hydraulic systems.

Maximizing chitin and chitosan recovery yields from Fusarium verticillioides using a many-factors-at-a-time approach

The extraction of chitin and chitosan presents challenges due to the complexity of the process and the influence of many variables. This study aimed to optimize chitin and chitosan extraction from Fusarium verticillioides by analyzing many additives and processing variables and modeling their yields using multiple linear regression (MLR) and evolutionary algorithms. FT-IR analysis confirmed the presence of characteristic bands in the extracted samples, and SEM analysis further revealed the microfibrillar appearance of the chitin and the dense, non-porous structure of the chitosan. The Ant Lion Optimizer (ALO) was employed to select significant factors and optimize model parameters. A transformation was applied to capture nonlinear relationships, and the fine-tuned models showed improved predictive power, with p-values of 0.00203 for chitin and 0.00884 for chitosan. Multi-objective optimization (MOO) using the Adaptive Geometry Estimation-based Multi-Objective Evolutionary Algorithm (AGE-MOEA) further identified significant factors for optimal yields, achieving 3 g of Arginine, 100 ml of culture medium volume, 7 to 11 days of incubation time, 0.2 to 1.76 ml of Oligochitin, 1.4 g of FeSO4, 1.5 g of K2HPO4, and 1 g of NaCl. Therefore, the integration of ALO and AGE-MOEA algorithms effectively modeled and optimized chitin and chitosan yields by maximizing biopolymer recovery, enabling significant industrial exploitation.

Interpretable large-scale belief rule base for complex industrial systems modeling with expert knowledge and limited data

Complex system modeling technology is a hot topic. Nowadays, many complex industrial systems present three characteristics: multiple input indicators, limited data and interpretability requirements. With good interpretability, belief rule base (BRB) serves as an efficient tool for modeling complex systems. However, as the number of input indicators of industrial systems increases, BRB suffers from the combinatorial explosion problem, which makes it hard to generate large-scale BRB and optimize it while maintaining its interpretability. For this purpose, an interpretable large-scale BRB is proposed for complex systems with limited data, where expert knowledge can be utilized effectively. First, a framework for generating an initial large-scale BRB using expert knowledge and limited data is developed, including the determination of attribute weight, basic belief degree and rule weight. Afterwards, a new parameter optimization model is designed to reduce the burden of parameter optimization and maintain the interpretability of BRB, where the Adaptive Moment Estimation (Adam) algorithm is adopted to further improve the efficiency of large-scale parameter optimization. Finally, a health assessment case of an inertial navigation system (INS) verifies the proposed method.

Refined prediction of SO2 concentration around Chinese coking enterprises and exposure risk assessment of different populations based on buffer Latin hypercube

Coking enterprises in China are recognized as significant sources of SO2 emissions, making them a key industry with high levels of SO2 intensity. Assessing the health risks for different populations around these coking enterprises nationwide is challenging due to the lack of clarity regarding SO2 concentrations at varying distances from these facilities. To address this issue, we developed a buffer Latin hypercube XGBoost particle swarm optimization (BLH-XGB-PSO) algorithm that combines efficient global search capabilities and accurate prediction performance. This algorithm enables effective traversal of monitoring points located at varying distances and directions around the enterprise while automatically seeking optimal model parameters. Using this model, we accurately predicted the concentration of SO2 every 0.5 km within a 10 km radius around China's coking enterprises in 2017, achieving a high prediction accuracy with an R2 value of 0.97. The prediction results indicate that the highest concentration of SO2 in the vicinity of Chinese coking enterprises is observed in the central region of Shanxi province (65.88 μg/m3). The average annual concentration of SO2 around all production enterprises amounts to 27.9 μg/m3. Furthermore, we conducted an assessment on the impact of coking enterprises on different age groups, genders, and regions regarding the number of affected individuals, health exposure risks, and control effectiveness. Our findings reveal that in 2017, around 5.5 thousand newborns (14.5% male, 85.5% female) had a hazard quotient (HQ) exceeding threshold value which poses potential human health risks. The implementation of the control policy successfully prevented 64,375 thousand people from being affected by higher concentrations of SO2. Greater attention should be devoted to the health risks faced by newborns residing in proximity to coking enterprises, with a particular emphasis on female infants.

Machine learning-assisted source tracing in domestic-industrial wastewater: A fluorescence information-based approach

An emergency water pollution incident poses a significant risk to the proper functioning of wastewater treatment plants, particularly in domestic-industrial integrated facilities. Source tracing is recognized as an effective method to mitigate ongoing impacts. Machine learning-assisted traceability is emerging as a more efficient and faster method compared to traditional methods. In this study, a total of 712 sets of characterization wastewater information from effluent samples from14 discharge enterprises across 6 different sectors, as well as domestic wastewater was collected using 3-dimensional fluorescence spectroscopy. After data cleaning and augmentation, a feature fingerprint database of wastewater was constructed to train a traceability model. Several machine learning algorithms, including Back Propagation neural network (BP), Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB) and K-Nearest Neighbors (KNN), were selected for constructing the traceability framework. Subsequently, an advanced Particle Swarm Optimization Random Forest model (PSO-RF), capable of automatically optimizing model parameters, was proposed and applied to trace the sources of wastewater in integrated wastewater treatment plant. The PSO-RF achieved and accuracy of 96.55 % in sector identification and 94.25 % in manufacturer identification. As part of the validation process, laboratory simulations were conducted using blended wastewater with different volume ratios of domestic and industrial wastewater to evaluated the potential application of PSO-RF. The results consistently demonstrated PSO-RF's effectiveness, particularly in tracing pharmaceutical wastewater sources, maintaining an accuracy of over 85 %. This work presents a novel strategy for tracing abnormal sources during emergency pollutant incidents, providing essential support for integrating artificial intelligence (AI) into meticulous wastewater management.

Enhancing requirements-to-code traceability with GA-XWCoDe: Integrating XGBoost, Node2Vec, and genetic algorithms for improving model performance and stability

This study addresses the challenge of requirements-to-code traceability by proposing a novel model, Genetic Algorithm-XGBoost With Code Dependency (GA-XWCoDe), which integrates eXtreme Gradient Boosting (XGBoost) with a Node2Vec model-weighted code dependency strategy and genetic algorithms for parameter optimisation. XGBoost mitigates overfitting and enhances model stability, while Node2Vec improves prediction accuracy for low-confidence links. Genetic algorithms are employed to optimise model parameters efficiently, reducing the resource intensity of traditional methods. Experimental results show that GA-XWCoDe outperforms the state-of-the-art method TRAceability lInk cLassifier (TRAIL) by 17.44% and Deep Forest for Requirement traceability (DF4RT) by 33.36% in terms of average F1 performance across four datasets. It is significantly superior to all baseline methods at a confidence level of α¡0.01 and demonstrates exceptional performance and stability across various training data scales.

Combining graph neural networks and transformers for few-shot nuclear receptor binding activity prediction

Nuclear receptors (NRs) play a crucial role as biological targets in drug discovery. However, determining which compounds can act as endocrine disruptors and modulate the function of NRs with a reduced amount of candidate drugs is a challenging task. Moreover, the computational methods for NR-binding activity prediction mostly focus on a single receptor at a time, which may limit their effectiveness. Hence, the transfer of learned knowledge among multiple NRs can improve the performance of molecular predictors and lead to the development of more effective drugs. In this research, we integrate graph neural networks (GNNs) and Transformers to introduce a few-shot GNN-Transformer, Meta-GTNRP to predict the binding activity of compounds using the combined information of different NRs and identify potential NR-modulators with limited data. The Meta-GTNRP model captures the local information in graph-structured data and preserves the global-semantic structure of molecular graph embeddings for NR-binding activity prediction. Furthermore, a few-shot meta-learning approach is proposed to optimize model parameters for different NR-binding tasks and leverage the complementarity among multiple NR-specific tasks to predict binding activity of compounds for each NR with just a few labeled molecules. Experiments with a compound database containing annotations on the binding activity for 11 NRs shows that Meta-GTNRP outperforms other graph-based approaches. The data and code are available at: https://github.com/ltorres97/Meta-GTNRP.Scientific contributionThe proposed few-shot GNN-Transformer model, Meta-GTNRP captures the local structure of molecular graphs and preserves the global-semantic information of graph embeddings to predict the NR-binding activity of compounds with limited available data; A few-shot meta-learning framework adapts model parameters across NR-specific tasks for different NRs in a joint learning procedure to predict the binding activity of compounds for each NR with just a few labeled molecules in highly imbalanced data scenarios; Meta-GTNRP is a data-efficient approach that combines the strengths of GNNs and Transformers to predict the NR-binding properties of compounds through an optimized meta-learning procedure and deliver robust results valuable to identify potential NR-based drug candidates.

Potentially suitable geographical area for Colletotrichum acutatum under current and future climatic scenarios based on optimized MaxEnt model.

Global climate warming has led to changes in the suitable habitats for fungi. Colletotrichum acutatum, a common fungus causing anthracnose disease, is widely distributed in southern China. Currently, research on the relationship between C. acutatum and environmental warming was limited. In this study, MaxEnt and ArcGIS software were used to predict the suitable habitats of C. acutatum under current and future climate conditions based on its occurrence records and environmental factors. The optimal MaxEnt model parameters were set as feature combination (FC) = lp and regularization multiplier (RM) = 2.6. Bio15, Bio12, Bio09, and Bio19 were identified as the main environmental factors influencing the distribution of C. acutatum. Under current climate conditions, C. acutatum was distributed across all continents globally, except Antarctica. In China, C. acutatum was primarily distributed south of the Qinling-Huaihe Line, with a total suitable area of 259.52 × 104 km2. Under future climate conditions, the potential suitable habitat area for C. acutatum was expected to increase and spread towards inland China. The results of this study provided timely risk assessment for the distribution and spread of C. acutatum in China and offer scientific guidance for monitoring and timely controlled of its distribution areas.