IPseU-NCP: Identifying RNA pseudouridine sites using random forest and NCP-encoded features

N6-methyladenine (6mA) is an important DNA methylation modification that serves a crucial function in various biological activities. Accurate prediction of 6mA sites is essential for elucidating its biological function and underlying mechanism. Although existing methods have achieved great success, there remains a pressing need for improved prediction accuracy and generalization cap ability across diverse species. This study aimed to develop a robust method to address these challenges. We proposed HD-6mAPred, a hybrid deep learning model that combines bidirectional gated recurrent unit (BiGRU), convolutional neural network (CNN) and attention mechanism, along with various DNA sequence coding schemes. Firstly, DNA sequences were encoded using four different ways: one-hot encoding, electron-ion interaction pseudo-potential (EIIP), enhanced nucleic acid composition (ENAC) and nucleotide chemical properties (NCP). Secondly, a hold-out search strategy was employed to identify the optimal features or feature combinations for both BiGRU and CNN. Finally, the attention mechanism was introduced to weigh the importance of features derived from the BiGRU and CNN. A series of experiments on the Rosaceae, rice and Arabidopsis datasets were conducted to demonstrate the superiority of HD-6mAPred. In Rosaceae, the HD-6mAPred model achieved excellent performance: accuracy (ACC) of 0.996, Matthew correlation coefficient (MCC) of 0.993, sensitivity (SN) and specificity (SP) of 0.995 and 0.998, respectively. In rice, the evaluation metrics are 0.952 (ACC), 0.905 (MCC), 0.955 (SN), and 0.949 (SP). In Arabidopsis, the corresponding metrics are 0.937 (ACC), 0.875 (MCC), 0.927 (SN), and 0.948 (SP). Compared to existing methods, these results demonstrate that HD-6mAPred achieves state-of-the-art performance in predicting 6mA sites across three plant species. Furthermore, HD-6mAPred not only improves the accuracy of 6mA site prediction, but also shows excellent generalization capability across species. The source code utilized in this study is publicly accessible at https://doi.org/10.5281/zenodo.15355131.

Pseudouridine is a ubiquitous RNA modification type present in eukaryotes and prokaryotes, which plays a vital role in various biological processes. Almost all kinds of RNAs are subject to this modification. However, it remains a great challenge to identify pseudouridine sites via experimental approaches, requiring expensive and time-consuming experimental research. Therefore, computational approaches that can be used to perform accurate in silico identification of pseudouridine sites from the large amount of RNA sequence data are highly desirable and can aid in the functional elucidation of this critical modification. Here, we propose a new computational approach, termed Porpoise, to accurately identify pseudouridine sites from RNA sequence data. Porpoise builds upon a comprehensive evaluation of 18 frequently used feature encoding schemes based on the selection of four types of features, including binary features, pseudo k-tuple composition, nucleotide chemical property and position-specific trinucleotide propensity based on single-strand (PSTNPss). The selected features are fed into the stacked ensemble learning framework to enable the construction of an effective stacked model. Both cross-validation tests on the benchmark dataset and independent tests show that Porpoise achieves superior predictive performance than several state-of-the-art approaches. The application of model interpretation tools demonstrates the importance of PSTNPs for the performance of the trained models. This new method is anticipated to facilitate community-wide efforts to identify putative pseudouridine sites and formulate novel testable biological hypothesis.

Robust multi-class model constructed for rapid quality control of Cordyceps sinensis

Using animal-mounted sensor technology and machine learning to predict time-to-calving in beef and dairy cows

To evaluate the performance of a within-project defect prediction approach, people normally use precision, recall, and F-measure scores. However, in machine learning literature, there are a large number of evaluation metrics to evaluate the performance of an algorithm, (e.g., Matthews Correlation Coefficient, G-means, etc.), and these metrics evaluate an approach from different aspects. In this paper, we investigate the performance of within-project defect prediction approaches on a large number of evaluation metrics. We choose 6 state-of-the-art approaches including naive Bayes, decision tree, logistic regression, kNN, random forest and Bayesian network which are widely used in defect prediction literature. And we evaluate these 6 approaches on 14 evaluation metrics (e.g., G-mean, F-measure, balance, MCC, J-coefficient, and AUC). Our goal is to explore a practical and sophisticated way for evaluating the prediction approaches comprehensively. We evaluate the performance of defect prediction approaches on 10 defect datasets from PROMISE repository. The results show that Bayesian network achieves a noteworthy performance. It achieves the best recall, FN-R, G-mean1 and balance on 9 out of the 10 datasets, and F-measure and J-coefficient on 7 out of the 10 datasets.

To ensure safety, autonomy, and context-aware control, reliable state recognition is still a challenge for stair-climbing wheelchairs, which offer mobility in environments with steps, curbs, and landings. This study uses instantaneous Inertial Measurement Unit (IMU) data to develop a simplified, window-free method for classifying wheelchair stair-related activities. Instead of sliding-window preprocessing or temporal sequence modeling, this study uses an 18-channel feature set that includes orientation, gyroscope, accelerometer, magnetometer, linear acceleration, and gravity signals. Stratified evaluation and several metrics, such as accuracy, macro-F1, Matthews Correlation Coefficient (MCC), ROC-AUC, and per-class precision-recall, were used to systematically benchmark eight classifiers: Multinomial Logistic Regression (MLR), Gaussian Naïve Bayes (GNB), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), RBF-kernel Support Vector Classifier (SVC), a compact Multilayer Perceptron (MLP), and an adaptive CatBoost configuration. The results show that CatBoost performed almost flawlessly (Accuracy = 0.999, MCC = 0.999), closely followed by compact MLP. RF, KNN, and SVC formed a solid middle tier. In a window-free regime, feature importance analysis showed that instantaneous gyroscope and linear acceleration made very little contribution, while orientation and magnetometer channels were found to be the most crucial features. These results show that accurate and computationally efficient recognition of stair-climbing wheelchair states is possible by features driven by posture and heading. The proposed method facilitates low-latency embedded deployment and identifies areas for future development, such as lightweight temporal enhancements, angle encoding, and magnetometer calibration.

As the reliance on digital networks grows, the need for robust security measures becomes paramount. It offers a thorough analysis of creating and assessing a Network Intrusion Detection System (NIDS) incorporating various machine learning algorithms. The selected algorithms consist of K Nearest Neighbour, Naïve Bayes, Decision Tree, Support Vector Machine, and Logistic Regression. Moreover, widely recognised ensemble learning models like CatBoost, AdaBoost, Gradient Boost, Random Forest, and Extreme Gradient Boost. The core objective is to improve the efficiency of intrusion detection by evaluating various machine-learning models. Utilizes feature selection techniques based on chi-square to enhance the relevance and effectiveness of the selected features. The evaluation metrics, particularly Matthews’ Correlation Coefficient (MCC) and ROC Curves, are used in assessing the models’ efficacy. They offer valuable insights into the models’ capability to differentiate between normal and malicious network activities. This study aims to advance cybersecurity by comparing classical machine learning and ensemble models for network intrusion detection. Significantly, our results underscore XGBoost’s effectiveness with 0.996 accuracy and 0.993 MCC, in enhancing digital network security.

The authors use three methods, including matrix scoring algorithm, increment of diversity algorithm and Random Forest algorithm. They are used to predict β-hairpin motifs in the ArchDB-EC and ArchDB40 dataset. In the ArchDB-EC dataset, we obtain the accuracy of 68.5%, 79.8% and 84.3%, respectively. Matthew's correlation coefficient are 0.17, 0.61 and 0.63, respectively. Using same three methods in the ArchDB40 dataset, we obtain the accuracy and Matthew's correlation coefficient of 67.9% and 0.39, 75.2% and 0.51, 83.5% and 0.60, respectively. Experiments show that Random Forest algorithm for predicting β-hairpin motifs is best and the predictive results in ArchDB40 dataset are better than previous results.

Anemia is one of the common adverse reactions after hip fracture surgery. The traditional method to solve anemia is allogeneic transfusion. However, the transfusion may lead to some complications such as septicemia and fever. So far, few studies have reported roles of machine learning in predicting whether blood transfusion is needed or not after hip fracture surgery. Therefore, the purpose of this study is to develop machine learning models to predict the likelihood of postoperative blood transfusion in patients undergoing hip fracture surgery. This study enrolled 1355 patients who underwent hip fracture surgery at the Affiliated Hospital of Qingdao University from January 2016 to December 2021. Among all patients, 210 cases received postoperative blood transfusion. All patients were randomly divided into a training group and a testing group at a ratio of 7:3. In the training group, univariate and multivariate logistic regression analyses were used to determine independent risk factors for the postoperative transfusion. Then, based on these independent risk factors, tenfold cross-validation method was utilized to develop five machine learning models, including logistic, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The receiver operating characteristic (ROC) curve, area under ROC curve (AUC), and Matthews correlation coefficient (MCC) were generated to evaluate the performance of the models. Calibration plot and decision curve analysis (DCA) were used to test the performance, stability, and clinical applicability of the models. The models were validated using the testing group; and the ROC curve, MCC, calibration plot, and DCA curves were also generated to validate the performance, stability, and clinical applicability of the models. To further verify the robustness of the model, we randomly grabbed 70% of the samples in the testing set, performed 1000 iterations, and calculated the AUC and confidence interval of the five models. Finally, we used SHapley Additive exPlanations (SHAP) to explain these models. Multivariate logistic regression analysis showed that there were 8 independent risk factors, including age, blood transfusion history, albumin (ALB), globulin (GLO), total bilirubin (TBIL), indirect bilirubin (IBIL), hemoglobin (HB), and blood loss > 200ml. We finally selected five independent risk factors including HB, GLO, age, IBIL, and blood loss > 200ml. Based on these five independent risk factors, we generated six characteristic variables, namely HB, HB × HB, HB × blood loss, GLO × HB, age, age × IBIL, and established five machine learning models using a tenfold cross-validation method. In the training group, the AUC values of logistic, RF, MLP, SVM, and XGB were 0.9320, 0.8911, 0.9327, 0.9225, and 0.8825, respectively, and the average AUC was 0.9122 ± 0.0212. The MCC values were 0.65, 0.77, 0.65, 0.66, and 0.68, respectively, and the calibration plot and DCA performed well. In the testing group the AUC values of logistic, RF, MLP, SVM, and XGB were 0.8483, 0.7978, 0.8576, 0.8598, and 0.8216, respectively. The average AUC was 0.8370 ± 0.0238, and the MCC values were 0.41, 0.35, 0.40, 0.41, and 0.41, respectively. The calibration plot and DCA in the testing group also showed good performance. The AUC values and confidence intervals of the 1000-iteration model were: logistic (AUC, min confidence interval [CI]-max confidence interval [CI] 0.848, 0.804-0.903), RF (AUC, minCI-maxCI 0.797, 0.734-0.857), MLP (AUC, minCI-maxCI 0.858, 0.812-0.902), SVM (AUC, minCI-maxCI 0.859, 0.819-0.910), and XGB (AUC, minCI-maxCI 0.821, 0.764-0.894). The model performed well. Finally, according to SHAP, among all five models, HB played the most important role in model prediction and interpretation. The five models we developed all performed well in predicting the likelihood of blood transfusion after hip fracture surgery. Therefore, we believed that the prediction model based on machine learning had great application prospects in clinical practice, which could help clinicians better predict the risk of blood transfusion after hip fracture surgery.

Landslides are disasters that cause huge losses to both human life and infrastructure. Therefore, this research purpose of carrying out landslide susceptibility spatial modelling using a random forest (RF) algorithm. This research uses 12 landslide conditioning factors to generate a landslide susceptibility map, which comprises elevation, slope, aspect, soil type, geological type, distance to river, NDVI (Normalized Different Index), river density, TWI (Topographic Wetness Index), annual rainfall, and land use. Each model was evaluated by 9 parameters including ROC (Receiver Operator Characteristic)-AUC (Area Under Curve), accuracy (acc), sensitivity (sn), specificity (sp), balanced accuracy (ba), g-mean (gm), cohen’s kappa (CK), and Matthew’s correlation coefficient (MCC). A total of 88 landslide locations were identified in Malang District using the regional disaster management authority of Malang District data. Of the 88 landslide inventories, 30% of the data were used for validation, and the remaining 70% were used for training purposes. The results show the ACC value of 0.884, 0.765 for SN, 0.962 for SP, 0.863 for GM, 0.857 for BA, 0.749 for CK, 0.876 for MCC, and 0.943 for AUC. From the entire landslide conditioning factors, the elevation parameter has the highest relative contribution level value, which is 100%. Moreover, the susceptibility map indicates that Malang District is dominated by a high susceptibility with an area of 177,208.83 ha (51% of the coverage area). 13 sub-districts that are dominated by high susceptibility levels area, including Ngantang, Kasembon, Apelgading, Pujon, Tirtoyudo, Poncokusumo, Sumbermanjing, Jabung, Dampit, Wonosari, Wagir, Dau and Gedangan sub-districts.

PEP-PREDNa+: A web server for prediction of highly specific peptides targeting voltage-gated Na+ channels using machine learning techniques

JOURNAL/atin/04.03/02274269-202509000-00002/figure1/v/2025-05-23T114004Z/r/image-tiff Neurotoxicity refers to harmful changes in the structure and function of the central and/or peripheral nervous system caused by exposure to chemical, physical, or biological factors. These changes can manifest as organic damage, functional disorders, and behavioral alterations. Traditional biological testing methods for neurotoxicity are often expensive, labor-intensive, and time-consuming. Additionally, existing predictive models rely on small datasets and lack comprehensive, large-scale, and professional algorithms and platforms for accurately predicting brain toxicity. In this study, we integrate molecular fingerprints and descriptors—namely, MorganFP, MACCS, RDKFP, and TopologicalTorsionFP—with machine learning models such as Random Forest and Support Vector Machine, as well as deep learning models such as Graph Neural Networks, to develop a neurotoxicity prediction model. The optimal model, MorganFP-SVM, demonstrates excellent performance in predicting neurotoxicity, achieving an accuracy of 86.56%. This significantly outperforms other neurotoxicity prediction models, including ADMETlab 3.0. When compared to existing neurotoxicity prediction models DINeuroT and ADMETlab 3.0, the MorganFP-SVM model exhibits superior performance across multiple key evaluation metrics, offering greater balance and comprehensiveness as a reliable tool for neurotoxicity prediction. The DINeuroT model shows weaknesses in specificity and Matthews correlation coefficient, while ADMETlab 3.0, though strong in sensitivity, has limited capacity to accurately identify negative samples. Overall, the comprehensive advantages of the MorganFP-SVM model in neurotoxicity prediction establish it as an essential tool in the field. It not only provides higher predictive accuracy but also demonstrates strong stability and reliability across various evaluation metrics. This model offers a promising approach for assessing neurotoxicity risks related to drug development and environmental pollutants, thereby providing a scientific basis for public health decision-making.

Integrating near-infrared hyperspectral imaging with machine learning and feature selection: Detecting adulteration of extra-virgin olive oil with lower-grade olive oils and hazelnut oil

Background Early detection of oppositional defiant behavior is warranted for timely intervention in children at risk. This study aimed to build a predictive model of persistent oppositional defiant behavior based on a machine learning algorithm. Methods With nationwide cohort data collected from 2012 to 2017, a tree-based ensemble model, random forest, was exploited to build a predictive model for persistent oppositional defiant behavior. The persistent oppositional defiant behavior was defined by the presence of oppositional defiant behavior for all the five years. The area under the receiver operating characteristic curve (AUC), overall accuracy, sensitivity, specificity, and Matthew’s correlation coefficients (MCC) were measured. Results Data of 1,323 children were used for building the machine learning-based predictive model. The baseline mean ± standard deviation month-age of the participants was 51.0 ± 1.2 months. The proportion of persistent oppositional defiant behavior was 0.98% (13/1323). In the hold-out test set, the overall accuracy, AUC, sensitivity, specificity, and MCC were 0.955, 0.982, 1.000, 0.954, and 0.417, respectively. Conclusion Our study demonstrated that the machine learning-based approach is useful for predicting persistent oppositional defiant behavior in preschool-aged children.

Using random forest to detect multiple inherited metabolic diseases simultaneously based on GC-MS urinary metabolomics