Prediction of RNA-Binding Proteins by Voting Systems

RNA editing is a post-transcriptional RNA process that provides RNA and protein complexity for regulating gene expression in eukaryotes. It is challenging to predict RNA editing by computational methods. In this study, we developed a novel method to predict RNA editing based on a random forest method. A careful feature selection procedure was performed based on the Maximum Relevance Minimum Redundancy (mRMR) and Incremental Feature Selection (IFS) algorithms. Eighteen optimal features were selected from the 77 features in our dataset and used to construct a final predictor. The accuracy and MCC (Matthews correlation coefficient) values for the training dataset were 0.866 and 0.742, respectively; for the testing dataset, the accuracy and MCC were 0.876 and 0.576, respectively. The performance was higher using 18 features than all 77, suggesting that a small feature set was sufficient to achieve accurate prediction. Analysis of the 18 features was performed and may shed light on the mechanism and dominant factors of RNA editing, providing a basis for future experimental validation.

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.

Recent studies have successfully reported the accuracy of using artificial neural networks to predict grip force in controlled settings. However, only relying on accuracy to evaluate the machine learning models may lead to overoptimistic results, especially on imbalanced datasets. The Matthews correlation coefficient (MCC) showed an advantage in capturing all the data characteristics in the confusion matrix. Therefore, a binary classification approach and the MCC value were introduced to assess the performance of previously proposed machine learning models. Our results show that the overall correlations ranging between 0.48 and 0.59 indicate a strong relationship between predictions and actual scenarios. The binary classification approach and the MCC values could be used for future performance comparison with other machine learning models.

Identifying protein arginine methylation sites using global features of protein sequence coupled with support vector machine optimized by particle swarm optimization algorithm

Enzymes play an important role in metabolism that helps in catalyzing bio-chemical reactions. Predicting functions of enzymes by experiments is costly and time consuming. Hence a computational method is required to predict the function of enzymes. This paper presents a supervised machine learning approach to predict the functional classes and subclass of protein sequences including enzymes and non-enzymes based on 857 sequence derived features. This paper used seven sequence derived properties including amino acid composition, dipeptide composition, correlation feature, composition, transition, distribution and pseudo amino acid composition. We have used recursive feature elimination technique (RFE), in order to select optimal number of features. The support vector machine (SVM) has been used to construct a three level model with optimal number of features selected by SVM-RFE, where top (first) level distinguish a query protein as an enzyme or nonenzyme, the next (second) level predicts the enzyme functional class and the last (third) level predict the subfunctional class. The proposed model reported overall accuracy of 97.6%, precision of 97.8%and Matthew Correlation Coefficient (MCC) value of 0.93 for the first level, whereas accuracy of 87.3%, precision of 87.7% and MCC value of 0.84 for second level and accuracy of 85.6%, precision of 87.9% and MCC value of 0.86 for the third level.

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

During the lithospheric buildup to an earthquake, complex physical changes occur within the earthquake hypocenter. Data pertaining to the changes in the ionosphere may be obtained by satellites, and the analysis of data anomalies can help identify earthquake precursors. In this paper, we present a deep-learning model, SeqNetQuake, that uses data from the first China Seismo-Electromagnetic Satellite (CSES) to identify ionospheric perturbations prior to earthquakes. SeqNetQuake achieves the best performance [F-measure (F1) = 0.6792 and Matthews correlation coefficient (MCC) = 0.427] when directly trained on the CSES dataset with a spatial window centered on the earthquake epicenter with the Dobrovolsky radius and an input sequence length of 20 consecutive observations during night time. We further explore a transferring learning approach, which initially trains the model with the larger Electro-Magnetic Emissions Transmitted from the Earthquake Regions (DEMETER) dataset, and then tunes the model with the CSES dataset. The transfer-learning performance is substantially higher than that of direct learning, yielding a 12% improvement in the F1 score and a 29% improvement in the MCC value. Moreover, we compare the proposed model SeqNetQuake with other five benchmarking classifiers on an independent test set, which shows that SeqNetQuake demonstrates a 64.2% improvement in MCC and approximately a 24.5% improvement in the F1 score over the second-best convolutional neural network model. SeqNetSquake achieves significant improvement in identifying pre-earthquake ionospheric perturbation and improves the performance of earthquake prediction using the CSES data.

The article considers the problem of detecting anomalies in the video stream from traffic surveillance cameras, which is an important element of modern intelligent transport systems. An object-centric approach “detector-tracker-analyzer of anomalies” is proposed, which provides increased reliability of automatic detection of anomalous events, in particular, driving at a prohibitory traffic light signal, speeding, emergency braking and prolonged stay in the intersection zone. The method is based on the modern object detector YOLOv8n, which is characterized by high processing speed and acceptable accuracy for real-time tasks, as well as the OC-SORT tracker, which demonstrates increased resistance to short-term occlusions and reduces the number of false associations in a dense traffic flow. To determine the speed characteristics of vehicles, a homographic transformation was used taking into account the camera calibration, which made it possible to correctly translate the coordinates of objects into the world system. To test the efficiency of the approach, the proprietary dataset based on open source videos (Friant Roulette channel, California) was generated, containing both normal and abnormal situations. A total of 160 video fragments were used. The experiments demonstrated that the use of the combination of YOLOv8n + OC-SORT provides higher accuracy compared to the basic combination of YOLOv8n + SORT, which is confirmed by the increase in the Matthews correlation coefficient (MCC) values. The best results were obtained for anomalies such as “running a red light” (MCC = 0.909) and “being in the intersection zone” (MCC = 0.881). The results for “speeding” (MCC = 0.815) and “emergency braking” (MCC = 0.505) were somewhat worse, which is explained by the sensitivity to the quality of the video stream, viewing angle and camera stability. The developed approach is promising for the integration into intelligent traffic monitoring systems, as it allows automating the process of detecting violations and reducing the workload on operators. Further development directions include the optimization of the detector model architecture, using re-identification modules to reduce the number of false associations, improving speed estimation algorithms, and expanding the list of anomalies, such as pedestrians on the roadway or prohibited parking.

This study investigates the linguistic competence of modern language models. Artificial neural networks demonstrate high quality in many natural language processing tasks. However, their implicit grammar knowledge remains unstudied. The ability to judge a sentence as grammatical or ungrammatical is regarded as key property of human’s linguistic competence. We suppose that language models’ grammar knowledge also occurs in their ability to judge the grammaticality of a sentence. In order to test neural networks’ linguistic competence, we probe their acquisition of number predicate agreement in Russian. A dataset consisted of artificially generated grammatical and ungrammatical sentences was created to train the language models. Automatic sentence generation allows us to test the acquisition of particular language phenomenon, to detach from vocabulary and pragmatic differences. We use transfer learning of pre-trained neural networks. The results show that all the considered models demonstrate high accuracy and Matthew's correlation coefficient values which can be attributed to successful acquisition of predicate agreement rules. The classification quality is reduced for sentences with inanimate nouns which show nominative-accusative case syncretism. The complexity of the syntactic structure turns out to be significant for Russian models and a model for Slavic languages, but it does not affect the errors distribution of multilingual models.

S-Palmitoylation is a key regulatory mechanism controlling protein targeting, localization, stability, and activity. Since increasing evidence shows that its disruption is implicated in many human diseases, the identification of palmitoylation sites is attracting more attention. However, the computational methods that are published so far for this purpose have suffered from a poor balance of sensitivity and specificity; hence, it is difficult to get a good generalized prediction ability on an external validation set, which holds back the further analysis of associations between disruption of palmitoylation and human inherited diseases. In this work, we present a reliable identification method for protein S-palmitoylation sites, called SeqPalm, based on a series of newly composed features from protein sequences and the synthetic minority oversampling technique. With only 16 extracted key features, this approach achieves the most favorable prediction performance up to now with sensitivity, specificity, and Matthew's correlation coefficient values of 95.4%, 96.3%, and 0.917, respectively. Then, all known disease-associated variations are studied by SeqPalm. It is found that 243 potential loss or gain of palmitoylation sites are highly associated with human inherited disease. The analysis presents several potential therapeutic targets for inherited diseases associated with loss or gain of palmitoylation function. There are even biological evidence that are coordinate with our prediction results. Therefore, this work presents a novel approach to discover the molecular basis of pathogenesis associated with abnormal palmitoylation. SeqPalm is now available online at http://lishuyan.lzu.edu.cn/seqpalm , which can not only annotate the palmitoylation sites of proteins but also distinguish loss or gain of palmitoylation sites by protein variations.

BackgroundThe computational prediction of mycobacterial proteins' subcellular localization is of key importance for proteome annotation and for the identification of new drug targets and vaccine candidates. Several subcellular localization classifiers have been developed over the past few years, which have comprised both general localization and feature-based classifiers. Here, we have validated the ability of different bioinformatics approaches, through the use of SignalP 2.0, TatP 1.0, LipoP 1.0, Phobius, PA-SUB 2.5, PSORTb v.2.0.4 and Gpos-PLoc, to predict secreted bacterial proteins. These computational tools were compared in terms of sensitivity, specificity and Matthew's correlation coefficient (MCC) using a set of mycobacterial proteins having less than 40% identity, none of which are included in the training data sets of the validated tools and whose subcellular localization have been experimentally confirmed. These proteins belong to the TBpred training data set, a computational tool specifically designed to predict mycobacterial proteins.ResultsA final validation set of 272 mycobacterial proteins was obtained from the initial set of 852 mycobacterial proteins. According to the results of the validation metrics, all tools presented specificity above 0.90, while dispersion sensitivity and MCC values were above 0.22. PA-SUB 2.5 presented the highest values; however, these results might be biased due to the methodology used by this tool. PSORTb v.2.0.4 left 56 proteins out of the classification, while Gpos-PLoc left just one protein out.ConclusionBoth subcellular localization approaches had high predictive specificity and high recognition of true negatives for the tested data set. Among those tools whose predictions are not based on homology searches against SWISS-PROT, Gpos-PLoc was the general localization tool with the best predictive performance, while SignalP 2.0 was the best tool among the ones using a feature-based approach. Even though PA-SUB 2.5 presented the highest metrics, it should be taken into account that this tool was trained using all proteins reported in SWISS-PROT, which includes the protein set tested in this study, either as a BLAST search or as a training model.

Headaches are the main reason for visits to Neurology clinics, and migraine is the most common primary headache. with migraine being the most frequent. Our objective was to develop a computer application (app) that could empower Primary Health Care (PHC) physicians in decision-making regarding migraine. A rule-based artificial intelligence system was designed to process patients' responses to the ID-Migraine screener and subsequently determine whether they met the diagnostic criteria for migraine or tension-type headache, according to the International Headache Society. The application, known as CefaleApp, is designed to generate a diagnosis of migraine, tension-type headache, or mixed headache. CefaleApp was validated in 152 patients referred from PHC clinics with a suspected diagnosis of migraine or tension-type headache. Patients were evaluated in the Neurology Department of a secondary-level hospital and in two regional hospitals. Agreement between the diagnosis generated by CefaleApp and that issued by an expert headache neurologist (gold standard) was estimated using Cohen's Kappa index and the Matthews correlation coefficient (MCC). Overall diagnostic accuracy was 90.8% (95% CI: 85.1-94.6%), Cohen's Kappa index was 0.73 (95% CI: 0.59-0.87), and the MCC value was 0.73. The migraine diagnosis generated by CefaleApp shows substantial-high agreement with that provided by the expert headache neurologist.

Brain tumors are abnormal tissue that grow uncontrolled and affect a patient's neurological function. Brain tumors come in different shapes and characteristics. Moreover, its location also differs for each patient. Brain tumors can be detected using machine learning algorithms using magnetic resonance imaging (MRI) images. However, a different machine-learning comparison is limited and needs further investigation. This study aims to compare three machine-learning methods, i.e., Support Vector Machine (SVM), Naive Bayes (NB), and Artificial Neural Network Back Propagation (ANN-BP) algorithms for detecting brain tumors. Before the comparison started, MRI image quality was enhanced by performing denoising, histogram equalization, and thresholding. After that, Gray Level Co-occurrence Matrix feature extraction was performed. MRI brain images in JPEG format were acquired from an open-access database. One thousand brain tumor and 1000 normal tumor images are used as the training data, while 100 brain tumor and 100 normal tumor images are used as testing data. Each algorithm's accuracy, precision, sensitivity, and Matthews Correlation Coefficient (MCC) are evaluated and reported. The study showed that the SVM algorithm acquired the highest performance in detecting brain tumors, followed by ANN-BP and NB. The highest accuracy, precision, sensitivity, and MCC values for testing in SVM were 98,75%, 98,22%, 99,30%, and 0,9751, respectively. Meanwhile, in testing, the highest accuracy, precision, sensitivity, and MCC values were 90.50%, 98.80%, 82.00%, and 0.8220, respectively. In conclusion, this study showed the superiority of the SVM algorithm in detecting brain tumor compared to ANN-BP and NB by performing image enhancement steps and GLCM feature extraction before its detection.

In this paper, a mode decomposition analysis-based adaptive approach is proposed to provide high diagnostic performance for automated voice pathology detection systems. The aim of the study is to develop a reliable and effective system using adaptive cepstral domain features derived from the empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and complete empirical mode decomposition with adaptive noise (CEEMDAN) methods. The descriptive feature sets are obtained by applying mel-frequency cepstral coefficients (MFCCs) and their derivatives, linear predictive coefficients (LPCs) and linear predictive cepstral coefficients (LPCCs) techniques to each decomposition level. The class-balanced data are generated on the VOice ICar fEDerico II database samples using the synthetic minority oversampling technique (SMOTE). The ReliefF algorithm is used to select the most effective and distinctive features. A combination of selected features and a support vector machine (SVM) classifier is used to identify pathological voices. In the pathology detection approach, the results show that the cepstral features based on EMD and SVM-cubic achieves the highest performance with 99.85\% accuracy, 99.85\% F1-score and 0.997 Matthews correlation coefficient (MCC). In pathology-type classification, the cepstral features based on EEMD and SVM-quadratic approach provided the highest performance with 96.49\% accuracy, 96.46\% F1 and 0.949 MCC values. The comprehensive results of this study reveal that mode decomposition-based approaches are more successful and effective than traditional methods for detection and classification of pathological voices.

Alzheimer’s disease (AD), a nervous system disease, lacks effective therapies at present. RNA expression is the basic way to regulate life activities, and identifying related characteristics in AD patients may aid the exploration of AD pathogenesis and treatment. This study developed a classifier that could accurately classify AD patients and healthy people, and then obtained 3 core genes that may be related to the pathogenesis of AD. To this end, RNA expression data of the middle temporal gyrus of AD patients were firstly downloaded from GEO database, and the data were then normalized using limma package following a supplementation of missing data by k-Nearest Neighbor (KNN) algorithm. Afterwards, the top 500 genes of the most feature importance were obtained through Max-Relevance and Min-Redundancy (mRMR) analysis, and based on these genes, a series of AD classifiers were constructed through Support Vector Machine (SVM), Random Forest (RF), and KNN algorithms. Then, the KNN classifier with the highest Matthews correlation coefficient (MCC) value composed of 14 genes in incremental feature selection (IFS) analysis was identified as the best AD classifier. As analyzed, the 14 genes played a pivotal role in determination of AD and may be core genes associated with the pathogenesis of AD. Finally, protein-protein interaction (PPI) network and Random Walk with Restart (RWR) analysis were applied to obtain core gene-associated genes, and key pathways related to AD were further analyzed. Overall, this study contributed to a deeper understanding of AD pathogenesis and provided theoretical guidance for related research and experiments.