Search Results (18)

Biological-sequence representation methods are pivotal for advancing machine learning in computational biology, transforming nucleotide and protein sequences into formats that enhance predictive modeling and downstream task performance. This review categorizes these methods into three developmental stages: computational-based, word embedding-based, and large language model (LLM)-based, detailing their principles, applications, and limitations. Computational-based methods, such as k-mer counting and position-specific scoring matrices (PSSM), extract statistical and evolutionary patterns to support tasks like motif discovery and protein–protein interaction prediction. Word embedding-based approaches, including Word2Vec and GloVe, capture contextual relationships, enabling robust sequence classification and regulatory element identification. Advanced LLM-based methods, leveraging Transformer architectures like ESM3 and RNAErnie, model long-range dependencies for RNA structure prediction and cross-modal analysis, achieving superior accuracy. However, challenges persist, including computational complexity, sensitivity to data quality, and limited interpretability of high-dimensional embeddings. Future directions prioritize integrating multimodal data (e.g., sequences, structures, and functional annotations), employing sparse attention mechanisms to enhance efficiency, and leveraging explainable AI to bridge embeddings with biological insights. These advancements promise transformative applications in drug discovery, disease prediction, and genomics, empowering computational biology with robust, interpretable tools. Full article

Math learning is a key educational goal, and one marked by substantial individual differences even in the earliest grades. Although considerable research has examined the extent to which domain-general processes, such as executive functions and fluid intelligence, contribute to this variability, there is a notable gap in understanding how they may interact to predict early math learning. In particular, prior work had not examined potential moderating effects whereby the relation between executive functions and math outcomes depends on a child’s fluid intelligence, and vice versa. The current study addressed this gap by examining the math skills in Russian first-graders (N = 160) as a function of fluid intelligence (measured with Raven’s matrices) and various components of executive functions. Consistent with prior research, the results revealed the main effects of Raven’s scores, verbal working memory, and the control component of executive function (a composite of inhibition and cognitive flexibility scores) on math growth. Importantly, extending previous research, the study found that both memory and control components of executive function interacted with fluid intelligence. Specifically, executive function had a stronger positive effect on math learning for children with lower levels of fluid intelligence. The implications for intervention research and educational practice are discussed. Full article

This study examines the effects of a working memory (WM) intervention package on the WM performance of students with Specific Learning Disabilities (SLDs). A pre-test post-test experimental design was applied with 40 students, divided equally into experimental (20 students) and control groups (20 students). Data were collected using the Working Memory Scale (WMS), Raven’s Standard Progressive Matrices (RSPM), and the Working Memory Performance Tasks Form (WM-PTF). The experimental group demonstrated statistically significant improvements in WMS and WM-PTF scores relative to the control group (p < 0.006, d = 1.96 for WMS; d = 1.42 for WM-PTF). Additionally, a positive correlation was observed between the increase in WM performance and intelligence scores, suggesting that intelligence may influence WM gains. In conclusion, the WM intervention package was significant in improving the WM performance of students with SLDs, indicating that such interventions have significant potential for enhancing cognitive functions and memory. These findings highlight the critical role of WM interventions in contributing to the cognitive development of students with learning difficulties. Full article

Protein secondary structure prediction (PSSP) plays a crucial role in resolving protein functions and properties. Significant progress has been made in this field in recent years, and the use of a variety of protein-related features, including amino acid sequences, position-specific score matrices (PSSM), amino acid properties, and secondary structure trend factors, to improve prediction accuracy is an important technical route for it. However, a comprehensive evaluation of the impact of these factor features in secondary structure prediction is lacking in the current work. This study quantitatively analyzes the impact of several major factors on secondary structure prediction models using a more explanatory four-class machine learning approach. The applicability of each factor in the different types of methods, the extent to which the different methods work on each factor, and the evaluation of the effect of multi-factor combinations are explored in detail. Through experiments and analyses, it was found that PSSM performs best in methods with strong high-dimensional features and complex feature extraction capabilities, while amino acid sequences, although performing poorly overall, perform relatively well in methods with strong linear processing capabilities. Also, the combination of amino acid properties and trend factors significantly improved the prediction performance. This study provides empirical evidence for future researchers to optimize multi-factor feature combinations and apply them to protein secondary structure prediction models, which is beneficial in further optimizing the use of these factors to enhance the performance of protein secondary structure prediction models. Full article

Beam management is a key functionality in establishing and maintaining reliable communication in cellular and vehicular networks, and it becomes more critical at millimeter-wave (mmWave) frequencies and for high-mobility scenarios. Traditional approaches consume wireless resources and incur high beam training overheads in finding the best beam pairings, thus necessitating alternative approaches such as position-aided, vision-aided, or, more generally, sensing-aided beam prediction approaches. Current systems are also leveraging artificial intelligence/machine learning (ML) to optimize the beam management procedures; however, the majority of the proposed ML frameworks have been applied to synthetic datasets, leading to overestimated performances. In this work, in the context of vehicle-to-infrastructure (V2I) communication and using the real-world DeepSense6G experimental datasets, we investigate the performance of four ML algorithms on beam prediction accuracy for mmWave V2I scenarios. We compare the performance of K-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), and naïve Bayes (NB) algorithms on position-aided beam prediction accuracy and related metrics such as precision, recall, specificity, and F1-score. The impacts of different beam codebook sizes and dataset split ratios on five different scenarios’ datasets were investigated, independently and collectively. Confusion matrices and area under the receiver operating characteristic curves were also employed to visualize the (mis)classification statistics of the considered ML algorithms. The results show that SVM outperforms the other three algorithms, for the most part, on the scenario-per-scenario cases. However, for the combined scenario with larger data samples, DT outperforms the other three algorithms for both the different codebook sizes and data split ratios. The results also show comparable performance for the different data split ratios considered for the different algorithms. However, with respect to the codebook sizes, the results show that the higher the codebook size, the lower the beam prediction accuracy. With the best accuracy results around 70% for the combined scenario in this study, multi-modal sensing-aided approaches can be explored to increase the beam prediction performance, although at the expense of higher system complexity when compared to the position-aided approach considered in this study. Full article

Previous research has highlighted that active lifestyles that contribute to improved physical fitness are positively related to cognitive functioning in children and adolescents. Specifically, the increase in physical condition at school age is considered relevant because it is related to better cognitive ability and greater academic performance. Thus, the aim of this study was to analyze the relationships between explosive strength, speed–agility, and fluid reasoning in schoolchildren. To achieve this objective, an associative, comparative, and predictive design was used in this research. A total of 129 children participated in this study (age: M = 9.48; SD = 0.99). To assess fluid reasoning, the Raven test’s Standard Progressive Matrices Subtest and the Wechsler Intelligence Scale for Children (WISC-V) were used. To assess physical fitness, the speed–agility test and the horizontal jump test (ALPHA-fitness battery tests), as well as the ball throw test (2 kg), were used. The results showed that the speed–agility test significantly predicted WISC-V Fluid Reasoning Index scores, and the medicine ball toss test significantly predicted Raven test scores. The results obtained highlight the associations between physical condition at these ages and fluid intelligence. This suggests that promoting active lifestyles that improve physical fitness could have a positive impact on children’s cognitive health. Full article

Empirical evidence suggests a great positive association between measures of fluid intelligence and working memory capacity, which implied to some researchers that fluid intelligence is little more than working memory. Because this conclusion is mostly based on correlation analysis, a causal relationship between fluid intelligence and working memory has not yet been established. The aim of the present study was therefore to provide an experimental analysis of this relationship. In a first study, 60 participants worked on items of the Advanced Progressive Matrices (APM) while simultaneously engaging in one of four secondary tasks to load specific components of the working memory system. There was a diminishing effect of loading the central executive on the APM performance, which could explain 15% of the variance in the APM score. In a second study, we used the same experimental manipulations but replaced the dependent variable with complex working memory span tasks from three different domains. There was also a diminishing effect of the experimental manipulation on span task performance, which could now explain 40% of the variance. These findings suggest a causal effect of working memory functioning on fluid intelligence test performance, but they also imply that factors other than working memory functioning must contribute to fluid intelligence. Full article

It remains unknown whether the C-C motif chemokine receptor type 5 (CCR5) coreceptor is still the predominant coreceptor used by Human Immunodeficiency Virus-1 (HIV-1) in Botswana, where the HIV-1 subtype C predominates. We sought to determine HIV-1C tropism in Botswana using genotypic tools, taking into account the effect of antiretroviral treatment (ART) and virologic suppression. HIV-1 gp120 V3 loop sequences from 5602 participants were analyzed for viral tropism using three coreceptor use predicting algorithms/tools: Geno2pheno, HIV-1C Web Position-Specific Score Matrices (WebPSSM) and the 11/25 charge rule. We then compared the demographic and clinical characteristics of people living with HIV (PLWH) harboring R5- versus X4-tropic viruses using χ² and Wilcoxon rank sum tests for categorical and continuous data analysis, respectively. The three tools congruently predicted 64% of viruses as either R5-tropic or X4-tropic. Geno2pheno and the 11/25 charge rule had the highest concordance at 89%. We observed a significant difference in ART status between participants harboring X4- versus R5-tropic viruses. X4-tropic viruses were more frequent among PLWH receiving ART (χ² test, p = 0.03). CCR5 is the predominant coreceptor used by HIV-1C strains circulating in Botswana, underlining the strong potential for CCR5 inhibitor use, even in PLWH with drug resistance. We suggest that the tools for coreceptor prediction should be used in combination. Full article

Purpose. A single-institution prospective pilot study was conducted to the assess correlation between salivary amylase and xerostomia in patients with head and neck squamous cell carcinoma (HNSCC) treated with intensity-modulated radiotherapy (IMRT). Methods and materials. Serum saliva amylase, clinician-reported xerostomia (using Common Terminology Criteria for Adverse Events), and patient-reported xerostomia (using 8-item self-reported xerostomia-specific questionnaire) were prospectively collected at baseline, during treatment and thereafter. Correlations between variables were assessed by correlation matrices. Results. Twelve patients with locally advanced HNSCC formed the cohort. Eighty-three percent were male, 75% were smokers, 100% had clinical positive lymph nodes at diagnosis, and 42% received induction chemotherapy. All patients received IMRT with concurrent cisplatin-based chemotherapy. No grade ≥4 xerostomia was observed. Severe (G3) acute and late xerostomia occurred in five cases (41.7%) and two cases (16.7%), respectively. Patient-reported xerostomia scores were highly correlated with the clinician-reported scores (ρ = 0.73). A significant correlation was recorded between the concentration of amylase and the acute (ρ = −0.70) and late (ρ = −0.80) xerostomia. Conclusion. Preliminary results are encouraging. Prospective clinical trials are needed to define the value of salivary amylase in the management of HNSCC tumors. Full article

The purpose of this research was to analyze how we can improve the space–temporal orientation ability with the help of physical exercises in physical education and sports lessons. In total,148 children between the ages of 8 and 11 participated in this study (M = 9.70; SD = 0.79). They were subjected to three tests, which measured general intelligence (Raven Progressive Matrices) and space–temporal orientation skills (Piaget-Head test and Bender–Santucci test). The tests were carried out both in the pre-test and in the post-test period. In the case of participants in the experimental group, a specific program was applied for a period of 12 weeks. The results showed that general intelligence level was identified as a predictor of spatial–temporal orientation (beta = 0.17, t = 2.08, p = 0.03) but only for the Piaget-Head test. Similarly, no differences between children’s age groups were identified in any of the spatial–temporal orientation test scores. However, children in the “+9” age category had higher scores on the intelligence test compared to younger children (77.31 vs. 35.70). In conclusion, the intervention program had a positive effect on spatial orientation skills. Full article

Protein–protein interactions (PPIs) are crucial for understanding the cellular processes, including signal cascade, DNA transcription, metabolic cycles, and repair. In the past decade, a multitude of high-throughput methods have been introduced to detect PPIs. However, these techniques are time-consuming, laborious, and always suffer from high false negative rates. Therefore, there is a great need of new computational methods as a supplemental tool for PPIs prediction. In this article, we present a novel sequence-based model to predict PPIs that combines Discrete Hilbert transform (DHT) and Rotation Forest (RoF). This method contains three stages: firstly, the Position-Specific Scoring Matrices (PSSM) was adopted to transform the amino acid sequence into a PSSM matrix, which can contain rich information about protein evolution. Then, the 400-dimensional DHT descriptor was constructed for each protein pair. Finally, these feature descriptors were fed to the RoF classifier for identifying the potential PPI class. When exploring the proposed model on the Yeast, Human, and Oryza sativa PPIs datasets, it yielded excellent prediction accuracies of 91.93, 96.35, and 94.24%, respectively. In addition, we also conducted numerous experiments on cross-species PPIs datasets, and the predictive capacity of our method is also very excellent. To further access the prediction ability of the proposed approach, we present the comparison of RoF with four powerful classifiers, including Support Vector Machine (SVM), Random Forest (RF), K-nearest Neighbor (KNN), and AdaBoost. We also compared it with some existing superiority works. These comprehensive experimental results further confirm the excellent and feasibility of the proposed approach. In future work, we hope it can be a supplemental tool for the proteomics analysis. Full article

As the basis for screening drug candidates, the identification of drug–target interactions (DTIs) plays a crucial role in the innovative drugs research. However, due to the inherent constraints of small-scale and time-consuming wet experiments, DTI recognition is usually difficult to carry out. In the present study, we developed a computational approach called RoFDT to predict DTIs by combining feature-weighted Rotation Forest (FwRF) with a protein sequence. In particular, we first encode protein sequences as numerical matrices by Position-Specific Score Matrix (PSSM), then extract their features utilize Pseudo Position-Specific Score Matrix (PsePSSM) and combine them with drug structure information-molecular fingerprints and finally feed them into the FwRF classifier and validate the performance of RoFDT on Enzyme, GPCR, Ion Channel and Nuclear Receptor datasets. In the above dataset, RoFDT achieved 91.68%, 84.72%, 88.11% and 78.33% accuracy, respectively. RoFDT shows excellent performance in comparison with support vector machine models and previous superior approaches. Furthermore, 7 of the top 10 DTIs with RoFDT estimate scores were proven by the relevant database. These results demonstrate that RoFDT can be employed to a powerful predictive approach for DTIs to provide theoretical support for innovative drug discovery. Full article

Background: The aim of this study was to evaluate the efficacy of a deep learning system in pterygium grading and recurrence prediction. Methods: This was a single center, retrospective study. Slit-lamp photographs, from patients with or without pterygium, were collected to develop an algorithm. Demographic data, including age, gender, laterality, grading, and pterygium area, recurrence, and surgical methods were recorded. Complex ocular surface diseases and pseudopterygium were excluded. Performance of the algorithm was evaluated by sensitivity, specificity, F1 score, accuracy, and area under the receiver operating characteristic curve. Confusion matrices and heatmaps were created to help explain the results. Results: A total of 237 eyes were enrolled, of which 176 eyes had pterygium and 61 were non-pterygium eyes. The training set and testing set were comprised of 189 and 48 photographs, respectively. In pterygium grading, sensitivity, specificity, F1 score, and accuracy were 80% to 91.67%, 91.67% to 100%, 81.82% to 94.34%, and 86.67% to 91.67%, respectively. In the prediction model, our results showed sensitivity, specificity, positive predictive value, and negative predictive values were 66.67%, 81.82%, 33.33%, and 94.74%, respectively. Conclusions: Deep learning systems can be useful in pterygium grading based on slit lamp photographs. When clinical parameters involved in the prediction of pterygium recurrence were included, the algorithm showed higher specificity and negative predictive value in prediction. Full article

Very high resolution satellite imageries provide an excellent foundation for precise mapping of plant communities and even single plants. We aim to perform individual tree recognition on the basis of very high resolution RGB (red, green, blue) satellite images using deep learning approaches for northern temperate mixed forests in the Primorsky Region of the Russian Far East. We used a pansharpened satellite RGB image by GeoEye-1 with a spatial resolution of 0.46 m/pixel, obtained in late April 2019. We parametrized the standard U-Net convolutional neural network (CNN) and trained it in manually delineated satellite images to solve the satellite image segmentation problem. For comparison purposes, we also applied standard pixel-based classification algorithms, such as random forest, k-nearest neighbor classifier, naive Bayes classifier, and quadratic discrimination. Pattern-specific features based on grey level co-occurrence matrices (GLCM) were computed to improve the recognition ability of standard machine learning methods. The U-Net-like CNN allowed us to obtain precise recognition of Mongolian poplar (Populus suaveolens Fisch. ex Loudon s.l.) and evergreen coniferous trees (Abies holophylla Maxim., Pinus koraiensis Siebold & Zucc.). We were able to distinguish species belonging to either poplar or coniferous groups but were unable to separate species within the same group (i.e. A. holophylla and P. koraiensis were not distinguishable). The accuracy of recognition was estimated by several metrics and exceeded values obtained for standard machine learning approaches. In contrast to pixel-based recognition algorithms, the U-Net-like CNN does not lead to an increase in false-positive decisions when facing green-colored objects that are similar to trees. By means of U-Net-like CNN, we obtained a mean accuracy score of up to 0.96 in our computational experiments. The U-Net-like CNN recognizes tree crowns not as a set of pixels with known RGB intensities but as spatial objects with a specific geometry and pattern. This CNN’s specific feature excludes misclassifications related to objects of similar colors as objects of interest. We highlight that utilization of satellite images obtained within the suitable phenological season is of high importance for successful tree recognition. The suitability of the phenological season is conceptualized as a group of conditions providing highlighting objects of interest over other components of vegetation cover. In our case, the use of satellite images captured in mid-spring allowed us to recognize evergreen fir and pine trees as the first class of objects (“conifers”) and poplars as the second class, which were in a leafless state among other deciduous tree species. Full article

The interactions between ncRNAs and proteins are critical for regulating various cellular processes in organisms, such as gene expression regulations. However, due to limitations, including financial and material consumptions in recent experimental methods for predicting ncRNA and protein interactions, it is essential to propose an innovative and practical approach with convincing performance of prediction accuracy. In this study, based on the protein sequences from a biological perspective, we put forward an effective deep learning method, named BGFE, to predict ncRNA and protein interactions. Protein sequences are represented by bi-gram probability feature extraction method from Position Specific Scoring Matrix (PSSM), and for ncRNA sequences, k-mers sparse matrices are employed to represent them. Furthermore, to extract hidden high-level feature information, a stacked auto-encoder network is employed with the stacked ensemble integration strategy. We evaluate the performance of the proposed method by using three datasets and a five-fold cross-validation after classifying the features through the random forest classifier. The experimental results clearly demonstrate the effectiveness and the prediction accuracy of our approach. In general, the proposed method is helpful for ncRNA and protein interacting predictions and it provides some serviceable guidance in future biological research. Full article