The absence of effective public databases greatly limits high-throughput prediction of hormonal effects mediated by nuclear receptors in aquatic organisms. In this study, we developed novel strategies for multi-species screening of estrogen receptor (ER) agonists in plastic additives using AlphaFold2. Firstly, Deep Forest (DF), artificial neural network (ANN) and conventional machine learning (ML) models were utilized to screen ERα agonists. The DF models using RDKit.Chem.Descriptors and MorganFingerprint achieved a sensitivity = 0.96, specificity > 0.99, and an F1 score > 0.95, identifying 42 plastic additives as ERα agonists. Subsequently, ERα structures for Danio rerio (Dr), Oryzias melastigma (Om), Delphinus delphis (Dd), Physeter catodon (Pc), Mytilus edulis (Me), Xenopus tropicalis (Xt), Nipponia nippon (Nn), and Aptenodytes forsteri (Af) were constructed using AlphaFold2. Except for Me ERα, most species shared two common key amino acid residues responsible for ERα activity: arginine 85 and glutamic acid 44 (aligned serial numbers in the LBD). However, aquatic-related species exhibited other three additional key residues: glycine 212, leucine 216 and phenylalanine 95 (aligned serial numbers in the LBD). The number of compounds with docking energy < -9 kcal/mol for Dr, Om, Dd, Pc, Me, Xt, Nn, and Af were 4, 8, 4, 12, 10, 13, 7, and 9, respectively. The docking energy of estrone in all species was < -9 kcal/mol, while that of bisphenol P varied greatly among different species. The combined application of ML and AlphaFold enables high-throughput evaluation of the ecotoxicity posed by emerging pollutants across multiple aquatic-related species.

Pancreatic cystic neoplasms (PCNs) are a complex group of lesions with a spectrum of malignancy. Accurate differentiation of PCN types is crucial for patient management, as misdiagnosis can result in unnecessary surgeries or treatment delays, affecting the quality of life. The significance of developing a non-invasive, accurate diagnostic model is underscored by the need to improve patient outcomes and reduce the impact of these conditions. We developed a machine learning model capable of accurately identifying different types of PCNs in a non-invasive manner, by using a dataset comprising 449 MRI and 568 CT scans from adult patients, spanning from 2009 to 2022. The study's results indicate that our multimodal machine learning algorithm, which integrates both clinical and imaging data, significantly outperforms single-source data algorithms. Specifically, it demonstrated state-of-the-art performance in classifying PCN types, achieving an average accuracy of 91.2%, precision of 91.7%, sensitivity of 88.9%, and specificity of 96.5%. Remarkably, for patients with mucinous cystic neoplasms (MCNs), regardless of undergoing MRI or CT imaging, the model achieved a 100% prediction accuracy rate. It indicates that our non-invasive multimodal machine learning model offers strong support for the early screening of MCNs, and represents a significant advancement in PCN diagnosis for improving clinical practice and patient outcomes. We also achieved the best results on an additional pancreatic cancer dataset, which further proves the generality of our model.

Patent value prediction is essential for technology innovation management. This study aims to enhance technology innovation management in the field of biomedical textiles by processing complex biomedical patent information to improve the accuracy of predicting patent values. A patent value grading prediction method based on a fusion of machine learning models is proposed, utilizing 113,428 biomedical textile patents as the research sample. The method combines BERT (Bidirectional Encoder Representations from Transformers) and a stacking strategy to classify and predict the value class of biomedical textile patents using both textual information and structured patent features. We implemented this method for patent value prediction in biomedical textiles, leading to the development of BioTexVal-the first dedicated patent value prediction model for this domain. BioTexVal's innovation lies in employing a stacking strategy that integrates multiple machine learning models to enhance predictive accuracy while leveraging unstructured data during training. Results have shown that this approach significantly outperforms previous predictive methods. Validated on 113,428 biomedical textile patents spanning from 2003 to 2023, BioTexVal achieved an accuracy of 88.38%. This study uses average annual forward citations as an indicator for distinguishing patent value grades. The method may require adjustments based on data characteristics when applied to other research fields to ensure its effectiveness.

Coronary artery extraction is a crucial prerequisite for computer-aided diagnosis of coronary artery disease. Accurately extracting the complete coronary tree remains challenging due to several factors, including presence of thin distal vessels, tortuous topological structures, and insufficient contrast. These issues often result in over-segmentation and under-segmentation in current segmentation methods. To address these challenges, we propose a topology-preserving three-stage framework for fully-connected coronary artery extraction. This framework includes vessel segmentation, centerline reconnection, and missing vessel reconstruction. First, we introduce a new centerline enhanced loss in the segmentation process. Second, for the broken vessel segments, we further propose a regularized walk algorithm to integrate distance, probabilities predicted by a centerline classifier, and directional cosine similarity, for reconnecting the centerlines. Third, we apply implicit neural representation and implicit modeling, to reconstruct the geometric model of the missing vessels. Experimental results show that our proposed framework outperforms existing methods, achieving Dice scores of 88.53% and 85.07%, with Hausdorff Distances (HD) of 1.07 mm and 1.63 mm on ASOCA and PDSCA datasets, respectively. Code will be available at https://github.com/YH-Qiu/CorSegRec.

Gene expression is the basis for cells to achieve various functions, while DNA methylation constitutes a critical epigenetic mechanism governing gene expression regulation. Here we propose DeepMethyGene, an adaptive recursive convolutional neural network model based on ResNet that predicts gene expression using DNA methylation information. Our model transforms methylation Beta values to M values for Gaussian distributed data optimization, dynamically adjusts the output channels according to input dimension, and implements residual blocks to mitigate the problem of gradient vanishing when training very deep networks. Benchmarking against the state-of-the-art geneEXPLORE model (R2 = 0.449), DeepMethyGene (R2 = 0.640) demonstrated superior predictive performance. Further analysis revealed that the number of methylation sites and the average distance between these sites and gene transcription start sites (TSS) significantly affected the prediction accuracy. By exploring the complex relationship between methylation and gene expression, this study provides theoretical support for disease progression prediction and clinical intervention. Relevant data and code are available at https://github.com/yaoyao-11/DeepMethyGene .

Accurate differentiation of benign and malignant pulmonary nodules in ultrasound remains a clinical challenge due to insufficient diagnostic precision. We propose the Deep Cross-Entropy Fusion (DCEF) model to enhance classification accuracy.

A retrospective dataset of 135 patients (27 benign, 68 malignant training; 11 benign, 29 malignant testing) was analyzed. Manually annotated ultrasound ROIs were preprocessed and input into DCEF, which integrates ResNet, DenseNet, VGG, and InceptionV3 via entropy-based fusion. Performance was evaluated using AUC, accuracy, sensitivity, specificity, precision, and F1-score.

DCEF achieved an AUC of 0.873 (training) and 0.792 (testing), outperforming traditional methods. Test metrics included 71.5% accuracy, 70.69% sensitivity, 70.58% specificity, 72.55% precision, and 71.13% F1-score, demonstrating robust diagnostic capability.

DCEF's multi-architecture fusion enhances diagnostic reliability for ultrasound-based nodule assessment. While promising, validation in larger multi-center cohorts is needed to address single-center data limitations. Future work will explore next-generation architectures and multi-modal integration.

Predicting the risk of developing pancreatic ductal adenocarcinoma (PDAC) is of paramount importance, given its high mortality rate. Current PDAC risk prediction models rely on a limited number of variables, do not include genetics, and have a modest accuracy.

This study aimed to develop an interpretable PDAC risk prediction model, based on machine learning (ML).

Five ML models (Adaptive Boosting, eXtreme Gradient Boosting, CatBoost, Deep Forest and Random Forest) built on 56 exposome variables and a polygenic risk score (PRS) were tested in 654 PDAC cases and 1,308 controls of the UK Biobank. Additionally, SHapley Additive exPlanation (SHAP) and Global model Interpretation via the Recursive Partitioning (Girp) were employed to explain the models.

All models provided similar performance, but based on recall the best was CatBoost (77.10 %). SHAP highlighted age and the PRS as primary contributors across all models. Girp developed rules to discern cases from controls, identifying age, PRS, and pancreatitis in most of the rules.

The predictive models tested have exhibited good performance, indicating their potential application in the clinical field in the near future, with the PRS playing a key role in identifying high-risk individuals as demonstrated by the explainers.

Accurately diagnosing Anxiety-Depression Comorbidity Syndrome in Gastroenterology Inpatients (ADCS-GI) shows significant challenges as traditional diagnostic methods fail to meet expectations due to patient hesitance and non-psychiatric healthcare professionals' limitations. Therefore, the need for objective diagnostics highlights the potential of machine learning in identifying and treating ADCS-GI.

A total of 1186 ADCS patients were recruited for this study. We conducted extensive studies for the dataset, including data quantification, equilibrium, and correlation analysis. Eight machine learning models, including Gaussian Naive Bayes (NB), Support Vector Classifier (SVC), K-Neighbors Classifier, RandomForest, XGB, CatBoost, Cascade Forest, and Decision Tree, were utilized to compare prediction efficacy, with an effort to minimize the dependency on subjective questionnaires.

Among eight machine learning algorithms, the Decision Tree and K-nearest neighbors models demonstrated an accuracy exceeding 81% and a sensitivity in the same range for detecting ADCS in patients. Notably, when identifying moderate and severe cases, the models achieved an accuracy above 88% and a sensitivity of 90%. Furthermore, the models trained without reliance on subjective questionnaires showed promising performance, indicating the feasibility of developing questionnaire-free early detection applications.

Machine learning algorithms can be used to identify ADCS among gastroenterology patients. This can help facilitate the early detection and intervention of psychological disorders in gastroenterology patients' care.

The sluggish pace of new antibacterial drug development reflects a vulnerability in the face of the current severe threat posed by bacterial resistance. Microbial natural products (NPs), as a reservoir of immense chemical potential, have emerged as the most promising avenue for the discovery of next generation antibacterial agent. Directly accessing the antibacterial activity of potential products derived from biosynthetic gene clusters (BGCs) would significantly expedite the process. To tackle this issue, we propose a CSEL-BGC framework that integrates machine learning (ML) techniques. This framework involves the development of a novel cascade-stacking ensemble learning (CSEL) model and the establishment of a groundbreaking model evaluation system. Based on this framework, we predict 6,666 BGCs with antibacterial activity from 3,468 complete bacterial genomes and elucidate a biosynthetic evolutionary landscape to reveal their antibacterial potential. This provides crucial insights for interpretating the synthesis and secretion mechanisms of unknown NPs.

Alzheimer's disease (AD) and vascular dementia (VaD) typically do not exhibit distinct differences in clinical manifestations and auxiliary examination results, which leads to a high misdiagnosis rate. However, significant differences in treatment approaches and prognosis between these two diseases underscore the critical need for an accurate diagnosis of AD and VaD. In this study, serum samples from 33 patients with AD patients, 37 patients with VaD, and 130 healthy individuals were collected, employing near-infrared aquaphotomics technology in combination with deep learning for differential diagnoses. Through an analysis of water absorption patterns among different diseases via aquaphotomics, the efficacies of traditional machine learning methods (Support Vector Machine and Decision Trees) and deep learning approaches (Deep Forest) in modeling were compared. Ultimately, by leveraging feature extraction techniques in conjunction with deep learning, a differential diagnostic model for AD and VaD was successfully developed. The results revealed that aquaphotomics could identify a certain correlation between the number of hydrogen bonds in water molecules and the development of AD and VaD; the deep learning model was found to be superior to traditional machine learning models, achieving an accuracy of 98.67 %, sensitivity of 97.33 %, and specificity of 100.00 %. The bands identified using the Competitive Adaptive Reweighting Algorithm method, primarily located at approximately 1300-1500 nm, showed a significant correlation with water molecules containing four hydrogen bonds. These results highlighted the potential role of the water molecule hydrogen-bond network in disease development and were consistent with the aquaphotomics analysis results. Therefore, the differential diagnostic model developed by integrating near-infrared spectroscopy and deep learning was proven to be effective and feasible, providing accurate and rapid diagnostic methods for AD and VaD diagnoses.

Multi-omics data have revolutionized biomedical research by providing a comprehensive understanding of biological systems and the molecular mechanisms of disease development. However, analyzing multi-omics data is challenging due to high dimensionality and limited sample sizes, necessitating proper data-reduction pipelines to ensure reliable analyses. Additionally, its multimodal nature requires effective data-integration pipelines. While several dimensionality reduction and data fusion algorithms have been proposed, crucial aspects are often overlooked. Specifically, the choice of projection space dimension is typically heuristic and uniformly applied across all omics, neglecting the unique high dimension small sample size challenges faced by individual omics. This paper introduces a novel multi-modal dimensionality reduction pipeline tailored to individual views. By leveraging intrinsic dimensionality estimators, we assess the curse-of-dimensionality impact on each view and propose a two-step reduction strategy for significantly affected views, combining feature selection with feature extraction. Compared to traditional uniform reduction pipelines in a crucial and supervised multi-omics analysis setting, our approach shows significant improvement. Additionally, we explore three effective unsupervised multi-omics data fusion methods rooted in the main data fusion strategies to gain insights into their performance under crucial, yet overlooked, settings.

We propose deep ensemble transformers (DETs), a fast, scalable approach for dimensionality reduction problems. This method leverages the power of deep neural networks and employs cascade ensemble techniques as its fundamental feature extraction tool. To handle high-dimensional data, our approach employs a flexible number of intermediate layers sequentially. These layers progressively transform the input data into decision tree predictions. To further enhance prediction performance, the output from the final intermediate layer is fed through a feed-forward neural network architecture for final prediction. We derive an upper bound of the disparity between the generalization error and the empirical error and demonstrate that it converges to zero. This highlights the generalizability of our method to parameter estimation and feature selection problems. In our experimental evaluations, DETs outperform existing models in terms of prediction accuracy, representation learning ability, and computational time. Specifically, the method achieves over 95% accuracy in gene expression data and can be trained on average 50% faster than traditional artificial neural networks (ANNs).

Enhancers are vital elements in the genome that boost the transcriptional activity of neighboring genes and are essential in regulating cell-specific gene expression. Therefore, accurately identifying and characterizing enhancers is essential for comprehending gene regulatory networks and the development of related diseases. This study introduces MPDL-Enhancer, a novel multi-perspective deep learning framework aimed at enhancer characterization and identification. In this study, enhancer sequences are encoded using the dna2vec model along with features derived from the structural properties of DNA sequences. Subsequently, these representations are processed through a novel dual-scale deep neural network designed to discern subtle correlations and extended interactions embedded within the semantic content of DNA. The predictive phase of our methodology employs a Support Vector Machine classifier to render the final classification. To rigorously assess the efficacy of our approach, a comprehensive evaluation was executed utilizing an independent test dataset, thereby substantiating the robustness and accuracy of our model. Our methodology demonstrated superior performance over existing computational techniques, with an accuracy (ACC) of 81.00 %, a sensitivity (SN) of 79.00 %, and specificity (SP) of 83.00 %. The innovative dual-scale deep neural network and the unique feature representation strategy contributed to this performance improvement. MPDL-Enhancer has effectively characterized enhancer sequences and achieved excellent predictive performance. Building upon this foundation, we conducted an interpretability analysis of the model, which can assist researchers in identifying key features and patterns that affect the functionality of enhancers, thereby promoting a deeper understanding of gene regulatory networks.

Umami peptides have recently gained attention for their ability to enhance umami flavor, reduce salt content, and provide nutritional benefits. However, traditional wet laboratory methods to identify them are time-consuming, laborious, and costly. Therefore, we developed the Umami-gcForest model using the deep forest algorithm. It constructs amino acid feature matrices using ProtBERT, amino acid composition, composition-transition-distribution, and pseudo amino acid composition, applying mutual information for feature selection to optimize dimensions. Compared to other machine learning baseline, umami peptide prediction, and composite models, the validation results of Umami-gcForest on different test sets demonstrated outstanding predictive accuracy. Using SHapley Additive exPlanations to calculate feature contributions, we found that the key features of Umami-gcForest were hydrophobicity, charge, and polarity. Based on this, an online platform was developed to facilitate its user application. In conclusion, Umami-gcForest serves as a powerful tool, providing a solid foundation for the efficient and accurate screening of umami peptides.

Top-down estimates of fossil fuel CO2 (FFCO2) emissions are crucial for tracking emissions and evaluating mitigation strategies. However, their practical application is hindered by limited data coverage and overreliance on NOx-to-CO2 emission ratios from emission inventories. We developed the Machine Learning-Driven Mapping Satellite-based XCO2en (ML-MSXE) model using the column-averaged dry-air mole fraction of CO2 enhancement (XCO2en) derived from OCO-2 and OCO-3 measurements to reconstruct the XCO2en distribution for monitoring FFCO2 emissions. Compared to the previous Machine Learning-Driven Deriving XCO2en from Mapped XCO2 (ML-DXEMX) model, ML-MSXE enhances the utilization of TROPOMI NO2 measurements, increasing their relative contribution from 4.3 to 21.7%, thereby improving XCO2en reconstruction accuracy and enhancing the ability to track emissions. Despite the COVID-19 lockdown, XCO2en levels in China rose from 1.33 ± 1.06 in 2019 to 1.39 ± 1.01 ppm in 2021. In February 2020, while the national average rate of XCO2en decline (16.3%) aligned with the reduction in FFCO2 emissions estimated by inventories, XCO2en further revealed varying rates of decline between cities. Furthermore, the spatial distribution of XCO2en identified hotspots where FFCO2 emissions might be underestimated by inventories. This study presents a space-based approach for monitoring FFCO2 emissions, offering valuable insights for assessing carbon neutrality progress and informing policy.

Deep Forest employs forest structures and leverages deep architecture to learn feature vector information adaptively. However, deep forest-based models have limitations such as manual hyperparameter optimization and time and memory usage inefficiencies. Bayesian optimization is a widely used model-based hyperparameter optimization method. Evolutionary algorithms such as Differential Evolution (DE) have recently been introduced to improve Bayesian optimization's acquisition function. Despite its effectiveness, DE has a significant drawback as it relies on randomly selecting indices from the population of target vectors to construct donor vectors in search of optimal solutions. This randomness is ineffective, as suboptimal or redundant indices may be selected. Therefore, in this research we developed a modified differential evolution (DE) acquisition function for improved host-pathogen protein-protein interaction prediction. The modified DE introduces a weighted and adaptive donor vector technique that selects the best-fitted donor vectors as opposed to the random approach. This modified optimization approach was implemented in a deep forest model for automatic hyperparameter optimization. The performance of the optimized deep forest model was evaluated on human-Plasmodium falciparum protein sequence datasets using 10-fold cross-validation. The results were compared with standard optimization methods such as traditional Bayesian optimization, genetic algorithms, evolutionary strategies, and other machine learning models. The optimized model achieved an accuracy of 89.3 %, outperforming other models across all metrics, including a sensitivity of 85.4 % and a precision of 91.6 %. Additionally, the optimized model predicted seven novel host-pathogen interactions. Finally, the model was implemented as a web application which is accessible at http://dfh3pi.covenantuniversity.edu.ng.

The Leaf Area Index (LAI) is an essential parameter that affects the exchange of energy and materials between the vegetative canopy and the surrounding environment. Estimating LAI using machine learning models with remote sensing data has become a prevalent method for large-scale LAI estimation. However, existing machine learning models have exhibited various flaws, hindering the accurate estimation of LAI. Thus, a new method for large-scale estimation of Dendrocalamus giganteus LAI was proposed, which integrates ICESat-2/ATLAS, and Sentinel-1/-2 data, and refines machine learning models through the application of Bayesian Optimization (BO), Particle Swarm Optimization (PSO), Genetic Algorithms (GA), and Simulated Annealing (SA). First, spatial interpolation was performed using the Sequential Gaussian Conditional Simulation (SGCS) method. Then, multi-source remote sensing data were leveraged to optimize feature variables through the Pearson correlation coefficient approach. Subsequently, optimization algorithms were applied to Random Forest Regression (RFR), Gradient Boosting Regression Tree (GBRT), and Support Vector Machine Regression (SVR) models, leading to efficient large-scale LAI estimation. The results showed that the BO-GBRT model achieved high accuracy in LAI estimation, with a coefficient of determination (R 2) of 0.922, a root mean square error (RMSE) of 0.263, a mean absolute error (MAE) of 0.187, and an overall estimation accuracy (P 1) of 92.38%. Compared to existing machine learning methods, the proposed approach demonstrated superior performance. This method holds significant potential for large-scale forest LAI inversion and can facilitate further research on other forest structure parameters.

Existing assessments might have underappreciated ozone-related health impacts worldwide. Here our study assesses current global ozone pollution using the high-resolution (0.05°) estimation from a geo-ensemble learning model, with key focuses on population exposure and all-cause mortality burden. Our model demonstrates strong performance, achieving a mean bias of less than -1.5 parts per billion against in-situ measurements. We estimate that 66.2% of the global population is exposed to excess ozone for short term (> 30 days per year), and 94.2% suffers from long-term exposure. Furthermore, severe ozone exposure levels are observed in Cropland areas, particularly over Asia. Importantly, the all-cause ozone-attributable deaths significantly surpass previous recognition from specific diseases worldwide. Notably, mid-latitude Asia (30°N) and the western United States show high mortality burden, contributing substantially to global ozone-attributable deaths. Our study highlights current significant global ozone-related health risks and may benefit the ozone-exposed population in the future.

In addressing elderly healthcare issues, cognitive impairment can cause significant disruptions in daily life and may potentially develop into dementia. Thus, finding ways to delay the progression of cognitive impairment is a critical issue.

This study aims to develop an adaptive artificial intelligence (AI) mechanism that creates enjoyable and beneficial content to help delay cognitive impairment in the elderly. Utilising virtual reality (VR) and a fishing game, the design enhances reaction time and attention through interactive fishing activities. The AI personalises content based on individual performance to improve cognitive function.

Experimental results showed that adaptive AI increased participant satisfaction from 86.84 to 91.05 points and future willingness from 75.26 to 85.68 points. The number of fish caught rose from 98 to 120, with the average per participant increasing from 2.64 to 2.85.

This is undoubtedly the trend of the future. VR allows the elderly to have a more impactful and memorable first experience, while AI dynamically adjusts the game's difficulty based on the elderly's performance, addressing the issue of reduced willingness to continue due to inappropriate game difficulty. The VR game developed in this study is designed to be relaxing and incorporates mechanisms to promote the elderly's health. It is not restricted by location or time and, more importantly, meets the health promotion needs of the elderly.

Eye tracking technology has become increasingly important in scientific research and practical applications. In the field of eye tracking research, analysis of eye movement data is crucial, particularly for classifying raw eye movement data into eye movement events. Current classification methods exhibit considerable variation in adaptability across different participants, and it is necessary to address the issues of class imbalance and data scarcity in eye movement classification. In the current study, we introduce a novel eye movement classification method based on cascade forest (EMCCF), which comprises two modules: 1) a feature extraction module that employs a multi-scale time window method to extract features from raw eye movement data; 2) a classification module that innovatively employs a layered ensemble architecture, integrating the cascade forest structure with ensemble learning principles, specifically for eye movement classification. Consequently, EMCCF not only enhanced the accuracy and efficiency of eye movement classification but also represents an advancement in applying ensemble learning techniques within this domain. Furthermore, experimental results indicated that EMCCF outperformed existing deep learning-based classification models in several metrics and demonstrated robust performance across different datasets and participants.

The application of antibody therapeutics is promising in the field of immunotherapy. While, heterologization should be done in most cases before applying the therapeutic antibodies into bodies, e.g., humanization, caninization and felinization for human beings, canine and feline, respectively. Here we report YabXnization, the platform which realizes antibody heterologization on the basis of rational design and artificial intelligence (AI)-assisted computation. YabXnization provides two ways for heterologization: traditional CDR-grafting and backmutation-based rational design; and AI-assisted fusion computational design. Taking humanization as example, both of the two ways first find the proper template for heavy and light chains with CDR-grafting followed. For rational design, bioinformatics analysis-based backmutation is then conducted. For AI-assisted computational design, the backmutation and humanness evaluation are implemented through evolutionary computation framework with DeepForest-based humanness evaluation model and the distance to the previously found human template as objective functions. Finally, the top K heterologized antibodies can be provided by YabXnization platform. We examined the platform with 18 antibodies to be heterologized, in which 10 for humanization, 6 for caninization and 2 for felinization, respectively. The heterologized antibodies were measured by indirect ELISA and BLI(Octet)/SPR(Biacore) binding affinity measurement methods. Test results show a 90% success rate with the binding affinity loss of heterologized antibodies within an order of magnitude compared to the corresponding chimeric antibodies. It even shows an increase in the binding affinity on some of the heterologized antibodies. The platform can be reached through https://www.genscript.com/tools/yabxnization-service.

Copy number variation (CNV) is an essential genetic driving factor of cancer formation and progression, making intelligent classification based on CNV feasible. However, there are a few challenges in the current machine learning and deep learning methods, such as the design of base classifier combination schemes in ensemble methods and the selection of layers of neural networks, which often result in low accuracy. Therefore, an adaptive bilinear dynamic cascade model (Adap-BDCM) is developed to further enhance the accuracy and applicability of these methods for intelligent classification on CNV datasets. In this model, a feature selection module is introduced to mitigate the interference of redundant information, and a bilinear model based on the gated attention mechanism is proposed to extract more beneficial deep fusion features. Furthermore, an adaptive base classifier selection scheme is designed to overcome the difficulty of manually designing base classifier combinations and enhance the applicability of the model. Lastly, a novel feature fusion scheme with an attribute recall submodule is constructed, effectively avoiding getting stuck in local solutions and missing some valuable information. Numerous experiments have demonstrated that our Adap-BDCM model exhibits optimal performance in cancer classification, stage prediction, and recurrence on CNV datasets. This study can assist physicians in making diagnoses faster and better.

Human oral bioavailability is a crucial factor in drug discovery. In recent years, researchers have constructed a variety of different prediction models. However, given the limited size of human oral bioavailability data sets, the challenge of making accurate predictions with small sample sizes has become a critical issue in the field. The deep forest model, with its adaptively determinable number of cascade levels, can perform exceptionally well even on small-scale data. However, the original deep forest suffers unbalanced multi-grained scanning process and premature stopping of cascade forest training. In this paper, we propose a human oral bioavailability predict method based on an improved deep forest, called balanced multi-grained scanning mapping cascade forest (bgmc-forest). Firstly, the mordred descriptor method is selected to feature extraction, then enhanced features are obtained by the improved balanced multi-grained scanning, which solves the problem of missing features at both ends. And finally, the prediction results are obtained by feature mapping cascaded forests, which is based on principal component analysis and cascade forests, ensures the effectiveness of the cascade forest. The superiority of the model constructed in this paper is demonstrated through comparative experiments, while the effectiveness of the improved module is verified through ablation experiments. Finally the decision-making process of the model is explained by the shapley additive explanations interpretation algorithm.

Monitoring China's carbon dioxide (CO2) concentration is essential for formulating effective carbon cycle policies to achieve carbon peaking and neutrality. Despite insufficient satellite observation coverage, this study utilizes high-resolution spatiotemporal data from the Orbiting Carbon Observatory 2 (OCO-2), supplemented with various auxiliary datasets, to estimate full-coverage, monthly, column-averaged carbon dioxide (XCO2) values across China from 2015 to 2022 at a spatial resolution of 0.05° via the deep forest model. The 10-fold cross-validation results indicate a correlation coefficient (R) of 0.95 and a determination coefficient (R²) of 0.90. Validation against ground-based station data yielded R values of 0.93, and R² values reached 0.81. Further validation from the Greenhouse Gases Observing Satellite (GOSAT) and the Copernicus Atmosphere Monitoring Service Reanalysis dataset (CAMS) produced R² values of 0.87 and 0.80, respectively. During the study period, CO2 concentrations in China were higher in spring and winter than in summer and autumn, indicating a clear annual increase. The estimates generated by this study could potentially support CO2 monitoring in China.

Hypertension is a major preventable risk factor for cardiovascular disease, affecting over 1.5 billion adults worldwide. Antihypertensive peptides (AHTPs) have gained attention as a natural therapeutic option with minimal side effects. This study proposes a Deep Forest-based machine learning framework for AHTP prediction, leveraging a multi-granularity cascade structure to enhance classification accuracy. We integrated data from BIOPEP-UWM and three previously used datasets, totaling 2000 peptide sequences, and introduced novel feature extraction methods to build a comprehensive dataset for model training. This study represents the first application of Deep Forest for AHTP identification, demonstrating substantial classification performance advantages over traditional methods (e.g., SVM, CNN, and XGBoost) as well as recent mainstream prediction models (Ensemble-AHTPpred, CNN-SVM Ensemble, and mAHTPred). Requiring no complex manual feature engineering, the model adapts flexibly to various data needs, offering a novel perspective for efficient AHTP prediction and promising utility in hypertension management. On the benchmark dataset, the model achieved high accuracy, sensitivity, and AUC, providing a robust tool for identifying safe and effective AHTPs. However, future efforts should incorporate larger and more diverse independent validation datasets to further improve the model and enhance its generalizability. Additionally, the model's predictive accuracy relies on known AHTP targets and sequence features, potentially limiting its ability to detect AHTPs with uncharacterized or atypical properties.

Unfertilized duck eggs not removed prior to incubation will deteriorate quickly, posing a risk of contaminating the normally fertilized duck eggs. Thus, detecting the fertilization status of breeding duck eggs as early as possible is a meaningful and challenging task. Most existing work usually focus on the characteristics of chicken eggs during mid-term hatching. However, little attention has been paid to the detection for duck eggs prior to incubation. In this paper, we present a novel hybrid deep learning detection framework for the fertilization status of pre-incubation duck eggs, termed CVAE-DF, based on visible/near-infrared (VIS/NIR) transmittance spectroscopy. The framework comprises the encoder of a convolutional variational autoencoder (CVAE) and an improved deep forest (DF) model. More specifically, we first collected transmittance spectral data (400-1000 nm) of 255 duck eggs before hatching. The multiplicative scatter correction (MSC) method was then used to eliminate noise and extraneous information of the raw spectral data. Two efficient data augmentation methods were adopted to provide sufficient data. After that, CVAE was applied to extract representative features and reduce the feature dimension for the detection task. Finally, an improved DF model was employed to build the classification model on the enhanced feature set. The CVAE-DF model achieved an overall accuracy of 95.94 % on the test dataset. These experimental results in terms of four metrics demonstrate that our CVAE-DF method outperforms the traditional methods by a significant margin. Furthermore, the results also indicate that CVAE holds great promise as a novel feature extraction method for the VIS/NIR spectral analysis of other agricultural products. It is extremely beneficial to practical engineering.

The stage prediction of kidney renal clear cell carcinoma (KIRC) is important for the diagnosis, personalized treatment, and prognosis of patients. Many prediction methods have been proposed, but most of them are based on unimodal gene data, and their accuracy is difficult to further improve. Therefore, we propose a novel multi-weighted dynamic cascade forest based on the bilinear feature extraction (MLW-BFECF) model for stage prediction of KIRC using multimodal gene data (RNA-seq, CNA, and methylation). The proposed model utilizes a dynamic cascade framework with shuffle layers to prevent early degradation of the model. In each cascade layer, a voting technique based on three gene selection algorithms is first employed to effectively retain gene features more relevant to KIRC and eliminate redundant information in gene features. Then, two new bilinear models based on the gated attention mechanism are proposed to better extract new intra-modal and inter-modal gene features; Finally, based on the idea of the bagging, a multi-weighted ensemble forest classifiers module is proposed to extract and fuse probabilistic features of the three-modal gene data. A series of experiments demonstrate that the MLW-BFECF model based on the three-modal KIRC dataset achieves the highest prediction performance with an accuracy of 88.9 %.

This article reveals the basic laws of straw supercritical water gasification (SCWG) and provides basic experimental data for the effective utilization of straw. The paper studied the impact of three operational conditions on the production of high-calorific value hydrogen-rich combustible gases through SCWG of straw within a quartz tube reactor. The findings reveal that elevated reaction temperatures, extended residence times, and reduced feedstock concentrations favor the SCWG of straw. When combustible gas contains carbon dioxide, the maximum low heating value (LHV) of the gas is 21 MJ/Nm3. Upon removing carbon dioxide, the LHV of the gas reached 38 MJ/Nm3. Subsequently, a machine learning (ML) model was developed to forecast gas yield and LHV during the SCWG process. The results demonstrate that the model exhibits robust generalization capabilities. ML can be extensively applied to forecast biomass SCWG processes across various operational conditions.

Land Use/ Cover Change (LUCC) plays a crucial role in influencing hydrological processes, nutrient cycling, and sediment transport in watersheds, ultimately impacting water quality on both spatial and temporal scales. Accurately predicting changes in watershed water quality is beneficial for the sustainable management of water resources. Current models often lack the ability to effectively predict water quality changes in a dynamic spatio-temporal context, particularly in complex watershed environments. The overall purpose of the study is to establish a comprehensive and dynamic modeling framework that links LUCC with water quality, allowing for accurate predictions of future water quality under varying land use scenarios. The model, which uses water quality as the dependent variable and LUCC as the independent variable, was developed to quantitatively predict changes in watershed water quality. To achieve this, annual multi-period remote sensing images from Landsat-5, Landsat-8 or Sentinel-2 satellites spanning from 1992 to 2022 were analyzed. Random Forest (achieving a Kappa coefficient of 0.9468) were employed to classify land use within the watershed. Based on classification results, a Cellular Automata-Markov chain model (CA-Markov) was constructed to simulate and predict the spatio-temporal patterns of land use, incorporating driving factors such as proximity to water systems, roads, elevation, and slope. Validation of the model using LUCC data from 2020 yielded a high prediction accuracy with a Kappa coefficient of 0.9505. The CA-Markov model was further utilized to project LUCC under three different scenarios-natural development, ecological protection, and arable land protection-between 2023 and 2033. Based on these projections, the coupled water quality and LUCC model was employed to predict water quality changes in the watershed over the same period. Key findings indicate that water quality is likely to improve under ecological protection scenario, while deterioration is expected under natural development scenario and cropland protection scenario due to urban expansion, agricultural practices, and water diversion for irrigation. This study provides a robust framework for watershed management, offering scientific guidance for source management and water purification efforts, thereby contributing significantly to the sustainable development of water resources.

Generalized Anxiety Disorder (GAD) is a chronic anxiety condition characterized by persistent excessive worry, anxiety, and fear. Current diagnostic practices primarily rely on clinicians' subjective assessments and experience, highlighting a need for more objective and reliable methods. This study collected 10-minute resting-state electroencephalogram (EEG) from 45 GAD patients and 36 healthy controls (HC), focusing on six frontal EEG channels for preprocessing, data segmentation, and frequency band division. Innovatively, this study introduced the "Differential Channel" method, which enhances classification performance by enhancing the information related to anxiety from the data, thereby highlighting signal differences. Utilizing the preprocessed EEG signals, undirected functional connectivity features (Phase Lag Index, Pearson Correlation Coefficient, and Mutual Information) and directed functional connectivity features (Partial Directed Coherence) were extracted. Multiple machine learning models were applied to distinguish between GAD patients and HC. The results show that the Deep Forest classifier achieves excellent performance with a 12-second time window of DiffFeature. In particular, the classification of GAD and HC was successfully obtained by combining OriFeature and DiffFeature on Mutual Information with a maximum accuracy of 98.08%. Furthermore, it was observed that undirected functional connectivity features significantly outperformed directed functional connectivity when fewer frontal channels were used. Overall, the methodologies developed in this study offer accurate and practical identification strategies for the early screening and clinical diagnosis of GAD, offering the necessary theoretical and technical support for further enhancing the portability of EEG devices.

The pathogenesis of cancer is complex, involving abnormalities in some genes in organisms. Accurately identifying cancer genes is crucial for the early detection of cancer and personalized treatment, among other applications. Recent studies have used graph deep learning methods to identify cancer driver genes based on biological networks. However, incompleteness and the noise of the networks will weaken the performance of models. To address this, we propose a cancer driver gene identification method based on self-supervision for graph convolutional networks, which can efficiently enhance the structure of the network and further improve predictive accuracy. The reliability of SSCI is verified by the area under the receiver operating characteristic curves (AUROC), the area under the precision-recall curves (AUPRC), and the F1 score, with respective values of 0.966, 0.964, and 0.913. The results show that our method can identify cancer driver genes with strong discriminative power and biological interpretability.

The gut microbiota plays a vital role in human health, and significant effort has been made to predict human phenotypes, especially diseases, with the microbiota as a promising indicator or predictor with machine learning (ML) methods. However, the accuracy is impacted by a lot of factors when predicting host phenotypes with the metagenomic data, e.g. small sample size, class imbalance, high-dimensional features, etc. To address these challenges, we propose MicroHDF, an interpretable deep learning framework to predict host phenotypes, where a cascade layers of deep forest units is designed for handling sample class imbalance and high dimensional features. The experimental results show that the performance of MicroHDF is competitive with that of existing state-of-the-art methods on 13 publicly available datasets of six different diseases. In particular, it performs best with the area under the receiver operating characteristic curve of 0.9182 ± 0.0098 and 0.9469 ± 0.0076 for inflammatory bowel disease (IBD) and liver cirrhosis, respectively. Our MicroHDF also shows better performance and robustness in cross-study validation. Furthermore, MicroHDF is applied to two high-risk diseases, IBD and autism spectrum disorder, as case studies to identify potential biomarkers. In conclusion, our method provides an effective and reliable prediction of the host phenotype and discovers informative features with biological insights.

Traffic-related air pollution (TRAP) is a major contributor to urban pollution and varies sharply at the street level, posing a challenge for air quality modeling. Traditional land use regression models combined with data from fixed monitoring stations may be unable to predict and characterize fine-scale TRAP, especially in complex urban environments influenced by various features. This study aims to estimate fine-scale (50 m) concentrations of nitrogen oxides (NO and NO₂) in Hong Kong using a deep learning (DL) structured model.

We collected data from mobile air quality sensors on buses and crowd-sourced Google real-time traffic status as a proxy for real-time traffic emissions. Our DL model was compared with existing machine learning models to assess performance improvements. Using an interpretable machine learning method, we hierarchically evaluated the global, local, and interaction effects for different features.

Our DL model outperformed existing machine learning models, achieving R2 values of 0.72 for NO and 0.69 for NO₂. The incorporation of traffic status as a key predictor improved model performance by 9% to 17%. The interpretable machine learning method revealed the importance of traffic-related features and their pairwise interactions.

The results indicate that traffic-related features significantly contribute to TRAP and provide insights and guidance for urban planning. By incorporating crowd-sourced Google traffic information, we assessed traffic abatement scenarios that could inform targeted strategies for improving urban air quality.

Soil organic carbon (SOC) is the largest carbon pool in terrestrial ecosystems and plays a crucial role in mitigating climate change and enhancing soil productivity. Microbial-derived carbon (MDC) is the main component of the persistent SOC pool. However, current formulas used to estimate the proportional contribution of MDC are plagued by uncertainties due to limited sample sizes and the neglect of bacterial group composition effects. Here, we compiled the comprehensive global dataset and employed machine learning approaches to refine our quantitative understanding of MDC contributions to total carbon storage. Our efforts resulted in a reduction in the relative standard errors in prevailing estimations by an average of 71% and minimized the effect of global variations in bacterial group compositions on estimating MDC. Our estimation indicates that MDC contributes approximately 758 Pg, representing approximately 40% of the global soil carbon stock. Our study updated the formulas of MDC estimation with improving the accuracy and preserving simplicity and practicality. Given the unique biochemistry and functioning of the MDC pool, our study has direct implications for modeling efforts and predicting the land-atmosphere carbon balance under current and future climate scenarios.

Anticancer peptides (ACPs) perform a promising role in discovering anti-cancer drugs. The growing research on ACPs as therapeutic agent is increasing due to its minimal side effects. However, identifying novel ACPs using wet-lab experiments are generally time-consuming, labor-intensive, and expensive. Leveraging computational methods for fast and accurate prediction of ACPs would harness the drug discovery process. Herein, a machine learning-based predictor, called PLMACPred, is developed for identifying ACPs from peptide sequence only. PLMACPred adopted a set of encoding schemes representing evolutionary-property, composition-property, and protein language model (PLM), i.e., evolutionary scale modeling (ESM-2)- and ProtT5-based embedding to encode peptides. Then, two-dimensional (2D) wavelet denoising (WD) was employed to remove the noise from extracted features. Finally, ensemble-based cascade deep forest (CDF) model was developed to identify ACP. PLMACPred model attained superior performance on all three benchmark datasets, namely, ACPmain, ACPAlter, and ACP740 over tenfold cross validation and independent dataset. PLMACPred outperformed the existing models and improved the prediction accuracy by 18.53%, 2.4%, 7.59% on ACPmain, ACPalter, ACP740 dataset, respectively. We showed that embedding from ProtT5 and ESM-2 was capable of capturing better contextual information from the entire sequence than the other encoding schemes for ACP prediction. For the explainability of proposed model, SHAP (SHapley Additive exPlanations) method was used to analyze the feature effect on the ACP prediction. A list of novel sequence motifs was proposed from the ACP sequence using MEME suites. We believe, PLMACPred will support in accelerating the discovery of novel ACPs as well as other activities of microbial peptides.

The identification of cancer subtypes plays a very important role in the field of medicine. Accurate identification of cancer subtypes is helpful for both cancer treatment and prognosis Currently, most methods for cancer subtype identification are based on single-omics data, such as gene expression data. However, multi-omics data can show various characteristics about cancer, which also can improve the accuracy of cancer subtype identification. Therefore, how to extract features from multi-omics data for cancer subtype identification is the main challenge currently faced by researchers. In this paper, we propose a cancer subtype identification method named CAEM-GBDT, which takes gene expression data, miRNA expression data, and DNA methylation data as input, and adopts convolutional autoencoder network to identify cancer subtypes. Through a convolutional encoder layer, the method performs feature extraction on the input data. Within the convolutional encoder layer, a convolutional self-attention module is embedded to recognize higher-level representations of the multi-omics data. The extracted high-level representations from the convolutional encoder are then concatenated with the input to the decoder. The GBDT (Gradient Boosting Decision Tree) is utilized for cancer subtype identification. In the experiments, we compare CAEM-GBDT with existing cancer subtype identifying methods. Experimental results demonstrate that the proposed CAEM-GBDT outperforms other methods. The source code is available from GitHub at https://github.com/gxh-1/CAEM-GBDT.git.

The misuse of antitussives preparations is a continuing problem in the world, and imply that they might have potential new psychoactive substances (NPS) activity. However, few study focus on their ecological toxicity towards fish. In the present study, the machine learning (ML) methods gcForest and random forest (RF) were employed to predict NPS activity in 30 antitussives. The potential toxic target, mode of action (MOA), acute toxicity and chronic toxicity to fish were further investigated. The results showed that both gcForest and RF achieved optimal performance when utilizing combined features of molecular fingerprint (MF) and molecular descriptor (MD), with area under the curve (AUC) = 0.99, accuracy >0.94 and f1 score > 0.94, and were applied to screen the NPS activity in antitussives. A total of 15 antitussives exhibited potential NPS activity, including frequently-used substances like codeine and dextromethorphan. The binding affinity of these antitussives with zebrafish dopamine transporter (zDAT) was high, and even surpassing that of some traditional narcotics and NPS. Some antitussives formed hydrogen bonds or salt bridges with aspartate (Asp) 95, tyrosine (Tyr) 171 of zDAT. For the ecotoxicity, the MOA of these 15 antitussives in fish was predicted as narcosis. The prenoxdiazin, pholcodine, codeine, dextromethorphan and dextrorphan exhibited very toxic/toxic to fish. It was necessary to pay close attention to the ecotoxicity of these antitussives. In this study, the integration of ML, molecular docking and ECOSAR approaches are powerful tools for understanding the toxicity profiles and ecological hazards posed by new pollutants.

Deep random forest (DRF), which combines deep learning and random forest, exhibits comparable accuracy, interpretability, low memory and computational overhead to deep neural networks (DNNs) in edge intelligence tasks. However, efficient DRF accelerator is lagging behind its DNN counterparts. The key to DRF acceleration lies in realizing the branch-split operation at decision nodes. In this work, we propose implementing DRF through associative searches realized with ferroelectric analog content addressable memory (ACAM). Utilizing only two ferroelectric field effect transistors (FeFETs), the ultra-compact ACAM cell performs energy-efficient branch-split operations by storing decision boundaries as analog polarization states in FeFETs. The DRF accelerator architecture and its model mapping to ACAM arrays are presented. The functionality, characteristics, and scalability of the FeFET ACAM DRF and its robustness against FeFET device non-idealities are validated in experiments and simulations. Evaluations show that the FeFET ACAM DRF accelerator achieves ∼106×/10× and ∼106×/2.5× improvements in energy and latency, respectively, compared to other DRF hardware implementations on state-of-the-art CPU/ReRAM.

Dexterous control of robot hands requires a robust neural-machine interface capable of accurately decoding multiple finger movements. Existing studies primarily focus on single-finger movement or rely heavily on multi-finger data for decoder training, which requires large datasets and high computation demand. In this study, we investigated the feasibility of using limited single-finger surface electromyogram (sEMG) data to train a neural decoder capable of predicting the forces of unseen multi-finger combinations.

We developed a deep forest-based neural decoder to concurrently predict the extension and flexion forces of three fingers (index, middle, and ring-pinky). We trained the model using varying amounts of high-density EMG data in a limited condition (i.e., single-finger data).

We showed that the deep forest decoder could achieve consistently commendable performance with 7.0% of force prediction errors and R2 value of 0.874, significantly surpassing the conventional EMG amplitude method and convolutional neural network approach. However, the deep forest decoder accuracy degraded when a smaller amount of data was used for training and when the testing data became noisy.

The deep forest decoder shows accurate performance in multi-finger force prediction tasks. The efficiency aspect of the deep forest lies in the short training time and small volume of training data, which are two critical factors in current neural decoding applications.

This study offers insights into efficient and accurate neural decoder training for advanced robotic hand control, which has the potential for real-life applications during human-machine interactions.

As an autoimmune-mediated inflammatory demyelinating disease of the central nervous system, multiple sclerosis (MS) is often confused with cerebral small vessel disease (cSVD), which is a regional pathological change in brain tissue with unknown pathogenesis. This is due to their similar clinical presentations and imaging manifestations. That misdiagnosis can significantly increase the occurrence of adverse events. Delayed or incorrect treatment is one of the most important causes of MS progression. Therefore, the development of a practical diagnostic imaging aid could significantly reduce the risk of misdiagnosis and improve patient prognosis. We propose an interpretable deep learning (DL) model that differentiates MS and cSVD using T2-weighted fluid-attenuated inversion recovery (FLAIR) images. Transfer learning (TL) was utilized to extract features from the ImageNet dataset. This pioneering model marks the first of its kind in neuroimaging, showing great potential in enhancing differential diagnostic capabilities within the field of neurological disorders. Our model extracts the texture features of the images and achieves more robust feature learning through two attention modules. The attention maps provided by the attention modules provide model interpretation to validate model learning and reveal more information to physicians. Finally, the proposed model is trained end-to-end using focal loss to reduce the influence of class imbalance. The model was validated using clinically diagnosed MS (n=112) and cSVD (n=321) patients from the Beijing Tiantan Hospital. The performance of the proposed model was better than that of two commonly used DL approaches, with a mean balanced accuracy of 86.06 % and a mean area under the receiver operating characteristic curve of 98.78 %. Moreover, the generated attention heat maps showed that the proposed model could focus on the lesion signatures in the image. The proposed model provides a practical diagnostic imaging aid for the use of routinely available imaging techniques such as magnetic resonance imaging to classify MS and cSVD by linking DL to human brain disease. We anticipate a substantial improvement in accurately distinguishing between various neurological conditions through this novel model.

The emergence and spread of antibiotic-resistant bacteria pose a significant public health threat, necessitating the exploration of alternative antibacterial strategies. Antibacterial peptide (ABP) is a kind of antimicrobial peptide (AMP) that has the potential ability to fight against bacteria infection, offering a promising avenue for developing novel therapeutic interventions. This study introduces AMPActiPred, a three-stage computational framework designed to identify ABPs, characterize their activity against diverse bacterial species, and predict their activity levels. AMPActiPred employed multiple effective peptide descriptors to effectively capture the compositional features and physicochemical properties of peptides. AMPActiPred utilized deep forest architecture, a cascading architecture similar to deep neural networks, capable of effectively processing and exploring original features to enhance predictive performance. In the first stage, AMPActiPred focuses on ABP identification, achieving an Accuracy of 87.6% and an MCC of 0.742 on an elaborate dataset, demonstrating state-of-the-art performance. In the second stage, AMPActiPred achieved an average GMean at 82.8% in identifying ABPs targeting 10 bacterial species, indicating AMPActiPred can achieve balanced predictions regarding the functional activity of ABP across this set of species. In the third stage, AMPActiPred demonstrates robust predictive capabilities for ABP activity levels with an average PCC of 0.722. Furthermore, AMPActiPred exhibits excellent interpretability, elucidating crucial features associated with antibacterial activity. AMPActiPred is the first computational framework capable of predicting targets and activity levels of ABPs. Finally, to facilitate the utilization of AMPActiPred, we have established a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼AMPActiPred/.

Modern society increasingly recognizes brain fatigue as a critical factor affecting human health and productivity. This study introduces a novel, portable, cost-effective, and user-friendly system for real-time collection, monitoring, and analysis of physiological signals aimed at enhancing the precision and efficiency of brain fatigue recognition and broadening its application scope. Utilizing raw physiological data, this study constructed a compact dataset that incorporated EEG and ECG data from 20 subjects to index fatigue characteristics. By employing a Bayesian-optimized multi-granularity cascade forest (Bayes-gcForest) for fatigue state recognition, this study achieved recognition rates of 95.71% and 96.13% on the DROZY public dataset and constructed dataset, respectively. These results highlight the effectiveness of the multi-modal feature fusion model in brain fatigue recognition, providing a viable solution for cost-effective and efficient fatigue monitoring. Furthermore, this approach offers theoretical support for designing rest systems for researchers.

Drug targets in living beings perform pivotal roles in the discovery of potential drugs. Conventional wet-lab characterization of drug targets is although accurate but generally expensive, slow, and resource intensive. Therefore, computational methods are highly desirable as an alternative to expedite the large-scale identification of druggable proteins (DPs); however, the existing in silico predictor's performance is still not satisfactory.

In this study, we developed a novel deep learning-based model DPI_CDF for predicting DPs based on protein sequence only. DPI_CDF utilizes evolutionary-based (i.e., histograms of oriented gradients for position-specific scoring matrix), physiochemical-based (i.e., component protein sequence representation), and compositional-based (i.e., normalized qualitative characteristic) properties of protein sequence to generate features. Then a hierarchical deep forest model fuses these three encoding schemes to build the proposed model DPI_CDF.

The empirical outcomes on 10-fold cross-validation demonstrate that the proposed model achieved 99.13 % accuracy and 0.982 of Matthew's-correlation-coefficient (MCC) on the training dataset. The generalization power of the trained model is further examined on an independent dataset and achieved 95.01% of maximum accuracy and 0.900 MCC. When compared to current state-of-the-art methods, DPI_CDF improves in terms of accuracy by 4.27% and 4.31% on training and testing datasets, respectively. We believe, DPI_CDF will support the research community to identify druggable proteins and escalate the drug discovery process.

The benchmark datasets and source codes are available in GitHub: http://github.com/Muhammad-Arif-NUST/DPI_CDF .

Phosphorylation is the most important and studied post-translational modification (PTM), which plays a crucial role in protein function studies and experimental design. Many significant studies have been performed to predict phosphorylation sites using various machine-learning methods. Recently, several studies have claimed that deep learning-based methods are the best way to predict the phosphorylation sites because deep learning as an advanced machine learning method can automatically detect complex representations of phosphorylation patterns from raw sequences and thus offers a powerful tool to improve phosphorylation site prediction. In this study, we report DF-Phos, a new phosphosite predictor based on the Deep Forest to predict phosphorylation sites. In DF-Phos, the feature vector taken from the CkSAApair method is as input for a Deep Forest framework for predicting phosphorylation sites. The results of 10-fold cross-validation show that the Deep Forest method has the highest performance among other available methods. We implemented a Python program of DF-Phos, which is freely available for non-commercial use at https://github.com/zahiriz/DF-Phos Moreover, users can use it for various PTM predictions.