Accurate prediction of discontinuous crack paths in random porous media via a generative deep learning model.

Pore structures provide extra freedoms for the design of porous media, leading to desirable properties, such as high catalytic rate, energy storage efficiency, and specific strength. This unfortunately makes the porous media susceptible to failure. Deep understanding of the failure mechanism in microstructures is a key to customizing high-performance crack-resistant porous media. However, solving the fracture problem of the porous materials is computationally intractable due to the highly complicated configurations of microstructures. To bridge the structural configurations and fracture responses of random porous media, a unique generative deep learning model is developed. A two-step strategy is proposed to deconstruct the fracture process, which sequentially corresponds to elastic deformation and crack propagation. The geometry of microstructure is translated into a scalar of elastic field as an intermediate variable, and then, the crack path is predicted. The neural network precisely characterizes the strong interactions among pore structures, the multiscale behaviors of fracture, and the discontinuous essence of crack propagation. Crack paths in random porous media are accurately predicted by simply inputting the images of targets, without inputting any additional input physical information. The prediction model enjoys an outstanding performance with a prediction accuracy of 90.25% and possesses a robust generalization capability. The accuracy of the present model is a record so far, and the prediction is accomplished within a second. This study opens an avenue to high-throughput evaluation of the fracture behaviors of heterogeneous materials with complex geometries.

Prediction of protein-ligand binding affinity via deep learning models.

Accurately predicting the binding affinity between proteins and ligands is crucial in drug screening and optimization, but it is still a challenge in computer-aided drug design. The recent success of AlphaFold2 in predicting protein structures has brought new hope for deep learning (DL) models to accurately predict protein-ligand binding affinity. However, the current DL models still face limitations due to the low-quality database, inaccurate input representation and inappropriate model architecture. In this work, we review the computational methods, specifically DL-based models, used to predict protein-ligand binding affinity. We start with a brief introduction to protein-ligand binding affinity and the traditional computational methods used to calculate them. We then introduce the basic principles of DL models for predicting protein-ligand binding affinity. Next, we review the commonly used databases, input representations and DL models in this field. Finally, we discuss the potential challenges and future work in accurately predicting protein-ligand binding affinity via DL models.

DeepGRNCS: deep learning-based framework for jointly inferring gene regulatory networks across cell subpopulations.

Inferring gene regulatory networks (GRNs) allows us to obtain a deeper understanding of cellular function and disease pathogenesis. Recent advances in single-cell RNA sequencing (scRNA-seq) technology have improved the accuracy of GRN inference. However, many methods for inferring individual GRNs from scRNA-seq data are limited because they overlook intercellular heterogeneity and similarities between different cell subpopulations, which are often present in the data. Here, we propose a deep learning-based framework, DeepGRNCS, for jointly inferring GRNs across cell subpopulations. We follow the commonly accepted hypothesis that the expression of a target gene can be predicted based on the expression of transcription factors (TFs) due to underlying regulatory relationships. We initially processed scRNA-seq data by discretizing data scattering using the equal-width method. Then, we trained deep learning models to predict target gene expression from TFs. By individually removing each TF from the expression matrix, we used pre-trained deep model predictions to infer regulatory relationships between TFs and genes, thereby constructing the GRN. Our method outperforms existing GRN inference methods for various simulated and real scRNA-seq datasets. Finally, we applied DeepGRNCS to non-small cell lung cancer scRNA-seq data to identify key genes in each cell subpopulation and analyzed their biological relevance. In conclusion, DeepGRNCS effectively predicts cell subpopulation-specific GRNs. The source code is available at https://github.com/Nastume777/DeepGRNCS.

MFD-GDrug: multimodal feature fusion-based deep learning for GPCR-drug interaction prediction.

The accurate identification of drug-protein interactions (DPIs) is crucial in drug development, especially concerning G protein-coupled receptors (GPCRs), which are vital targets in drug discovery. However, experimental validation of GPCR-drug pairings is costly, prompting the need for accurate predictive methods. To address this, we propose MFD-GDrug, a multimodal deep learning model. Leveraging the ESM pretrained model, we extract protein features and employ a CNN for protein feature representation. For drugs, we integrated multimodal features of drug molecular structures, including three-dimensional features derived from Mol2vec and the topological information of drug graph structures extracted through Graph Convolutional Neural Networks (GCN). By combining structural characterizations and pretrained embeddings, our model effectively captures GPCR-drug interactions. Our tests on leading GPCR-drug interaction datasets show that MFD-GDrug outperforms other methods, demonstrating superior predictive accuracy.

An artificial intelligence-enabled electrocardiogram algorithm for the prediction of left atrial low-voltage areas in persistent atrial fibrillation.

OBJECTIVES: We aimed to construct an artificial intelligence-enabled electrocardiogram (ECG) algorithm that can accurately predict the presence of left atrial low-voltage areas (LVAs) in patients with persistent atrial fibrillation. METHODS: The study included 587 patients with persistent atrial fibrillation who underwent catheter ablation procedures between March 2012 and December 2023 and 942 scanned images of 12-lead ECGs obtained before the ablation procedures were performed. Artificial intelligence-based algorithms were used to construct models for predicting the presence of LVAs. The DR-FLASH and APPLE clinical scores for LVA prediction were calculated. We used a receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis to evaluate model performance. RESULTS: The data obtained from the participants were split into training (n = 469), validation (n = 58), and test sets (n = 60). LVAs were detected in 53.7% of all participants. Using ECG alone, the deep learning algorithm achieved an area under the ROC curve (AUROC) of 0.752, outperforming both the DR-FLASH score (AUROC = 0.610) and the APPLE score (AUROC = 0.510). The random forest classification model, which integrated a probabilistic deep learning model and clinical features, showed a maximum AUROC of 0.759. Moreover, the ECG-based deep learning algorithm for predicting extensive LVAs achieved an AUROC of 0.775, with a sensitivity of 0.816 and a specificity of 0.896. The random forest classification model for predicting extensive LVAs achieved an AUROC of 0.897, with a sensitivity of 0.862, and a specificity of 0.935. CONCLUSION: The deep learning model based exclusively on ECG data and the machine learning model that combined a probabilistic deep learning model and clinical features both predicted the presence of LVAs with a higher degree of accuracy than the DR-FLASH and the APPLE risk scores.

Artificial intelligence evaluation of coronary computed tomography angiography for coronary stenosis classification and diagnosis.

BACKGROUND: Ruling out obstructive coronary artery disease (CAD) using coronary computed tomography angiography (CCTA) is time-consuming and challenging. This study developed a deep learning (DL) model to assist in detecting obstructive CAD on CCTA to streamline workflows. METHODS: In total, 2929 DICOM files and 7945 labels were extracted from curved planar reformatted CCTA images. A modified Inception V3 model was adopted. To validate the artificial intelligence (AI) model, two cardiologists labelled and adjudicated the classification of coronary stenosis on CCTA. The model was trained to differentiate the coronary artery into binary stenosis classifications <50% and ≥50% stenosis. Using the quantitative coronary angiography (QCA) consensus results as a reference standard, the performance of the AI model and CCTA radiology readers was compared by calculating Cohen's kappa coefficients at patient and vessel levels. The net reclassification index was used to evaluate the net benefit of the DL model. RESULTS: The diagnostic accuracy of the AI model was 92.3% and 88.4% at the patient and vessel levels, respectively. Compared with CCTA radiology readers, the AI model had a better agreement for binary stenosis classification at both patient and vessel levels (Cohen kappa coefficient: .79 vs. .39 and .77 vs. .40, p < .0001). The AI model also exhibited significantly improved model discrimination and reclassification (Net reclassification index = .350; Z = 4.194; p < .001). CONCLUSIONS: The developed AI model identified obstructive CAD, and the model results correlated well with QCA results. Incorporating the model into the reporting system of CCTA may improve workflows.

Improved pregnancy prediction performance in an updated deep-learning embryo selection model: a retrospective independent validation study.

RESEARCH QUESTION: What is the effect of increasing training data on the performance of ongoing pregnancy prediction after single vitrified-warmed blastocyst transfer (SVBT) in a deep-learning model? DESIGN: A total of 3960 SVBT cycles were retrospectively analysed. Embryos were stratified according to the Society for Assisted Reproductive Technology age groups. Embryos were scored by deep-learning models iDAScore v1.0 (IDA-V1) and iDAScore v2.0 (IDA-V2) (15% more training data than v1.0) and by Gardner grading. The discriminative performance of the pregnancy prediction for each embryo scoring model was compared using the area under the curve (AUC) of the receiver operating characteristic curve for each maternal age group. RESULTS: The AUC of iDA-V2, iDA-V1 and Gardener grading in all cohort were 0.736, 0.720 and 0.702, respectively. iDA-V2 was significantly higher than iDA-V1 and Gardener grading (P < 0.0001). Group > 35 years (n = 757): the AUC of iDA-V2 was significantly higher than Gardener grading (0.718 versus 0.694, P = 0.015); group aged 35-37 years (n = 821), the AUC of iDA-V2 was significantly higher than iDA-V1 (0.712 versus 0.696, P = 0.035); group aged 41-42 years (n = 715, the AUC of iDA-V2 was significantly higher than Gardener grading (0.745 versus 0.696, P = 0.007); group > 42 years (n = 660) and group aged 38-40 years (n = 1007), no significant differences were found between the groups. CONCLUSION: The performance of deep learning models for pregnancy prediction will be improved by increasing the size of the training data.

Enhancing resolution and contrast in fibre bundle-based fluorescence microscopy using generative adversarial network.

Fibre bundle (FB)-based endoscopes are indispensable in biology and medical science due to their minimally invasive nature. However, resolution and contrast for fluorescence imaging are limited due to characteristic features of the FBs, such as low numerical aperture (NA) and individual fibre core sizes. In this study, we improved the resolution and contrast of sample fluorescence images acquired using in-house fabricated high-NA FBs by utilising generative adversarial networks (GANs). In order to train our deep learning model, we built an FB-based multifocal structured illumination microscope (MSIM) based on a digital micromirror device (DMD) which improves the resolution and the contrast substantially compared to basic FB-based fluorescence microscopes. After network training, the GAN model, employing image-to-image translation techniques, effectively transformed wide-field images into high-resolution MSIM images without the need for any additional optical hardware. The results demonstrated that GAN-generated outputs significantly enhanced both contrast and resolution compared to the original wide-field images. These findings highlight the potential of GAN-based models trained using MSIM data to enhance resolution and contrast in wide-field imaging for fibre bundle-based fluorescence microscopy. Lay Description: Fibre bundle (FB) endoscopes are essential in biology and medicine but suffer from limited resolution and contrast for fluorescence imaging. Here we improved these limitations using high-NA FBs and generative adversarial networks (GANs). We trained a GAN model with data from an FB-based multifocal structured illumination microscope (MSIM) to enhance resolution and contrast without additional optical hardware. Results showed significant enhancement in contrast and resolution, showcasing the potential of GAN-based models for fibre bundle-based fluorescence microscopy.

Mining and rational design of psychrophilic catalases using metagenomics and deep learning models.

A complete catalase-encoding gene, designated soiCat1, was obtained from soil samples via metagenomic sequencing, assembly, and gene prediction. soiCat1 showed 73% identity to a catalase-encoding gene of Mucilaginibacter rubeus strain P1, and the amino acid sequence of soiCAT1 showed 99% similarity to the catalase of a psychrophilic bacterium, Pedobacter cryoconitis. soiCAT1 was identified as a psychrophilic enzyme due to the low optimum temperature predicted by the deep learning model Preoptem, which was subsequently validated through analysis of enzymatic properties. Experimental results showed that soiCAT1 has a very narrow range of optimum temperature, with maximal specific activity occurring at the lowest test temperature (4 °C) and decreasing with increasing reaction temperature from 4 to 50 °C. To rationally design soiCAT1 with an improved temperature range, soiCAT1 was engineered through site-directed mutagenesis based on molecular evolution data analyzed through position-specific amino acid possibility calculation. Compared with the wild type, one mutant, soiCAT1S205K, exhibited an extended range of optimum temperature ranging from 4 to 20 °C. The strategies used in this study may shed light on the mining of genes of interest and rational design of desirable proteins. KEY POINTS: • Numerous putative catalases were mined from soil samples via metagenomics. • A complete sequence encoding a psychrophilic catalase was obtained. • A mutant psychrophilic catalase with an extended range of optimum temperature was engineered through site-directed mutagenesis.

Discovery of novel Akt1 inhibitors by an ensemble-based virtual screening method, molecular dynamics simulation, and in vitro biological activity testing.

Akt1, as an important member of the Akt family, plays a controlled role in cancer cell growth and survival. Inhibition of Akt1 activity can promote cancer cell apoptosis and inhibit tumor growth. Therefore, in this investigation, a multilayer virtual screening approach, including receptor-ligand interaction-based pharmacophore, 3D-QSAR, molecular docking, and deep learning methods, was utilized to construct a virtual screening platform for Akt1 inhibitors. 17 representative compounds with different scaffolds were identified as potential Akt1 inhibitors from three databases. Among these 17 compounds, the Hit9 exhibited the best inhibitory activity against Akt1 with inhibition rate of 33.08% at concentration of 1 µM. The molecular dynamics simulations revealed that Hit9 and Akt1 could form a compact and stable complex. Moreover, Hit9 interacted with some key residues by hydrophobic, electrostatic, and hydrogen bonding interactions and induced substantial conformation changes in the hinge region of the Akt1 active site. The average binding free energies for the Akt1-CQU, Akt1-Ipatasertib, and Akt1-Hit9 systems were - 34.44, - 63.37, and - 39.14 kJ mol-1, respectively. In summary, the results obtained in this investigation suggested that Hit9 with novel scaffold may be a promising lead compound for developing new Akt1 inhibitor for treatment of various cancers with Akt1 overexpressed.

Prediction of Arteriovenous Access Dysfunction by Mel Spectrogram-based Deep Learning Model.

Background: The early detection of arteriovenous (AV) access dysfunction is crucial for maintaining the patency of vascular access. This study aimed to use deep learning to predict AV access malfunction necessitating further vascular management. Methods: This prospective cohort study enrolled prevalent hemodialysis (HD) patients with an AV fistula or AV graft from a single HD center. Their AV access bruit sounds were recorded weekly using an electronic stethoscope from three different sites (arterial needle site, venous needle site, and the midpoint between the arterial and venous needle sites) before HD sessions. The audio signals were converted to Mel spectrograms using Fourier transformation and utilized to develop deep learning models. Three deep learning models, (1) Convolutional Neural Network (CNN), (2) Convolutional Recurrent Neural Network (CRNN), and (3) Vision Transformers-Gate Recurrent Unit (ViT-GRU), were trained and compared to predict the likelihood of dysfunctional AV access. Results: Total 437 audio recordings were obtained from 84 patients. The CNN model outperformed the other models in the test set, with an F1 score of 0.7037 and area under the receiver operating characteristic curve (AUROC) of 0.7112. The Vit-GRU model had high performance in out-of-fold predictions, with an F1 score of 0.7131 and AUROC of 0.7745, but low generalization ability in the test set, with an F1 score of 0.5225 and AUROC of 0.5977. Conclusions: The CNN model based on Mel spectrograms could predict malfunctioning AV access requiring vascular intervention within 10 days. This approach could serve as a useful screening tool for high-risk AV access.

Crosslinked-hybrid nanoparticle embedded in thermogel for sustained co-delivery to inner ear.

Treatment-induced ototoxicity and accompanying hearing loss are a great concern associated with chemotherapeutic or antibiotic drug regimens. Thus, prophylactic cure or early treatment is desirable by local delivery to the inner ear. In this study, we examined a novel way of intratympanically delivered sustained nanoformulation by using crosslinked hybrid nanoparticle (cHy-NPs) in a thermoresponsive hydrogel i.e. thermogel that can potentially provide a safe and effective treatment towards the treatment-induced or drug-induced ototoxicity. The prophylactic treatment of the ototoxicity can be achieved by using two therapeutic molecules, Flunarizine (FL: T-type calcium channel blocker) and Honokiol (HK: antioxidant) co-encapsulated in the same delivery system. Here we investigated, FL and HK as cytoprotective molecules against cisplatin-induced toxic effects in the House Ear Institute - Organ of Corti 1 (HEI-OC1) cells and in vivo assessments on the neuromast hair cell protection in the zebrafish lateral line. We observed that cytotoxic protective effect can be enhanced by using FL and HK in combination and developing a robust drug delivery formulation. Therefore, FL-and HK-loaded crosslinked hybrid nanoparticles (FL-cHy-NPs and HK-cHy-NPs) were synthesized using a quality-by-design approach (QbD) in which design of experiment-central composite design (DoE-CCD) following the standard least-square model was used for nanoformulation optimization. The physicochemical characterization of FL and HK loaded-NPs suggested the successful synthesis of spherical NPs with polydispersity index < 0.3, drugs encapsulation (> 75%), drugs loading (~ 10%), stability (> 2 months) in the neutral solution, and appropriate cryoprotectant selection. We assessed caspase 3/7 apopototic pathway in vitro that showed significantly reduced signals of caspase 3/7 activation after the FL-cHy-NPs and HK-cHy-NPs (alone or in combination) compared to the CisPt. The final formulation i.e. crosslinked-hybrid-nanoparticle-embedded-in-thermogel was developed by incorporating drug-loaded cHy-NPs in poloxamer-407, poloxamer-188, and carbomer-940-based hydrogel. A combination of artificial intelligence (AI)-based qualitative and quantitative image analysis determined the particle size and distribution throughout the visible segment. The developed formulation was able to release the FL and HK for at least a month. Overall, a highly stable nanoformulation was successfully developed for combating treatment-induced or drug-induced ototoxicity via local administration to the inner ear.

Application of deep learning for automated diagnosis and classification of hip dysplasia on plain radiographs.

BACKGROUND: Hip dysplasia is a condition where the acetabulum is too shallow to support the femoral head and is commonly considered a risk factor for hip osteoarthritis. The objective of this study was to develop a deep learning model to diagnose hip dysplasia from plain radiographs and classify dysplastic hips based on their severity. METHODS: We collected pelvic radiographs of 571 patients from two single-center cohorts and one multicenter cohort. The radiographs were split in half to create hip radiographs (n = 1022). One orthopaedic surgeon and one resident assessed the radiographs for hip dysplasia on either side. We used the center edge (CE) angle as the primary diagnostic criteria. Hips with a CE angle < 20°, 20° to 25°, and > 25° were labeled as dysplastic, borderline, and normal, respectively. The dysplastic hips were also classified with both Crowe and Hartofilakidis classification of dysplasia. The dataset was divided into train, validation, and test subsets using 80:10:10 split-ratio that were used to train two deep learning models to classify images into normal, borderline and (1) Crowe grade 1-4 or (2) Hartofilakidis grade 1-3. A pre-trained on Imagenet VGG16 convolutional neural network (CNN) was utilized by performing layer-wise fine-turning. RESULTS: Both models struggled with distinguishing between normal and borderline hips. However, achieved high accuracy (Model 1: 92.2% and Model 2: 83.3%) in distinguishing between normal/borderline vs. dysplastic hips. The overall accuracy of Model 1 was 68% and for Model 2 73.5%. Most misclassifications for the Crowe and Hartofilakidis classifications were +/- 1 class from the correct class. CONCLUSIONS: This pilot study shows promising results that a deep learning model distinguish between normal and dysplastic hips with high accuracy. Future research and external validation are warranted regarding the ability of deep learning models to perform complex tasks such as identifying and classifying disorders using plain radiographs. LEVEL OF EVIDENCE: Diagnostic level IV.

A lightweight intelligent laryngeal cancer detection system for rural areas.

OBJECTIVE: Early diagnosis of laryngeal cancer (LC) is crucial, particularly in rural areas. Despite existing studies on deep learning models for LC identification, challenges remain in selecting suitable models for rural areas with shortages of laryngologists and limited computer resources. We present the intelligent laryngeal cancer detection system (ILCDS), a deep learning-based solution tailored for effective LC screening in resource-constrained rural areas. METHODS: We compiled a dataset comprised of 2023 laryngoscopic images and applied data augmentation techniques for dataset expansion. Subsequently, we utilized eight deep learning models-AlexNet, VGG, ResNet, DenseNet, MobileNet, ShuffleNet, Vision Transformer, and Swin Transformer-for LC identification. A comprehensive evaluation of their performances and efficiencies was conducted, and the most suitable model was selected to assemble the ILCDS. RESULTS: Regarding performance, all models attained an average accuracy exceeding 90 % on the test set. Particularly noteworthy are VGG, DenseNet, and MobileNet, which exceeded an accuracy of 95 %, with scores of 95.32 %, 95.75 %, and 95.99 %, respectively. Regarding efficiency, MobileNet excels owing to its compact size and fast inference speed, making it an ideal model for integration into ILCDS. CONCLUSION: The ILCDS demonstrated promising accuracy in LC detection while maintaining modest computational resource requirements, indicating its potential to enhance LC screening accuracy and alleviate the workload on otolaryngologists in rural areas.

Deep learning model for classifying shoulder pain rehabilitation exercises using IMU sensor.

BACKGROUND: Artificial intelligence is being used for rehabilitation, including monitoring exercise compliance through sensor technology. AI classification of shoulder exercise wearing an IMU sensor has only been reported in normal (i.e. painless) subjects. To prove the feasibility of monitoring exercise compliance, we aimed to classify 11 types of shoulder rehabilitation exercises using an AI (artificial intelligence) algorithm in patients with shoulder pain. We had the patients wear an IMU-based sensor, collected data during exercise, and determined the accuracy of exercise classification. METHODS: Data were collected from 58 patients (27 males, 31 females, age range 37-82 years) diagnosed with shoulder diseases such as adhesive capsulitis and rotator cuff disease. 11 types of shoulder pain rehabilitation exercise programs were developed and repeated each exercise ten times per session while wearing an IMU sensor. The study applied the Rectified Linear Unit (ReLU) and the SoftMax as the activation function for hidden layers, the output layer. RESULTS: The acquired data was used to train a DNN model using the multilayer perceptron algorithm. The trained model was used to classify 11 types of shoulder pain rehabilitation exercises. The training accuracy was 0.975 and the test accuracy was 0.925. CONCLUSION: The study demonstrates that IMU sensor data can effectively classify shoulder pain rehabilitation exercises, providing more appropriate feedback for patients. The model can be utilized to establish a system for remotely monitoring patients' exercise performance. The use of deep learning in patient monitoring and rehabilitation has significant potential to bring innovative changes to healthcare service delivery.

Deep Learning-Based State-of-Health Estimation of Proton-Exchange Membrane Fuel Cells under Dynamic Operation Conditions.

Proton-exchange membrane fuel cells (PEMFCs) play a crucial role in the transition to sustainable energy systems. Accurately estimating the state of health (SOH) of PEMFCs under dynamic operating conditions is essential for ensuring their reliability and longevity. This study designed dynamic operating conditions for fuel cells and conducted durability tests using both crack-free fuel cells and fuel cells with uniform cracks. Utilizing deep learning methods, we estimated the SOH of PEMFCs under dynamic operating conditions and investigated the performance of long short-term memory networks (LSTM), gated recurrent units (GRU), temporal convolutional networks (TCN), and transformer models for SOH estimation tasks. We also explored the impact of different sampling intervals and training set proportions on the predictive performance of these models. The results indicated that shorter sampling intervals and higher training set proportions significantly improve prediction accuracy. The study also highlighted the challenges posed by the presence of cracks. Cracks cause more frequent and intense voltage fluctuations, making it more difficult for the models to accurately capture the dynamic behavior of PEMFCs, thereby increasing prediction errors. However, under crack-free conditions, due to more stable voltage output, all models showed improved predictive performance. Finally, this study underscores the effectiveness of deep learning models in estimating the SOH of PEMFCs and provides insights into optimizing sampling and training strategies to enhance prediction accuracy. The findings make a significant contribution to the development of more reliable and efficient PEMFC systems for sustainable energy applications.

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

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

S-LIGHT: Synthetic Dataset for the Separation of Diffuse and Specular Reflection Images.

Several studies in computer vision have examined specular removal, which is crucial for object detection and recognition. This research has traditionally been divided into two tasks: specular highlight removal, which focuses on removing specular highlights on object surfaces, and reflection removal, which deals with specular reflections occurring on glass surfaces. In reality, however, both types of specular effects often coexist, making it a fundamental challenge that has not been adequately addressed. Recognizing the necessity of integrating specular components handled in both tasks, we constructed a specular-light (S-Light) DB for training single-image-based deep learning models. Moreover, considering the absence of benchmark datasets for quantitative evaluation, the multi-scale normalized cross correlation (MS-NCC) metric, which considers the correlation between specular and diffuse components, was introduced to assess the learning outcomes.

Interpretable Multi-Scale Deep Learning for RNA Methylation Analysis across Multiple Species.

RNA modification plays a crucial role in cellular regulation. However, traditional high-throughput sequencing methods for elucidating their functional mechanisms are time-consuming and labor-intensive, despite extensive research. Moreover, existing methods often limit their focus to specific species, neglecting the simultaneous exploration of RNA modifications across diverse species. Therefore, a versatile computational approach is necessary for interpretable analysis of RNA modifications across species. A multi-scale biological language-based deep learning model is proposed for interpretable, sequential-level prediction of diverse RNA modifications. Benchmark comparisons across species demonstrate the model's superiority in predicting various RNA methylation types over current state-of-the-art methods. The cross-species validation and attention weight visualization also highlight the model's capability to capture sequential and functional semantics from genomic backgrounds. Our analysis of RNA modifications helps us find the potential existence of "biological grammars" in each modification type, which could be effective for mapping methylation-related sequential patterns and understanding the underlying biological mechanisms of RNA modifications.

Integrated Computational Approaches for Drug Design Targeting Cruzipain.

Cruzipain inhibitors are required after medications to treat Chagas disease because of the need for safer, more effective treatments. Trypanosoma cruzi is the source of cruzipain, a crucial cysteine protease that has driven interest in using computational methods to create more effective inhibitors. We employed a 3D-QSAR model, using a dataset of 36 known inhibitors, and a pharmacophore model to identify potential inhibitors for cruzipain. We also built a deep learning model using the Deep purpose library, trained on 204 active compounds, and validated it with a specific test set. During a comprehensive screening of the Drug Bank database of 8533 molecules, pharmacophore and deep learning models identified 1012 and 340 drug-like molecules, respectively. These molecules were further evaluated through molecular docking, followed by induced-fit docking. Ultimately, molecular dynamics simulation was performed for the final potent inhibitors that exhibited strong binding interactions. These results present four novel cruzipain inhibitors that can inhibit the cruzipain protein of T. cruzi.