AUC Metrics Research Articles

Subclassification of lung adenocarcinoma through comprehensive multi-omics data to benefit survival outcomes

ObjectivesLung adenocarcinoma (LUAD) is the most common subtype of non-small cell lung cancer. Understanding the molecular mechanisms underlying tumor progression is of great clinical significance. This study aims to identify novel molecular markers associated with LUAD subtypes, with the goal of improving the precision of LUAD subtype classification. Additionally, optimization efforts are directed towards enhancing insights from the perspective of patient survival analysis. Materials and methodsWe propose an innovative feature-selection approach that focuses on LUAD classification, which is comprehensive and robust. The proposed method integrates multi-omics data from The Cancer Genome Atlas (TCGA) and leverages a synergistic combination of max-relevance and min-redundancy, least absolute shrinkage and selection operator, and Boruta algorithms. These selected features were deployed in six machine-learning classifiers: logistic regression, random forest, support vector machine, naive Bayes, k-Nearest Neighbor, and XGBoost. ResultsThe proposed approach achieved an area under the receiver operating characteristic curve (AUC) of 0.9958 for LR. Notably, the accuracy and AUC of a composite model incorporating copy number, methylation, as well as RNA- sequencing data for expression of exons, genes, and miRNA mature strands surpassed the accuracy and AUC metrics of models with single-omics data or other multi-omics combinations. Survival analyses, revealed the SVM classifier to elicit optimal classification, outperforming that achieved by TCGA. To enhance model interpretability, SHapley Additive exPlanations (SHAP) values were utilized to elucidate the impact of each feature on the predictions. Gene Ontology (GO) enrichment analysis identified significant biological processes, molecular functions, and cellular components associated with LUAD subtypes. ConclusionIn summary, our feature selection process, based on TCGA multi-omics data and combined with multiple machine learning classifiers, proficiently identifies molecular subtypes of lung adenocarcinoma and their corresponding significant genes. Our method could enhance the early detection and diagnosis of LUAD, expedite the development of targeted therapies and, ultimately, lengthen patient survival.

Self-supervised dual-layer 2D normalizing flow method for industrial anomaly detection

To address the shortcomings in feature representation and abstraction ability of NFs in the field of unsupervised industrial anomaly detection, as well as the ambiguity in determining the decision boundary between normal and anomaly features, this study proposes the SDNF. This method is dedicated to accurately identifying anomalies by mastering the differences in the distribution of normal and anomaly features. The adopted AFS enables the model to more clearly define the decision boundaries, while the application of the DNF enhances the feature representation and abstraction capabilities. By utilizing the mapping principle of NF, we successfully distinguished between normal and anomaly features, achieving efficient anomaly localization. Furthermore, the ESAM is introduced into the DNF’s sub-networks, allowing the model to focus more on anomaly features, thereby significantly improving the performance of anomaly detection. Experimental validation shows that this method significantly improves the image-level and pixel-level AUC metrics on the MVTec AD dataset, reaching 99.33 % and 98.48 % respectively, surpassing previous research results in terms of the accuracy and quality of anomaly detection. While ensuring high-precision anomaly detection, this research also balances the complexity and inference efficiency of the model, contributing to the advancement of industrial anomaly detection. The related code has been made open source, for more details please visit https://github.com/FutureIAI.

Establishment and risk factor assessment of the abnormal body temperature probability prediction model (ABTP) for dairy cattle

The study aims to develop an abnormal body temperature probability (ABTP) model for dairy cattle, utilizing environmental and physiological data. This model is designed to enhance the management of heat stress impacts, providing an early warning system for farm managers to improve dairy cattle welfare and farm productivity in response to climate change. The study employs the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm to analyze environmental and physiological data from 320 dairy cattle, identifying key factors influencing body temperature anomalies. This method supports the development of various models, including the Lyman Kutcher-Burman (LKB), Logistic, Schultheiss, and Poisson models, which are evaluated for their ability to predict abnormal body temperatures in dairy cattle effectively. The study successfully validated multiple models to predict abnormal body temperatures in dairy cattle, with a focus on the temperature-humidity index (THI) as a critical determinant. These models, including LKB, Logistic, Schultheiss, and Poisson, demonstrated high accuracy, as measured by the AUC and other performance metrics such as the Brier score and Hosmer–Lemeshow (HL) test. The results highlight the robustness of the models in capturing the nuances of heat stress impacts on dairy cattle. The research develops innovative models for managing heat stress in dairy cattle, effectively enhancing detection and intervention strategies. By integrating advanced technologies and novel predictive models, the study offers effective measures for early detection and management of abnormal body temperatures, improving cattle welfare and farm productivity in changing climatic conditions. This approach highlights the importance of using multiple models to accurately predict and address heat stress in livestock, making significant contributions to enhancing farm management practices.

Behavioral Adaptations in Tropical Dairy Cows: Insights into Calving Day Predictions.

This study examined changes in the activity patterns of tropical dairy cows during the transition period to assess their potential for predicting calving days. This study used the AfiTag-II biosensor to monitor activity, rest time, rest per bout, and restlessness ratio in 298 prepartum and 347 postpartum Holstein Friesian cows across three lactation groups (1, 2, and ≥3). The data were analyzed using generalized linear mixed models in SPSS, and five machine learning models, including random forest, decision tree, gradient boosting, Naïve Bayes, and neural networks, were used to predict the calving day, with their performance evaluated via ROC curves and AUC metrics. For all lactations, activity levels peak on the calving day, followed by a gradual return to prepartum levels within two weeks. First-lactation cows displayed the shortest rest duration, with a prepartum rest time of 568.8 ± 5.4 (mean ± SE), which is significantly lower than higher-lactation animals. The random forest and gradient boosting displayed an effective performance, achieving AUCs of 85% and 83%, respectively. These results indicate that temporal changes in activity behavior have the potential to be a useful indicator for calving day prediction, particularly in tropical climates where seasonal variations can obscure traditional prepartum indicators.

Decoding children dental health risks: a machine learning approach to identifying key influencing factors.

This study investigates key factors influencing dental caries risk in children aged 7 and under using machine learning techniques. By addressing dental caries' prevalence, it aims to enhance early identification and preventative strategies for high-risk individuals. Data from clinical examinations of 356 children were analyzed using Logistic Regression, Decision Trees, and Random Forests models. These models assessed the influence of dietary habits, fluoride exposure, and socio-economic status on caries risk, emphasizing accuracy, precision, recall, F1 score, and AUC metrics. Poor oral hygiene, high sugary diet, and low fluoride exposure were identified as significant caries risk factors. The Random Forest model demonstrated superior performance, illustrating the potential of machine learning in complex health data analysis. Our SHAP analysis identified poor oral hygiene, high sugary diet, and low fluoride exposure as significant caries risk factors. Machine learning effectively identifies and quantifies dental caries risk factors in children. This approach supports targeted interventions and preventive measures, improving pediatric dental health outcomes. By leveraging machine learning to pinpoint crucial caries risk factors, this research lays the groundwork for data-driven preventive strategies, potentially reducing caries prevalence and promoting better dental health in children.

Predicating risk habitats of Oncomelania hupensis, the intermediate host of schistosoma japonicum under multiple environmental drivers

BackgroundOncomelania hupensis (O. hupensis), the unique intermediate host for Schistosoma japonicum, exerts a substantial influence on the risk of schistosomiasis. Being amphibious freshwater snails, the growth, development, and reproductive distribution of O. hupensis are intricately tied to climatic environmental variables. This study aims to predict O. hupensis habitat risks along the Yangtze River in China, considering multiple environmental factors. MethodsData pertaining to the distribution of O. hupensis, including both presence and absence records, with the Jiangsu section of the Yangtze River basin for the period 2017–2021, were retrieved from the Jiangsu Schistosomiasis Control Information Platform. Ten machine learning algorithms and an ensemble model were used to explore environmental drivers. Three datasets (Snail_CLIM, Snail_TOPO, and Snail_ALL) incorporating climatic and topographic variables were examined for their impact on model accuracy. We conducted validation using the AUC and TSS metrics. Moreover, we utilized the data from the 2022 snail field survey for model external validation. ResultsThe findings demonstrate that snail_ALL, which incorporates both climatic and topographic variables, exhibits superior performance (ensemble model: sensitivity = 98.000, specificity = 95.960, AUC = 0.994). Among the ten model algorithms, Random Forest (RF) exhibited the highest degree of accuracy and stability (Snail_ALL: AUC = 1.000 ± 0.000, TSS = 0.985 ± 0.005). The key environmental factors affecting snail distribution included the distance to the nearest river, elevation, annual precipitation, and annual average pressure. High-risk areas manifested as two distinct concentrations: downstream of the Luhe District in Nanjing and at the confluence of Zhenjiang and Yangzhou. The results of 2022 field validation showed that over 90 % of the data points for snail breeding sites are concentrated in medium to high-risk areas. ConclusionBy selecting pertinent environmental variables and employing ensemble modeling techniques, we can accurately predict O. hupensis habitats. The resulting risk distribution map for snail habitats not only provides valuable insights but also serves as a guiding tool for targeted monitoring and control measures. The holds particular significance within the contest of the Yangtze River protection and restoration projects.

Predicting Tumor Dynamics Post-Staged GKRS: Machine Learning Models in Brain Metastases Prognosis.

This study assesses the predictive performance of six machine learning models and a 1D Convolutional Neural Network (CNN) in forecasting tumor dynamics within three months following Gamma Knife radiosurgery (GKRS) in 77 brain metastasis (BM) patients. The analysis meticulously evaluates each model before and after hyperparameter tuning, utilizing accuracy, AUC, and other metrics derived from confusion matrices. The CNN model showcased notable performance with an accuracy of 98% and an AUC of 0.97, effectively complementing the broader model analysis. Initial findings highlighted that XGBoost significantly outperformed other models with an accuracy of 0.95 and an AUC of 0.95 before tuning. Post-tuning, the Support Vector Machine (SVM) demonstrated the most substantial improvement, achieving an accuracy of 0.98 and an AUC of 0.98. Conversely, XGBoost showed a decline in performance after tuning, indicating potential overfitting. The study also explores feature importance across models, noting that features like "control at one year", "age of the patient", and "beam-on time for volume V1 treated" were consistently influential across various models, albeit their impacts were interpreted differently depending on the model's underlying mechanics. This comprehensive evaluation not only underscores the importance of model selection and hyperparameter tuning but also highlights the practical implications in medical diagnostic scenarios, where the accuracy of positive predictions can be crucial. Our research explores the effects of staged Gamma Knife radiosurgery (GKRS) on larger tumors, revealing no significant outcome differences across protocols. It uniquely considers the impact of beam-on time and fraction intervals on treatment efficacy. However, the investigation is limited by a small patient cohort and data from a single institution, suggesting the need for future multicenter research.

HGGN: Prediction of microRNA-Mediated drug sensitivity based on interpretable heterogeneous graph global-attention network

Drug sensitivity significantly influences therapeutic outcomes. Recent discoveries have highlighted the pivotal role of miRNAs in regulating drug sensitivity by modulating genes associated with drug metabolism and action. As crucial regulators of gene expression, miRNAs have emerged as influential factors in determining an individual’s response to pharmaceutical interventions. However, current methods for predicting miRNA-drug sensitivity associations overlook the challenges posed by heterogeneous networks and data sparsity. In this paper, we design a dual-channel feature representation strategy for heterogeneous networks and construct HGGN, an interpretable deep learning framework designed to predict miRNA-drug sensitivity associations. HGGN advances beyond traditional approaches by employing a unique dual-channel feature extraction method for miRNAs and drugs, enhancing information retrieval from miRNA-drug networks. It incorporates a Global Attention mechanism to overcome feature propagation interruption in sparse networks. Our experiments on public datasets demonstrate HGGN’s superior prediction accuracy over existing methods. The AUC and AUPR metrics of HGGN reached 0.9649 and 0.9610 respectively, and the Accuracy, Precision, Recall and F1 metrics were all above 0.9. We constructed the model toward different negative sample selection strategies with an accuracy gap of less than 1%, which proves the robustness of HGGN. Additionally, HGGN’s application in modeling analyses and case studies reveals hidden miRNA-mediated drug sensitivity pathways, showcasing its potential for exploratory analysis.

Predicting Corporate Financial Risk Using Artificial Bee Colony-Attention-Gated Recurrent Unit Model

Corporate financial risk prediction is a critical task for ensuring the stability and success of businesses in today's dynamic economic landscape. However, existing models often fall short in accurately assessing and managing these risks. They often rely on historical financial data alone, which fails to account for sudden market fluctuations or unforeseen external events, leading to suboptimal risk assessments. Recognizing the paramount importance of time series analysis in financial risk prediction, we introduce a novel approach to the ABC-Attention-GRU combination model. This innovative model leverages the strengths of Artificial Bee Colony (ABC), the attention mechanism, and Gated Recurrent Unit (GRU) to enhance predictive accuracy and robustness. In our experiments, the ABC-Attention-GRU model consistently outperformed state-of-the-art methods across various financial datasets. It effectively captured complex temporal dependencies, resulting in superior Precision, Recall, F1 Score, and AUC metrics.

A class-imbalanced hybrid learning strategy based on Raman spectroscopy of serum samples for the diagnosis of hepatitis B, hepatitis A, and thyroid dysfunction

Computer-aided vibrational spectroscopy detection technology has achieved promising results in the field of early disease diagnosis. Yet limited by factors such as the number of actual samples and the cost of spectral acquisition in clinical medicine, the data available for model training are insufficient, and the amount of data varies greatly between different diseases, which constrain the performance optimization and enhancement of the diagnostic model. In this study, vibrational spectroscopy data of three common diseases are selected as research objects, and experimental research is conducted around the class imbalance situation that exists in medical data. When dealing with the challenge of class imbalance in medical vibrational spectroscopy research, it no longer relies on some kind of independent and single method, but considers the combined effect of multiple strategies. SVM, K-Nearest Neighbor (KNN), and Decision Tree (DT) are used as baseline comparison models on Raman spectroscopy medical datasets with different imbalance rates. The performance of the three strategies, Ensemble Learning, Feature Extraction, and Resampling, is verified on the class imbalance dataset by G-mean and AUC metrics, respectively. The results show that all the above three methods mitigate the negative impact caused by unbalanced learning. Based on this, we propose a hybrid ensemble classifier (HEC) that integrates resampling, feature extraction, and ensemble learning to verify the effectiveness of the hybrid learning strategy in solving the class imbalance problem. The G-mean and AUC values of the HEC method are 82.7 % and 83.12 % for the HBV dataset, is 2.02 % and 1.98 % higher than the optimal strategy; 83.62 % and 83.76 % for the HCV dataset, is 9.79 % and 8.47 % higher than the optimal strategy; while for the thyroid dysfunction dataset are 77.56 % and 77.85 %, is 6.92 % and 6.36 % higher than that of the optimal strategy, respectively. The experimental results show that the G-mean and AUC metrics of the HEC method are higher than those of the baseline classifier as well as the optimal combination using separate strategies. It can be seen that the HEC method can effectively counteract the unfavorable effects of imbalance learning and is expected to be applied to a wider range of imbalance scenarios.

An Ensemble Classifiers for Improved Prediction of Native-Non-Native Protein-Protein Interaction.

In this study, we present an innovative approach to improve the prediction of protein-protein interactions (PPIs) through the utilization of an ensemble classifier, specifically focusing on distinguishing between native and non-native interactions. Leveraging the strengths of various base models, including random forest, gradient boosting, extreme gradient boosting, and light gradient boosting, our ensemble classifier integrates these diverse predictions using a logistic regression meta-classifier. Our model was evaluated using a comprehensive dataset generated from molecular dynamics simulations. While the gains in AUC and other metrics might seem modest, they contribute to a model that is more robust, consistent, and adaptable. To assess the effectiveness of various approaches, we compared the performance of logistic regression to four baseline models. Our results indicate that logistic regression consistently underperforms across all evaluated metrics. This suggests that it may not be well-suited to capture the complex relationships within this dataset. Tree-based models, on the other hand, appear to be more effective for problems involving molecular dynamics simulations. Extreme gradient boosting (XGBoost) and light gradient boosting (LightGBM) are optimized for performance and speed, handling datasets effectively and incorporating regularizations to avoid over-fitting. Our findings indicate that the ensemble method enhances the predictive capability of PPIs, offering a promising tool for computational biology and drug discovery by accurately identifying potential interaction sites and facilitating the understanding of complex protein functions within biological systems.

A Contribution-Aware Noise Feature representation model for image manipulation localization

Noise feature modules play a prevalent role in image manipulation localization. However, existing approach involves utilizing a specific noise feature module tailored to address distinct categories of tampering procedures, limiting its adaptability across diverse scenarios. This limitation becomes particularly pronounced in image manipulation localization where a singular noise module struggles to comprehensively represent all potential tampering types, given the inherent uncertainty surrounding the nature of tampering. A novel Contribution-Aware Noise Feature (CANF) representation model, specifically designed to tackle the intricacies of image tamper noise, is introduced in this paper. The proposed model integrates existing noise feature modules, autonomously enhancing their capabilities. This enhancement not only contributes significantly to image manipulation localization during the inference phase but also enables a quantitative evaluation of the distinct contributions of various noise modules to the inference results. To optimize the utilization of image information, the Red–Green–Blue (RGB) and CANF data are fused, leading to the development of a standardized image manipulation localization architecture. This architecture exhibits heightened efficiency in harnessing diverse types of information, thereby enhancing the overall performance of image manipulation localization. Experimental results demonstrate that our approach, alongside established methods IF-OSN, MSFF, PCL, and NCL, surpasses the state-of-the-art NCL by 8.5% and 5.4% concerning average F1 and AUC metrics across four standard image manipulation localization datasets: NIST16, CASIAv1, Columbia, and Coverage. In addition, we comprehensively explore the impact of various noise characterization modules on different types of tampering and the fact that Late Fusion is more conducive to image tampering localization.

Leveraging machine learning for predicting acute graft-versus-host disease grades in allogeneic hematopoietic cell transplantation for T-cell prolymphocytic leukaemia

Orphan diseases, exemplified by T-cell prolymphocytic leukemia, present inherent challenges due to limited data availability and complexities in effective care. This study delves into harnessing the potential of machine learning to enhance care strategies for orphan diseases, specifically focusing on allogeneic hematopoietic cell transplantation (allo-HCT) in T-cell prolymphocytic leukemia. The investigation evaluates how varying numbers of variables impact model performance, considering the rarity of the disease. Utilizing data from the Center for International Blood and Marrow Transplant Research, the study scrutinizes outcomes following allo-HCT for T-cell prolymphocytic leukemia. Diverse machine learning models were developed to forecast acute graft-versus-host disease (aGvHD) occurrence and its distinct grades post-allo-HCT. Assessment of model performance relied on balanced accuracy, F1 score, and ROC AUC metrics. The findings highlight the Linear Discriminant Analysis (LDA) classifier achieving the highest testing balanced accuracy of 0.58 in predicting aGvHD. However, challenges arose in its performance during multi-class classification tasks. While affirming the potential of machine learning in enhancing care for orphan diseases, the study underscores the impact of limited data and disease rarity on model performance.

Tongue feature recognition to monitor rehabilitation: deep neural network with visual attention mechanism.

We endeavor to develop a novel deep learning architecture tailored specifically for the analysis and classification of tongue features, including color, shape, and coating. Unlike conventional methods based on architectures like VGG or ResNet, our proposed method aims to address the challenges arising from their extensive size, thereby mitigating the overfitting problem. Through this research, we aim to contribute to the advancement of techniques in tongue feature recognition, ultimately leading to more precise diagnoses and better patient rehabilitation in Traditional Chinese Medicine (TCM). In this study, we introduce TGANet (Tongue Feature Attention Network) to enhance model performance. TGANet utilizes the initial five convolutional blocks of pre-trained VGG16 as the backbone and integrates an attention mechanism into this backbone. The integration of the attention mechanism aims to mimic human cognitive attention, emphasizing model weights on pivotal regions of the image. During the learning process, the allocation of attention weights facilitates the interpretation of causal relationships in the model's decision-making. Experimental results demonstrate that TGANet outperforms baseline models, including VGG16, ResNet18, and TSC-WNet, in terms of accuracy, precision, F1 score, and AUC metrics. Additionally, TGANet provides a more intuitive and meaningful understanding of tongue feature classification models through the visualization of attention weights. In conclusion, TGANet presents an effective approach to tongue feature classification, addressing challenges associated with model size and overfitting. By leveraging the attention mechanism and pre-trained VGG16 backbone, TGANet achieves superior performance metrics and enhances the interpretability of the model's decision-making process. The visualization of attention weights contributes to a more intuitive understanding of the classification process, making TGANet a promising tool in tongue diagnosis and rehabilitation.

Enhancing multiple myeloma staging: a novel cell death risk model approach

The prognostication of survival trajectories in multiple myeloma (MM) patients presents a substantial clinical challenge. Leveraging transcriptomic and clinical profiles from an expansive cohort of 2,088 MM patients, sourced from the Gene Expression Omnibus and The Cancer Genome Atlas repositories, we applied a sophisticated nested lasso regression technique to construct a prognostic model predicated on 28 gene pairings intrinsic to cell death pathways, thereby deriving a quantifiable risk stratification metric. Employing a threshold of 0.15, we dichotomized the MM samples into discrete high-risk and low-risk categories. Notably, the delineated high-risk cohort exhibited a statistically significant diminution in survival duration, a finding which consistently replicated across both training and external validation datasets. The prognostic acumen of our cell death signature was further corroborated by TIME ROC analyses, with the model demonstrating robust performance, evidenced by AUC metrics consistently surpassing the 0.6 benchmark across the evaluated arrays. Further analytical rigor was applied through multivariate COX regression analyses, which ratified the cell death risk model as an independent prognostic determinant. In an innovative stratagem, we amalgamated this risk stratification with the established International Staging System (ISS), culminating in the genesis of a novel, refined ISS categorization. This tripartite classification system was subjected to comparative analysis against extant prognostic models, whereupon it manifested superior predictive precision, as reflected by an elevated C-index. In summation, our endeavors have yielded a clinically viable gene pairing model predicated on cellular mortality, which, when synthesized with the ISS, engenders an augmented prognostic tool that exhibits pronounced predictive prowess in the context of multiple myeloma.

Multi-Model Analysis to Predict the Potential Suitable Habitat for Quercus oblongata D. Don (Fagaceae) in the Western Himalayan Region

Quercus oblongata D. Don is an economically and ecologically important tree species. It is distributed in the western Himalayan region of India as well as Nepal, Pakistan, Thailand, and Vietnam. The present study explored the potential distribution and habitat suitability of Q. oblongata using ensemble modeling. Eleven environmental variables (eight bioclimatic and three topographic), and 121 occurrence records were used in the analysis. Four algorithms: Generalized Additive Model (GAM), Generalized Linear Model (GLM), Random Forest (RF), and Maximum Entropy (Max Ent) were used to build the ensemble model for potential suitable habitat of Q. oblongata. To evaluate the model performance, AUC and TSS metrics were used, which showed high AUC (>0.94) and TSS (>0.86) metrics for all the models. The environmental variables that displayed high contribution in the prediction were temperature annual range (bio7, 48.5%), precipitation of wettest period (bio13 ; 41%), and elevation (elev ; 40%). The total suitable area was 22634 km2, including the least (12546 km2), moderate (7935 km2), and highly (2153 km2) suitable areas. Habitat suitability of Q. oblongata is predicted in most of the regions of Nainital, Almora, central Tehri Garhwal, eastern Mussoorie and Chakrata region of Dehradun District of Uttarakhand. A sizeable wide patch was found in Southern Chamba with Northern Kangra District, including the northern region of Mandi District of Himachal Pradesh. The predicted suitable habitat can be used for future exploration for the study of genetic diversity and conservation purposes.

MMGAT: a graph attention network framework for ATAC-seq motifs finding.

Motif finding in Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) data is essential to reveal the intricacies of transcription factor binding sites (TFBSs) and their pivotal roles in gene regulation. Deep learning technologies including convolutional neural networks (CNNs) and graph neural networks (GNNs), have achieved success in finding ATAC-seq motifs. However, CNN-based methods are limited by the fixed width of the convolutional kernel, which makes it difficult to find multiple transcription factor binding sites with different lengths. GNN-based methods has the limitation of using the edge weight information directly, makes it difficult to aggregate the neighboring nodes' information more efficiently when representing node embedding. To address this challenge, we developed a novel graph attention network framework named MMGAT, which employs an attention mechanism to adjust the attention coefficients among different nodes. And then MMGAT finds multiple ATAC-seq motifs based on the attention coefficients of sequence nodes and k-mer nodes as well as the coexisting probability of k-mers. Our approach achieved better performance on the human ATAC-seq datasets compared to existing tools, as evidenced the highest scores on the precision, recall, F1_score, ACC, AUC, and PRC metrics, as well as finding 389 higher quality motifs. To validate the performance of MMGAT in predicting TFBSs and finding motifs on more datasets, we enlarged the number of the human ATAC-seq datasets to 180 and newly integrated 80 mouse ATAC-seq datasets for multi-species experimental validation. Specifically on the mouse ATAC-seq dataset, MMGAT also achieved the highest scores on six metrics and found 356 higher-quality motifs. To facilitate researchers in utilizing MMGAT, we have also developed a user-friendly web server named MMGAT-S that hosts the MMGAT method and ATAC-seq motif finding results. The advanced methodology MMGAT provides a robust tool for finding ATAC-seq motifs, and the comprehensive server MMGAT-S makes a significant contribution to genomics research. The open-source code of MMGAT can be found at https://github.com/xiaotianr/MMGAT , and MMGAT-S is freely available at https://www.mmgraphws.com/MMGAT-S/ .

Improving the power of drug toxicity measurements by quantitative nuclei imaging

Imaging-based anticancer drug screens are becoming more prevalent due to development of automated fluorescent microscopes and imaging stations, as well as rapid advancements in image processing software. Automated cell imaging provides many benefits such as their ability to provide high-content data, modularity, dynamics recording and the fact that imaging is the most direct way to access cell viability and cell proliferation. However, currently most publicly available large-scale anticancer drugs screens, such as GDSC, CTRP and NCI-60, provide cell viability data measured by assays based on colorimetric or luminometric measurements of NADH or ATP levels. Although such datasets provide valuable data, it is unclear how well drug toxicity measurements can be integrated with imaging data. Here we explored the relations between drug toxicity data obtained by XTT assay, two quantitative nuclei imaging methods and trypan blue dye exclusion assay using a set of four cancer cell lines with different morphologies and 30 drugs with different mechanisms of action. We show that imaging-based approaches provide high accuracy and the differences between results obtained by different methods highly depend on drug mechanism of action. Selecting AUC metrics over IC50 or comparing data where significantly drugs reduced cell numbers noticeably improves consistency between methods. Using automated cell segmentation protocols we analyzed mitochondria activity in more than 11 thousand drug-treated cells and showed that XTT assay produces unreliable data for CDK4/6, Aurora A, VEGFR and PARP inhibitors due induced cell size growth and increase in individual mitochondria activity. We also explored several benefits of image-based analysis such as ability to monitor cell number dynamics, dissect changes in total and individual mitochondria activity from cell proliferation, and ability to identify chromatin remodeling drugs. Finally, we provide a web tool that allows comparing results obtained by different methods.

DON6D: a decoupled one-stage network for 6D pose estimation

The six-dimensional (6D) pose object estimation is a key task in robotic manipulation and grasping scenes. Many existing two-stage solutions with a slow inference speed require extra refinement to handle the challenges of variations in lighting, sensor noise, object occlusion, and truncation. To address these challenges, this work proposes a decoupled one-stage network (DON6D) model for 6D pose estimation that improves inference speed on the premise of maintaining accuracy. Particularly, since the RGB images are aligned with the RGB-D images, the proposed DON6D first uses a two-dimensional detection network to locate the interested objects in RGB-D images. Then, a module of feature extraction and fusion is used to extract color and geometric features fully. Further, dual data augmentation is performed to enhance the generalization ability of the proposed model. Finally, the features are fused, and an attention residual encoder–decoder, which can improve the pose estimation performance to obtain an accurate 6D pose, is introduced. The proposed DON6D model is evaluated on the LINEMOD and YCB-Video datasets. The results demonstrate that the proposed DON6D is superior to several state-of-the-art methods regarding the ADD(-S) and ADD(-S) AUC metrics.

Boosting the classification success in imbalanced data of bee larva cells

Selecting the appropriate honey harvesting method is crucial for sustainable beekeeping and optimal honey production. The use of primitive harvesting methods can lead to the death of bees and a decrease in honey yield. This study aims to address the issue of detecting and classifying young larvae on honeycombs. However, the area where young larvae are found is limited compared to other areas. In this study, the dataset obtained from honeycombs was imbalanced, which has used the Synthetic Minority Oversampling TEchnique (SMOTE) algorithm to balance it. The SMOTE algorithm is a synthetic data generation method. The balanced dataset was then used for classification processes with k-Nearest Neighbors algorithm (k-NN), Decision Trees, and Support Vector Machines. The evaluation of the classification results included the F1-Score, G-Mean, and AUC metrics. The results showed that the classification of the dataset balanced with synthetic data was more successful.