RESUMO
Metabolism refers to a series of orderly chemical reactions used to maintain life activities in organisms. In healthy individuals, metabolism remains within a normal range. However, specific diseases can lead to abnormalities in the levels of certain metabolites, causing them to either increase or decrease. Detecting these deviations in metabolite levels can aid in diagnosing a disease. Traditional biological experiments often rely on a lot of manpower to do repeated experiments, which is time consuming and labor intensive. To address this issue, we develop a deep learning model based on the auto-encoder and non-negative matrix factorization named as MDA-AENMF to predict the potential associations between metabolites and diseases. We integrate a variety of similarity networks and then acquire the characteristics of both metabolites and diseases through three specific modules. First, we get the disease characteristics from the five-layer auto-encoder module. Later, in the non-negative matrix factorization module, we extract both the metabolite and disease characteristics. Furthermore, the graph attention auto-encoder module helps us obtain metabolite characteristics. After obtaining the features from three modules, these characteristics are merged into a single, comprehensive feature vector for each metabolite-disease pair. Finally, we send the corresponding feature vector and label to the multi-layer perceptron for training. The experiment demonstrates our area under the receiver operating characteristic curve of 0.975 and area under the precision-recall curve of 0.973 in 5-fold cross-validation, which are superior to those of existing state-of-the-art predictive methods. Through case studies, most of the new associations obtained by MDA-AENMF have been verified, further highlighting the reliability of MDA-AENMF in predicting the potential relationships between metabolites and diseases.
Assuntos
Algoritmos , Redes Neurais de Computação , Humanos , Reprodutibilidade dos TestesRESUMO
Simultaneous measurement of multiple modalities in single-cell analysis, represented by CITE-seq, is a promising approach to link transcriptional changes to cellular phenotype and function, requiring new computational methods to define cellular subtypes and states based on multiple data types. Here, we design a flexible single-cell multimodal analysis framework, called CITEMO, to integrate the transcriptome and antibody-derived tags (ADT) data to capture cell heterogeneity from the multi omics perspective. CITEMO uses Principal Component Analysis (PCA) to obtain a low-dimensional representation of the transcriptome and ADT, respectively, and then employs PCA again to integrate these low-dimensional multimodal data for downstream analysis. To investigate the effectiveness of the CITEMO framework, we apply CITEMO to analyse the cell subtypes of Cord Blood Mononuclear Cells (CBMC) samples. Results show that the CITEMO framework can comprehensively analyse single-cell multimodal samples and accurately identify cell subtypes. Besides, we find some specific immune cells that co-express multiple ADT markers. To better describe the co-expression phenomenon, we introduce the co-expression entropy to measure the heterogeneous distribution of the ADT combinations. To further validate the robustness of the CITEMO framework, we analyse Human Bone Marrow Cell (HBMC) samples and identify different states of the same cell type. CITEMO has an excellent performance in identifying cell subtypes and states for multimodal omics data. We suggest that the flexible design idea of CITEMO can be an inspiration for other single-cell multimodal tasks. The complete source code and dataset of the CITEMO framework can be obtained from https://github.com/studentiz/CITEMO.
Assuntos
Biologia Computacional/métodos , Heterogeneidade Genética , Sistema Imunitário/citologia , Sistema Imunitário/metabolismo , Análise de Célula Única/métodos , Software , Linhagem da Célula/genética , Regulação da Expressão Gênica , Genômica/métodos , Humanos , Sistema Imunitário/imunologiaRESUMO
INTRODUCTION: With the escalating menace of organic compounds in environmental pollution imperiling the survival of aquatic organisms, the investigation of organic compound toxicity across diverse aquatic species assumes paramount significance for environmental protection. Understanding how different species respond to these compounds helps assess the potential ecological impact of pollution on aquatic ecosystems as a whole. Compared with traditional experimental methods, deep learning methods have higher accuracy in predicting aquatic toxicity, faster data processing speed and better generalization ability. OBJECTIVES: This article presents ATFPGT-multi, an advanced multi-task deep neural network prediction model for organic toxicity. METHODS: The model integrates molecular fingerprints and molecule graphs to characterize molecules, enabling the simultaneous prediction of acute toxicity for the same organic compound across four distinct fish species. Furthermore, to validate the advantages of multi-task learning, we independently construct prediction models, named ATFPGT-single, for each fish species. We employ cross-validation in our experiments to assess the performance and generalization ability of ATFPGT-multi. RESULTS: The experimental results indicate, first, that ATFPGT-multi outperforms ATFPGT-single on four fish datasets with AUC improvements of 9.8%, 4%, 4.8%, and 8.2%, respectively, demonstrating the superiority of multi-task learning over single-task learning. Furthermore, in comparison with previous algorithms, ATFPGT-multi outperforms comparative methods, emphasizing that our approach exhibits higher accuracy and reliability in predicting aquatic toxicity. Moreover, ATFPGT-multi utilizes attention scores to identify molecular fragments associated with fish toxicity in organic molecules, as demonstrated by two organic molecule examples in the main text, demonstrating the interpretability of ATFPGT-multi. CONCLUSION: In summary, ATFPGT-multi provides important support and reference for the further development of aquatic toxicity assessment. All of codes and datasets are freely available online at https://github.com/zhaoqi106/ATFPGT-multi.
RESUMO
Cardiovascular disease management often involves adjusting medication dosage based on changes in electrocardiogram (ECG) signals' waveform and rhythm. However, the diagnostic utility of ECG signals is often hindered by various types of noise interference. In this work, we propose a novel filter based on a multi-engine evolution framework named MEAs-Filter to address this issue. Our approach eliminates the need for predefined dimensions and allows adaptation to diverse ECG morphologies. By leveraging state-of-the-art optimization algorithms as evolution engine and incorporating prior information inputs from classical filters, MEAs-Filter achieves superior performance while minimizing order. We evaluate the effectiveness of MEAs-Filter on a real ECG database and compare it against commonly used filters such as the Butterworth, Chebyshev filters, and evolution algorithm-based (EA-based) filters. The experimental results indicate that MEAs-Filter outperforms other filters by achieving a reduction of approximately 30% to 60% in terms of the loss function compared to the other algorithms. In denoising experiments conducted on ECG waveforms across various scenarios, MEAs-Filter demonstrates an improvement of approximately 20% in signal-to-noise (SNR) ratio and a 9% improvement in correlation. Moreover, it does not exhibit higher losses of the R-wave compared to other filters. These findings highlight the potential of MEAs-Filter as a valuable tool for high-fidelity extraction of ECG signals, enabling accurate diagnosis in the field of cardiovascular diseases.
RESUMO
Organ segmentation in abdominal or thoracic computed tomography (CT) images plays a crucial role in medical diagnosis as it enables doctors to locate and evaluate organ abnormalities quickly, thereby guiding surgical planning, and aiding treatment decision-making. This paper proposes a novel and efficient medical image segmentation method called SUnet for multi-organ segmentation in the abdomen and thorax. SUnet is a fully attention-based neural network. Firstly, an efficient spatial reduction attention (ESRA) module is introduced not only to extract image features better, but also to reduce overall model parameters, and to alleviate overfitting. Secondly, SUnet's multiple attention-based feature fusion module enables effective cross-scale feature integration. Additionally, an enhanced attention gate (EAG) module is considered by using grouped convolution and residual connections, providing richer semantic features. We evaluate the performance of the proposed model on synapse multiple organ segmentation dataset and automated cardiac diagnostic challenge dataset. SUnet achieves an average Dice of 84.29% and 92.25% on these two datasets, respectively, outperforming other models of similar complexity and size, and achieving state-of-the-art results.
Assuntos
Coração , Redes Neurais de Computação , Semântica , Tórax , Tomografia Computadorizada por Raios X , Processamento de Imagem Assistida por ComputadorRESUMO
Introduction: Real-time evaluations of the severity of depressive symptoms are of great significance for the diagnosis and treatment of patients with major depressive disorder (MDD). In clinical practice, the evaluation approaches are mainly based on psychological scales and doctor-patient interviews, which are time-consuming and labor-intensive. Also, the accuracy of results mainly depends on the subjective judgment of the clinician. With the development of artificial intelligence (AI) technology, more and more machine learning methods are used to diagnose depression by appearance characteristics. Most of the previous research focused on the study of single-modal data; however, in recent years, many studies have shown that multi-modal data has better prediction performance than single-modal data. This study aimed to develop a measurement of depression severity from expression and action features and to assess its validity among the patients with MDD. Methods: We proposed a multi-modal deep convolutional neural network (CNN) to evaluate the severity of depressive symptoms in real-time, which was based on the detection of patients' facial expression and body movement from videos captured by ordinary cameras. We established behavioral depression degree (BDD) metrics, which combines expression entropy and action entropy to measure the depression severity of MDD patients. Results: We found that the information extracted from different modes, when integrated in appropriate proportions, can significantly improve the accuracy of the evaluation, which has not been reported in previous studies. This method presented an over 74% Pearson similarity between BDD and self-rating depression scale (SDS), self-rating anxiety scale (SAS), and Hamilton depression scale (HAMD). In addition, we tracked and evaluated the changes of BDD in patients at different stages of a course of treatment and the results obtained were in agreement with the evaluation from the scales. Discussion: The BDD can effectively measure the current state of patients' depression and its changing trend according to the patient's expression and action features. Our model may provide an automatic auxiliary tool for the diagnosis and treatment of MDD.
RESUMO
Background: Radiation proctitis is a common complication after radiotherapy for cervical cancer. Unlike simple radiation damage to other organs, radiation proctitis is a complex disease closely related to the microbiota. However, analysis of the gut microbiota is time-consuming and expensive. This study aims to mine rectal information using radiomics and incorporate it into a nomogram model for cheap and fast prediction of severe radiation proctitis prediction in postoperative cervical cancer patients. Methods: The severity of the patient's radiation proctitis was graded according to the RTOG/EORTC criteria. The toxicity grade of radiation proctitis over or equal to grade 2 was set as the model's target. A total of 178 patients with cervical cancer were divided into a training set (n = 124) and a validation set (n = 54). Multivariate logistic regression was used to build the radiomic and non-raidomic models. Results: The radiomics model [AUC=0.6855(0.5174-0.8535)] showed better performance and more net benefit in the validation set than the non-radiomic model [AUC=0.6641(0.4904-0.8378)]. In particular, we applied SHapley Additive exPlanation (SHAP) method for the first time to a radiomics-based logistic regression model to further interpret the radiomic features from case-based and feature-based perspectives. The integrated radiomic model enables the first accurate quantitative assessment of the probability of radiation proctitis in postoperative cervical cancer patients, addressing the limitations of the current qualitative assessment of the plan through dose-volume parameters only. Conclusion: We successfully developed and validated an integrated radiomic model containing rectal information. SHAP analysis of the model suggests that radiomic features have a supporting role in the quantitative assessment of the probability of radiation proctitis in postoperative cervical cancer patients.
RESUMO
The diminishing of the polarization effect is important in the applications of dielectric multilayer reflectors in many optical systems, such as low-loss broadband waveguides, optical fibers, and LEDs. Low-polarizing broadband reflections were identified from birefringent-guanine-crystal-based multilayer reflectors in the skins of some fish. Previous models for these intriguing natural optical phenomena suggested the combined action of two populations of guanine crystals with an orthogonal low-refractive-index optic axis. Here we report a novel realization of polarization-insensitive broadband reflectivity in a spider, Phoroncidia rubroargentea, based solely on the type of guanine crystals with the low-refractive-index optic axis normal to the crystal plates. We examined the three-dimensional structure of the guanine assembly in the spider and performed finite-difference time-domain (FDTD) optical modeling of the guanine-based multilayer reflector. Comparative modeling studies reveal that the biological selection of the guanine crystal type and specific spatial arrangement work synergistically to optimize the polarization-insensitive broadband reflection. This study demonstrates the importance of both crystallographic characteristics and 3D arrangement of guanine crystals in understanding relevant natural optical effects and also provides new insights into similar broadband, low-polarizing reflections in biological optical systems. Learning from relevant biofunctional assembly of guanine crystals could promote the bioinspired design of nonpolarizing dielectric multilayer reflectors.
RESUMO
Multiple types of sleep arousal account for a large proportion of the causes of sleep disorders. The detection of sleep arousals is very important for diagnosing sleep disorders and reducing the risk of further complications including heart disease and cognitive impairment. Sleep arousal scoring is manually completed by sleep experts by checking the recordings of several periods of sleep polysomnography (PSG), which is a time-consuming and tedious work. Therefore, the development of efficient, fast, and reliable automatic sleep arousal detection system from PSG may provide powerful help for clinicians. This paper reviews the automatic arousal detection methods in recent years, which are based on statistical rules and deep learning methods. For statistical detection methods, three important processes are typically involved, including preprocessing, feature extraction and classifier selection. For deep learning methods, different models are discussed by now, including convolution neural network (CNN), recurrent neural network (RNN), long-term and short-term memory neural network (LSTM), residual neural network (ResNet), and the combinations of these neural networks. The prediction results of these neural network models are close to the judgments of human experts, and these methods have shown robust generalization capabilities on different data sets. Therefore, we conclude that the deep neural network will be the main research method of automatic arousal detection in the future.