Active disease-related compound identification based on capsule network

Capsule neural network and its applications in drug discovery

Deep learning holds great promise in drug discovery, yet its application is hindered by high labeling costs and limited datasets. Developing algorithms that effectively learn from sparsely labeled data is crucial. Capsule networks (CapsNet), introduced in 2017, solve the spatial information loss in traditional neural networks and excel in handling small datasets by capturing spatial hierarchical relationships among features. This capability makes CapsNet particularly promising for drug discovery, where data scarcity is a common challenge. Various modified CapsNet architectures have been successfully applied to drug design and discovery tasks. This review provides a comprehensive analysis of CapsNet's theoretical foundations, its current applications in drug discovery, and its performance in addressing key challenges in the field. Additionally, the study highlights the limitations of CapsNet and outlines potential future research directions to further enhance its utility in drug discovery, offering valuable insights for researchers in both computational and pharmaceutical sciences.

The Fault Diagnosis of Rolling Bearings Is Conducted by Employing a Dual-Branch Convolutional Capsule Neural Network

Currently, many fault diagnosis methods for rolling bearings based on deep learning are facing two main challenges. Firstly, the deep learning model exhibits poor diagnostic performance and limited generalization ability in the presence of noise signals and varying loads. Secondly, there is incomplete utilization of fault information and inadequate extraction of fault features, leading to the low diagnostic accuracy of the model. To address these problems, this paper proposes an improved dual-branch convolutional capsule neural network for rolling bearing fault diagnosis. This method converts the collected bearing vibration signals into grayscale images to construct a grayscale image dataset. By fully considering the types of bearing faults and damage diameters, the data are labeled using a dual-label format. A multi-scale convolution module is introduced to extract features from the data and maximize feature information extraction. Additionally, a coordinate attention mechanism is incorporated into this module to better extract useful channel features and enhance feature extraction capability. Based on adaptive fusion between fault type (damage diameter) features and labels, a dual-branch convolutional capsule neural network model for rolling bearing fault diagnosis is established. The model was experimentally validated using both Case Western Reserve University's bearing dataset and self-made datasets. The experimental results demonstrate that the fault type branch of the model achieves an accuracy rate of 99.88%, while the damage diameter branch attains an accuracy rate of 99.72%. Both branches exhibit excellent classification performance and display robustness against noise interference and variable working conditions. In comparison with other algorithm models cited in the reference literature, the diagnostic capability of the model proposed in this study surpasses them. Furthermore, the generalization ability of the model is validated using a self-constructed laboratory dataset, yielding an average accuracy rate of 94.25% for both branches.

Metabolomic profiling combined with network analysis of serum pharmacochemistry to reveal the therapeutic mechanism of Ardisiae Japonicae Herba against acute lung injury

Introduction: Acute lung injury (ALI) is a common and devastating respiratory disease associated with uncontrolled inflammatory response and transepithelial neutrophil migration. In recent years, a growing number of studies have found that Ardisiae Japonicae Herba (AJH) has a favorable anti-inflammatory effect. However, its serum material basis and molecular mechanism are still unknown in ALI treatment. In this study, metabolomics and network analysis of serum pharmacochemistry were used to explore the therapeutic effect and molecular mechanism of AJH against lipopolysaccharide (LPS)-induced ALI. Methods: A total of 12 rats for serum pharmacochemistry analysis were randomly divided into the LPS group and LPS + AJH-treated group (treated with AJH extract 20 g/kg/d), which were administered LPS (2 mg/kg) by intratracheal instillation and then continuously administered for 7 days. Moreover, 36 rats for metabolomic research were divided into control, LPS, LPS + AJH-treated (5, 10, and 20 g/kg/d), and LPS + dexamethasone (Dex) (2.3 × 10-4 g/kg/d) groups. After 1 h of the seventh administration, the LPS, LPS + AJH-treated, and LPS + Dex groups were administered LPS by intratracheal instillation to induce ALI. The serum pharmacochemistry profiling was performed by UPLC-Orbitrap Fusion MS to identify serum components, which further explore the molecular mechanism of AJH against ALI by network analysis. Meanwhile, metabolomics was used to select the potential biomarkers and related metabolic pathways and to analyze the therapeutic mechanism of AJH against ALI. Results: The results showed that 71 serum components and 18 related metabolites were identified in ALI rat serum. We found that 81 overlapping targets were frequently involved in AGE-RAGE, PI3K-AKT, and JAK-STAT signaling pathways in network analysis. The LPS + AJH-treated groups exerted protective effects against ALI by reducing the infiltration of inflammatory cells and achieved anti-inflammatory efficacy by significantly regulating the interleukin (IL)-6 and IL-10 levels. Metabolomics analysis shows that the therapeutic effect of AJH on ALI involves 43 potential biomarkers and 14 metabolic pathways, especially phenylalanine, tyrosine, and tryptophan biosynthesis and linoleic acid metabolism pathways, to be influenced, which implied the potential mechanism of AJH in ALI treatment. Discussion: Our study initially elucidated the material basis and effective mechanism of AJH against ALI, which provided a solid basis for AJH application.

Construction of a neural network diagnostic model for renal fibrosis and investigation of immune infiltration characteristics

Background

Recently, the incidence rate of renal fibrosis has been increasing worldwide, greatly increasing the burden on society. However, the diagnostic and therapeutic tools available for the disease are insufficient, necessitating the screening of potential biomarkers to predict renal fibrosis.

Methods

Using the Gene Expression Omnibus (GEO) database, we obtained two gene array datasets (GSE76882 and GSE22459) from patients with renal fibrosis and healthy individuals. We identified differentially expressed genes (DEGs) between renal fibrosis and normal tissues and analyzed possible diagnostic biomarkers using machine learning. The diagnostic effect of the candidate markers was evaluated using receiver operating characteristic (ROC) curves and verified their expression using Reverse transcription quantitative polymerase chain reaction (RT-qPCR). The CIBERSORT algorithm was used to determine the proportions of 22 types of immune cells in patients with renal fibrosis, and the correlation between biomarker expression and the proportion of immune cells was studied. Finally, we developed an artificial neural network model of renal fibrosis.

Results

Four candidate genes namely DOCK2, SLC1A3, SOX9 and TARP were identified as biomarkers of renal fibrosis, with the area under the ROC curve (AUC) values higher than 0.75. Next, we verified the expression of these genes by RT-qPCR. Subsequently, we revealed the potential disorder of immune cells in the renal fibrosis group through CIBERSORT analysis and found that immune cells were highly correlated with the expression of candidate markers.

Conclusion

DOCK2, SLC1A3, SOX9, and TARP were identified as potential diagnostic genes for renal fibrosis, and the most relevant immune cells were identified. Our findings provide potential biomarkers for the diagnosis of renal fibrosis.

A neural network model to screen feature genes for pancreatic cancer

All the time, pancreatic cancer is a problem worldwide because of its high degree of malignancy and increased mortality. Neural network model analysis is an efficient and accurate machine learning method that can quickly and accurately predict disease feature genes. The aim of our research was to build a neural network model that would help screen out feature genes for pancreatic cancer diagnosis and prediction of prognosis. Our study confirmed that the neural network model is a reliable way to predict feature genes of pancreatic cancer, and immune cells infiltrating play an essential role in the development of pancreatic cancer, especially neutrophils. ANO1, AHNAK2, and ADAM9 were eventually identified as feature genes of pancreatic cancer, helping to diagnose and predict prognosis. Neural network model analysis provides us with a new idea for finding new intervention targets for pancreatic cancer.

Identification of species-specific RNA N6-methyladinosine modification sites from RNA sequences

N6-methyladinosine (m6A) modification is the most abundant co-transcriptional modification in eukaryotic RNA and plays important roles in cellular regulation. Traditional high-throughput sequencing experiments used to explore functional mechanisms are time-consuming and labor-intensive, and most of the proposed methods focused on limited species types. To further understand the relevant biological mechanisms among different species with the same RNA modification, it is necessary to develop a computational scheme that can be applied to different species. To achieve this, we proposed an attention-based deep learning method, adaptive-m6A, which consists of convolutional neural network, bi-directional long short-term memory and an attention mechanism, to identify m6A sites in multiple species. In addition, three conventional machine learning (ML) methods, including support vector machine, random forest and logistic regression classifiers, were considered in this work. In addition to the performance of ML methods for multi-species prediction, the optimal performance of adaptive-m6A yielded an accuracy of 0.9832 and the area under the receiver operating characteristic curve of 0.98. Moreover, the motif analysis and cross-validation among different species were conducted to test the robustness of one model towards multiple species, which helped improve our understanding about the sequence characteristics and biological functions of RNA modifications in different species.

Evaluation of convolutional neural networks for herbicide susceptibility-based weed detection in turf

Deep learning methods for weed detection typically focus on distinguishing weed species, but a variety of weed species with comparable plant morphological characteristics may be found in turfgrass. Thus, it is difficult for deep learning models to detect and distinguish every weed species with high accuracy. Training convolutional neural networks for detecting weeds susceptible to herbicides can offer a new strategy for implementing site-specific weed detection in turf. DenseNet, EfficientNet-v2, and ResNet showed high F₁ scores (≥0.986) and MCC values (≥0.984) to detect and distinguish the sub-images containing dollarweed, goosegrass, old world diamond-flower, purple nutsedge, or Virginia buttonweed growing in bermudagrass turf. However, they failed to reliably detect crabgrass and tropical signalgrass due to the similarity in plant morphology. When training the convolutional neural networks for detecting and distinguishing the sub-images containing weeds susceptible to ACCase-inhibitors, weeds susceptible to ALS-inhibitors, or weeds susceptible to synthetic auxin herbicides, all neural networks evaluated in this study achieved excellent F₁ scores (≥0.995) and MCC values (≥0.994) in the validation and testing datasets. ResNet demonstrated the fastest inference rate and outperformed the other convolutional neural networks on detection efficiency, while the slow inference of EfficientNet-v2 may limit its potential applications. Grouping different weed species growing in turf according to their susceptibility to herbicides and detecting and distinguishing weeds by herbicide categories enables the implementation of herbicide susceptibility-based precision herbicide application. We conclude that the proposed method is an effective strategy for site-specific weed detection in turf, which can be employed in a smart sprayer to achieve precision herbicide spraying.

Identification of a New Prediction Model for Bladder Cancer Related to Immune Functions and Chemotherapy Using Gene Sets of Biological Processes

Background. Biological processes serve crucial functions in the initiation and development of cancer. Therefore, we constructed and validated a model for bladder cancer (BLCA) with good predictive power for immunity, prognosis, and therapy. Methods. Using the expression of the gene sets based on biological processes, BLCA patients were divided into three clusters by consensus cluster analysis. By performing LASSO regression analysis twice, key genes were selected, and the biological processes-related genes’ (BPRG) score was calculated. Differences in immune infiltration, tumor microenvironment, tumor mutation burden, immunotherapy, and sensitivity towards chemotherapy were analyzed between two groups divided by BPRG score. Results. Good accuracy was observed for the three clusters. They showed different prognoses and levels of immune cell infiltration. The selected key genes were mainly enriched in immune-related pathways. The high-BPRG score group was related to poor prognosis, higher immune cell infiltration, interstitial scores, and increased tumor mutation. Moreover, the effects of immunotherapy were good, and those of chemotherapy were poor. Conclusion. Overall, key genes may be involved in various complex immune regulation processes. Therefore, the quantification and verification of the BPRG score are expected to facilitate the understanding of the immunosuppressive microenvironment in BLCA and guide the choice of chemotherapeutic drugs and immunotherapeutic regimens and help predict the prognoses of patients with BLCA.

Bioinformatics analysis to screen for genes related to myocardial infarction

Myocardial infarction (MI) is an acute and persistent myocardial ischemia caused by coronary artery disease. This study screened potential genes related to MI. Three gene expression datasets related to MI were downloaded from the Gene Expression Omnibus database. Differentially expressed genes (DEGs) were screened using the MetaDE package. Afterward, the modules and genes closely related to MI were screened and a gene co-expression network was constructed. A support vector machine (SVM) classification model was then constructed based on the GSE61145 dataset using the e1071 package in R. A total of 98 DEGs were identified in the MI samples. Next, three modules associated with MI were screened and an SVM classification model involving seven genes was constructed. Among them, BCL6, CEACAM8, and CUGBP2 showed co-interactions in the gene co-expression network. Therefore, ACOX1, BCL6, CEACAM8, and CUGBP2, in addition to GPX7, might be feature genes related to MI.

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

Aiming at detecting COVID-19 effectively, a multiscale class residual attention (MCRA) network is proposed via chest X-ray (CXR) image classification. First, to overcome the data shortage and improve the robustness of our network, a pixel-level image mixing of local regions was introduced to achieve data augmentation and reduce noise. Secondly, multi-scale fusion strategy was adopted to extract global contextual information at different scales and enhance semantic representation. Last but not least, class residual attention was employed to generate spatial attention for each class, which can avoid inter-class interference and enhance related features to further improve the COVID-19 detection. Experimental results show that our network achieves superior diagnostic performance on COVIDx dataset, and its accuracy, PPV, sensitivity, specificity and F1-score are 97.71%, 96.76%, 96.56%, 98.96% and 96.64%, respectively; moreover, the heat maps can endow our deep model with somewhat interpretability.

DeeProPre: A promoter predictor based on deep learning

The promoter is a DNA sequence recognized, bound and transcribed by RNA polymerase. It is usually located at the upstream or 5'end of the transcription start site (TSS). Studies have shown that the structure of the promoter affects its affinity for RNA polymerase, thus affecting the level of gene expression. Therefore, the correct identification of core promoter and common structural gene is of great significance in the field of biomedicine. At present, many methods have been proposed to improve the accuracy of promoter recognition, but the performances still need to be further improved. In this study, a deep learning algorithm (DeeProPre) based on bidirectional long short-term memory (BiLSTM) and convolutional neural network (CNN) was proposed. Firstly, the supervised embedding layer was applied to map the sequence to a high-dimensional space. Secondly, two 1D convolutional layers, BiLSTM and attentional mechanism layer were used for extracting features. Finally, the full connection layer activated by Sigmoid function was used to obtain the probability of classification into target categories. This model can identify the promoter region of eukaryotes with high accuracy, providing an analytical basis for further understanding of promoter physiological functions and studies of gene transcription mechanisms. The source code of DeeProPre is freely available at https://github.com/zzwwmmm/DeeProPre/tree/master.

Gene Ontology Capsule GAN: an improved architecture for protein function prediction

Proteins are the core of all functions pertaining to living things. They consist of an extended amino acid chain folding into a three-dimensional shape that dictates their behavior. Currently, convolutional neural networks (CNNs) have been pivotal in predicting protein functions based on protein sequences. While it is a technology crucial to the niche, the computation cost and translational invariance associated with CNN make it impossible to detect spatial hierarchies between complex and simpler objects. Therefore, this research utilizes capsule networks to capture spatial information as opposed to CNNs. Since capsule networks focus on hierarchical links, they have a lot of potential for solving structural biology challenges. In comparison to the standard CNNs, our results exhibit an improvement in accuracy. Gene Ontology Capsule GAN (GOCAPGAN) achieved an F1 score of 82.6%, a precision score of 90.4% and recall score of 76.1%.

Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet

Brown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as low accuracy, low efficiency, strong subjectivity, and so on. Therefore, it is very necessary to find a method that could effectively identify tea plants diseases and pests. In this study, we proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet. First, Mask R-CNN model was used to segment disease spots and insect spots from tea leaves. Second, the two-dimensional discrete wavelet transform was used to enhance the features of the disease spots and insect spots images, so as to obtain the images with four frequencies. Finally, the images of four frequencies were simultaneously input into the four-channeled residual network (F-RNet) to identify symptoms of tea leaf diseases and insect pests. The results showed that Mask R-CNN model could detect 98.7% of DSIS, which ensure that almost disease spots and insect spots can be extracted from leaves. The accuracy of F-RNet model is 88%, which is higher than that of the other models (like SVM, AlexNet, VGG16 and ResNet18). Therefore, this experimental framework can accurately segment and identify diseases and insect spots of tea leaves, which not only of great significance for the accurate identification of tea plant diseases and insect pests, but also of great value for further using artificial intelligence to carry out the comprehensive control of tea plant diseases and insect pests.

Failure Detection in Deep Neural Networks for Medical Imaging

Deep neural networks (DNNs) have started to find their role in the modern healthcare system. DNNs are being developed for diagnosis, prognosis, treatment planning, and outcome prediction for various diseases. With the increasing number of applications of DNNs in modern healthcare, their trustworthiness and reliability are becoming increasingly important. An essential aspect of trustworthiness is detecting the performance degradation and failure of deployed DNNs in medical settings. The softmax output values produced by DNNs are not a calibrated measure of model confidence. Softmax probability numbers are generally higher than the actual model confidence. The model confidence-accuracy gap further increases for wrong predictions and noisy inputs. We employ recently proposed Bayesian deep neural networks (BDNNs) to learn uncertainty in the model parameters. These models simultaneously output the predictions and a measure of confidence in the predictions. By testing these models under various noisy conditions, we show that the (learned) predictive confidence is well calibrated. We use these reliable confidence values for monitoring performance degradation and failure detection in DNNs. We propose two different failure detection methods. In the first method, we define a fixed threshold value based on the behavior of the predictive confidence with changing signal-to-noise ratio (SNR) of the test dataset. The second method learns the threshold value with a neural network. The proposed failure detection mechanisms seamlessly abstain from making decisions when the confidence of the BDNN is below the defined threshold and hold the decision for manual review. Resultantly, the accuracy of the models improves on the unseen test samples. We tested our proposed approach on three medical imaging datasets: PathMNIST, DermaMNIST, and OrganAMNIST, under different levels and types of noise. An increase in the noise of the test images increases the number of abstained samples. BDNNs are inherently robust and show more than 10% accuracy improvement with the proposed failure detection methods. The increased number of abstained samples or an abrupt increase in the predictive variance indicates model performance degradation or possible failure. Our work has the potential to improve the trustworthiness of DNNs and enhance user confidence in the model predictions.

Phage_UniR_LGBM: Phage Virion Proteins Classification with UniRep Features and LightGBM Model

Phage, the most prevalent creature on the planet, serves a variety of critical roles. Phage's primary role is to facilitate gene-to-gene communication. The phage proteins can be defined as the virion proteins and the nonvirion ones. Nowadays, experimental identification is a difficult process that necessitates a significant amount of laboratory time and expense. Considering such situation, it is critical to design practical calculating techniques and develop well-performance tools. In this work, the Phage_UniR_LGBM has been proposed to classify the virion proteins. In detailed, such model utilizes the UniRep as the feature and the LightGBM algorithm as the classification model. And then, the training data train the model, and the testing data test the model with the cross-validation. The Phage_UniR_LGBM was compared with the several state-of-the-art features and classification algorithms. The performances of the Phage_UniR_LGBM are 88.51% in Sp,89.89% in Sn, 89.18% in Acc, 0.7873 in MCC, and 0.8925 in F1 score.

Effective identification of varieties by nucleotide polymorphisms and its application for essentially derived variety identification in rice

BACKGROUND

Plant variety identification is the one most important of agricultural systems. Development of DNA marker profiles of released varieties to compare with candidate variety or future variety is required. However, strictly speaking, scientists did not use most existing variety identification techniques for "identification" but for "distinction of a limited number of cultivars," of which generalization ability always not be well estimated. Because many varieties have similar genetic backgrounds, even some essentially derived varieties (EDVs) are involved, which brings difficulties for identification and breeding progress. A fast, accurate variety identification method, which also has good performance on EDV determination, needs to be developed.

RESULTS

In this study, with the strategy of "Divide and Conquer," a variety identification method Conditional Random Selection (CRS) method based on SNP of the whole genome of 3024 rice varieties was developed and be applied in essentially derived variety (EDV) identification of rice. CRS is a fast, efficient, and automated variety identification method. Meanwhile, in practical, with the optimal threshold of identity score searched in this study, the set of SNP (including 390 SNPs) showed optimal performance on EDV and non-EDV identification in two independent testing datasets.

CONCLUSION

This approach first selected a minimal set of SNPs to discriminate non-EDVs in the 3000 Rice Genome Project, then united several simplified SNP sets to improve its generalization ability for EDV and non-EDV identification in testing datasets. The results suggested that the CRS method outperformed traditional feature selection methods. Furthermore, it provides a new way to screen out core SNP loci from the whole genome for DNA fingerprinting of crop varieties and be useful for crop breeding.