A deep learning model for DNA enhancer prediction based on nucleotide position aware feature encoding.

Enhancers, genomic DNA elements, regulate neighboring gene expression crucial for biological processes like cell differentiation and stress response. However, current machine learning methods for predicting DNA enhancers often underutilize hidden features in gene sequences, limiting model accuracy. Hence, this article proposes the PDCNN model, a deep learning-based enhancer prediction method. PDCNN extracts statistical nucleotide representations from gene sequences, discerning positional distribution information of nucleotides in modifier-like DNA sequences. With a convolutional neural network structure, PDCNN employs dual convolutional and fully connected layers. The cross-entropy loss function iteratively updates using a gradient descent algorithm, enhancing prediction accuracy. Model parameters are fine-tuned to select optimal combinations for training, achieving over 95% accuracy. Comparative analysis with traditional methods and existing models demonstrates PDCNN's robust feature extraction capability. It outperforms advanced machine learning methods in identifying DNA enhancers, presenting an effective method with broad implications for genomics, biology, and medical research.

Detection of Chylous Plasma Based on Machine Learning and Hyperspectral Techniques.

Chylous blood is the main cause of unqualified and scrapped blood among volunteer blood donors. Therefore, a diagnostic method that can quickly and accurately identify chylous blood before donation is needed. In this study, the GaiaSorter "Gaia" hyperspectral sorter was used to extract 254 bands of plasma images, ranging from 900 nm to 1700 nm. Four different machine learning algorithms were used, including decision tree, Gaussian Naive Bayes (GaussianNB), perceptron, and stochastic gradient descent models. First, the preliminary classification accuracies were compared with the original data, which showed that the effects of the decision tree and GaussianNB models were better; their average accuracies could reach over 90%. Then, the feature dimension reduction was performed on the original data. The results showed that the effects of the decision tree were better with a classification accuracy of 93.33%. the classification of chylous plasma using different chylous indices suggested that the accuracies of the decision trees model both before and after the feature dimension reductions were the best with over 80% accuracy. The results of feature dimension reduction showed that the characteristic bands corresponded to all kinds of plasma, thereby showing their classification and identification potential. By applying the spectral characteristics of plasma to medical technology, this study suggested a rapid and effective method for the identification of chylous plasma and provided a reference for the blood detection technology to achieve the goal of reducing wasting blood resources and improving the work efficiency of the medical staff.

Essential genes identification model based on sequence feature map and graph convolutional neural network.

BACKGROUND: Essential genes encode functions that play a vital role in the life activities of organisms, encompassing growth, development, immune system functioning, and cell structure maintenance. Conventional experimental techniques for identifying essential genes are resource-intensive and time-consuming, and the accuracy of current machine learning models needs further enhancement. Therefore, it is crucial to develop a robust computational model to accurately predict essential genes. RESULTS: In this study, we introduce GCNN-SFM, a computational model for identifying essential genes in organisms, based on graph convolutional neural networks (GCNN). GCNN-SFM integrates a graph convolutional layer, a convolutional layer, and a fully connected layer to model and extract features from gene sequences of essential genes. Initially, the gene sequence is transformed into a feature map using coding techniques. Subsequently, a multi-layer GCN is employed to perform graph convolution operations, effectively capturing both local and global features of the gene sequence. Further feature extraction is performed, followed by integrating convolution and fully-connected layers to generate prediction results for essential genes. The gradient descent algorithm is utilized to iteratively update the cross-entropy loss function, thereby enhancing the accuracy of the prediction results. Meanwhile, model parameters are tuned to determine the optimal parameter combination that yields the best prediction performance during training. CONCLUSIONS: Experimental evaluation demonstrates that GCNN-SFM surpasses various advanced essential gene prediction models and achieves an average accuracy of 94.53%. This study presents a novel and effective approach for identifying essential genes, which has significant implications for biology and genomics research.

Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network.

DNA methylation takes on critical significance to the regulation of gene expression by affecting the stability of DNA and changing the structure of chromosomes. DNA methylation modification sites should be identified, which lays a solid basis for gaining more insights into their biological functions. Existing machine learning-based methods of predicting DNA methylation have not fully exploited the hidden multidimensional information in DNA gene sequences, such that the prediction accuracy of models is significantly limited. Besides, most models have been built in terms of a single methylation type. To address the above-mentioned issues, a deep learning-based method was proposed in this study for DNA methylation site prediction, termed the MEDCNN model. The MEDCNN model is capable of extracting feature information from gene sequences in three dimensions (i.e., positional information, biological information, and chemical information). Moreover, the proposed method employs a convolutional neural network model with double convolutional layers and double fully connected layers while iteratively updating the gradient descent algorithm using the cross-entropy loss function to increase the prediction accuracy of the model. Besides, the MEDCNN model can predict different types of DNA methylation sites. As indicated by the experimental results,the deep learning method based on coding from multiple dimensions outperformed single coding methods, and the MEDCNN model was highly applicable and outperformed existing models in predicting DNA methylation between different species. As revealed by the above-described findings, the MEDCNN model can be effective in predicting DNA methylation sites.

Biological Activity Predictions of Ligands Based on Hybrid Molecular Fingerprinting and Ensemble Learning.

The biological activity predictions of ligands are an important research direction, which can improve the efficiency and success probability of drug screening. However, the traditional prediction method has the disadvantages of complex modeling and low screening efficiency. Machine learning is considered an important research direction to solve these traditional method problems in the near future. This paper proposes a machine learning model with high predictive accuracy and stable prediction ability, namely, the back propagation neural network cross-support vector regression model (BPCSVR). By comparing multiple molecular descriptors, MACCS fingerprint and ECFP6 fingerprint were selected as inputs, and the stable prediction ability of the model was improved by integrating multiple models and correcting similar samples. We used leave-one-out cross-validation on 3038 samples from six data sets. The coefficient of determination, root mean square error, and absolute error were used as the evaluation parameters. After comparing the multiclass models, the results show that the BPCSVR model has stable prediction ability in different data sets, and the prediction accuracy is higher than other comparison models.

Prediction of the Aqueous Solubility of Compounds Based on Light Gradient Boosting Machines with Molecular Fingerprints and the Cuckoo Search Algorithm.

Aqueous solubility is one of the most important physicochemical properties in drug discovery. At present, the prediction of aqueous solubility of compounds is still a challenging problem. Machine learning has shown great potential in solubility prediction. Most machine learning models largely rely on the setting of hyperparameters, and their performance can be improved by setting the hyperparameters in a better way. In this paper, we used MACCS fingerprints to represent the structural features and optimized the hyperparameters of the light gradient boosting machine (LightGBM) with the cuckoo search algorithm (CS). Based on the above representation and optimization, the CS-LightGBM model was established to predict the aqueous solubility of 2446 organic compounds and the obtained prediction results were compared with those obtained with the other six different machine learning models (RF, GBDT, XGBoost, LightGBM, SVR, and BO-LightGBM). The comparison results showed that the CS-LightGBM model had a better prediction performance than the other six different models. RMSE, MAE, and R 2 of the CS-LightGBM model were, respectively, 0.7785, 0.5117, and 0.8575. In addition, this model has good scalability and can be used to solve solubility prediction problems in other fields such as solvent selection and drug screening.

Brain Magnetic Resonance Imaging Features of Nicotine-Dependent Individuals and Its Correlation with Polymorphisms of Dopamine D Receptor Gene.

The aim of this research was developed to provide a scientific basis for individualized prevention, clinical diagnosis, and corrective treatment of nicotine addiction. The objects were 214 cases in the smoke group and 43 cases in the control group. According to the Fagerstrom Nicotine Dependence Test (FTND), the smokers were divided into mild nicotine dependence group (FTND < 6 points, 138 cases) and nicotine severe dependence group (≥6 points, 76 cases). The brain structure in long-term smokers was evaluated by using magnetic resonance imaging (MRI). The nicotine dependence was further analyzed by grouping the included individuals, and some candidate genes related to nicotine addiction were screened by combining with bioinformatics analysis. The family research strategy was adopted to detect nicotine addiction susceptibility genes and their polymorphisms. The MRI imaging results showed that the bilateral thalamus, right parietal, and left lens gram-molecule volume (GMV) were negatively correlated with smoking index and smoking years in the smoking group. The GMV of the posterior cingulate cortex in the severe nicotine dependence group was lower than that of the control group, and the GMVs of bilateral thalamus and bilateral superior limbic gyrus in the mild nicotine dependence group were lower than those of the control group. The gene polymorphism detection showed that rs6275 was highly polymorphic in the target population and the frequency of rs6275-C allele was 53.26%. Therefore, the MRI imaging characteristics suggested that the affected brain regions of smokers and people with varying degrees of nicotine dependence were mainly concentrated in response-related pathways and the limbic system and had cumulative effects on the central nervous system. In addition, the M6275 polymorphism of DRD2 gene was associated with susceptibility to nicotine addiction in Chinese population, and the M6275-C allele had a protective effect on susceptibility to nicotine addiction and smoking initiation.

Femtosecond Pulsed Fiber Laser by an Optical Device Based on NaOH-LPE Prepared WSe2 Saturable Absorber.

We report on all-optical devices prepared from WSe2 combined with drawn tapered fibers as saturable absorbers to achieve ultrashort pulse output. The saturable absorber with a high damage threshold and high saturable absorption characteristics is prepared for application in erbium-doped fiber lasers by the liquid phase exfoliation method for WSe2, and the all-optical device exhibited strong saturable absorption characteristics with a modulation depth of 15% and a saturation intensity of 100.58 W. The net dispersion of the erbium-doped fiber laser cavity is ~-0.1 ps2, and a femtosecond pulse output with a bandwidth of 11.4 nm, a pulse width of 390 fs, and a single-pulse capability of 42 pJ is obtained. Results indicate that the proposed WSe2 saturable absorbers are efficient, photonic devices to realize stable fiber lasers. The results demonstrate that the WSe2 saturable absorber is an effective photonic device for realizing stable fiber lasers, which have a certain significance for the development of potential photonic devices.

Highly Sensitive Photothermal Fiber Sensor Based on MXene Device and Vernier Effect.

A photothermal fiber sensor based on a microfiber knot resonator (MKR) and the Vernier effect is proposed and demonstrated. An MXene Ti3C2Tx nanosheet was deposited onto the ring of an MKR using an optical deposition method to prepare photothermal devices. An MXeneMKR and a bare MKR were used as the sensing part and reference part, respectively, of a Vernier-cascade system. The optical and photothermal properties of the bare MKR and the MXeneMKR were tested. Ti3C2Tx was applied to a photothermal fiber sensor for the first time. The experimental results showed that the modulation efficiency of the MXeneMKR was 0.02 nm/mW, and based on the Vernier effect, the modulation efficiency of the cascade system was 0.15 nm/mW. The sensitivity was amplified 7.5 times. Our all-fiber photothermal sensor has many advantages such as low cost, small size, and good system compatibility. Our sensor has broad application prospects in many fields. The proposed stable MKR device based on two-dimensional-material modification provides a new solution for improving the sensitivity of optical fiber sensors.

Regulatory role of miR-129 and miR-384-5p on apoptosis induced by oxygen and glucose deprivation in PC12 cell.

This study aimed to establish the role of miR-129 and miR-384-5p in cerebral ischemia-induced apoptosis. Using PC12 cells transfected with miR-129 or miR-384-5p mimics or inhibitors, oxygen glucose deprivation (OGD) conditions were applied for 4 h to simulate transient cerebral ischemia. Apoptotic phenotypes were assessed via lactate dehydrogenase (LDH) assay, MTT cell metabolism assay, and fluorescence-activated cell sorting (FACS). The effect of miR overexpression and inhibition was evaluated by protein and mRNA detection of bcl-2 and caspase-3, critical apoptosis factors. Finally, the direct relationship of miR-129 and bcl-2 and miR-384-5p and caspase-3 was measured by luciferase reporter assay. The overexpression of miR-384-5p and miR-129 deficiency significantly enhanced cell viability, reduced LDH release, and inhibited apoptosis. By contrast, overexpression of miR-129 and miR-384-5p deficiency aggravated hypoxia-induced apoptosis and cell injury. miR-129 overexpression significantly reduced mRNA and protein levels of bcl-2 and miR-129 inhibition significantly increased mRNA and protein levels of bcl-2 in hypoxic cells.miR-384-5p overexpression significantly reduced protein levels of caspase-3 while miR-384-5p deficiency significantly increased protein levels of caspase-3. However, no changes were observed in caspase-3 mRNA in either transfection paradigm. Finally, luciferase reporter assay confirmed caspase-3 to be a direct target of miR-384-5p; however, no binding activity was detected between bcl-2 and miR-129.Transient cerebral ischemia induces differential expression of miR-129 and miR-384-5p which influences apoptosis by regulating apoptotic factors caspase-3 and bcl-2, thereby participating in the pathological mechanism of cerebral ischemia, and becoming potential targets for the treatment of ischemic cerebral injury in the future.

Immediate effects of Zhongji point acupuncture on pelvic floor structure in female patients with stress urinary incontinence: a randomized, single-blind, and sham-controlled clinical trial protocol.

BACKGROUND: Stress urinary incontinence (SUI) is defined as involuntary leakage of urine from the external urethra due to increased abdominal pressure, for example, upon sneezing, coughing, or exercise. Acupuncture is an effective therapy for patients with SUI, although objective evidence of its benefits or mechanism of action is limited. Patients with SUI often harbor structural changes of pelvic floor, the parameters of which are measurable from various perspectives and in multiple dimensions, dynamically and comprehensively, through transperineal ultrasound (TPUS). The status of such changes may then be assessed following acupuncture procedures. In the present investigation, TPUS serves to gauge the immediate effects of acupuncture on pelvic floor structures in female patients with SUI. METHODS: This protocol calls for a prospective, randomized, controlled, and single-blinded study of 72 female patients with SUI, each randomly assigned as test or control group members. The test group is subjected to one-time acupuncture at the Zhongji (RN3) acupoint for a period of 10 min, whereas the control group undergoes sham acupuncture in the same manner. In both groups, TPUS imaging of pelvic floor is performed before, during, and immediately after acupuncture procedures. Bladder neck mobility (BND), urethral rotation angle (URA), retrovesical angle (RVA), lowest point of bladder (BN-S), and presence/absence of urethral funneling or bladder bulging are then recorded as outcome measures. DISCUSSION: Above efforts are intended to assess real-time pelvic floor structural changes in women undergoing acupuncture for SUI. The subsequent findings may help objectively document the efficacy of acupuncture in this setting and clarify its mechanism of action. TRIAL REGISTRATION: Registration with the Chinese Clinical Trial Registry (ChiCTR200041559) (http://www.chictr.org.cn/edit.aspx?pid=64591&htm=4), was effective December 29, 2020. DATES OF STUDY: 12/19/2020 to 06/30/2022.

Prediction Model of Organic Molecular Absorption Energies based on Deep Learning trained by Chaos-enhanced Accelerated Evolutionary algorithm.

As an important physical property of molecules, absorption energy can characterize the electronic property and structural information of molecules. Moreover, the accurate calculation of molecular absorption energies is highly valuable. Present linear and nonlinear methods hold low calculation accuracies due to great errors, especially irregular complicated molecular systems for structures. Thus, developing a prediction model for molecular absorption energies with enhanced accuracy, efficiency, and stability is highly beneficial. By combining deep learning and intelligence algorithms, we propose a prediction model based on the chaos-enhanced accelerated particle swarm optimization algorithm and deep artificial neural network (CAPSO BP DNN) that possesses a seven-layer 8-4-4-4-4-4-1 structure. Eight parameters related to molecular absorption energies are selected as inputs, such as a theoretical calculating value Ec of absorption energy (B3LYP/STO-3G), molecular electron number Ne, oscillator strength Os, number of double bonds Ndb, total number of atoms Na, number of hydrogen atoms Nh, number of carbon atoms Nc, and number of nitrogen atoms NN; and one parameter representing the molecular absorption energy is regarded as the output. A prediction experiment on organic molecular absorption energies indicates that CAPSO BP DNN exhibits a favourable predictive effect, accuracy, and correlation. The tested absolute average relative error, predicted root-mean-square error, and square correlation coefficient are 0.033, 0.0153, and 0.9957, respectively. Relative to other prediction models, the CAPSO BP DNN model exhibits a good comprehensive prediction performance and can provide references for other materials, chemistry and physics fields, such as nonlinear prediction of chemical and physical properties, QSAR/QAPR and chemical information modelling, etc.

Prediction of pKa Values for Neutral and Basic Drugs based on Hybrid Artificial Intelligence Methods.

The pKa value of drugs is an important parameter in drug design and pharmacology. In this paper, an improved particle swarm optimization (PSO) algorithm was proposed based on the population entropy diversity. In the improved algorithm, when the population entropy was higher than the set maximum threshold, the convergence strategy was adopted; when the population entropy was lower than the set minimum threshold the divergence strategy was adopted; when the population entropy was between the maximum and minimum threshold, the self-adaptive adjustment strategy was maintained. The improved PSO algorithm was applied in the training of radial basis function artificial neural network (RBF ANN) model and the selection of molecular descriptors. A quantitative structure-activity relationship model based on RBF ANN trained by the improved PSO algorithm was proposed to predict the pKa values of 74 kinds of neutral and basic drugs and then validated by another database containing 20 molecules. The validation results showed that the model had a good prediction performance. The absolute average relative error, root mean square error, and squared correlation coefficient were 0.3105, 0.0411, and 0.9685, respectively. The model can be used as a reference for exploring other quantitative structure-activity relationships.

Neuroprotective Effect of the Ginsenoside Rg1 on Cerebral Ischemic Injury In Vivo and In Vitro Is Mediated by PPARγ-Regulated Antioxidative and Anti-Inflammatory Pathways.

The ginsenoside Rg1 exerts a neuroprotective effect during cerebral ischemia/reperfusion injury. Rg1 has been previously reported to improve PPARγ expression and signaling, consequently enhancing its regulatory processes. Due to PPARγ's role in the suppression of oxidative stress and inflammation, Rg1's PPARγ-normalizing capacity may play a role in the observed neuroprotective action of Rg1 during ischemic brain injury. We utilized a middle cerebral artery ischemia/reperfusion injury model in rats in addition to an oxygen glucose deprivation model in cortical neurons to elucidate the mechanisms underlying the neuroprotective effects of Rg1. We found that Rg1 significantly increased PPARγ expression and reduced multiple indicators of oxidative stress and inflammation. Ultimately, Rg1 treatment improved neurological function and diminished brain edema, indicating that Rg1 may exert its neuroprotective action on cerebral ischemia/reperfusion injury through the activation of PPARγ signaling. In addition, the present findings suggested that Rg1 was a potent PPARγ agonist in that it upregulated PPARγ expression and was inhibited by GW9662, a selective PPARγ antagonist. These findings expand our previous understanding of the molecular basis of the therapeutic action of Rg1 in cerebral ischemic injury, laying the ground work for expanded study and clinical optimization of the compound.

Transcriptional and Epigenetic Regulation in Injury-Mediated Neuronal Dendritic Plasticity.

Injury to the nervous system induces localized damage in neural structures and neuronal death through the primary insult, as well as delayed atrophy and impaired plasticity of the delicate dendritic fields necessary for interneuronal communication. Excitotoxicity and other secondary biochemical events contribute to morphological changes in neurons following injury. Evidence suggests that various transcription factors are involved in the dendritic response to injury and potential therapies. Transcription factors play critical roles in the intracellular regulation of neuronal morphological plasticity and dendritic growth and patterning. Mounting evidence supports a crucial role for epigenetic modifications via histone deacetylases, histone acetyltransferases, and DNA methyltransferases that modify gene expression in neuronal injury and repair processes. Gene regulation through epigenetic modification is of great interest in neurotrauma research, and an early picture is beginning to emerge concerning how injury triggers intracellular events that modulate such responses. This review provides an overview of injury-mediated influences on transcriptional regulation through epigenetic modification, the intracellular processes involved in the morphological consequences of such changes, and potential approaches to the therapeutic manipulation of neuronal epigenetics for regulating gene expression to facilitate growth and signaling through dendritic arborization following injury.

Molecular examination of bone marrow stromal cells and chondroitinase ABC-assisted acellular nerve allograft for peripheral nerve regeneration.

The present study aimed to evaluate the molecular mechanisms underlying combinatorial bone marrow stromal cell (BMSC) transplantation and chondroitinase ABC (Ch-ABC) therapy in a model of acellular nerve allograft (ANA) repair of the sciatic nerve gap in rats. Sprague Dawley rats (n=24) were used as nerve donors and Wistar rats (n=48) were randomly divided into the following groups: Group I, Dulbecco's modified Eagle's medium (DMEM) control group (ANA treated with DMEM only); Group II, Ch-ABC group (ANA treated with Ch-ABC only); Group III, BMSC group (ANA seeded with BMSCs only); Group IV, Ch-ABC + BMSCs group (Ch-ABC treated ANA then seeded with BMSCs). After 8 weeks, the expression of nerve growth factor, brain-derived neurotrophic factor and vascular endothelial growth factor in the regenerated tissues were detected by reverse transcription-quantitative polymerase chain reaction and immunohistochemistry. Axonal regeneration, motor neuron protection and functional recovery were examined by immunohistochemistry, horseradish peroxidase retrograde neural tracing and electrophysiological and tibialis anterior muscle recovery analyses. It was observed that combination therapy enhances the growth response of the donor nerve locally as well as distally, at the level of the spinal cord motoneuron and the target muscle organ. This phenomenon is likely due to the propagation of retrograde and anterograde transport of growth signals sourced from the graft site. Collectively, growth improvement on the donor nerve, target muscle and motoneuron ultimately contribute to efficacious axonal regeneration and functional recovery. Thorough investigation of molecular peripheral nerve injury combinatorial strategies are required for the optimization of efficacious therapy and full functional recovery following ANA.

Sciatic nerve regeneration in KLF7-transfected acellular nerve allografts.

OBJECTIVE: Krüppel-like Factor 7 (KLF7) is a transcription factor that promotes axon regeneration in the central nervous system. Here, we assessed whether KLF7 stimulates regeneration after peripheral nerve injury. METHODS: C57BL/6 mice received an acellular nerve allograft (ANA) injected with either adeno-associated virus 2 (AAV2) vector or AAV2-KLF7 for sciatic nerve gap repair. After 4 weeks, KLF7 was detected by RT-PCR, western blot and immunohistochemistry in regenerated nerves. Axonal regeneration and functional recovery were examined by immunohistochemistry, Fluorogold (FG) and cholera toxin B (CTB) retrograde neural tracing, sciatic function index (SFI), angle of ankle, Hargreaves test and electrophysiological analysis. RESULTS: With AAV2-KLF7 injection, KLF7 expression increased in regenerated nerves, and amplitude, score of SFI, angle of ankle and FG-labelled spinal cord neurons were increased. We observed elevated CTB-labelled neurons in dorsal root ganglia (DRG), neurofilaments, P0 (peripheral myelin) and S100 and decreased latency period and withdrawal latencies in the Hargreaves test. The SFI was significantly correlated with amplitude and regenerated axon number. Tyrosine kinase A (TrkA) and B (TrkB) receptors were also increased in the DRG. CONCLUSIONS: Our findings suggest that KLF7 promoted peripheral nerve axonal regeneration, further supporting a role for KLF7 as a growth-promoting transcription factor in the injured nervous system.

Nicotine inhibits microglial proliferation and is neuroprotective in global ischemia rats.

Ischemic injury in rodent models reliably leads to the activation of microglia, which might play a detrimental role in neuronal survival. Our preliminary studies suggest that nicotine plays a potential role in decreasing the numbers of cultured microglia in vitro. In the present study, we found treatment with nicotine 2, 6, and 12 h after ischemia for 7 days significantly increased the survival of CA1 pyramidal neurons in ischemia/reperfusion rats. This effect was accompanied by a significant reduction in the increase of microglia rather than astrocytes, as well as a significant reduction of enhanced expression of tumor necrosis factor-alpha (TNF-α) and interleukin-1beta (IL-1ß) in CA1 induced by ischemia/reperfusion. Nicotine inhibits microglial proliferation in primary cultures with and without the stimulation of granulocyte-macrophage colony-stimulating factor (GM-CSF). Pre-treatment with α-bungarotoxin, a selective α7 nicotinic acetylcholine receptor (α7 nAChR) antagonist, could prevent the inhibitory effects of nicotine on cultured microglial proliferation suggesting that nicotine inhibits the microglial proliferation in an α7 nAChR-dependent fashion. Our results suggest that nicotine inhibits the inflammation mediated by microglia via α7 nAChR and is neuroprotective against ischemic stroke, even when administered 12 h after the insult. α7 nAChR agonists may have uses as anti-ischemic compounds in humans.