A metric to quantify the time-varying characteristics of underwater acoustic communication channels.

Underwater acoustic communication signals suffer from time dispersion due to time-varying multipath propagation in the ocean. This leads to intersymbol interference, which in turn degrades the performance of the communication system. Typically, the channel correlation functions are employed to describe these characteristics. In this paper, a metric called the channel average correlation coefficient (CACC) is proposed from the correlation function to quantify the time-varying characteristics. It has a theoretical negative relationship with communication performance. Comparative analysis involving simulations and experimental data processing highlights the superior effectiveness of CACC over the traditional metric, the channel coherence time.

ELF5-Regulated lncRNA-TTN-AS1 Alleviates Myocardial Cell Injury via Recruiting PCBP2 to Increase CDK6 Stability in Myocardial Infarction.

Myocardial infarction (MI) seriously threatens the health of elderly people, and reducing myocardial injury is of great significance for the treatment of MI. LncRNA-TTN-AS1 shows protective effects on cardiomyocyte injury, while the role of TTN-AS1 in MI remains unknown. CCK8, flow cytometry, and JC-1 staining assessed cell viability, apoptosis and mitochondrial membrane potential (MMP), respectively. Cellular reactive oxygen species (ROS) and secreted lactate dehydrogenase (LDH) levels were measured. The interactions between ELF5, TTN-AS1, PCBP2 and CDK6 were explored using ChIP, luciferase reporter assay, RIP, and pull-down. The severity of MI in mice was evaluated using TTC, H&E, and TUNEL staining. The data revealed that OGD/R significantly induced ROS, mitochondrial injury and apoptosis in AC16 cells, while overexpression of ELF5 or TTN-AS1 reversed these phenomena. ELF5 transcriptionally activated TTN-AS1 through binding with its promoter. TTN-AS1 increased CDK6 stability via recruiting PCBP2. CDK6 knockdown abolished the inhibitory effects of TTN-AS1 overexpression on OGD/R-induced myocardial injury. Furthermore, overexpression of TTN-AS1 or ELF5 alleviated MI progression in mice by upregulating CDK6. Collectively, TTN-AS1 transcriptionally regulated by ELF5 alleviated myocardial apoptosis and injury during MI via recruiting PCBP2 to increase CDK6 stability, which shed new lights on exploring new strategies against MI.

Portraying on-road CO2 concentrations using street view panoramas and ensemble learning.

A significant reduction in carbon dioxide (CO2) emissions caused by transportation is essential for attaining sustainable urban development. Carbon concentrations from road traffic in urban areas exhibit complex spatial patterns due to the impact of street configurations, mobile sources, and human activities. However, a comprehensive understanding of these patterns, which involve complex interactions, is still lacking due to the human perspective of road interface characteristics has not been taken into account. In this study, a mobile travel platform was constructed to collect both on-road navigation Street View Panoramas (OSVPs) and the corresponding CO2 concentrations. >100 thousand sample pairs that matched "street view-CO2 concentration" were obtained, covering 675.8 km of roads in Shenzhen, China. In addition, four ensemble learning (EL) models were utilized to establish nonlinear connections between the semantic and object features of streetscapes and CO2 concentrations. After performing EL fusion modeling, the predictive R2 in the test set exceeded 90 %, and the mean absolute error (MAE) was <3.2 ppm. The model was applied to Baidu Street View Panoramas (BSVPs) in Shenzhen to generate a map of average on-road CO2 with a 100 m resolution, and the Local Indicator of Spatial Association (LISA) was then used to identify high CO2 intensity spatial clusters. Additionally, the Light Gradient Boost-SHapley Additive exPlanation (LGB-SHAP) analysis revealed that vertically planted trees can reduce CO2 emissions from on-road sources. Moreover, the factors that affect on-road CO2 exhibit interaction and threshold effects. Street View Panoramas (SVPs) and Artificial Intelligence (AI) were adopted here to enhance the spatial measurement of on-road CO2 concentrations and the understanding of driving factors. Our approach facilitates the assessment and design of low-emission transportation in urban areas, which is critical for promoting sustainable traffic development.

Study on the Correlation Between Patent Foramen Ovale and Migraine Based on Meta Analysis.

Objective: This meta-analysis systematically investigates the association between Patent Foramen Ovale (PFO) and the prevalence of migraine. Our goal is to quantify this relationship and evaluate its implications for clinical practice and future research. Methods: An extensive literature search was carried out in various databases, such as PubMed, Embase, The Cochrane Library, Web of Science, CNKI, VIP, WanFang Data, and CBM, up to November 2023. The search focused on case-control, cross-sectional, and cohort studies examining the link between PFO and migraine. The literature screening and data extraction, based on predefined inclusion and exclusion criteria, were independently conducted by two reviewers. The studies' quality was evaluated using the Newcastle-Ottawa Scale (NOS), and RevMan 5.3 software was employed for the meta-analysis. Results: A total of 27 studies involving 8,875 participants were included in the meta-analysis. The results indicate a statistically significant association between PFO and migraine prevalence. Key findings include: (1) Overall, individuals with migraine had higher rates of PFO compared to healthy controls (OR = 3.22, 95% CI = 2.21 to 4.67, P < .00001). (2) The association was stronger in the Migraine with Aura group (OR = 3.69, 95% CI = 1.93 to 7.04, P < .0001) than in the Non-Migraine with Aura group (OR = 1.48, 95% CI = 1.09 to 2.00, P = .01). (3) The prevalence of PFO was notably higher in the Migraine with Aura group compared to the Non-Migraine with Aura group (OR = 2.32, 95% CI = 1.96 to 2.76, P < .00001). Conclusion: The analysis confirms a noteworthy correlation between PFO and migraine, underscoring the relationship and suggesting additional studies need to elucidate the underlying mechanisms and clinical ramifications.

Comprehensive genome-wide analysis of wheat xylanase inhibitor protein (XIP) genes: unveiling their role in Fusarium head blight resistance and plant immune mechanisms.

In this comprehensive genome-wide study, we identified and classified 83 Xylanase Inhibitor Protein (XIP) genes in wheat, grouped into five distinct categories, to enhance understanding of wheat's resistance to Fusarium head blight (FHB), a significant fungal threat to global wheat production. Our analysis reveals the unique distribution of XIP genes across wheat chromosomes, particularly at terminal regions, suggesting their role in the evolutionary expansion of the gene family. Several XIP genes lack signal peptides, indicating potential alternative secretion pathways that could be pivotal in plant defense against FHB. The study also uncovers the sequence homology between XIPs and chitinases, hinting at a functional diversification within the XIP gene family. Additionally, the research explores the association of XIP genes with plant immune mechanisms, particularly their linkage with plant hormone signaling pathways like abscisic acid and jasmonic acid. XIP-7A3, in particular, demonstrates a significant increase in expression upon FHB infection, highlighting its potential as a key candidate gene for enhancing wheat's resistance to this disease. This research not only enriches our understanding of the XIP gene family in wheat but also provides a foundation for future investigations into their role in developing FHB-resistant wheat cultivars. The findings offer significant implications for wheat genomics and breeding, contributing to the development of more resilient crops against fungal diseases.

Identifying diagnostic indicators for type 2 diabetes mellitus from physical examination using interpretable machine learning approach.

Background: Identification of patients at risk for type 2 diabetes mellitus (T2DM) can not only prevent complications and reduce suffering but also ease the health care burden. While routine physical examination can provide useful information for diagnosis, manual exploration of routine physical examination records is not feasible due to the high prevalence of T2DM. Objectives: We aim to build interpretable machine learning models for T2DM diagnosis and uncover important diagnostic indicators from physical examination, including age- and sex-related indicators. Methods: In this study, we present three weighted diversity density (WDD)-based algorithms for T2DM screening that use physical examination indicators, the algorithms are highly transparent and interpretable, two of which are missing value tolerant algorithms. Patients: Regarding the dataset, we collected 43 physical examination indicator data from 11,071 cases of T2DM patients and 126,622 healthy controls at the Affiliated Hospital of Southwest Medical University. After data processing, we used a data matrix containing 16004 EHRs and 43 clinical indicators for modelling. Results: The indicators were ranked according to their model weights, and the top 25% of indicators were found to be directly or indirectly related to T2DM. We further investigated the clinical characteristics of different age and sex groups, and found that the algorithms can detect relevant indicators specific to these groups. The algorithms performed well in T2DM screening, with the highest area under the receiver operating characteristic curve (AUC) reaching 0.9185. Conclusion: This work utilized the interpretable WDD-based algorithms to construct T2DM diagnostic models based on physical examination indicators. By modeling data grouped by age and sex, we identified several predictive markers related to age and sex, uncovering characteristic differences among various groups of T2DM patients.

Characteristics of Damage to Brown Rice Kernels under Single and Continuous Mechanical Compression Conditions.

During the rice milling process, single and continuous compression occurs between brown rice and the processing parts. When the external load exceeds the yield limit of brown rice, brown rice kernels are damaged; with an increase in compression deformation or the extent of compression, the amount of damage to the kernels expands and accumulates, ultimately leading to the fracture and breakage of kernels. In order to investigate the mechanical compression damage characteristics of brown rice kernels under real-world working conditions, this study constructs an elastic-plastic compression model and a continuous damage model of brown rice kernels based on Hertz theory and continuous damage theory; the accuracy of this model is verified through experiments, and the relevant processing critical parameters are calculated. In this study, three varieties of brown rice kernels are taken as the research object, and mechanical compression tests are carried out using a texture apparatus; finally, the test data are analysed and calculated by combining them with the theoretical model to obtain the relevant critical parameters of damage. The results of the single compression crushing test of brown rice kernels showed that the maximum destructive forces Fc in the single compression of Hunan Early indica 45, Hunan Glutinous 28, and Southern Japonica 518 kernels were 134.77 ± 11.20 N, 115.64 ± 4.35 N, and 115.84 ± 5.89 N, respectively; the maximum crushing deformations αc in the single compression crushing test were 0.51 ± 0.04 mm, 0.43 ± 0.01 mm, and 0.48 ± 0.17 mm, respectively; and the critical average deformations αs of elasticity-plasticity deformation were 0.224 mm, 0.267 mm, and 0.280 mm, respectively. The results of the continuous compression crushing test of brown rice kernels showed that the critical deformations αd of successive compression damage formation were 0.224 mm, 0.267 mm, and 0.280 mm, and the deformation ratios δ of compression damage were 12.24%, 14.35%, and 12.84%. From the test results, it can be seen that the continuous application of compression load does not result in the crushing of kernels if the compression deformation is less than αd during mechanical compression. The continuous application of compressive loads can lead to fragmentation of the kernels if the compressive deformation exceeds αd; the larger the compression variant, the less compression is required for crushing. If the compression deformation exceeds αc, then a single compressive load can directly fragment the kernels. Therefore, the load employed during rice milling should be based on the variety of brown rice used in order to prevent brown rice deformation, which should be less than αd, and the maximum load should not exceed Fc. The results of this study provide a theoretical reference for the structure and parameter optimisation of a rice milling machine.

Model fusion for predicting unconventional proteins secreted by exosomes using deep learning.

Unconventional secretory proteins (USPs) are vital for cell-to-cell communication and are necessary for proper physiological processes. Unlike classical proteins that follow the conventional secretory pathway via the Golgi apparatus, these proteins are released using unconventional pathways. The primary modes of secretion for USPs are exosomes and ectosomes, which originate from the endoplasmic reticulum. Accurate and rapid identification of exosome-mediated secretory proteins is crucial for gaining valuable insights into the regulation of non-classical protein secretion and intercellular communication, as well as for the advancement of novel therapeutic approaches. Although computational methods based on amino acid sequence prediction exist for predicting unconventional proteins secreted by exosomes (UPSEs), they suffer from significant limitations in terms of algorithmic accuracy. In this study, we propose a novel approach to predict UPSEs by combining multiple deep learning models that incorporate both protein sequences and evolutionary information. Our approach utilizes a convolutional neural network (CNN) to extract protein sequence information, while various densely connected neural networks (DNNs) are employed to capture evolutionary conservation patterns.By combining six distinct deep learning models, we have created a superior framework that surpasses previous approaches, achieving an ACC score of 77.46% and an MCC score of 0.5406 on an independent test dataset.

Household Decision-Making Choices: Investment in Children's Education or Self-Consumption.

Analyzing the sustainable decision-making mechanism between household consumption and education investment can theoretically develop education. This study uses the continuous-time utility model to demonstrate the independent characteristics of consumption and education investment, as well as the principle of decision incompatibility in the decision-making process of the utility maximization problem. Then, we establish a three-phase logarithmic utility model to obtain the intertemporal decision-making path of a family. The analysis shows that the investment allocation ratio between the two phases depends on the expected and discounted level of the offsprings' abilities, while the total investment level is related to parental altruism. When parents, with foresight, factor in prospective transfer payments from progeny, the optimal decision is to maximize their children's ultimate human capital within a given total investment. Education investment not only squeezes out consumption but also promotes consumption in various periods due to future transfer payments. The decision-making process of three typical growth stages indicates that as offspring mature and their human capital increases, parents' willingness to invest in education decreases while self-consumption escalates. This study provides a new perspective and theoretical basis for studying household education expenditure, motivation, and related policy formulation.

Constructing a 3D Bi2WO6/ZnIn2S4 direct Z-scheme heterostructure for improved photocatalytic CO2 reduction performance.

Developing efficient heterojunction photocatalysts with enhanced charge transfer and reduced recombination rates of photogenerated carriers is crucial for harnessing solar energy in the photocatalytic CO2 reduction into renewable fuels. This study employed electrostatic self-assembly techniques to construct a 3D Bi2WO6/ZnIn2S4 direct Z-scheme heterojunctions. The unique 3D structure provided abundant active sites and facilitated CO2 adsorption. Moreover, the optimized Bi2WO6/ZnIn2S4 composite demonstrated an impressive CH4 yield of 19.54 µmol g-1 under 4 h of simulated sunlight irradiation, which was about 8.73 and 16.30-fold higher than pure ZnIn2S4 and Bi2WO6. The observed enhancements in photocatalytic performance are attributed to forming a direct Z-scheme heterojunction, which effectively promotes charge transport and migration. This research introduces a novel strategy for constructing photocatalysts through the synergistic effect of morphological interface modifications.

Transcription factor FOXP4 inversely governs tumor suppressor genes and contributes to thyroid cancer progression.

Objective: In recent decades, thyroid cancer (TC) has exhibited a rising incidence pattern. Elevated levels of the transcription factor FOXP4 have been strongly linked to the progression of diverse tumors; nevertheless, its specific role in thyroid cancer remains underexplored. The primary objective of this study was to elucidate the functions of FOXP4 and its associated target gene, FBXW7, in the context of thyroid cancer. Methods: FOXP4 and FBXW7 expression levels in TC tissues and cell lines were assessed through immunohistochemistry and RT-qPCR analyses. The functional aspects of FOXP4, including its effects on cell proliferation, migration capabilities, cell cycle regulation, and epithelial-mesenchymal transition (EMT), were investigated. Furthermore, the interaction between FOXP4 and FBXW7 was confirmed using chromatin immunoprecipitation (ChIP) assays. The impact of FBXW7 on FOXP4-mediated cellular phenotypes was subsequently examined. Additionally, the in vivo role of FOXP4 and FBXW7 in tumor growth was elucidated through the establishment of a murine tumor model. Results: Elevated levels of FOXP4 were observed in papillary carcinoma tissues, and patients exhibiting high FBXW7 levels showed a more favorable prognosis. KTC-1 cells displayed a concomitant increase in FOXP4 expression and decrease in FBXW7 expression. FOXP4 overexpression in these cells enhanced cell proliferation, migration capabilities, and EMT. The interaction between the FOXP4 protein and the FBXW7 promoter was confirmed, and the effects of FOXP4 were mitigated upon overexpression of FBXW7. Furthermore, knockdown of FOXP4 led to decelerated growth of transplanted tumors and increased FBXW7 levels within the tumors. Conclusion: The findings of the current study underscore the regulatory role of FOXP4 in the transcription of FBXW7 and establish a clear link between aberrations in FBXW7 expression and the manifestation of malignant phenotypes in highly aggressive TC cells.

Research on rice starch gel preparation and crosslink network structure-rheological property based on direct-writing 3D printing.

Amylopectin and amylose components are natural polymers within rice starch granules, intertwined in specific conditions to form gel polymerized with pore crosslink network, has potential printing properties. In this study, a rice starch gel preparation scheme is proposed for stable properties, and starch granule phase transition mechanism is analyzed based on RVA test during preparation, it can be divided into four-stage, swelling, reacting, homogenizing and self-assembling stages. Gel surface tension and contact angle tested with starch concentration effect, a correlation is developed, reflecting a competition result to gel droplet macro-morphology between the intermolecular cohesion and crosslink network. SEM is used to reveal typical crosslink structures of different starch molecular component proportions, providing objective support for starch gel rheologic property change. Results indicate gel interior crosslink network formed under concentration 12 %, the gel with amylose 4.475 % presents better printing accuracy. Gel shear modulus positively correlated with amylose proportion. Japonica gel under 20 % is of higher viscosity and rapid reassembly ability after interior crosslink network is broken. Max dynamic viscosity is positively correlated with starch concentration. The study aims to provide theoretical and practical support for in-depth analysis of rice starch material application in direct-write 3D printing.

EnsembleDL-ATG: Identifying autophagy proteins by integrating their sequence and evolutionary information using an ensemble deep learning framework.

Autophagy is a primary mechanism for maintaining cellular homeostasis. The synergistic actions of autophagy-related (ATG) proteins strictly regulate the whole autophagic process. Therefore, accurate identification of ATGs is a first and critical step to reveal the molecular mechanism underlying the regulation of autophagy. Current computational methods can predict ATGs from primary protein sequences, but owing to the limitations of algorithms, significant room for improvement still exists. In this research, we propose EnsembleDL-ATG, an ensemble deep learning framework that aggregates multiple deep learning models to predict ATGs from protein sequence and evolutionary information. We first evaluated the performance of individual networks for various feature descriptors to identify the most promising models. Then, we explored all possible combinations of independent models to select the most effective ensemble architecture. The final framework was built and maintained by an organization of four different deep learning models. Experimental results show that our proposed method achieves a prediction accuracy of 94.5 % and MCC of 0.890, which are nearly 4 % and 0.08 higher than ATGPred-FL, respectively. Overall, EnsembleDL-ATG is the first ATG machine learning predictor based on ensemble deep learning. The benchmark data and code utilized in this study can be accessed for free at https://github.com/jingry/autoBioSeqpy/tree/2.0/examples/EnsembleDL-ATG.

Cluster-aware channel estimation with deep learning method in deep-water acoustic communications.

In underwater acoustic (UWA) communications, channels often exhibit a clustered-sparse structure, wherein most of the channel impulse responses are near zero, and only a small number of nonzero taps assemble to form clusters. Several algorithms have used the time-domain sparse characteristic of UWA channels to reduce the complexity of channel estimation and improve the accuracy. Employing the clustered structure to enhance channel estimation performance provides another promising research direction. In this work, a deep learning-based channel estimation method for UWA orthogonal frequency division multiplexing (OFDM) systems is proposed that leverages the clustered structure information. First, a cluster detection model based on convolutional neural networks is introduced to detect the cluster of UWA channels. This method outperforms the traditional Page test algorithm with better accuracy and robustness, particularly in low signal-to-noise ratio conditions. Based on the cluster detection model, a cluster-aware distributed compressed sensing channel estimation method is proposed, which reduces the noise-induced errors by exploiting the joint sparsity between adjacent OFDM symbols and limiting the search space of channel delay spread. Numerical simulation and sea trial results are provided to illustrate the superior performance of the proposed approach in comparison with existing sparse UWA channel estimation methods.

Bidirectional negative feedback actions of DNMT3A and miR-145 in regulating autophagy in cardiac fibroblasts and affecting myocardial fibrosis.

Epigenetic regulation has crucial implications for myocardial fibrosis. It has been reported that autophagy, regulated by miR-145, is implicated in the proliferation and fibrosis of cardiac fibroblasts (CFs). However, how it works during the process remains unclear. This study explored the exact effects of epigenetic regulation of miR-145 expression on autophagy, proliferation, and fibrosis of CFs. To examine the expression levels of myocardial fibrosis markers (α-SMA and collagen I), autophagy-related proteins (LC3I, LC3II, p62), DNMT3A, and miR-145, qRT-PCR and western blot were employed. And the proliferation of CFs was detected by CCK-8 and ErdU. As for the determination of the binding relationship between DNMT3A and miR-145, dual-luciferase assay was conducted. Next, the detection of the methylation level of the pre-miR-145 promoter region was completed by MSP. And the verification of the effect of the DNMT3A/miR-145 axis on myocardial fibrosis was accomplished by constructing mouse myocardial infarction (MI) models based on the ligation of the left anterior descending method. In TGF-ß1-activated CFs, remarkable up-regulation of DNMT3 and considerable down-regulation of miR-145 were observed. And further experiments indicated that DNMT3A was able to down-regulate miR-145 expression by maintaining the hypermethylation level of the pre-miR-145 promoter region. In addition, DNMT3A expression could be directly targeted and negatively modulated by miR-145. Moreover, in vitro cell experiments and mouse MI models demonstrated that DNMT3A overexpression could inhibit autophagy, and promote cell proliferation and fibrosis of CFs. However, this kind of effect could be reversed by miR-145 overexpression. In summary, myocardial fibroblast autophagy can be regulated by bidirectional negative feedback actions of DNMT3A and miR-145, thus affecting myocardial fibrosis. This finding will provide a potential target for the clinical treatment of myocardial fibrosis.

Research on microstructural-mechanical and shearing properties of castor seed during mechanical extraction.

Castor seed oil, as an important biomass fuel, has attracted extensive attention worldwide due to inclusive applications. Castor seed screw mechanical extraction is in fact seed shear damage and oil output. Seed shearing mechanism has been investigated with a developed tribometer. Influences of pressing load, shearing speed, roller roughness were analyzed. Castor seed structural damage was in-situ observed with optical microscope, and in-depth analyzed with Scanning Electron Microscopy and Energy Dispersive Spectroscopy. The results reveal that shear interaction can be divided into three stages: coat damage, transition shearing and endosperm oil output. Seed shear mechanism includes coat peeling, endosperm plowing, tissue transferring and oil lubrication. High pressing load leads to more damage of coat and endosperm, causing more oil to flow out. With shearing speed increasing, coat is easily peeled, obvious endosperm shear plowing and oil lubrication happened in contact area. Coat damage by high roughness leads more oil output. Castor oil enters the contact area and work as lubricant, leading to the decrease of friction resistance.

Targeting of cold-inducible RNA-binding protein alleviates sepsis via alleviating inflammation, apoptosis and oxidative stress in heart.

A systemic inflammatory response is observed in patients undergoing shock and sepsis. This study aimed to explore the effects of cold-inducible RNA-binding protein (CIRP) on sepsis-associated cardiac dysfunction and the underlying mechanism. In vivo and in vitro lipopolysaccharide (LPS)-induced sepsis models were established in mice and neonatal rat cardiomyocytes (NRCMs), respectively. CRIP expressions were increased in the mouse heart and NRCMs treated with LPS. CIRP knockdown alleviated LPS-induced decreases of left ventricular ejection fraction and fractional shortening. CIRP downregulation attenuated the increases of inflammatory factors in the LPS-induced septic mouse heart, and NRCMs. The enhanced oxidative stress in the LPS-induced septic mouse heart and NRCMs was suppressed after CIRP knockdown. By contrast, CIRP overexpression yielded the opposite results. Our current study indicates that the knockdown of CIRP protects against sepsis-induced cardiac dysfunction through alleviating inflammation, apoptosis and oxidative stress of cardiomyocytes.

Evaluation and development of deep neural networks for RNA 5-Methyluridine classifications using autoBioSeqpy.

Post-transcriptionally RNA modifications, also known as the epitranscriptome, play crucial roles in the regulation of gene expression during development. Recently, deep learning (DL) has been employed for RNA modification site prediction and has shown promising results. However, due to the lack of relevant studies, it is unclear which DL architecture is best suited for some pyrimidine modifications, such as 5-methyluridine (m5U). To fill this knowledge gap, we first performed a comparative evaluation of various commonly used DL models for epigenetic studies with the help of autoBioSeqpy. We identified optimal architectural variations for m5U site classification, optimizing the layer depth and neuron width. Second, we used this knowledge to develop Deepm5U, an improved convolutional-recurrent neural network that accurately predicts m5U sites from RNA sequences. We successfully applied Deepm5U to transcriptomewide m5U profiling data across different sequencing technologies and cell types. Third, we showed that the techniques for interpreting deep neural networks, including LayerUMAP and DeepSHAP, can provide important insights into the internal operation and behavior of models. Overall, we offered practical guidance for the development, benchmark, and analysis of deep learning models when designing new algorithms for RNA modifications.

Fast and Efficient Design of Deep Neural Networks for Predicting N7-Methylguanosine Sites Using autoBioSeqpy.

N7-Methylguanosine (m7G) is a crucial post-transcriptional RNA modification that plays a pivotal role in regulating gene expression. Accurately identifying m7G sites is a fundamental step in understanding the biological functions and regulatory mechanisms associated with this modification. While whole-genome sequencing is the gold standard for RNA modification site detection, it is a time-consuming, expensive, and intricate process. Recently, computational approaches, especially deep learning (DL) techniques, have gained popularity in achieving this objective. Convolutional neural networks and recurrent neural networks are examples of DL algorithms that have emerged as versatile tools for modeling biological sequence data. However, developing an efficient network architecture with superior performance remains a challenging task, requiring significant expertise, time, and effort. To address this, we previously introduced a tool called autoBioSeqpy, which streamlines the design and implementation of DL networks for biological sequence classification. In this study, we utilized autoBioSeqpy to develop, train, evaluate, and fine-tune sequence-level DL models for predicting m7G sites. We provided detailed descriptions of these models, along with a step-by-step guide on their execution. The same methodology can be applied to other systems dealing with similar biological questions. The benchmark data and code utilized in this study can be accessed for free at http://github.com/jingry/autoBioSeeqpy/tree/2.0/examples/m7G.

ATP-Binding Cassette Exporter PDR11-Mediated Terpenoid Secretion in Engineered Yeast.

The metabolic burden caused by terpenoid accumulation limits the development of highly efficient microbial cell factories, which can be circumvented using exporter-mediated product secretion. Although our previous study showed that the pleiotropic drug resistance exporter (PDR11) mediates the export of rubusoside in Saccharomyces cerevisiae, the underlying mechanism is still unclear. Herein, we used GROMACS software to simulate PDR11-mediated rubusoside recruitment and found six residues (D116, D167, Y168, P521, R663, and L1146) on PDR11 that are critical for this process. We also explored the exportation potential of PDR11 for 39 terpenoids by calculating their binding affinity using batch molecular docking. Then, we verified the accuracy of the predicted results by conducting experiments with squalene, lycopene, and ß-carotene as examples. We found that PDR11 can efficiently secrete terpenoids with binding affinities lower than -9.0 kcal/mol. Combining the computer-based prediction and experimental verification, we proved that binding affinity is a reliable parameter to screen exporter substrates and might potentially enable rapid screening of exporters for natural products in microbial cell factories.