CAVE: a cloud-based platform for analysis and visualization of metabolic pathways.

Flux balance analysis (FBA) is an important method for calculating optimal pathways to produce industrially important chemicals in genome-scale metabolic models (GEMs). However, for biologists, the requirement of coding skills poses a significant obstacle to using FBA for pathway analysis and engineering target identification. Additionally, a time-consuming manual drawing process is often needed to illustrate the mass flow in an FBA-calculated pathway, making it challenging to detect errors or discover interesting metabolic features. To solve this problem, we developed CAVE, a cloud-based platform for the integrated calculation, visualization, examination and correction of metabolic pathways. CAVE can analyze and visualize pathways for over 100 published GEMs or user-uploaded GEMs, allowing for quicker examination and identification of special metabolic features in a particular GEM. Additionally, CAVE offers model modification functions, such as gene/reaction removal or addition, making it easy for users to correct errors found in pathway analysis and obtain more reliable pathways. With a focus on the design and analysis of optimal pathways for biochemicals, CAVE complements existing visualization tools based on manually drawn global maps and can be applied to a broader range of organisms for rational metabolic engineering. CAVE is available at https://cave.biodesign.ac.cn/.

Profiling of circulating extracellular vesicle microRNAs reveals diagnostic potential and pathways in non-obstructive and obstructive azoospermia.

The accurate diagnosis of non-obstructive azoospermia (NOA) and obstructive azoospermia (OA) is crucial for selecting appropriate clinical treatments. This study aimed to investigate the pivotal role of miRNAs in circulating plasma extracellular vesicles (EVs) in distinguishing between NOA and OA, as well as uncovering the signaling pathways involved in azoospermia pathogenesis. In this study, differential expression of EV miR-513c-5p and miR-202-5p was observed between NOA and OA patients, while the selenocompound metabolism pathway could be affected in azoospermia through Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analysis. The predictive power of these microRNAs was evaluated using ROC-AUC analysis, demonstrating promising sensitivity, specificity, and area under the curve values. A binomial regression equation incorporating circulating plasma levels of EVs miR-202-5p and miR-513c-5p along with follicle-stimulating hormone was calculated to provide a clinically applicable method for diagnosing NOA and OA. This study presents a potentially non-invasive testing approach for distinguishing between NOA and OA, offering a possibly valuable tool for clinical practice.

EfficientNet-based machine learning architecture for sleep apnea identification in clinical single-lead ECG signal data sets.

OBJECTIVE: Our objective was to create a machine learning architecture capable of identifying obstructive sleep apnea (OSA) patterns in single-lead electrocardiography (ECG) signals, exhibiting exceptional performance when utilized in clinical data sets. METHODS: We conducted our research using a data set consisting of 1656 patients, representing a diverse demographic, from the sleep center of China Medical University Hospital. To detect apnea ECG segments and extract apnea features, we utilized the EfficientNet and some of its layers, respectively. Furthermore, we compared various training and data preprocessing techniques to enhance the model's prediction, such as setting class and sample weights or employing overlapping and regular slicing. Finally, we tested our approach against other literature on the Apnea-ECG database. RESULTS: Our research found that the EfficientNet model achieved the best apnea segment detection using overlapping slicing and sample-weight settings, with an AUC of 0.917 and an accuracy of 0.855. For patient screening with AHI > 30, we combined the trained model with XGBoost, leading to an AUC of 0.975 and an accuracy of 0.928. Additional tests using PhysioNet data showed that our model is comparable in performance to existing models regarding its ability to screen OSA levels. CONCLUSIONS: Our suggested architecture, coupled with training and preprocessing techniques, showed admirable performance with a diverse demographic dataset, bringing us closer to practical implementation in OSA diagnosis. Trial registration The data for this study were collected retrospectively from the China Medical University Hospital in Taiwan with approval from the institutional review board CMUH109-REC3-018.

Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images.

Automated coronary angiography assessment requires precise vessel segmentation, a task complicated by uneven contrast filling and background noise. Our research introduces an ensemble U-Net model, SE-RegUNet, designed to accurately segment coronary vessels using 100 labeled angiographies from angiographic images. SE-RegUNet incorporates RegNet encoders and squeeze-and-excitation blocks to enhance feature extraction. A dual-phase image preprocessing strategy further improves the model's performance, employing unsharp masking and contrast-limited adaptive histogram equalization. Following fivefold cross-validation and Ranger21 optimization, the SE-RegUNet 4GF model emerged as the most effective, evidenced by performance metrics such as a Dice score of 0.72 and an accuracy of 0.97. Its potential for real-world application is highlighted by its ability to process images at 41.6 frames per second. External validation on the DCA1 dataset demonstrated the model's consistent robustness, achieving a Dice score of 0.76 and an accuracy of 0.97. The SE-RegUNet 4GF model's precision in segmenting blood vessels in coronary angiographies showcases its remarkable efficiency and accuracy. However, further development and clinical testing are necessary before it can be routinely implemented in medical practice.

Construction and application of high-quality genome-scale metabolic model of Zymomonas mobilis to guide rational design of microbial cell factories.

High-quality genome-scale metabolic models (GEMs) could play critical roles on rational design of microbial cell factories in the classical Design-Build-Test-Learn cycle of synthetic biology studies. Despite of the constant establishment and update of GEMs for model microorganisms such as Escherichia coli and Saccharomyces cerevisiae, high-quality GEMs for non-model industrial microorganisms are still scarce. Zymomonas mobilis subsp. mobilis ZM4 is a non-model ethanologenic microorganism with many excellent industrial characteristics that has been developing as microbial cell factories for biochemical production. Although five GEMs of Z. mobilis have been constructed, these models are either generating ATP incorrectly, or lacking information of plasmid genes, or not providing standard format file. In this study, a high-quality GEM iZM516 of Z. mobilis ZM4 was constructed. The information from the improved genome annotation, literature, datasets of Biolog Phenotype Microarray studies, and recently updated Gene-Protein-Reaction information was combined for the curation of iZM516. Finally, 516 genes, 1389 reactions, 1437 metabolites, and 3 cell compartments are included in iZM516, which also had the highest MEMOTE score of 91% among all published GEMs of Z. mobilis. Cell growth was then predicted by iZM516, which had 79.4% agreement with the experimental results of the substrate utilization. In addition, the potential endogenous succinate synthesis pathway of Z. mobilis ZM4 was proposed through simulation and analysis using iZM516. Furthermore, metabolic engineering strategies to produce succinate and 1,4-butanediol (1,4-BDO) were designed and then simulated under anaerobic condition using iZM516. The results indicated that 1.68 mol/mol succinate and 1.07 mol/mol 1,4-BDO can be achieved through combinational metabolic engineering strategies, which was comparable to that of the model species E. coli. Our study thus not only established a high-quality GEM iZM516 to help understand and design microbial cell factories for economic biochemical production using Z. mobilis as the chassis, but also provided guidance on building accurate GEMs for other non-model industrial microorganisms.

Machine learning approaches for biomarker discovery to predict large-artery atherosclerosis.

Large-artery atherosclerosis (LAA) is a leading cause of cerebrovascular disease. However, LAA diagnosis is costly and needs professional identification. Many metabolites have been identified as biomarkers of specific traits. However, there are inconsistent findings regarding suitable biomarkers for the prediction of LAA. In this study, we propose a new method integrates multiple machine learning algorithms and feature selection method to handle multidimensional data. Among the six machine learning models, logistic regression (LR) model exhibited the best prediction performance. The value of area under the receiver operating characteristic curve (AUC) was 0.92 when 62 features were incorporated in the external validation set for the LR model. In this model, LAA could be well predicted by clinical risk factors including body mass index, smoking, and medications for controlling diabetes, hypertension, and hyperlipidemia as well as metabolites involved in aminoacyl-tRNA biosynthesis and lipid metabolism. In addition, we found that 27 features were present among the five adopted models that could provide good results. If these 27 features were used in the LR model, an AUC value of 0.93 could be achieved. Our study has demonstrated the effectiveness of combining machine learning algorithms with recursive feature elimination and cross-validation methods for biomarker identification. Moreover, we have shown that using shared features can yield more reliable correlations than either model, which can be valuable for future identification of LAA.

Identification and Characterization of Genes Related to Ampicillin Antibiotic Resistance in Zymomonas mobilis.

Antibiotics can inhibit or kill microorganisms, while microorganisms have evolved antibiotic resistance strategies to survive antibiotics. Zymomonas mobilis is an ideal industrial microbial chassis and can tolerate multiple antibiotics. However, the mechanisms of antibiotic resistance and genes associated with antibiotic resistance have not been fully analyzed and characterized. In this study, we investigated genes associated with antibiotic resistance using bioinformatic approaches and examined genes associated with ampicillin resistance using CRISPR/Cas12a-based genome-editing technology. Six ampicillin-resistant genes (ZMO0103, ZMO0893, ZMO1094, ZMO1650, ZMO1866, and ZMO1967) were identified, and five mutant strains ZM4∆0103, ZM4∆0893, ZM4∆1094, ZM4∆1650, and ZM4∆1866 were constructed. Additionally, a four-gene mutant ZM4∆ARs was constructed by knocking out ZMO0103, ZMO0893, ZMO1094, and ZMO1650 continuously. Cell growth, morphology, and transformation efficiency of mutant strains were examined. Our results show that the cell growth of ZM4∆0103 and ZM4∆ARs was significantly inhibited with 150 µg/mL ampicillin, and cells changed to a long filament shape from a short rod shape. Moreover, the transformation efficiencies of ZM4∆0103 and ZM4∆ARs were decreased. Our results indicate that ZMO0103 is the key to ampicillin resistance in Z. mobilis, and other ampicillin-resistant genes may have a synergetic effect with it. In summary, this study identified and characterized genes related to ampicillin resistance in Z. mobilis and laid a foundation for further study of other antibiotic resistance mechanisms.

A plasmid-free Zymomonas mobilis mutant strain reducing reactive oxygen species for efficient bioethanol production using industrial effluent of xylose mother liquor.

Genome minimization is an effective way for industrial chassis development. In this study, Zymomonas mobilis ZMNP, a plasmid-free mutant strain of Z. mobilis ZM4 with four native plasmids deleted, was constructed using native type I-F CRISPR-Cas system. Cell growth of ZMNP under different temperatures and industrial effluent of xylose mother liquor were examined to investigate the impact of native plasmid removal. Despite ZMNP grew similarly as ZM4 under different temperatures, ZMNP had better xylose mother liquor utilization than ZM4. In addition, genomic, transcriptomic, and proteomic analyses were applied to unravel the molecular changes between ZM4 and ZMNP. Whole-genome resequencing result indicated that an S267P mutation in the C-terminal of OxyR, a peroxide-sensing transcriptional regulator, probably alters the transcription initiation of antioxidant genes for stress responses. Transcriptomic and proteomic studies illustrated that the reason that ZMNP utilized the toxic xylose mother liquor better than ZM4 was probably due to the upregulation of genes in ZMNP involving in stress responses as well as cysteine biosynthesis to accelerate the intracellular ROS detoxification and nucleic acid damage repair. This was further confirmed by lower ROS levels in ZMNP compared to ZM4 in different media supplemented with furfural or ethanol. The upregulation of stress response genes due to the OxyR mutation to accelerate ROS detoxification and DNA/RNA repair not only illustrates the underlying mechanism of the robustness of ZMNP in the toxic xylose mother liquor, but also provides an idea for the rational design of synthetic inhibitor-tolerant microorganisms for economic lignocellulosic biochemical production.

Molecular mechanism of enhanced ethanol tolerance associated with hfq overexpression in Zymomonas mobilis.

Zymomonas mobilis is a promising microorganism for industrial bioethanol production. However, ethanol produced during fermentation is toxic to Z. mobilis and affects its growth and bioethanol production. Although several reports demonstrated that the RNA-binding protein Hfq in Z. mobilis contributes to the tolerance against multiple lignocellulosic hydrolysate inhibitors, the role of Hfq on ethanol tolerance has not been investigated. In this study, hfq in Z. mobilis was either deleted or overexpressed and their effects on cell growth and ethanol tolerance were examined. Our results demonstrated that hfq overexpression improved ethanol tolerance of Z. mobilis, which is probably due to energy saving by downregulating flagellar biosynthesis and heat stress response proteins, as well as reducing the reactive oxygen species induced by ethanol stress via upregulating the sulfate assimilation and cysteine biosynthesis. To explore proteins potentially interacted with Hfq, the TEV protease mediated Yeast Endoplasmic Reticulum Sequestration Screening system (YESS) was established in Z. mobilis. YESS results suggested that Hfq may modulate the cytoplasmic heat shock response by interacting with the heat shock proteins DnaK and DnaJ to deal with the ethanol inhibition. This study thus not only revealed the underlying mechanism of enhanced ethanol tolerance by hfq overexpression, but also provided an alternative approach to investigate protein-protein interactions in Z. mobilis.

Code-Switching Automatic Speech Recognition for Nursing Record Documentation: System Development and Evaluation.

BACKGROUND: Taiwan has insufficient nursing resources due to the high turnover rate of health care providers. Therefore, reducing the heavy workload of these employees is essential. Herein, speech transcription, which has various potential clinical applications, was employed for the documentation of nursing records. The requirement of including only one speaker per transcription facilitated data collection and system development. Moreover, authorization from patients was unnecessary. OBJECTIVE: The aim of this study was to construct a speech recognition system for nursing records such that health care providers can complete nursing records without typing or with only a few edits. METHODS: Nursing records in Taiwan are mainly written in Mandarin, with technical terms and abbreviations presented in both Mandarin and English. Therefore, the training set consisted of English code-switching information. Next, transfer learning (TL) and meta-TL (MTL) methods, which perform favorably in code-switching scenarios, were applied. RESULTS: As of September 2021, the China Medical University Hospital Artificial Intelligence Speech (CMaiSpeech) data set was established by manually annotating approximately 100 hours of recordings from 525 speakers. The word error rate (WER) of the benchmark model of syllable-based TL was 29.54% in code-switching. The WER of the proposed model of syllable-based MTL was 22.20% in code-switching. The test set comprised 17,247 words. Moreover, in a clinical case, the proposed model of syllable-based MTL yielded a WER of 31.06% in code-switching. The clinical test set contained 1159 words. CONCLUSIONS: This paper has two main contributions. First, the CMaiSpeech data set-a Mandarin-English corpus-has been established. Health care providers in Taiwan are often compelled to use a mixture of Mandarin and English in nursing records. Second, an automatic speech recognition system for nursing record document conversion was proposed. The proposed system can shorten the work handover time and further reduce the workload of health care providers.

Corrigendum: Artificial intelligence-assisted remote detection of ST-elevation myocardial infarction using a mini-12-lead electrocardiogram device in prehospital ambulance care.

[This corrects the article DOI: 10.3389/fcvm.2022.1001982.].

Artificial intelligence-assisted remote detection of ST-elevation myocardial infarction using a mini-12-lead electrocardiogram device in prehospital ambulance care.

Objective: To implement an all-day online artificial intelligence (AI)-assisted detection of ST-elevation myocardial infarction (STEMI) by prehospital 12-lead electrocardiograms (ECGs) to facilitate patient triage for timely reperfusion therapy. Methods: The proposed AI model combines a convolutional neural network and long short-term memory (CNN-LSTM) to predict STEMI on prehospital 12-lead ECGs obtained from mini-12-lead ECG devices equipped in ambulance vehicles in Central Taiwan. Emergency medical technicians (EMTs) from the 14 AI-implemented fire stations performed the on-site 12-lead ECG examinations using the mini portable device. The 12-lead ECG signals were transmitted to the AI center of China Medical University Hospital to classify the recordings as "STEMI" or "Not STEMI". In 11 non-AI fire stations, the ECG data were transmitted to a secure network and read by available on-line emergency physicians. The response time was defined as the time interval between the ECG transmission and ECG interpretation feedback. Results: Between July 17, 2021, and March 26, 2022, the AI model classified 362 prehospital 12-lead ECGs obtained from 275 consecutive patients who had called the 119 dispatch centers of fire stations in Central Taiwan for symptoms of chest pain or shortness of breath. The AI's response time to the EMTs in ambulance vehicles was 37.2 ± 11.3 s, which was shorter than the online physicians' response time from 11 other fire stations with no AI implementation (113.2 ± 369.4 s, P < 0.001) after analyzing another set of 335 prehospital 12-lead ECGs. The evaluation metrics including accuracy, precision, specificity, recall, area under the receiver operating characteristic curve, and F1 score to assess the overall AI performance in the remote detection of STEMI were 0.992, 0.889, 0.994, 0.941, 0.997, and 0.914, respectively. During the study period, the AI model promptly identified 10 STEMI patients who underwent primary percutaneous coronary intervention (PPCI) with a median contact-to-door time of 18.5 (IQR: 16-20.8) minutes. Conclusion: Implementation of an all-day real-time AI-assisted remote detection of STEMI on prehospital 12-lead ECGs in the field is feasible with a high diagnostic accuracy rate. This approach may help minimize preventable delays in contact-to-treatment times for STEMI patients who require PPCI.

Identification and Characterization of a Trillin Rhamnosyltransferase From Dioscorea zingiberensis.

Dioscorea zingiberensis accumulates abundant steroidal saponins, such as dioscin, which is the principal bioactive ingredient displaying a wide range of pharmacological activities. Diosgenin is the aglycone of dioscin, and recently, genes encoding cytochrome P450 enzymes in the late steps of diosgenin biosynthesis have been isolated. Diosgenin was successfully synthesized in the cholesterol-producing yeasts. From diosgenin to dioscin, one glucose and two rhamnose groups need to be added. Although genes encoding UDP-glucosyltransferases converting diosgenin to trillin were isolated, genes encoding UDP-rhamnosyltransferases involved in dioscin biosynthesis remain unknown. In this study, we isolated the cDNA encoding the trillin rhamnosyltransferase (designated DzGT1) from D. zingiberensis. Heterologous expression of DzGT1 in Escherichia coli cells showed that the gene product exhibits an enzyme activity that glycosylates the trillin to form prosapogenin A of dioscin (PSA). The transcript level of DzGT1 is in accord with PSA accumulation in different organs of D. zingiberensis. Integration of the biochemical, metabolic, and transcriptional data supported the function of DzGT1 in dioscin biosynthesis. The identification and characterization of DzGT1 will help understand the metabolism of steroidal saponins in D. zingiberensis and provide candidate UDP-rhamnosyltransferase for efficient production of PSA, dioscin, and relevant steroidal saponins in microbial hosts.

Comparison of multiple imputation algorithms and verification using whole-genome sequencing in the CMUH genetic biobank.

A genome-wide association study (GWAS) can be conducted to systematically analyze the contributions of genetic factors to a wide variety of complex diseases. Nevertheless, existing GWASs have provided highly ethnic specific data. Accordingly, to provide data specific to Taiwan, we established a large-scale genetic database in a single medical institution at the China Medical University Hospital. With current technological limitations, microarray analysis can detect only a limited number of single-nucleotide polymorphisms (SNPs) with a minor allele frequency of >1%. Nevertheless, imputation represents a useful alternative means of expanding data. In this study, we compared four imputation algorithms in terms of various metrics. We observed that among the compared algorithms, Beagle5.2 achieved the fastest calculation speed, smallest storage space, highest specificity, and highest number of high-quality variants. We obtained 15,277,414 high-quality variants in 175,871 people by using Beagle5.2. In our internal verification process, Beagle5.2 exhibited an accuracy rate of up to 98.75%. We also conducted external verification. Our imputed variants had a 79.91% mapping rate and 90.41% accuracy. These results will be combined with clinical data in future research. We have made the results available for researchers to use in formulating imputation algorithms, in addition to establishing a complete SNP database for GWAS and PRS researchers. We believe that these data can help improve overall medical capabilities, particularly precision medicine, in Taiwan.

In Vivo Mesoscopic Voltage-Sensitive Dye Imaging of Brain Activation.

Functional mapping of brain activity is important in elucidating how neural networks operate in the living brain. The whisker sensory system of rodents is an excellent model to study peripherally evoked neural activity in the central nervous system. Each facial whisker is represented by discrete modules of neurons all along the pathway leading to the neocortex. These modules are called "barrels" in layer 4 of the primary somatosensory cortex. Their location (approximately 300-500 µm below cortical surface) allows for convenient imaging of whisker-evoked neural activity in vivo. Fluorescence laminar optical tomography (FLOT) provides depth-resolved fluorescence molecular information with an imaging depth of a few millimeters. Angled illumination and detection configurations can improve both resolution and penetration depth. We applied angled FLOT (aFLOT) to record 3D neural activities evoked in the whisker system of mice by deflection of a single whisker in vivo. A 100 µm capillary and a pair of microelectrodes were inserted to the mouse brain to test the capability of the imaging system. The results show that it is possible to obtain 3D functional maps of the sensory periphery in the brain. This approach can be broadly applicable to functional imaging of other brain structures.

Coherence-gated Doppler: a fiber sensor for precise localization of blood flow.

Miniature optical sensors that can detect blood vessels in front of advancing instruments will significantly benefit many interventional procedures. Towards this end, we developed a thin and flexible coherence-gated Doppler (CGD) fiber probe (O.D. = 0.125 mm) that can be integrated with minimally-invasive tools to provide real-time audio feedback of blood flow at precise locations in front of the probe. Coherence-gated Doppler (CGD) is a hybrid technology with features of laser Doppler flowmetry (LDF) and Doppler optical coherence tomography (DOCT). Because of its confocal optical design and coherence-gating capabilities, CGD provides higher spatial resolution than LDF. And compared to DOCT imaging systems, CGD is simpler and less costly to produce. In vivo studies of rat femoral vessels using CGD demonstrate its ability to distinguish between artery, vein and bulk movement of the surrounding soft tissue. Finally, by placing the CGD probe inside a 30-gauge needle and advancing it into the brain of an anesthetized sheep, we demonstrate that it is capable of detecting vessels in front of advancing probes during simulated stereotactic neurosurgical procedures. Using simultaneous ultrasound (US) monitoring from the surface of the brain we show that CGD can detect at-risk blood vessels up to 3 mm in front of the advancing probe. The improved spatial resolution afforded by coherence gating combined with the simplicity, minute size and robustness of the CGD probe suggest it may benefit many minimally invasive procedures and enable it to be embedded into a variety of surgical instruments.