Cm-siRPred: Predicting chemically modified siRNA efficiency based on multi-view learning strategy.

The rational modification of siRNA molecules is crucial for ensuring their drug-like properties. Machine learning-based prediction of chemically modified siRNA (cm-siRNA) efficiency can significantly optimize the design process of siRNA chemical modifications, saving time and cost in siRNA drug development. However, existing in-silico methods suffer from limitations such as small datasets, inadequate data representation capabilities, and lack of interpretability. Therefore, in this study, we developed the Cm-siRPred algorithm based on a multi-view learning strategy. The algorithm employs a multi-view strategy to represent the double-strand sequences, chemical modifications, and physicochemical properties of cm-siRNA. It incorporates a cross-attention model to globally correlate different representation vectors and a two-layer CNN module to learn local correlation features. The algorithm demonstrates exceptional performance in cross-validation experiments, independent dataset, and case studies on approved siRNA drugs, and showcasing its robustness and generalization ability. In addition, we developed a user-friendly webserver that enables efficient prediction of cm-siRNA efficiency and assists in the design of siRNA drug chemical modifications. In summary, Cm-siRPred is a practical tool that offers valuable technical support for siRNA chemical modification and drug efficiency research, while effectively assisting in the development of novel small nucleic acid drugs. Cm-siRPred is freely available at https://cellknowledge.com.cn/sirnapredictor/.

ncRS: A resource of non-coding RNAs in sepsis.

Sepsis, a life-threatening condition triggered by the body's response to infection, presents a significant global healthcare challenge characterized by disarrayed host responses, widespread inflammation, organ impairment, and heightened mortality rates. This study introduces the ncRS database (http://www.ncrdb.cn), a meticulously curated repository housing 1144 experimentally validated non-coding RNAs (ncRNAs) intricately linked with sepsis. ncRS offers comprehensive RNA data, exhaustive experimental insights, and integrated annotations from diverse databases. This resource empowers researchers and clinicians to decipher ncRNAs' roles in sepsis pathogenesis, potentially identifying vital biomarkers for early diagnosis and prognosis, thus facilitating personalized treatments.

An orally bioavailable SARS-CoV-2 main protease inhibitor exhibits improved affinity and reduced sensitivity to mutations.

Inhibitors of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) main protease (Mpro) such as nirmatrelvir (NTV) and ensitrelvir (ETV) have proven effective in reducing the severity of COVID-19, but the presence of resistance-conferring mutations in sequenced viral genomes raises concerns about future drug resistance. Second-generation oral drugs that retain function against these mutants are thus urgently needed. We hypothesized that the covalent hepatitis C virus protease inhibitor boceprevir (BPV) could serve as the basis for orally bioavailable drugs that inhibit SARS-CoV-2 Mpro more efficiently than existing drugs. Performing structure-guided modifications of BPV, we developed a picomolar-affinity inhibitor, ML2006a4, with antiviral activity, oral pharmacokinetics, and therapeutic efficacy similar or superior to those of NTV. A crucial feature of ML2006a4 is a derivatization of the ketoamide reactive group that improves cell permeability and oral bioavailability. Last, ML2006a4 was found to be less sensitive to several mutations that cause resistance to NTV or ETV and occur in the natural SARS-CoV-2 population. Thus, anticipatory design can preemptively address potential resistance mechanisms to expand future treatment options against coronavirus variants.

MCSdb, a database of proteins residing in membrane contact sites.

Organelles do not act as autonomous discrete units but rather as interconnected hubs that engage in extensive communication by forming close contacts called "membrane contact sites (MCSs)". And many proteins have been identified as residing in MCS and playing important roles in maintaining and fulfilling specific functions within these microdomains. However, a comprehensive compilation of these MCS proteins is still lacking. Therefore, we developed MCSdb, a manually curated resource of MCS proteins and complexes from publications. MCSdb documents 7010 MCS protein entries and 263 complexes, involving 24 organelles and 44 MCSs across 11 species. Additionally, MCSdb orchestrates all data into different categories with multitudinous information for presenting MCS proteins. In summary, MCSdb provides a valuable resource for accelerating MCS functional interpretation and interorganelle communication deciphering.

Applications of single­cell omics and spatial transcriptomics technologies in gastric cancer (Review).

Gastric cancer (GC) is a prominent contributor to global cancer-related mortalities, and a deeper understanding of its molecular characteristics and tumor heterogeneity is required. Single-cell omics and spatial transcriptomics (ST) technologies have revolutionized cancer research by enabling the exploration of cellular heterogeneity and molecular landscapes at the single-cell level. In the present review, an overview of the advancements in single-cell omics and ST technologies and their applications in GC research is provided. Firstly, multiple single-cell omics and ST methods are discussed, highlighting their ability to offer unique insights into gene expression, genetic alterations, epigenomic modifications, protein expression patterns and cellular location in tissues. Furthermore, a summary is provided of key findings from previous research on single-cell omics and ST methods used in GC, which have provided valuable insights into genetic alterations, tumor diagnosis and prognosis, tumor microenvironment analysis, and treatment response. In summary, the application of single-cell omics and ST technologies has revealed the levels of cellular heterogeneity and the molecular characteristics of GC, and holds promise for improving diagnostics, personalized treatments and patient outcomes in GC.

SAGESDA: Multi-GraphSAGE networks for predicting SnoRNA-disease associations.

Over the years, extensive research has highlighted the functional roles of small nucleolar RNAs in various biological processes associated with the development of complex human diseases. Therefore, understanding the existing relationships between different snoRNAs and diseases is crucial for advancing disease diagnosis and treatment. However, classical biological experiments for identifying snoRNA-disease associations are expensive and time-consuming. Therefore, there is an urgent need for cost-effective computational techniques that can enhance the efficiency and accuracy of prediction. While several computational models have already been proposed, many suffer from limitations and suboptimal performance. In this study, we introduced a novel Graph Neural Network-based (GNN) classification model, called SAGESDA, which is implemented through the GraphSAGE architecture with attention for the prediction of snoRNA-disease associations. The classifier leverages local neighbouring nodes in a heterogeneous network to generate new node embeddings through message passing. The mini-batch gradient descent technique was applied to divide the graph into smaller sub-graphs, which enhances the model's accuracy, speed and scalability. With these advancements, SAGESDA attained an area under the receiver operating characteristic (ROC) curve (AUC) of 0.92 using the standard dot product classifier, surpassing previous related studies. This notable performance demonstrates that SAGESDA is a promising model for predicting unknown snoRNA-disease associations with high accuracy. The SAGESDA implementation details can be obtained from https://github.com/momanyibiffon/SAGESDA.git.

MetaboliteCOVID: A manually curated database of metabolite markers for COVID-19.

In the realm of unraveling COVID-19's intricacies, numerous metabolomic investigations have been conducted to discern the unique metabolic traits exhibited within infected patients. These endeavors have yielded a substantial reservoir of potential data pertaining to metabolic biomarkers linked to the virus. Despite these strides, a comprehensive and meticulously structured database housing these crucial biomarkers remains absent. In this study, we developed MetaboliteCOVID, a manually curated database of COVID-19-related metabolite markers. The database currently comprises 665 manually selected entries of significantly altered metabolites associated with early diagnosis, disease severity, prognosis, and drug response in COVID-19, encompassing 337 metabolites. Additionally, the database offers a user-friendly interface, containing abundant information for querying, browsing, and analyzing COVID-19-related abnormal metabolites in different body fluids. In summary, we believe that this database will effectively facilitate research on the functions and mechanisms of COVID-19-related metabolic biomarkers, thereby advancing both basic and clinical research on COVID-19. MetaboliteCOVID is free available at: https://cellknowledge.com.cn/MetaboliteCOVID.

A quantitative study of airway ultrasound in predicting difficult laryngoscopy: A prospective study.

PURPOSE: As common clinical screening tests cannot effectively predict a difficult airway, and unanticipated difficult laryngoscopy remains a challenge for physicians. We herein used ultrasound to develop some point-of-care predictors for difficult laryngoscopy. METHODS: This prospective observational study included 502 patients who underwent laryngoscopy and a detailed sonographic assessment. Patients under 18 years old, or with maxillofacial deformities or fractures, limited mouth opening, limited neck movement or history of neck surgery were excluded from the study. Laryngoscopic views of all patients were scored and grouping using the modified Cormack-Lehane (CL) scoring system. The measurements acquired comprised tongue width, the longitudinal cross-sectional area of the tongue, tongue volume, the mandible-hyoid bone distance, the hyoid bone-glottis distance, the mandible-hyoid bone-glottis angle, the skin-thyrohyoid membrane distance, the glottis-superior edge of the thyroid cartilage distance (DGTC), the skin-hyoid bone distance, and the epiglottis midway-skin distance. ANOVA and Chi-square were used to compare differences between groups. Logistic regression was used to identify risk factors for difficult laryngoscopy and it was visualized by receiver operating characteristic curves and nomogram. R version 3.6.3 and SPSS version 26.0 were used for statistical analyses. RESULTS: Difficult laryngoscopy was indicated in 49 patients (CL grade Ⅲ - Ⅳ) and easy laryngoscopy in 453 patients (CL grade Ⅰ - Ⅱ). The ultrasound-measured mandible-hyoid bone-glottis angle and DGTC significantly differed between the 2 groups (p < 0.001). Difficult laryngoscopy was predicted by an area under the curve (AUC) of 0.930 with a threshold mandible-hyoid bone-glottis angle of 125.5° and by an AUC of 0.722 with a threshold DGTC of 1.22 cm. The longitudinal cross-sectional area of the tongue, tongue width, tongue volume, the mandible-hyoid distance, and the hyoid-glottis distance did not significantly differ between the groups. CONCLUSION: Difficult laryngoscopy may be anticipated in patients in whom the mandible-hyoid bone-glottis angle is smaller than 125.5° or DGTC is larger than 1.22 cm.

Host-derived peptide signals regulate Pseudomonas aeruginosa virulence stress via the ParRS and CprRS two-component systems.

Pseudomonas aeruginosa, a versatile bacterium, has dual significance because of its beneficial roles in environmental soil processes and its detrimental effects as a nosocomial pathogen that causes clinical infections. Understanding adaptability to environmental stress is essential. This investigation delves into the complex interplay of two-component system (TCS), specifically ParRS and CprRS, as P. aeruginosa interprets host signals and navigates stress challenges. In this study, through phenotypic and proteomic analyses, the nuanced contributions of ParRS and CprRS to the pathogenesis and resilience mechanisms were elucidated. Furthermore, the indispensable roles of the ParS and CprS extracellular sensor domains in orchestrating signal perception remain unknown. Structural revelations imply a remarkable convergence of TCS sensors in interacting with host peptides, suggesting evolutionary strategies for bacterial adaptation. This pioneering work not only established links between cationic antimicrobial peptide (CAMP) resistance-associated TCSs and virulence modulation in nosocomial bacteria, but also transcended conventional boundaries. These implications extend beyond clinical resistance, permeating into the realm of soil revitalization and environmental guardianship. As it unveils P. aeruginosa intricacies, this study assumes a mantle of guiding strategies to mitigate clinical hazards, harness environmental advantages, and propel sustainable solutions forward.

Temporal Control of Fluorescent EuW10 Aggregates for Autonomous DNA Capture and Information Encryption.

Self-assembly exploits noncovalent interaction to offer an effective method for the fabrication of materials. For Na9 [EuW10 O36 ] ⋅ 32H2 O (EuW10 ), the negative charges and abundant oxygen atoms on its surface provide a handle for static self-assembly. New properties are envisioned for EuW10 aggregates which are able to display such kinetics and time-programming characteristics, in order to satisfy more complex and intelligent application scenarios, such as DNA binding and information encryption. In this work, EuW10 coupling with stimuli-responsive dodecyl dimethylamine oxide (C12 DMAO) can generate versatile aggregates with pH-responsive properties. We demonstrated the temporal programming of the assembly and disassembly of EuW10 nanospheres using a pH clock reaction of acid/urease hydrolysis. The pH clock reaction endows EuW10 assemblies with dynamical properties, in which the charges and fluorescence changes are coded in this system. These fluorescent assemblies provide new application in time-programmed DNA capture and information encryption.

Association between hopelessness and job burnout among Chinese nurses during the COVID-19 epidemic: The mediating role of career calling and the moderating role of social isolation.

Background: The COVID-19 pandemic has led to an increased workload and work pressure on nurses owing to the unpredictable changes during this challenging situation. Herein, we explored the relationship between hopelessness and job burnout in nurses working in China against the backdrop of the COVID-19 outbreak. Method: This was a cross-sectional study involving 1216 nurses in two hospitals in Anhui Province. The data was collected using an online survey. The mediation and moderation model was constructed, and the data was analyzed using SPSS PROCESS macro software. Results: Our results showed that the nurses had an average job burnout score of 1.75 ± 0.85. Further analysis revealed a negative correlation between hopelessness and career calling (r = -0.551, P < 0.01) and a positive correlation between hopelessness and job burnout (r = 0.133, P < 0.01). Additionally, a negative correlation was demonstrated between career calling and job burnout (r = -0.138, P < 0.01). Moreover, career calling strongly mediated (by 40.9%) the relationship between hopelessness and job burnout in the nurses. Finally, social isolation in the nurses was a moderating factor for the association between hopelessness and job burnout (ß = 0.028, t = 2.851, P < 0.01). Conclusion: Burnout severity in nurses increased during the COVID-19 pandemic. Career calling mediated the relationship between hopelessness and burnout, with greater burnout levels in nurses who experienced social isolation. Therefore, we suggest that job burnout in nurses can be improved by mitigating the effects of hopelessness and social isolation through psychological interventions and enhancing their sense of career calling through education to strengthen their professional identity.

Kinase-Modulated Bioluminescent Indicators Enable Noninvasive Imaging of Drug Activity in the Brain.

Aberrant kinase activity contributes to the pathogenesis of brain cancers, neurodegeneration, and neuropsychiatric diseases, but identifying kinase inhibitors that function in the brain is challenging. Drug levels in blood do not predict efficacy in the brain because the blood-brain barrier prevents entry of most compounds. Rather, assessing kinase inhibition in the brain requires tissue dissection and biochemical analysis, a time-consuming and resource-intensive process. Here, we report kinase-modulated bioluminescent indicators (KiMBIs) for noninvasive longitudinal imaging of drug activity in the brain based on a recently optimized luciferase-luciferin system. We develop an ERK KiMBI to report inhibitors of the Ras-Raf-MEK-ERK pathway, for which no bioluminescent indicators previously existed. ERK KiMBI discriminates between brain-penetrant and nonpenetrant MEK inhibitors, reveals blood-tumor barrier leakiness in xenograft models, and reports MEK inhibitor pharmacodynamics in native brain tissues and intracranial xenografts. Finally, we use ERK KiMBI to screen ERK inhibitors for brain efficacy, identifying temuterkib as a promising brain-active ERK inhibitor, a result not predicted from chemical characteristics alone. Thus, KiMBIs enable the rapid identification and pharmacodynamic characterization of kinase inhibitors suitable for treating brain diseases.

Associations between body circumference and testosterone levels and risk of metabolic dysfunction-associated fatty liver disease: a mendelian randomization study.

BACKGROUD: Body circumference and testosterone levels have been reported as associated with metabolic dysfunction-associated fatty liver disease (MAFLD) risk. However, whether body circumference and testosterone levels play a role in the development of MAFLD remains inconclusive. METHODS: Using a large database of genome-wide association studies, genetic loci that are independent of each other and strongly associated with body circumference and testosterone levels were selected as instrumental variables, the causal relationship between body circumference and testosterone and risk of MAFLD was investigated by two-sample Mendelian randomization methods such as inverse variance weighted (IVW), MR-Egger regression, and weighted median estimator (WME), using the odds ratios (ORs) as evaluation indicators. RESULTS: A total of 344 SNPs were included as instrumental variables in this study, including 180 for waist circumference, 29 for waist-to-hip ratio, and 135 for testosterone levels. Using the above two-sample Mendelian Randomization method to derive the causal association between exposure and outcome. The results of this study showed that three exposure factors were causally associated with the risk of MAFLD. Waist circumference obtained three statistically significant results for IVW, WME and Weighted mode (IVW: OR = 3.53, 95%CI: 2.23-5.57, P < 0.001; WME: OR = 3.88, 95%CI: 1.81-8.29, P < 0.001; Weighted mode: OR = 3.58, 95%CI: 1.05-12.16, P = 0.043). Waist-to-hip ratio obtained one statistically significant result for IVW (OR = 2.29, 95%CI: 1.12-4.66, P = 0.022). Testosterone levels obtained one statistically significant result for IVW (OR = 1.93, 95%CI: 1.30-2.87, P = 0.001). Waist circumference, waist-to-hip ratio and testosterone level were considered as risk factors for MAFLD. The Cochran Q test for IVW and MR-Egger method indicated that there was no intergenic heterogeneity in SNPs. The test for pleiotropy indicated that the possibility of pleiotropy in the causal analysis was weak. CONCLUSION: The results of the two-sample Mendelian randomization analysis showed that waist circumference was the exact risk factor for MAFLD, waist-to-hip ratio and testosterone levels were potential risk factors for MAFLD, the risk of developing MAFLD increases with these three exposure factors.

Construction of a Combined Hypoxia-related Genes Model for Hepatocellular Carcinoma Prognosis.

BACKGROUND: Hepatocellular carcinoma (HCC) is the most common liver malignancy where tumorigenesis and metastasis are believed to be tied to the hallmarks of hypoxia and tumor microenvironment (TME). METHODS: In this study, to investigate the relationships among hypoxia, TME, and HCC prognosis, we collected two independent datasets from a public database (TCGA-LIHC for identification, GSE14520 for validation) and identified the hypoxia-related differentially expressed genes (DEGs) from the TCGA data, and the univariable Cox regression and lasso regression analyses were performed to construct the prognosis model. An HCC prognosis model with 4 hypoxiarelated DEGs ("NDRG1", "ENO1", "SERPINE1", "ANXA2") was constructed, and high- and low-risk groups of HCC were established by the median of the model risk score. RESULTS: The survival analysis revealed significant differences between the two groups in both datasets, with the results of the AUC of the ROC curve of 1, 3, and 5 years in two datasets indicating the robustness of the prognosis model. Meanwhile, for the TCGA-LIHC data, the immune characteristics between the two groups revealed that the low-risk group presented higher levels of activated NK cells, monocytes, and M2 macrophages, and 7 immune checkpoint genes were found upregulated in the high-risk group. Additionally, the two groups have no difference in molecular characteristics (tumor mutational burden, TMB). The proportion of recurrence was higher in the high-risk group, and the correlation between the recurrence month and risk score was negative, indicating high-risk correlates with a short recurrence month. CONCLUSION: In summary, this study shows the association among hypoxic signals, TME, and HCC prognosis and may help reveal potential regulatory mechanisms between hypoxia, tumorigenesis, and metastasis in HCC. The hypoxia-related model demonstrated the potential to be a predictor and drug target of prognosis.

Research Progress on Regulatory Role of CircPVT1 in Tumors / 肿瘤防治研究

Circular RNA (circRNA) is involved in tumor progression. CircPVT1 is an oncogene that is abnormally expressed and correlated with a variety of tumors. It can regulate tumors' malignant behavior and affect the survival and prognosis of patients. This article reviews research on the regulatory roles of circPVT1 in tumors to provide references for accurate treatment.

Attention is all you need: utilizing attention in AI-enabled drug discovery.

Recently, attention mechanism and derived models have gained significant traction in drug development due to their outstanding performance and interpretability in handling complex data structures. This review offers an in-depth exploration of the principles underlying attention-based models and their advantages in drug discovery. We further elaborate on their applications in various aspects of drug development, from molecular screening and target binding to property prediction and molecule generation. Finally, we discuss the current challenges faced in the application of attention mechanisms and Artificial Intelligence technologies, including data quality, model interpretability and computational resource constraints, along with future directions for research. Given the accelerating pace of technological advancement, we believe that attention-based models will have an increasingly prominent role in future drug discovery. We anticipate that these models will usher in revolutionary breakthroughs in the pharmaceutical domain, significantly accelerating the pace of drug development.

The single pregnancy predicting model of 1 minute Apgar score less than 7 after preterm birth: A retrospective study.

Preterm delivery is greatly associated with perinatal mortality and morbidity, while there is no objective way to identify high-risk newborns currently. This study aimed at discovering the risk factor for Apgar score less than 7 at 1 minute of preterm neonates born with vaginal delivery. A retrospective study was performed in single pregnancy women with a vaginal delivery before 37 weeks of gestation. All the preterm infants were categorized into three types: very preterm birth (28 to 32 weeks), moderate preterm birth (32 to 34 weeks) and late preterm birth (34 to 37 weeks). Risk factors were identified through logistic regression analysis in every category of newborns mentioned above. And the receiver operating characteristic analysis was used in continuous variables to determine the best threshold of the outcome. On the basis of the selected factors, the predicting models are created and its prognosticating ability is compared by the area under the curve. A nomogram was established for the proved best model. A total of 981 cases were investigated, of whom 55 were found with 1 min Apgar scores less than 7. The nomogram was set for the predicting model with larger area under the receiver operating characteristic curve, of which is 0.742(95% confidence interval = 0.670-0.805) in very preterm birth, with the variables of first and second labor stage(> = 1.6 hours), birthweight and MgSO4(magnesium sulfate), and is 0.807(95% confidence interval = 0.776-0.837) in late preterm birth, with the variables of second labor stage(> = 1.23 hours), birthweight, a history of previous cesarean delivery, fetal distress and placental abruption. The combination of first and second labor stage, newborn weight and MgSO4 use can predict 74.2% of 1 minute Apgar score < 7 in very preterm neonates. And 80.7% high-risk infants can be identified when second labor stage, newborn weight, VBAC (vaginal birth after cesarean) and the occur of placental abruption and fetal distress were combined in the predicting model for late preterm birth. These predicting models would bring out great assistance towards obstetricians and reduce unnecessary adverse fetal outcomes.

Nucleotide binding as an allosteric regulatory mechanism for Akkermansia muciniphila ß-N-acetylhexosaminidase Am2136.

ß-N-acetylhexosaminidases (EC3.2.1.52), which belong to the glycosyl hydrolase family GH20, are important enzymes for oligosaccharides modification. Numerous microbial ß-N-acetylhexosaminidases have been investigated for applications in biology, biomedicine and biotechnology. Akkermansia muciniphila is an anaerobic intestinal commensal bacterium which possesses specific ß-N-acetylhexosaminidases for gut mucosal layer colonization and mucin degradation. In this study, we assessed the in vitro mucin glycan cleavage activity of the A. muciniphila ß-N-acetylhexosaminidase Am2136 and demonstrated its ability that hydrolyzing the ß-linkages joining N-acetylglucosamine to a wide variety of aglycone residues, which indicated that Am2136 may be a generalist ß-N-acetylhexosaminidase. Structural and enzyme activity assay experiments allowed us to probe the essential function of the inter-domain interactions in ß23-ß33. Importantly, we revealed that the hydrolysis activity of Am2136 was enhanced by nucleotides. We further speculated that this activation mechanism might be associated with the conformational motions between domain III and IV. To our knowledge, this is the first report of nucleotide effector regulated ß-N-acetylhexosaminidase, to reveal its novel biological functions. These findings contribute to understanding the distinct properties within the GH20 family and lay a certain foundation to develop controllable glycan hydrolyzing catalysts.Abbreviations: OD600 - optical cell densities at 600 nm; LB - Luria-Bertani; IPTG - isopropyl ß-D-1-thiogalactopyranoside; PMSF - phenylmethanesulfonyl fluoride; rmsd - root mean square deviation; GlcNAc - N-acetyl-ß-D-glucosamine; GalNAc - N-acetyl-ß-D-galactosamine; Gal - galactose.

TCM2COVID: A resource of anti-COVID-19 traditional Chinese medicine with effects and mechanisms.

In China, traditional Chinese medicine (TCM) has been widely used for coronavirus infectious disease 2019 (COVID-19) prevention, treatment, and recovery and has played a part in the battle against the disease. A variety of TCM treatments have been recommended for different stages of COVID-19. But, to the best of our knowledge, a comprehensive database for storing and organizing anti-COVID TCM treatments is still lacking. Herein, we developed TCM2COVID, a manually curated resource of anti-COVID TCM formulas, natural products (NPs), and herbs. The current version of TCM2COVID (1) documents over 280 TCM formulas (including over 300 herbs) with detailed clinical evidence and therapeutic mechanism information; (2) records over 80 NPs with detailed potential therapeutic mechanisms; and (3) launches a useful web server for querying, analyzing and visualizing documented formulas similar to those supplied by the user (formula similarity analysis). In summary, TCM2COVD provides a user-friendly and practical platform for documenting, querying, and browsing anti-COVID TCM treatments, and will help in the development and elucidation of the mechanisms of action of new anti-COVID TCM therapies to support the fight against the COVID-19 epidemic. TCM2COVID is freely available at http://zhangy-lab.cn/tcm2covid/.

Analysis and modeling of myopia-related factors based on questionnaire survey.

With the rapid development of science and technology, the trend of low age myopia is becoming increasingly significant. The latest national survey done by the Chinese government found that more than 80% of Chinese teenagers suffer from myopia. Adolescent myopia is closely related to living environment, heredity, and living habits. Quantifying the relationship between myopia and living environment, heredity, and living habits is conductive to the prevention and intervention of adolescent myopia. In this study, we investigated the relationships between four main factors (environment, habits, parental vision, and demographic) and myopia status by analyzing the questionnaire data. Data were collected from Chengdu, China in 2021, including 2808 myopia samples and 5693 non-myopia samples, with a total of 22 features. Then, these 22 features were inputted into three machine learning algorithms to discriminate the two classes of samples. Results show that the computational model could produce an AUC of 0.768. To pick out the most important features which play important roles in classification, we used incremental feature selection strategy to screen the 22 features. As a result, we found that the 4 most influential features with XGBoost could achieve a competitive AUC of 0.764. To further investigate the risk and protective factors affecting adolescent myopia, we used OR values derived from MLE-LR to analyze the relationship between 22 features and adolescent myopia. Results showed that the age variable was the most significant risk factor for myopia, followed by the myopia status of parents. The most protective factor for eyesight is the measure taken by the children, followed by the distance between books and eyes when reading. These discoveries can guide the prevention and control of myopia in children and adolescents.