Application of Machine Learning Algorithms to Analyze the Clinical Characteristics of NIHL Caused by Impulse Noise and Steady Noise.

Background: Occupational hearing loss of workers exposed to impulse noise and workers exposed to steady noise for a long time may have different clinical characteristics. Methods: As of May 2019, all 92 servicemen working in a weapon experimental field exposed to impulse noise for over 1 year were collected as the impulse noise group. As of Dec 2019, all 78 servicemen working in an engine working experimental field exposed to steady noise for over 1 year were collected as the steady noise group. The propensity score matching (PSM) model was used to eliminate the imbalance of age and working time between the two groups of subjects. After propensity score matching, 51 subjects in each group were finally included in the study. The machine learning model is constructed according to pure tone auditory threshold, and the performance of the machine learning model is evaluated by accuracy, sensitivity, specificity, and AUC. Results: Subjects in the impulse noise group and the steady noise group had significant hearing loss at high frequencies. The hearing of the steady noise group was worse than that of the impulse noise group at speech frequency especially at the frequency of 1 kHz. Among machine learning models, XGBoost has the best prediction and classification performance. Conclusion: The pure tone auditory threshold of subjects in both groups decreased and at high frequency. The hearing of the steady noise group at 1 kHz was significantly worse than that of the impulse noise group. XGBoost is the best model to predict the classification of our two groups. Our research can guide the prevention of damage caused by different types of noises.

The association between systemic immune-inflammation index and cardiotoxicity related to 5-Fluorouracil in colorectal cancer.

BACKGROUND AND AIMS: The cardiotoxicity related to 5-Fluorouracil (5-FU) in cancer patients has garnered widespread attention. The systemic immune-inflammation index (SII) has recently been identified as a novel predictive marker for the development of cardiovascular illnesses in individuals without pre-existing health conditions. However, it remains unclear whether the levels of SII are linked to cardiotoxicity related to 5-FU. This retrospective study aims to fill this knowledge gap by examining the correlation between SII and cardiotoxicity related to 5-FU in a colorectal cancer cohort. METHODS: The study comprised colorectal cancer patients who received 5-FU-based chemotherapy at the affiliated cancer hospital of Guizhou Medical University between January 1, 2018 and December 31, 2020. After adjustment for confounders and stratification by tertiles of the interactive factor, linear regression analyses, curve fitting and threshold effect analyses were conducted. RESULTS: Of the 754 patients included final analysis, approximately 21% (n = 156) of them ultimately experienced cardiotoxicity related to 5-FU. Monocytes (M) was found as an influential element in the interaction between SII and cardiotoxicity related to 5-FU. In the low tertile of M (T1: M ≤ 0.38 × 109/L), increasing log SII was positively correlated with cardiotoxicity related to 5-FU (Odds Ratio [OR], 8.04; 95% confidence interval [95%CI], 1.68 to 38.56). However, a curvilinear relationship between log SII and cardiotoxicity was observed in the middle tertile of M (T2: 0.38 < M ≤ 0.52 × 109/L). An increase in log SII above 1.37 was shown to be associated with a decreased risk of cardiotoxicity (OR, 0.14; 95%CI, 0.02 to 0.88), indicating a threshold effect. In the high tertile of M (T3: M > 0.52 × 109/L), there was a tendency towards a negative linear correlation between the log SII and cardiotoxicity was observed (OR, 0.85; 95%CI, 0.37 to 1.98). CONCLUSION: Our findings suggest that SII may serve as a potential biomarker for predicting cardiotoxicity related to 5-FU in colorectal cancer patients. SII is an independent risk factor for cardiotoxicity related to 5-FU with low monocytes levels (T1). Conversely, in the middle monocytes levels (T2), SII is a protective factor for cardiotoxicity related to 5-FU but with a threshold effect.

Preoperative computed tomography-guided localization for pulmonary nodules: a randomized controlled trial of coil and anchored needle localization.

Introduction: In patients with pulmonary nodules (PNs), computed tomography (CT)-guided localization is commonly performed prior to the resection of these nodules through video-assisted thoracic surgery (VATS). Aim: To evaluate the relative clinical efficacy of coil and anchored needle (AN) insertion as approaches to preoperative CT-guided PN localization. Material and methods: This single-center, prospective, open-label, randomized controlled trial (registration number: NCT05183945) enrolled consecutive patients from January 2022 to July 2022, assigning these patients at random to undergo either coil or AN localization prior to VATS. Efficacy and safety outcomes in these two groups were then compared. Results: This study enrolled in total 100 patients with 120 PNs who were assigned at random to the coil (patients = 50; PNs = 60) and AN (patients = 50; PNs = 60) localization groups. The respective technical success rates for coil and AN localization were 98.3% (59/60) and 100% (60/60), with no significant difference between the groups (p = 1.000). The coil group had a significantly longer median duration of localization relative to the AN group (16.0 min vs. 8.0 min, p < 0.001). Similar rates of localization-related pneumothorax (8.3% vs. 5.0%, p = 0.715) and pulmonary hemorrhage (5.0% vs. 13.3%, p = 0.110) were observed in both groups. In addition, the VATS resection procedures achieved 100% technical success rates in both of these localization groups. Conclusions: Both coil- and AN-based localization approaches can be successfully employed to localize PNs prior to VATS resection, with the AN localization procedure requiring less time to complete on average as compared to the coil-based approach.

Identifying influencing factors of metabolic syndrome in patients with major depressive disorder: A real-world study with Bayesian network modeling.

BACKGROUND: The bidirectional relationships between metabolic syndrome (MetS) and major depressive disorder (MDD) were discovered, but the influencing factors of the comorbidity were barely investigated. We aimed to fully explore the factors and their associations with MetS in MDD patients. METHODS: The data were retrieved from the electronic medical records of a tertiary psychiatric hospital in Beijing from 2016 to 2021. The influencing factors were firstly explored by univariate analysis and multivariate logistic regressions. The propensity score matching was used to reduce the selection bias of participants. Then, the Bayesian networks (BNs) with hill-climbing algorithm and maximum likelihood estimation were preformed to explore the relationships between influencing factors with MetS in MDD patients. RESULTS: Totally, 4126 eligible subjects were included in the data analysis. The proportion rate of MetS was 32.6 % (95 % CI: 31.2 %-34.1 %). The multivariate logistic regression suggested that recurrent depression, uric acid, duration of depression, marriage, education, number of hospitalizations were significantly associated with MetS. In the BNs, number of hospitalizations and uric acid were directly connected with MetS. Recurrent depression and family history psychiatric diseases were indirectly connected with MetS. The conditional probability of MetS in MDD patients with family history of psychiatric diseases, recurrent depression and two or more times of hospitalizations was 37.6 %. CONCLUSION: Using the BNs, we found that number of hospitalizations, recurrent depression and family history of psychiatric diseases contributed to the probability of MetS, which could help to make health strategies for specific MDD patients.

In silico off-target profiling for enhanced drug safety assessment.

Ensuring drug safety in the early stages of drug development is crucial to avoid costly failures in subsequent phases. However, the economic burden associated with detecting drug off-targets and potential side effects through in vitro safety screening and animal testing is substantial. Drug off-target interactions, along with the adverse drug reactions they induce, are significant factors affecting drug safety. To assess the liability of candidate drugs, we developed an artificial intelligence model for the precise prediction of compound off-target interactions, leveraging multi-task graph neural networks. The outcomes of off-target predictions can serve as representations for compounds, enabling the differentiation of drugs under various ATC codes and the classification of compound toxicity. Furthermore, the predicted off-target profiles are employed in adverse drug reaction (ADR) enrichment analysis, facilitating the inference of potential ADRs for a drug. Using the withdrawn drug Pergolide as an example, we elucidate the mechanisms underlying ADRs at the target level, contributing to the exploration of the potential clinical relevance of newly predicted off-target interactions. Overall, our work facilitates the early assessment of compound safety/toxicity based on off-target identification, deduces potential ADRs of drugs, and ultimately promotes the secure development of drugs.

Prevalence and Characteristics of Salmonella from Tibetan Pigs in Tibet, China.

This study aimed to understand the epidemiological characteristics of Salmonella in Tibetan pigs. We isolated, identified, and examined via antimicrobial susceptibility testing on Salmonella from Tibetan pigs breeder farms and slaughterhouses in Tibet, China. A genetic evolutionary tree was constructed on the basis of whole genome sequencing (WGS). A total of 81 Salmonella isolates were isolated from 987 samples. The main serovars were Salmonella Typhimurium and Salmonella London in Tibetan pigs. The isolated Salmonella Typhimurium isolates subjected to antimicrobial susceptibility testing showed varying degrees of resistance to ß-lactams, aminoglycosides, fluoroquinolones, sulfonamides, tetracyclines, and amphenicols. WGS analysis was performed on 20 Salmonella Typhimurium isolates in Tibet (n = 10), Jiangsu (n = 10), and 205 genome sequences downloaded from the Enterobase database to reveal their epidemiological and genetic characteristics. They were divided into two clusters based on core genome single-nucleotide polymorphisms: Cluster A with 112 isolates from Tibet and other regions in China and Cluster B with 113 isolates from Jiangsu and other regions. The isolates in Cluster A were further divided into two subclusters: A-1 with 40 isolates including Tibet and A-2 with 72 isolates from other regions. Virulence factors analysis revealed that all isolates from Tibet carried adeG, but this observation was not as common in Salmonella isolates from Jiangsu and other regions of China. Antibiotic resistance genes (ARGs) analysis showed that all isolates from Tibet carried blaTEM-55 and rmtB, which were absent in Salmonella isolates from Jiangsu and other regions of China. Genetic characteristic analysis and biofilm determination indicated that the biofilm formation capabilities of the isolates from Tibet were stronger than those of the isolates from Jiangsu and other regions of China. Our research revealed the epidemic patterns and genomic characteristics of Salmonella in Tibetan pigs and provided theoretical guidance for the prevention and control of local salmonellosis.

Integrating muti-omics data to identify tissue-specific DNA methylation biomarkers for cancer risk.

The relationship between tissue-specific DNA methylation and cancer risk remains inadequately elucidated. Leveraging resources from the Genotype-Tissue Expression consortium, here we develop genetic models to predict DNA methylation at CpG sites across the genome for seven tissues and apply these models to genome-wide association study data of corresponding cancers, namely breast, colorectal, renal cell, lung, ovarian, prostate, and testicular germ cell cancers. At Bonferroni-corrected P < 0.05, we identify 4248 CpGs that are significantly associated with cancer risk, of which 95.4% (4052) are specific to a particular cancer type. Notably, 92 CpGs within 55 putative novel loci retain significant associations with cancer risk after conditioning on proximal signals identified by genome-wide association studies. Integrative multi-omics analyses reveal 854 CpG-gene-cancer trios, suggesting that DNA methylation at 309 distinct CpGs might influence cancer risk through regulating the expression of 205 unique cis-genes. These findings substantially advance our understanding of the interplay between genetics, epigenetics, and gene expression in cancer etiology.

Alterations in electroencephalographic functional connectivity in individuals with major depressive disorder: a resting-state electroencephalogram study.

Background: Major depressive disorder (MDD) is the leading cause of disability among all mental illnesses with increasing prevalence. The diagnosis of MDD is susceptible to interference by several factors, which has led to a trend of exploring objective biomarkers. Electroencephalography (EEG) is a non-invasive procedure that is being gradually applied to detect and diagnose MDD through some features such as functional connectivity (FC). Methods: In this research, we analyzed the resting-state EEG of patients with MDD and healthy controls (HCs) in both eyes-open (EO) and eyes-closed (EC) conditions. The phase locking value (PLV) method was utilized to explore the connection and synchronization of neuronal activities spatiotemporally between different brain regions. We compared the PLV between participants with MDD and HCs in five frequency bands (theta, 4-8 Hz; alpha, 8-12 Hz; beta1, 12-16 Hz; beta2, 16-24 Hz; and beta3, 24-40 Hz) and further analyzed the correlation between the PLV of connections with significant differences and the severity of depression (via the scores of 17-item Hamilton Depression Rating Scale, HDRS-17). Results: During the EO period, lower PLVs were found in the right temporal-left midline occipital cortex (RT-LMOC; theta, alpha, beta1, and beta2) and posterior parietal-right temporal cortex (PP-RT; beta1 and beta2) in the MDD group compared with the HC group, while PLVs were higher in the MDD group in LT-LMOC (beta2). During the EC period, for the MDD group, lower theta and beta (beta1, beta2, and beta3) PLVs were found in PP-RT, as well as lower theta, alpha, and beta (beta1, beta2, and beta3) PLVs in RT-LMOC. Additionally, in the left midline frontal cortex-right temporal cortex (LMFC-RT) and posterior parietal cortex-right temporal cortex (PP-RMOC), higher PLVs were observed in beta2. There were no significant correlations between PLVs and HDRS-17 scores when connections with significantly different PLVs (all p > 0.05) were checked. Conclusion: Our study confirmed the presence of differences in FC between patients with MDD and healthy individuals. Lower PLVs in the connection of the right temporal-left occipital cortex were mostly observed, whereas an increase in PLVs was observed in patients with MDD in the connections of the left temporal with occipital lobe (EO), the circuits of the frontal-temporal lobe, and the parietal-occipital lobe. The trends in FC involved in this study were not correlated with the level of depression. Limitations: The study was limited due to the lack of further analysis of confounding factors and follow-up data. Future studies with large-sampled and long-term designs are needed to further explore the distinguishable features of EEG FC in individuals with MDD.

Self-breakdown statistics of a high-pressure spark gap with a microarray graphite cathode.

Comparative measurements with high-pressure spark gaps (gas pressure: 0.2-0.9 MPa nitrogen, gap spacing 5 mm) are presented, one with a regular Bruce-profile polished graphite cathode (diameter 25 mm, thickness 8 mm) and the other with a microarray graphite cathode of equal dimensions. By microstructuring, a V-type graphite microarray is created by purpose-developed laser treatment of a plane graphite electrode. The microarray graphite cathode brings more initial plasma and then produces more initial electrons. It is beneficial for electron emission, which improves the stability of the switch breakdown. The experimental results are achieved at a gas pressure of 0.9 MPa and a 200-kV voltage pulse applied to the switch. With these parameters, the mean breakdown voltage is 91.7 kV, the minimum is 91.4 kV, and the mean relative standard deviation in breakdown voltage of the first 100 shots is 0.4%. Compared to a plane graphite cathode, the mean breakdown voltage is about 10% lower, and the mean relative standard deviation is reduced by more than 90%. The main result can be stated that microarray graphite cathodes are a suitable choice as electrodes for low-jitter high-pressure spark gaps.

Structural basis for the H2AK119ub1-specific DNMT3A-nucleosome interaction.

Isoform 1 of DNA methyltransferase DNMT3A (DNMT3A1) specifically recognizes nucleosome monoubiquitylated at histone H2A lysine-119 (H2AK119ub1) for establishment of DNA methylation. Mis-regulation of this process may cause aberrant DNA methylation and pathogenesis. However, the molecular basis underlying DNMT3A1-nucleosome interaction remains elusive. Here we report the cryo-EM structure of DNMT3A1's ubiquitin-dependent recruitment (UDR) fragment complexed with H2AK119ub1-modified nucleosome. DNMT3A1 UDR occupies an extensive nucleosome surface, involving the H2A-H2B acidic patch, a surface groove formed by H2A and H3, nucleosomal DNA, and H2AK119ub1. The DNMT3A1 UDR's interaction with H2AK119ub1 affects the functionality of DNMT3A1 in cells in a context-dependent manner. Our structural and biochemical analysis also reveals competition between DNMT3A1 and JARID2, a cofactor of polycomb repression complex 2 (PRC2), for nucleosome binding, suggesting the interplay between different epigenetic pathways. Together, this study reports a molecular basis for H2AK119ub1-dependent DNMT3A1-nucleosome association, with important implications in DNMT3A1-mediated DNA methylation in development.

Tracing groundwater nitrate sources in an intensive agricultural region integrated of a self-organizing map and end-member mixing model tool.

The traceability of groundwater nitrate pollution is crucial for controlling and managing polluted groundwater. This study integrates hydrochemistry, nitrate isotope (δ15N-NO3- and δ18O-NO3-), and self-organizing map (SOM) and end-member mixing (EMMTE) models to identify the sources and quantify the contributions of nitrate pollution to groundwater in an intensive agricultural region in the Sha River Basin in southwestern Henan Province. The results indicate that the NO3--N concentration in 74% (n = 39) of the groundwater samples exceeded the WHO standard of 10 mg/L. According to the results of EMMTE modeling, soil nitrogen (68.4%) was the main source of nitrate in Cluster-1, followed by manure and sewage (16.5%), chemical fertilizer (11.9%) and atmospheric deposition (3.3%). In Cluster-2, soil nitrogen (60.1%) was the main source of nitrate, with a significant increase in the contribution of manure and sewage (35.5%). The considerable contributions of soil nitrogen may be attributed to the high nitrogen fertilizer usage that accumulated in the soil in this traditional agricultural area. Moreover, it is apparent that most Cluster-2 sampling sites with high contributions of manure and sewage are located around residential land. Therefore, the arbitrary discharge and leaching of domestic sewage may be responsible for these results. Therefore, this study provides useful assistance for the continuous management and pollution control of groundwater in the Sha River Basin.

Cyanobacteria mediate the dissemination of bacterial antibiotic resistance through conjugal transfer.

Cyanobacterial blooms are expanding world-wide in freshwater and marine environments, and can cause serious ecological and environmental issues, which also contribute to the spread of antibiotic resistance genes (ARGs). However, the mechanistic understanding of cyanobacteria-mediated resistance dynamics is not fully elucidated yet. We selected Microcystis aeruginosa as a model cyanobacteria to illustrate how cyanobacteria mediate the evolution and transfer processes of bacterial antibiotic resistance. The results show that the presence of cyanobacteria significantly decreased the abundance of antibiotic resistant bacteria (ARB) and antibiotic resistant genes (ARGs) by 3% - 99% and 2%-18%, respectively. In addition, it clearly altered bacterial community structure, with the dominant genera evolving from Acinetobacter (27%) and Enterobacter (42%) to Porphyrobacter (59%). The abundance of ARGs positively correlated with Proteobacteria and Firmicutes, rather than Cyanobacteria, and Bacteroidetes. In the presence of cyanobacteria, the transfer events of bacterial resistance genes via conjugation were found to decrease by 10% - 89% (p < 0.05). Surprisingly, we found an extradentary high transfer frequency (about 0.1) for the ARGs via plasmid conjugation from the bacteria into M. aeruginosa population. It confirmed the role of cyanobacterial population as the competent hosts to facilitate ARGs spreading. Our findings provide valuable information on the risk evaluation of ARGs caused by cyanobacterial blooms in aquatic environments, key for the protection and assessment of aquatic environmental quality.

Modeling and Analysis of Environmental Electromagnetic Interference in Multiple-Channel Neural Recording Systems for High Common-Mode Interference Rejection Performance.

Environmental electromagnetic interference (EMI) has always been a major interference source for multiple-channel neural recording systems, and little theoretical work has been attempted to address it. In this paper, equivalent circuit models are proposed to model both electromagnetic interference sources and neural signals in such systems, and analysis has been performed to generate the design guidelines for neural probes and the subsequent recording circuit towards higher common-mode interference (CMI) rejection performance while maintaining the recorded neural action potential (AP) signal quality. In vivo animal experiments with a configurable 32-channel neural recording system are carried out to validate the proposed models and design guidelines. The results show the power spectral density (PSD) of environmental 50 Hz EMI interference is reduced by three orders from 4.43 × 10-3 V2/Hz to 4.04 × 10-6 V2/Hz without affecting the recorded AP signal quality in an unshielded experiment environment.

Species Composition of a Small Mammal Community and Prevalence of Echinococcus spp. in the Alpine Pastoral Area of the Eastern Tibetan Plateau.

We aimed to investigate the species composition of a small mammal community and the prevalence of Echinococcus spp. in a typical endemic area of the Tibetan Plateau. One pika and five rodent species were identified based on the morphological characteristics of 1278 small mammal specimens collected during 2014-2019. Detection of Echinococcus DNA in tissue samples from small mammal specimens revealed that Ochotona curzoniae (pika, total prevalence: 6.02%, 26/432), Neodon fuscus (5.91%, 38/643), N. leucurus (2.50%, 3/120), and Alexandromys limnophilus (21.74%, 10/46) were infected by both E. multilocularis and E. shiquicus; Cricetulus longicaudatus (16.67%, 1/6) was infected by E. shiquicus; and no infection was detected in N. irene (0/15). Neodon fuscus and O. curzoniae were the two most abundant small mammal species. There was no significant difference in the prevalence of pika and the overall rodent species assemblage (6.26%, 53/846); however, the larger rodent populations suggested that more attention should be paid to their role in the transmission of echinococcosis in the wildlife reservoir, which has long been underestimated. Moreover, although DNA barcoding provides a more efficient method than traditional morphological methods for identifying large numbers of small mammal samples, commonly used barcodes failed to distinguish the three Neodon species in this study. The close genetic relationships between these species suggest the need to develop more powerful molecular taxonomic tools.

Metabolomics analysis based on UHPLC-QTOF-MS/MS to explore the synthesis mechanism and culture conditions optimization of Penicillium EF-2 exopolysaccharide.

Penicillium exopolysaccharide (EPS) inhibits galactose lectins and enhances immunity. However, EPS production is low and its synthesis mechanism remains unclear. Penicillium EF-2 strains with high EPS production were selected for this study, and Penicillium fermentation conditions were subsequently improved. The optimal culture conditions were 30 g/L lactose, 6 g/L yeast extract powder, 4 d seed age, 10 % inoculation amount, 3 d of secondary fermentation time, and the final EPS yield was 3.97 g/L. UHPLC-Q-TOF-MS/MS was used to explore the mechanism of EPS synthesis at the metabolic level. Optimal carbon source: lactose and optimal nitrogen source: yeast extract can provide precursors for EPS synthesis through related metabolic pathways. Moreover, regulating the energy, vitamin, and lipid metabolic pathways created favourable conditions for EPS synthesis and secretion. These findings explain the mechanism of EPS synthesis at the metabolic level and provide a theoretical basis for optimising and industrialising EPS production.

Enhancing lucerne (Medicago sativa) yield and nutritional quality: a meta-analysis of fertilization types and environmental factors in China.

Introduction: Lucerne (Medicago sativa), is a cornerstone of China's livestock industry, however, due to the backward agronomic strategies and technology, lucerne in China faces cultivation challenges that result in lower productivity and quality than global standards. Therefore, we undertook a meta-analysis to evaluate the impact of five distinct fertilization types on lucerne yield and nutritional quality in various locations in China. The fertilizer practices included manure application, combined mineral fertilizer and manure application (FM), biological fertilizer application, unbalanced application of two or more mineral fertilizer types, and balanced mineral fertilizer application. Furthermore, we investigate influential factors of yield and quality of lucerne under fertilization, including climatic variables (mean annual precipitation, mean annual temperature), initial soil properties (soil organic carbon; total nitrogen, pH), and agronomic factors (seeding rate, harvest frequency, and lucerne stand age). Methods: Our study analyzed 53 published papers to discern the most beneficial fertilizer for enhancing lucerne yield and nutritional quality. Results and discussion: The results showed that the fertilizer practices, on average, significantly improved yield by 31.72% and crude protein content by 11.29%, with FM emerging as the most effective, this is because mineral fertilizers provide available nutrients for lucerne, manure provides essential organic matter for microorganisms and improve soil properties. In addition, the fertilizer practices significantly reduced neutral and acid detergent fiber contents by 6.28% and 8.50%, respectively, while increasing ash content and relative feeding value. Furthermore, climatic variables, soil properties, and planting system factors such as sowing date and harvest frequency significantly affected yield and nutritional quality. The practical implications of our results emphasize the need for balanced and strategic fertilizer application to optimize lucerne production and highlight the potential to adjust cultivation practices according to environmental conditions. Balanced and strategic fertilizer application can simultaneously improve soil properties, enhance soil carbon sequestration, and reduce the emission of greenhouse gases from the soil, which is a vital measure for realizing sustainable agricultural development.

Learning generalizable AI models for multi-center histopathology image classification.

Investigation of histopathology slides by pathologists is an indispensable component of the routine diagnosis of cancer. Artificial intelligence (AI) has the potential to enhance diagnostic accuracy, improve efficiency, and patient outcomes in clinical pathology. However, variations in tissue preparation, staining protocols, and histopathology slide digitization could result in over-fitting of deep learning models when trained on the data from only one center, thereby underscoring the necessity to generalize deep learning networks for multi-center use. Several techniques, including the use of grayscale images, color normalization techniques, and Adversarial Domain Adaptation (ADA) have been suggested to generalize deep learning algorithms, but there are limitations to their effectiveness and discriminability. Convolutional Neural Networks (CNNs) exhibit higher sensitivity to variations in the amplitude spectrum, whereas humans predominantly rely on phase-related components for object recognition. As such, we propose Adversarial fourIer-based Domain Adaptation (AIDA) which applies the advantages of a Fourier transform in adversarial domain adaptation. We conducted a comprehensive examination of subtype classification tasks in four cancers, incorporating cases from multiple medical centers. Specifically, the datasets included multi-center data for 1113 ovarian cancer cases, 247 pleural cancer cases, 422 bladder cancer cases, and 482 breast cancer cases. Our proposed approach significantly improved performance, achieving superior classification results in the target domain, surpassing the baseline, color augmentation and normalization techniques, and ADA. Furthermore, extensive pathologist reviews suggested that our proposed approach, AIDA, successfully identifies known histotype-specific features. This superior performance highlights AIDA's potential in addressing generalization challenges in deep learning models for multi-center histopathology datasets.

Universal subunit vaccine protects against multiple SARS-CoV-2 variants and SARS-CoV.

Although Omicron RBD of SARS-CoV-2 accumulates many mutations, the backbone region (truncated RBD) of spike protein is highly conserved. Here, we designed several subunit vaccines by keeping the conserved spike backbone region of SARS-CoV-2 Omicron BA.1 subvariant (S-6P-no-RBD), or inserting the RBD of Delta variant (S-6P-Delta-RBD), Omicron (BA.5) variant (S-6P-BA5-RBD), or ancestral SARS-CoV-2 (S-6P-WT-RBD) to the above backbone construct, and evaluated their ability to induce immune responses and cross-protective efficacy against various SARS-CoV-2 variants and SARS-CoV. Among the four subunit vaccines, S-6P-Delta-RBD protein elicited broad and potent neutralizing antibodies against all SARS-CoV-2 variants tested, including Alpha, Beta, Gamma, and Delta variants, the BA.1, BA.2, BA.2.75, BA.4.6, and BA.5 Omicron subvariants, and the ancestral strain of SARS-CoV-2. This vaccine prevented infection and replication of SARS-CoV-2 Omicron, and completely protected immunized mice against lethal challenge with the SARS-CoV-2 Delta variant and SARS-CoV. Sera from S-6P-Delta-RBD-immunized mice protected naive mice against challenge with the Delta variant, with significantly reduced viral titers and without pathological effects. Protection correlated positively with the serum neutralizing antibody titer. Overall, the designed vaccine has potential for development as a universal COVID-19 vaccine and/or a pan-sarbecovirus subunit vaccine that will prevent current and future outbreaks caused by SARS-CoV-2 variants and SARS-related CoVs.

Decoding Wilson disease: a machine learning approach to predict neurological symptoms.

Objectives: Wilson disease (WD) is a rare autosomal recessive disorder caused by a mutation in the ATP7B gene. Neurological symptoms are one of the most common symptoms of WD. This study aims to construct a model that can predict the occurrence of neurological symptoms by combining clinical multidimensional indicators with machine learning methods. Methods: The study population consisted of WD patients who received treatment at the First Affiliated Hospital of Anhui University of Traditional Chinese Medicine from July 2021 to September 2023 and had a Leipzig score ≥ 4 points. Indicators such as general clinical information, imaging, blood and urine tests, and clinical scale measurements were collected from patients, and machine learning methods were employed to construct a prediction model for neurological symptoms. Additionally, the SHAP method was utilized to analyze clinical information to determine which indicators are associated with neurological symptoms. Results: In this study, 185 patients with WD (of whom 163 had neurological symptoms) were analyzed. It was found that using the eXtreme Gradient Boosting (XGB) to predict achieved good performance, with an MCC value of 0.556, ACC value of 0.929, AUROC value of 0.835, and AUPRC value of 0.975. Brainstem damage, blood creatinine (Cr), age, indirect bilirubin (IBIL), and ceruloplasmin (CP) were the top five important predictors. Meanwhile, the presence of brainstem damage and the higher the values of Cr, Age, and IBIL, the more likely neurological symptoms were to occur, while the lower the CP value, the more likely neurological symptoms were to occur. Conclusions: To sum up, the prediction model constructed using machine learning methods to predict WD cirrhosis has high accuracy. The most important indicators in the prediction model were brainstem damage, Cr, age, IBIL, and CP. It provides assistance for clinical decision-making.