A versatile attention-based neural network for chemical perturbation analysis and its potential to aid surgical treatment: A experimental study.

Deep learning models have emerged as rapid, accurate, and effective approaches for clinical decisions. Through a combination of drug screening and deep learning models, drugs that may benefit patients before and after surgery can be discovered to reduce the risk of complications or speed recovery. However, most existing drug prediction methods have high data requirements and lack interpretability, which has a limited role in adjuvant surgical treatment. To address these limitations, we propose the attention-based convolution transpositional interfusion network (ACTIN) for flexible and efficient drug discovery. ACTIN leverages the graph convolution and the transformer mechanism, utilizing drug and transcriptome data to assess the impact of chemical pharmacophores containing certain elements on gene expression. Remarkably, just with only 393 training instances, only one-tenth of the other models, ACTIN achieves state-of-the-art performance, demonstrating its effectiveness even with limited data. By incorporating chemical element embedding disparity and attention mechanism-based parameter analysis, it identifies the possible pharmacophore containing certain elements that could interfere with specific cell lines, which is particularly valuable for screening useful pharmacophores for new drugs tailored to adjuvant surgical treatment. To validate its reliability, we conducted comprehensive examinations by utilizing transcriptome data from the lung tissue of fatal COVID-19 patients as additional input for ACTIN, we generated novel lead chemicals that align with clinical evidence. In summary, ACTIN offers insights into the perturbation biases of elements within pharmacophore on gene expression, which holds the potential for guiding the development of new drugs that benefit surgical treatment.

Investigating the prognostic role of lncRNAs associated with disulfidptosis-related genes in clear cell renal cell carcinoma.

INTRODUCTION: Renal cell carcinoma (RCC) is a grave malignancy that poses a significant global health burden with over 400,000 new cases annually. Disulfidptosis, a newly discovered programmed cell death process, is linked to the actin cytoskeleton, which plays a vital role in maintaining cell shape and survival. The role of disulfidptosis is poorly depicted in the clear cell histologic variant of RCC (ccRCC). METHODS: Three sets of ccRCC cohorts, ICGC_RECA-EU (n = 91), GSE76207 (n = 32) and TCGA-KIRC (n = 607), were included in our study, the batch effect of which was removed using the "combat" function. Correlation was calculated using the "rcorr" function of the "Hmisc" package for Pearson analysis, which was visualized using the "pheatmap" package. Principal component analysis was performed by the "vegan" package, visualized using the "scatterplot3d" package. Long non-coding RNAs (lncRNAs) associated with disulfidptosis were screened out using least absolute shrinkage and selection operator (LASSO) and COX analysis. Tumor mutation, immune landscaping and immunotherapy prediction were performed for further characterization of two risk groups. RESULTS: A total of 1822 disulfidptosis-related lncRNAs was selected, among which 308 lncRNAs were found to be significantly associated with the clinical outcome of ccRCC patients. We retained 11 disulfidptosis-related lncRNAs, namely, AP000439.3, RP11-417E7.1, RP11-119D9.1, LINC01510, SNHG3, AC156455.1, RP11-291B21.2, EMX2OS, AC093850.2, HAGLR and RP11-389C8.2, through LASSO and COX analysis for prognosis model construction, which displayed satisfactory accuracy (area under the curve, AUC, values all above 0.6 in multiple cohorts) in stratification of ccRCC prognosis. A nomogram model was constructed by integrating clinical factors with risk score, which further enhanced the prediction efficacy (AUC values all above 0.7 in multiple cohorts). We found that patients of male gender, higher clinical stages and advanced pathological T stage were inclined to have higher risk score values. Dactinomycin_1911, Vinblastine_1004, Daporinad_1248 and Vinorelbine_2048 were identified as promising candidate drugs for treating ccRCC patients of higher risk score value. Moreover, patients of higher risk value were prone to be resistant to immunotherapy. CONCLUSION: We developed a prognosis predicting model based on 11 selected disulfidptosis-related lncRNAs, the efficacy of which was verified in different cohorts. Furthermore, we delineated an intricate portrait of tumor mutation, immune topography and pharmacosensitivity evaluations within disparate risk stratifications.

Early diagnosis and prognostic potential of RAC3 in bladder tumor.

BACKGROUND AND PURPOSE: Bladder tumors are among the most prevalent malignancies in the urinary system, and RAC3 has been linked to various types of cancer. This article seeks to explore the potential of RAC3 as both an early diagnostic marker for bladder tumors and a novel therapeutic target. METHODS/PATIENTS: The expression of RAC3 in bladder tissue was detected using immunohistochemical staining. Additionally, the protein expression of RAC3 was measured and quantified through enzyme-linked immunosorbent assay (ELISA). Subsequently, the correlation between the expression level of RAC3 and bladder tumors was investigated through multifactorial analysis and survival analysis. RESULTS: Our findings revealed that RAC3 expression was upregulated in bladder tumor tissues. Moreover, we observed higher levels of RAC3 expression in the serum and urine of patients with bladder tumors compared to those with non-bladder tumors. Additionally, we identified a significant positive correlation between RAC3 expression levels and the stage, degree of differentiation, and infiltration of bladder tumors. Importantly, high RAC3 expression emerged as an influential factor in the poor prognosis of bladder tumors, as patients with high RAC3 expression exhibited a lower overall survival rate than those with low RAC3 expression. CONCLUSION: Based on our results, RAC3 shows promise as both a marker for early diagnosis of bladder tumors and a potential therapeutic target.

The significance of serum Klotho to hearing loss: a potential protector under noise pollution.

The issue of hearing protection in the presence of noise pollution is of great importance in the fields of environmental science and clinical medicine. Currently, the clinical significance of Klotho in relation to hearing has not been revealed. The aim of this study was to examine the correlation between serum Klotho levels and Pure Tone Average (PTA) hearing thresholds among individuals in the U.S.. The analysis involved a sample of 1,781 individuals aged 20 to 69, obtained from the 2007-2012 National Health and Nutrition Examination Survey. Various methods were utilized for the analysis, including univariate and multivariate linear regression, stratified analysis, smooth curve fitting, a two-segment linear regression model, and log-likelihood ratio analysis. The results of the univariate analysis indicated that serum Klotho concentration, age, education level, hypertension, diabetes, and smoking all exhibited a significant influence on PTAs. After adjusting for potential confounding factors, it was observed that a decrease in serum Klotho was significantly associated with PTA thresholds at low frequency (ß = -0.002; 95% CI: -0.003, -0.001; P = 0.004), speech frequency (ß = -0.002; 95% CI: -0.003, -0.001; P = 0.007), and high frequency (ß = -0.002; 95% CI: -0.003, -0.001; P = 0.045). Specifically, for every 1 pg/ml decrease in serum Klotho concentration, the PTAs increased by 0.002 dB. Moreover, age and gender-specific analyses revealed significant associations. For individuals aged 59-69, a significant association was found between serum Klotho concentration and high-frequency PTA (ß = -4.153; 95% CI: -7.948, -0.358; P = 0.032). Additionally, among females, significant associations were observed between serum Klotho concentration and speech-frequency PTA (ß = -1.648, 95% CI: -3.197, -0.099; P = 0.037) as well as high-frequency PTA (ß = -3.046; 95% CI: -5.319, -0.772; P = 0.009). Finally, the results of smooth curve fitting and threshold effect analyses indicated a potential negative linear correlation between serum Klotho concentration and PTA thresholds. In conclusion, a lower level of serum Klotho was found to be associated with increased hearing thresholds, particularly among the elderly population. This finding has significant implications for the prevention and treatment of hearing damage.

[Study on the accuracy of automatic segmentation of knee CT images based on deep learning].

Objective: To develop a neural network architecture based on deep learning to assist knee CT images automatic segmentation, and validate its accuracy. Methods: A knee CT scans database was established, and the bony structure was manually annotated. A deep learning neural network architecture was developed independently, and the labeled database was used to train and test the neural network. Metrics of Dice coefficient, average surface distance (ASD), and Hausdorff distance (HD) were calculated to evaluate the accuracy of the neural network. The time of automatic segmentation and manual segmentation was compared. Five orthopedic experts were invited to score the automatic and manual segmentation results using Likert scale and the scores of the two methods were compared. Results: The automatic segmentation achieved a high accuracy. The Dice coefficient, ASD, and HD of the femur were 0.953±0.037, (0.076±0.048) mm, and (3.101±0.726) mm, respectively; and those of the tibia were 0.950±0.092, (0.083±0.101) mm, and (2.984±0.740) mm, respectively. The time of automatic segmentation was significantly shorter than that of manual segmentation [(2.46±0.45) minutes vs. (64.73±17.07) minutes; t=36.474, P<0.001). The clinical scores of the femur were 4.3±0.3 in the automatic segmentation group and 4.4±0.2 in the manual segmentation group, and the scores of the tibia were 4.5±0.2 and 4.5±0.3, respectively. There was no significant difference between the two groups ( t=1.753, P=0.085; t=0.318, P=0.752). Conclusion: The automatic segmentation of knee CT images based on deep learning has high accuracy and can achieve rapid segmentation and three-dimensional reconstruction. This method will promote the development of new technology-assisted techniques in total knee arthroplasty.

Reinnervation of the rectum with transfer of the genital branch of the genitofemoral nerve to the pelvic nerve in rats.

OBJECTIVE The purpose of this study was to determine the feasibility of rectum reinnervation with transfer of a primarily genitofemoral nerve to the pelvic nerve in the rat. METHODS Thirty-six male rats were randomly divided into 3 groups: rats in the nerve transfer group (n = 12) were subjected to rectal denervation and then bilateral genitofemoral nerve-pelvic nerve transfer; rats in the nerve resection group (n = 12) underwent rectum denervation without nerve transfer; and rats in the control group (n = 12) underwent sham surgery. Rectum denervation was achieved by transection of the L-6 spinal nerves, the spinal nerves below L-6, and the pelvic nerve. Four months postoperatively, retrograde nerve tracing, regenerative nerve morphological examination, and rectal manometry assessment were performed. RESULTS Regenerative nerve morphological examination showed good axonal regeneration after genitofemoral nerve transfer. Nerve stimulation induced increased rectal pressures in 10 of 12 rats in the nerve transfer group. The mean rectal pressure in this group was 54.9 ± 7.1 mm Hg, which is higher than the mean value in the nerve resection group (5.5 ± 2.0 mm Hg) but lower than that in the control group (70.6 ± 8.5 mm Hg) (p < 0.05). The appearance of FluoroGold-labeled neurons in the L-1 and L-2 spinal cord segments in the nerve transfer group confirmed the formation of new neural pathways. CONCLUSIONS The results have demonstrated that genitofemoral nerve-pelvic nerve transfer can achieve nerve regeneration. In this animal model, the authors were able to reinnervate the rectum by nerve transfer.

Functional Restoration of Erectile Function Using End-to-side Autonomic-to-somatic Neurorrhaphy in Rats.

OBJECTIVE: To investigate the feasibility of erectile function rehabilitation using end-to-side autonomic-to-somatic neurorrhaphy in rats. MATERIALS AND METHODS: Thirty-six adult male Sprague-Dawley rats were divided into 3 groups (n = 12 per group): in the end-to-side coaptation group, the left L6 and S1 spinal nerves were transected, and the distal stump of L6 ventral root was sutured to L4 ventral root through end-to-side neurorrhaphy; in the no-coaptation group, the rats did not undergo coaptation; and in the control group, the left L6 and S1 spinal nerves were transected, but L6 ventral root was preserved. After 4 months, retrograde tracing, histomorphological technique, mating test, and evaluation of functional properties of the regenerated nerve were performed. RESULTS: Mating test showed a significantly higher intromission behavior rate in the end-to-side coaptation group (41.7%) and control group (58.3%) than in the no-coaptation group (0%) (P < .001). Intracavernous pressure in end-to-side coaptation group was 31.6 ± 12.0 mmHg, significantly higher than in the no-coaptation group (3.1 ± 1.4 mmHg), but lower than in the control group (67.9 ± 18.0 mmHg) (P < .0001). Retrograde tracing indicated the establishment of the new neural pathway. Axon counting and ultrastructure observation confirmed axonal regeneration in the end-to-side coaptation group. The bilateral tibialis anterior muscles wet weight in the end-to-side coaptation group were 0.6686 ± 0.0427 g and 0.6707 ± 0.0515 g (P = .93). The wet weight and morphology of the tibialis anterior muscles revealed no detrimental effect on the donor nerve. CONCLUSION: Nerve regeneration can be achieved using end-to-side autonomic-to-somatic neurorrhaphy, and erectile function can be restored without the functional impairment of the donor somatic nerve.