Advancements in artificial intelligence (AI) and emerging technologies are rapidly expanding the exploration of chemical space, facilitating innovative drug discovery. However, the transformation of novel compounds into safe and effective drugs remains a lengthy, high-risk, and costly process. Comprehensive early-stage evaluation is essential for reducing costs and improving the success rate of drug development. Despite this need, no comprehensive tool currently supports systematic evaluation and efficient screening. Here, we present druglikeFilter, a deep learning-based framework designed to assess drug-likeness across four critical dimensions: 1) physicochemical rule evaluated by systematic determination, 2) toxicity alert investigated from multiple perspectives, 3) binding affinity measured by dual-path analysis, and 4) compound synthesizability assessed by retro-route prediction. By enabling automated, multidimensional filtering of compound libraries, druglikeFilter not only streamlines the drug development process but also plays a crucial role in advancing research efforts towards viable drug candidates, which can be freely accessed at https://idrblab.org/drugfilter/.

Hyperparathyroidism-jaw tumor syndrome (HPT-JT) is a rare familial autosomal dominant genetic disease with primary hyperparathyroidism, jaw tumors, kidney tumors and uterine tumors caused by cell division cycle 73 (CDC73) germline mutations. A 42-year-old male patient was admitted for pancreatitis and further examination revealed elevated PTH at 54.00pmol/L and a history of jaw tumors. This patient was diagnosed as HPT-JT finally and underwent upper right, lower right, and upper left parathyroid glands resection and genetic testing. Postoperative pathology revealed that atypical adenomatous nodules of parathyroid glands with extensive atypia and nucleus division and parathyroid hyperplasia and whole exome sequencing suggested that the CDC73 mutation.

Advancements in artificial intelligence(AI)and emerging technologies are rapidly expanding the exploration of chemical space,facilitating innovative drug discovery.However,the transformation of novel compounds into safe and effective drugs remains a lengthy,high-risk,and costly process.Comprehensive early-stage evaluation is essential for reducing costs and improving the success rate of drug development.Despite this need,no comprehensive tool currently supports systematic evaluation and efficient screening.Here,we present druglikeFilter,a deep learning-based framework designed to assess drug-likeness across four critical dimensions:1)physicochemical rule evaluated by systematic determination,2)toxicity alert investigated from multiple perspectives,3)binding affinity measured by dual-path analysis,and 4)compound synthesizability assessed by retro-route prediction.By enabling automated,multidimensional filtering of compound libraries,druglikeFilter not only streamlines the drug development process but also plays a crucial role in advancing research efforts towards viable drug candidates,which can be freely accessed at https://idrblab.org/drugfilter/.

Objective To explore the value of ultrasound artificial intelligence(AI)in assisting naval grassroots doctors for the diagnosis of thyroid nodule in naval.Methods A total of 177 patients with thyroid nodules(200 thyroid nodules)who visited The First Affiliated Hospital of Naval Medical University from November 2020 to November 2023 were selected as research objects.The thyroid nodules were diagnosed by naval grassroots doctors,naval grassroots doctors assisted by AI,and senior doctors,respectively.Results The pathological results showed that there were 110 malignant nodules and 90 benign nodules.The diagnostic accuracy rate of AI-assisted group(85.0%)was similar to that of senior doctor group(87.0%),which were higher than that of naval grassroots doctor group(71.5%).Pathological results were taken as the gold standard,Kappa consistency test was carried out,and the area under the receiver operating characteristic(ROC)curve(AUC)was compared among groups.The diagnostic results of naval grassroots doctor group had a moderate consistency with pathological results(Kappa value was 0.424,P<0.001).The diagnostic results of AI group and senior doctor group had strong consistencies with pathological results(Kappa values were 0.693 and 0.735,respectively,both P<0.001).There was no significant difference in the AUC between AI group and senior doctor group(0.842 vs.0.864,P>0.05).However,there was a significant difference in the AUC between naval grassroots doctor group and AI group(0.712 vs.0.842,P<0.001).Conclusion AI can assist naval grassroots doctors in improving the diagnostic level of thyroid nodules.It has certain application prospects in naval forces.

Hyperparathyroidism-jaw tumor syndrome (HPT-JT) is a rare familial autosomal dominant genetic disease with primary hyperparathyroidism, jaw tumors, kidney tumors and uterine tumors caused by cell division cycle 73 (CDC73) germline mutations. A 42-year-old male patient was admitted for pancreatitis and further examination revealed elevated PTH at 54.00pmol/L and a history of jaw tumors. This patient was diagnosed as HPT-JT finally and underwent upper right, lower right, and upper left parathyroid glands resection and genetic testing. Postoperative pathology revealed that atypical adenomatous nodules of parathyroid glands with extensive atypia and nucleus division and parathyroid hyperplasia and whole exome sequencing suggested that the CDC73 mutation.

OBJECTIVE To investigate the effects and mechanism of luteolin on osteogenic repair of bone defects. METHODS The targets and potential pathways of luteolin in the treatment of bone defects were screened by network pharmacology method， and then the top 2 targets were selected by Hub gene screening for molecular docking verification， with binding energy as the evaluation standard. In vitro experiments were conducted on rat bone mesenchymal stem cells （BMSC） and rat umbilical vein endothelial cells （RUVEC）. Phenotypic validation was performed using alkaline phosphatase staining， alizarin red S staining， and in vitro angiogenesis experiments. Western blot assay was used to detect the protein expressions of phosphatidylinositol 3 kinase （PI3K） and protein kinase 1 （Akt1）， so as to validate the mechanism of luteolin on osteogenic differentiation of BMSC and angiogenesis of RUVEC in vitro. RESULTS The results of network pharmacology showed that the effects of luteolin on vascular formation and bone repair in bone defects were mainly related to Akt1， SRC， estrogen receptor 1， epidermal growth factor receptor， cyclooxygenase 2， matrix metalloproteinase 9 targets， and were closely related to PI3K-Akt signaling pathway. The results of molecular docking showed that luteolin binding to Akt1 and SRC proteins was stable. The results of in vitro experiments showed that luteolin could significantly improve the expressions and activities of alkaline phosphatase in BMSC， increased the number of calcium salt deposits and calcified nodules， and promoted calcification of BMSC. Compared with luteolin 0 μmol/L group， the angiogenesis ability of RUVEC was enhanced significantly in luteolin 1， 10 μmol/L groups， the length of blood vessels and the protein expressions of PI3K and Akt1 were significantly increased （P＜0.05 or P＜0.01）； the higherthe concentration， the better the effect. CONCLUSIONS Luteolin may play a role in promoting angiogenesis and bone repair at the fracture site by activating PI3K/Akt signaling pathway and promoting the protein expressions of PI3K and Akt1.

Objective:To evaluate the value of ultrasonographic features and classification defined by the Chinese-Thyroid Imaging Reporting and Data System (C-TIRADS) in differentiating follicular thyroid carcinoma (FTC) from follicular thyroid adenoma (FTA) .Methods:Data of 87 patients who underwent thyroid nodule-related surgery at Tianjin Medical University General Hospital from Jan. 2019 to Feb. 2023 and whose postoperative pathology confirmed FTC or FTA was divided into FTC group (26 cases) and FTA group (61 cases) were retrospectively analyzed. The differences of general data, pathological diagnosis, surgical methods, ultrasonographic features of thyroid nodules and C-TIRADS classification between the two groups were compared. Multivariate Logistic regression analysis was used to screen the independent predictors related to the occurrence of FTC, a regression model was established based on the independent predictors and a nomogram was drawn. Bootstrap method was used to verify the nomogram internally, and ROC curve and calibration curve were drawn to evaluate the diagnostic efficiency and predictive ability of the nomogram.Results:There were statistically significant differences between orientation, echo, composition, calcification, margin, halo and C-TIRADS classification between groups (all P<0.05) ; maximum diameter, echotexture, blood flow, general data, pathological diagnosis and surgical methods had no statistically significant differences between groups (all P>0.05) .Single-factor logistic regression analysis showed taller-than-wide, peripheral calcification, blurred/irregular edges or external invasion, C-TIRADS 4B/4C class were candidate variables for predicting the occurrence of FTC ( OR=10.909, 19.059, 19.259, 49.333, all P<0.05). Multivariate logistic regression analysis showed that peripheral calcification, blurry/irregular edges or extra-thyroid invasion, C-TIRADS 4B/4C class were independent predictors for the occurrence of FTC ( OR=33.731, 11.620, 22.794, all P<0.05) .The nomogram of FTC occurrence was constructed based on the above three independent predictors, and the AUC was 0.920 (95% CI=0.854-0.986), which showed that the nomogram had high diagnostic efficacy, and the optimal diagnostic threshold determined by the Youden index was 0.23 (corresponding to the total score of the nomogram is about 52 points), the sensitivity was 88.5%, and the specificity was 82.0%. The calibration curve drawn by internal verification was close to the reference line, suggesting that the nomogram had a high predictive ability. Conclusions:The nomogram prediction model for FTC occurrence based on the ultrasonographic features and classification defined by C-TIRADS has high diagnostic efficiency and predictive ability, and can help in the preoperative identification of FTC and FTA.

Objective:To evaluate the clinical curative effect of self-made Lishi Qufeng Juanbi Decoction combined with Febuxostat tablet on uric acid nephropathy (UAN).Methods:Randomized controlled trial. A total of 150 patients with UAN in Yixing Hospital of Traditional Chinese Medicine were enrolled as the observation objects between October 2019 to October 2021. According to random number table method, they were divided into two groups, 75 in each group. The control group was treated with Febuxostat tablets on basis of routine diet intervention, while the observation group was treated with self-made Lishi Qufeng Juanbi Decoction on basis of control group. All were continuously treated for 6 months. TCM syndromes were scored before and after treatment. The levels of serum uric acid (SUA) and creatinine (SCr) were detected by full-automatic biochemical analyzer, and levels of serum CRP, IL-6 and IL-8 were detected by ELISA. The 24h urine was collected to detect 24 h urine protein quantitation. The adverse events were recorded, and clinical curative effect was evaluated.Results:There were significant differences in total response rate between observation group and control group [93.33% (70/75) vs. 80.00% (60/75); χ2=5.77, P=0.016]. After treatment, scores of waist soreness-fatigue and frequent nocturia in observation group were significantly lower than those in the control group ( t=9.17, 2.67, P<0.01), and frequency of joint swelling pain was significantly lower than that of the control group ( t=9.49, P<0.01). The levels of serum SUA and SCr, and 24 h urine protein quantitation in observation group were significantly lower than those in the control group ( t=3.38, 2.49, 12.55, P<0.01 or P<0.05), and levels of CRP, IL-6 and IL-8 were significantly lower than those in the control group ( t=5.44, 4.15, 9.61, P<0.01). There was no significant difference in incidence of adverse reactions between observation group and control group [4.00% (3/75) vs. 10.67% (8/75); χ2=2.45, P=0.117]. Conclusion:The self-made Lishi Qufeng Juanbi Decoction combined with Febuxostat tablets can promote uric acid metabolism, improve high uric acid environment, protect renal function, inhibit the release of inflammatory factors, improve curative effect and reduce adverse reactions in UAN patients.

Objective: To explore the mediating effect and gender difference of mobile phone use in the association between different types of childhood abuse experiences and sleep quality of medical students, so as to provide reference for promoting sleep quality of medical students. Methods: A longitudinal study design method was used to select freshmen and sophomores in two medical colleges in Anhui Province from November to December 2019, follow up data were collected from May to June 2020, and a total of 6 879 students were included in this study. Spearman correlation was used to analyze the association between baseline childhood abuse experiences, baseline mobile phone use and follow up sleep quality. Bootstrap program and Process software were applied to test the mediating effect of mobile phone use in the relationship between childhood abuse and sleep quality. Results: Childhood abuse experiences were positively correlated with mobile phone use and sleep quality score ( r = 0.27 , 0.24, P <0.01), and mobile phone use was positively correlated with sleep quality score ( r =0.31, P <0.01). In the total sample, after adjusting for confounding factors, mobile phone use played a partial mediating role in childhood abuse experiences (including emotional abuse, physical abuse, sexual abuse) and sleep quality, and the mediating effect was 18.08% (18.12%, 17.15%, 24.09%). The mediating effect of mobile phone use on the relationship between childhood emotional abuse, sexual abuse, childhood abuse and sleep quality in girls(18.32%, 28.05%, 18.24%) was higher than in boys(17.81%, 18.94%, 17.63%). Conclusion Mobile phone use has a mediating effect on the relationship between childhood abuse and sleep quality, controlling mobile phone overuse may contribute to improving the sleep quality for those who have experienced childhood abuse.

Objective: : Extracranial supra-aortic dissections (ESADs) with severe stenosis, occlusion and/or pseudoaneurysm presents potential risk of stroke. Endovascular stenting to reconstruct non acute phase ESADs (NAP-ESADs) is an alternative to anticoagulant or antiplatelet therapy. However, its feasibility, safety and efficacy of stenting in NAP-ESADs is unclear. This study aims to investigate the long-term outcomes of the feasibility, safety and efficacy of stenting in NAP-ESADs. Methods: : Seventy-four patients with 91 NAP-ESAD vessels with severe stenosis, occlusion and/or pseudoaneurysm presents potential risk of stroke who underwent stent remodeling were enrolled into this respective study from December 2008 to March 2020. Technical success rate, complications, clinical and angiographic results were harvested and analyzed. Results: : Success rate of stent deployment was 99% (90/91) with no procedural mortality or morbidity. Transient ischemic attack occurred in three patients during operation (4.1%, 3/74). Asymptomatic embolisms of distal intracranial vessels were found in two patients (2.7%, 2/74). One hundred and forty-two stents deployed at 85 carotid (135 stents) and six vertebral (seven stents) vessels. Six stent types (Wingspan, 28/135, 20.7%; Solitaire, 10/135, 7.4%; Neuroform, 8/135, 5.9%; LVIS, 2/135, 1.5%; Precise, 75/135, 55.6%; Acculink, 12/135, 8.9%) were deployed at carotid arterial dissection while two types (Wingspan, 5/7, 71.4%; Solitaire 2/7, 28.6%) at vertebral arterial dissection. Digital subtracted angiography (56%, 51/91), computational tomography angiography (41.8%, 38/91) and high resolution magnetic resonance imaging (2.2%, 2/91) were adopted for follow up, with a mean time of 17.2±15.4 months (5–77). All patient modified Rankin Scale scores showed no increase at discharge or follow-up. Angiographically, dissections in 86 vessels in 69 patients (94.5%, 86/91) were completely reconstructed with only minor remnant dissections in four vessels in four patients (4.4%, 4/91). Severe re-stenosis in the stented segment required re-stenting in one patient (1.1%, 1/91). Conclusion : Stent remodeling technique provides feasible, safe and efficacious treatment of ESADs patients with severe stenosis, occlusion and/or pseudoaneurysm.