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/.

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 evaluate the incidence, clinical features, factors affecting initial diagnosis, efficacy, and safety of therapy and prognosis of small intestinal Dieulafoy lesions (DL).Methods:Clinical data including clinical background, diagnosis, and treatment details of patients who were admitted to the Department of Gastroenterology, Air Force Medical Center, for suspected small bowel bleeding, diagnosed as having small bowel DL and treated with balloon-assisted enteroscopy (BAE) were retrospectively analyzed from November 2017 to March 2024.Results:Among 800 patients, 30 cases (3.75%, 30/800, 17 males and 13 females) were diagnosed as having small intestine DL with the mean age of 60.90 years. Clinical symptoms included melena (56.67%, 17/30), hematochezia (43.33%, 13/30), and hemodynamic instability (30.00%, 9/30). Active bleeding occurred in 23 (76.67%) patients. Comorbidities existed in 70.00% (21/30) and 33.33% (10/30) used long-term antithrombotic agents. Diagnosis was confirmed after a single BAE in 63.33% (19/30) and after multiple BAEs (mean 1.6 procedures) in 36.67% (11/30). Lesions were predominantly located at jejunal. All patients achieved successful treatment with a single BAE procedure. The median follow-up period was 12.25 months (range: 5.25-23.00 months). Five cases (16.67%) experienced recurrent bleeding, with one case transfered to surgical intervention. Two cases (6.67%) reported post-operative symptoms of dizziness and fatigue, which resolved after symptomatic management. Multivariate analysis showed that long-term oral anticoagulant therapy ( OR=0.06, 95% CI: 0.01-0.73) was an independent predictor of single-session diagnosis. Conclusion:Small intestinal DL is rare and challenging to diagnose. Antithrombotic therapy may facilitate the diagnosis of DL at the first BAE. Jejunal localization is common, and combined endoscopic therapy (including clipping) is effective and safe.

Objective:To evaluate the incidence, clinical features, factors affecting initial diagnosis, efficacy, and safety of therapy and prognosis of small intestinal Dieulafoy lesions (DL).Methods:Clinical data including clinical background, diagnosis, and treatment details of patients who were admitted to the Department of Gastroenterology, Air Force Medical Center, for suspected small bowel bleeding, diagnosed as having small bowel DL and treated with balloon-assisted enteroscopy (BAE) were retrospectively analyzed from November 2017 to March 2024.Results:Among 800 patients, 30 cases (3.75%, 30/800, 17 males and 13 females) were diagnosed as having small intestine DL with the mean age of 60.90 years. Clinical symptoms included melena (56.67%, 17/30), hematochezia (43.33%, 13/30), and hemodynamic instability (30.00%, 9/30). Active bleeding occurred in 23 (76.67%) patients. Comorbidities existed in 70.00% (21/30) and 33.33% (10/30) used long-term antithrombotic agents. Diagnosis was confirmed after a single BAE in 63.33% (19/30) and after multiple BAEs (mean 1.6 procedures) in 36.67% (11/30). Lesions were predominantly located at jejunal. All patients achieved successful treatment with a single BAE procedure. The median follow-up period was 12.25 months (range: 5.25-23.00 months). Five cases (16.67%) experienced recurrent bleeding, with one case transfered to surgical intervention. Two cases (6.67%) reported post-operative symptoms of dizziness and fatigue, which resolved after symptomatic management. Multivariate analysis showed that long-term oral anticoagulant therapy ( OR=0.06, 95% CI: 0.01-0.73) was an independent predictor of single-session diagnosis. Conclusion:Small intestinal DL is rare and challenging to diagnose. Antithrombotic therapy may facilitate the diagnosis of DL at the first BAE. Jejunal localization is common, and combined endoscopic therapy (including clipping) is effective and safe.

To observe the effects of emodin ( Emo) on acute fatty liver in mice induced by DL-ethionine ( DL-Eth) or tetracyclin ( Tetra) and its potential mechanism, ICR mice of acute fatty liver model induced by DL-Eth were orally administered with Emo or positive control, ursodeoxycholic acid ( UDCA) for 7 days. On day 7, except that the control and Emo groups were treated with vehicle control, animals were orally administered with DL-Eth to induce acute fatty liver model. ICR mice of acute fatty liver model induced by Tetra were orally administered with Emo or positive control, Dong Bao Gan Tai ( DB) or total flavonoid C-glycosides from Abrus mollis extract ( AME) for 7 days. From day 4, except that the control group was treated with vehicle control, animals were injec-ted with Tetra intraperitoneally for 4 days to induce acute fatty liver model. Liver histopathological analyses were determined by HE staining. Serum aspartate transaminase ( AST) , alanine transaminase ( ALT) , serum triglyceride ( TG) , hepatic TG and hepatic total cholesteol ( TC) were detected. The expression of phosphorylated AMP-activa-ted kinase ( p-AMPK) , phosphorylated acetyl-CoA carboxylase ( p-ACC) , SREBP1 and fatty acid synthase ( FAS) were determined by Western blot. The expression of fatty acid translocase ( CD36 ) , peroxisome proliferator activa-ted receptor alpha ( PPARα) and microsomal triglyceride transfer protein ( MTTP ) in liver were determined by RT-PCR. Compared with model groups, Emo could improve hepatocyte swelling and hepatic steatosis induced by DL-Eth or Tetra. Serum AST, ALT, serum TG, hepatic TG and hepatic TC were decreased by Emo significantly. DL-Eth-induced increase of fatty acid synthetase-associated protein was down-regulated by Emo. Fatty acid uptake was down-regulated by Emo; fatty acid oxidation and secretion were increased by Emo. Emo might be effective in preventing acute fatty liver in mice induced by DL-Eth or Tetra.

To investigate the hypoglycemic effects of terpenes from Fructus Corni(TFC)on type 2 diabetes mellitus, the db/db diabetic mice were intragastrically administered with 25, 50, 100 mg/kg of TFC for 10 weeks. The fasting blood glucose, insulin(Ins), glycosylated serum protein(GSP), total cholesterol(TC)and triglyceride(TG)levels were determined. At weeks 8 and 10, intraperitoneal injections of glucose and gavage starch tolerance tests were performed, respectively. The db/db mice showed obvious obesity. Each dose of TFC could significantly reduce the body weight of db/db mice(P< 0. 05). After 4 weeks of administration, all doses of TFC significantly reduced the fasting blood glucose of db/db mice(P< 0. 05). The serum TC, TG levels were also significantly decreased in the TFC middle- and high-dose groups(P< 0. 05). In addition, middle- and high-dose of TFC could significantly reduce the level of GSP. Middle- and high-dose of TFC also significantly improve the glucose tolerance and gavage starch tolerance in db/db mice(P< 0. 05). These results suggest that TFC could improve diabetes-related symptoms via regulating glucose and lipids metabolism.