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/.

Drug development encompasses multiple processes, wherein protein subcellular localization is essential. It promotes target identification, treatment development, and the design of drug delivery systems. In this research, a deep learning framework called LocPro is presented for predicting protein subcellular localization. Specifically, LocPro is unique in (a) combining protein representations from the pre-trained large language model (LLM) ESM2 and the expert-driven tool PROFEAT, (b) implementing a hybrid deep neural network architecture that integrates convolutional neural network (CNN), fully connected (FC) layer, and bidirectional long short-term memory (BiLSTM) blocks, and (c) developing a multi-label framework for predicting protein subcellular localization at multiple granularity levels. Additionally, a dataset was curated and divided using a homology-based strategy for training and validation. Comparative analyses show that LocPro outperforms existing methods in sequence-based multi-label protein subcellular localization prediction. The practical utility of this framework is further demonstrated through case studies on drug target subcellular localization. All in all, LocPro serves as a valuable complement to existing protein localization prediction tools. The web server is freely accessible at https://idrblab.org/LocPro/.

Drug development encompasses multiple processes,wherein protein subcellular localization is essential.It promotes target identification,treatment development,and the design of drug delivery systems.In this research,a deep learning framework called LocPro is presented for predicting protein subcellular localization.Specifically,LocPro is unique in(a)combining protein representations from the pre-trained large language model(LLM)ESM2 and the expert-driven tool PROFEAT,(b)implementing a hybrid deep neural network architecture that integrates convolutional neural network(CNN),fully connected(FC)layer,and bidirectional long short-term memory(BiLSTM)blocks,and(c)developing a multi-label framework for predicting protein subcellular localization at multiple granularity levels.Additionally,a dataset was curated and divided using a homology-based strategy for training and validation.Compar-ative analyses show that LocPro outperforms existing methods in sequence-based multi-label protein subcellular localization prediction.The practical utility of this framework is further demonstrated through case studies on drug target subcellular localization.All in all,LocPro serves as a valuable complement to existing protein localization prediction tools.The web server is freely accessible at https://idrblab.org/LocPro/.

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/.

This review summarizes recent advances in neoadjuvant immunotherapy for advanced gastric cancer.Through literature search in PubMed,Web of Science,and CNKI databases from 2020 to 2023,we systematically analyzed the mechanisms,clinical applications,and bio-marker research.Programmed death-1(PD-1)inhibitors combined with chemotherapy significantly improve patient outcomes,while mi-crosatellite instability(MSI),programmed death-ligand 1(PD-L1)expression,and tumor mutational burden(TMB)have been identified as important predictive biomarkers.Multi-omics analysis shows great potential in identifying optimal responders,with pyroptosis-related gene scoring system(PRS)positively correlating with anti-tumor immune infiltration.Metabolic reprogramming and epigenetic regulation in the tumor microenvironment play key roles in immune evasion,while emerging targets such as Claudin 18.2 and combination targeting strategies further enhance therapeutic efficacy.Despite significant progress,precise patient selection and overcoming resistance mechan-isms remain major challenges.Future research should focus on biomarker validation,personalized treatment strategy development,tumor microenvironment dynamic analysis,and novel combination therapy exploration to improve clinical outcomes.

A 58-year-old female patient with anti-synthetase syndrome received compound sulfamethoxazole [containing trimethoprim (TMP) 80 mg and sulfamethoxazole (SMZ) 0.4 g, SMZ-TMP] 3 tablets thrice daily orally for the treatment of Pneumocystis jirovecii pneumonia. Before medication, the patient′s blood potassium was 3.3 mmol/L and blood chlorine was 116 mmol/L. Three days after SMZ-TMP treatment, the patient′s blood potassium was 5.7 mmol/L, blood chlorine was 114 mmol/L, blood pH was 7.3, urine pH was <5.5, blood chlorine was 114 mmol/L, and bicarbonate was 15 mmol/L. Hyperkalemia type renal tubular acidosis due to SMZ-TMP was considered. The dosage of SMZ-TMP was reduced to 2 tablets once daily orally. After 1 day of diuretic and potassium excretion treatments, the patient′s blood potassium levels returned to normal; after 2 days of the treatments, her blood chlorine was 109 mmol/L and bicarbonate was 17 mmol/L; after 3 days of the treatments, her chest CT showed emphysema in the neck and mediastinum. The dose of SMZ-TMP was changed to 3 tablets thrice daily orally, and at the same time intravenous infusion of ganciclovir 0.3 g twice daily was given. And again, her blood potassium increased and blood pH decreased. Sodium bicarbonate 1 g thrice daily orally was given to correct the acidosis. After adding SMZ-TMP for 2 days, SMZ-TMP dosage was reduced to 2 tablets once daily orally again. Seven days later, the patient′s vital signs were stable, her mediastinal emphysema was significantly improved, her blood potassium was 4.7 mmol/L, and blood pH was 7.4.

This review summarizes recent advances in neoadjuvant immunotherapy for advanced gastric cancer.Through literature search in PubMed,Web of Science,and CNKI databases from 2020 to 2023,we systematically analyzed the mechanisms,clinical applications,and bio-marker research.Programmed death-1(PD-1)inhibitors combined with chemotherapy significantly improve patient outcomes,while mi-crosatellite instability(MSI),programmed death-ligand 1(PD-L1)expression,and tumor mutational burden(TMB)have been identified as important predictive biomarkers.Multi-omics analysis shows great potential in identifying optimal responders,with pyroptosis-related gene scoring system(PRS)positively correlating with anti-tumor immune infiltration.Metabolic reprogramming and epigenetic regulation in the tumor microenvironment play key roles in immune evasion,while emerging targets such as Claudin 18.2 and combination targeting strategies further enhance therapeutic efficacy.Despite significant progress,precise patient selection and overcoming resistance mechan-isms remain major challenges.Future research should focus on biomarker validation,personalized treatment strategy development,tumor microenvironment dynamic analysis,and novel combination therapy exploration to improve clinical outcomes.

A 58-year-old female patient with anti-synthetase syndrome received compound sulfamethoxazole [containing trimethoprim (TMP) 80 mg and sulfamethoxazole (SMZ) 0.4 g, SMZ-TMP] 3 tablets thrice daily orally for the treatment of Pneumocystis jirovecii pneumonia. Before medication, the patient′s blood potassium was 3.3 mmol/L and blood chlorine was 116 mmol/L. Three days after SMZ-TMP treatment, the patient′s blood potassium was 5.7 mmol/L, blood chlorine was 114 mmol/L, blood pH was 7.3, urine pH was <5.5, blood chlorine was 114 mmol/L, and bicarbonate was 15 mmol/L. Hyperkalemia type renal tubular acidosis due to SMZ-TMP was considered. The dosage of SMZ-TMP was reduced to 2 tablets once daily orally. After 1 day of diuretic and potassium excretion treatments, the patient′s blood potassium levels returned to normal; after 2 days of the treatments, her blood chlorine was 109 mmol/L and bicarbonate was 17 mmol/L; after 3 days of the treatments, her chest CT showed emphysema in the neck and mediastinum. The dose of SMZ-TMP was changed to 3 tablets thrice daily orally, and at the same time intravenous infusion of ganciclovir 0.3 g twice daily was given. And again, her blood potassium increased and blood pH decreased. Sodium bicarbonate 1 g thrice daily orally was given to correct the acidosis. After adding SMZ-TMP for 2 days, SMZ-TMP dosage was reduced to 2 tablets once daily orally again. Seven days later, the patient′s vital signs were stable, her mediastinal emphysema was significantly improved, her blood potassium was 4.7 mmol/L, and blood pH was 7.4.

To investigate the short-term effectiveness and safety of sublingual allergen immunotherapy with allergen sprays (SLIT-sprays) in Chinese patients with allergic rhinitis (AR) with or without asthma using real-world data. The retrospective cohort study included 100 patients who received SLIT-sprays in the ENT departments in Hainan Shulan (Boao) Hospital and Boao Super Hospital between October 2023 and August 2024. A questionnaire survey was conducted to collect clinical data on the effectiveness and safety of SLIT-sprays, examining the types and incidence of adverse events (AEs) during treatment, treatments after the occurrence of AEs, and changes in Visual Analog Scale (VAS) scores before and after SLIT-sprays. Self-reports from 100 patients were collected. The results showed that the average treatment duration for the 100 patients was (90.7±58.9) days, median 78.5 days. Using changes in VAS scores as the effectiveness assessment, the average VAS score increased by 4.2 (95% CI: 4.06-4.34). The incidence of AEs during the SLIT-sprays was 17.0% (17/100), all of which were mild to moderate local reactions, with no serious AEs reported. There were no significant differences in AE incidence among patients with different diseases (AR or AR with asthma and asthma alone) (χ 2=1.831, P>0.05), different age group (χ 2=1.477, P>0.05), different types of allergen extracts (χ 2=1.613, P>0.05), or the number of allergen extracts used (patients using one or two allergen extracts) (Fisher′s exact test, P>0.05). In conclusion, Chinese patients showed good safety and tolerability to SLIT-sprays, with all AEs being mild to moderate local reactions and no serious or systemic AEs occurring. Patients reported positive subjective evaluations of the early treatment effects.