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/.

Objective:To establish a high-performance liquid chromatography-tandem mass spectrometry (LC-MS/MS) method for the determination of voliconazole (VRC), posaconazole (PCZ), and linazolam (LNZ) in human serum.Methods:This study is a methodological validation by LC-MS/MS. The blood concentration results of VRC, PCZ, and LNZ in our hospital′s anti-infection patients were collected. Voriconazole, Posaconazole, and Linezolid were accurately weighed and prepared. Linezolid-[2H3] was used as the internal standard. After gradient elution on the ACE PFP column, the residuals were analyzed by LC-MS/MS in the positive electrospray ionization mode and multiple reaction monitor (MRM) mode. The method′s linearity, precision, lower limit of detection, and recovery rate were validated according to standard guidelines.Results:The linear correlation coefficient ( r) of the standard curve was above 0.99 ( r>0.99). The linear range of VRC and PCZ were 0.10 mg/L~10.00 mg/L, and the lower limit of detection were 0.01 mg/L. The linear range of LNZ was 0.50 mg/L~50.00 mg/L, and the lower limit of detection was 0.05 mg/L. The recoveries of VRC, PCZ and LNZ were 90.96%-103.18%, 91.84%-99.17%, and 97.04%-100.41%, respectively. Intra-and inter-batch precision (% CV) for VRC were less than 8.30%. Intra-and inter-batch precision (% CV) for PCZ was less than 9.78%. Intra-and inter-batch precision (% CV) for LNZ was less than 7.14%. Drug concentrations in 155 cases of VRC, 44 cases of PCZ, and 59 cases of LNZ were detected. Conclusion:We have established an LC-MS/MS method for the rapid, accurate, highly specific determination of VRC, PCZ, and LNZ concentrations in human serum. This method is suitable for analyzing large clinical sample sets.

Objective:To explore the efficacy of subcutaneous injection of granulocyte-macrophage colony-stimulating factor (GM-CSF) in preventing invasive fungal disease (IFD) in patients with multiple myeloma (MM).Methods:The clinical data of 222 patients who were admitted to the Second Hospital of Harbin Medical University from January 2015 to June 2021 were retrospectively analyzed. The patients was given GM-CSF (3-5 μg·kg -1·d -1, GM-CSF group) or granulocyte colony-stimulating factor (G-CSF, 2-5 μg·kg -1·d -1, G-CSF group) when neutrophils (ANC) ≤1.5×10 9/L after induction chemotherapy. Patients were discontinued when white blood cell count (WBC) ≥10.0×10 9/L. The incidence of IFD (including confirmed, clinical and proposed diagnosis) and breakthrough invasive fungal infections was compared between the two groups. Results:The incidence of IFD was 8.1% (18/222) in all patients. The incidence of IFD was 3.5% (3/85) and 10.9% (15/137) in the GM-CSF and G-CSF groups, respectively, and the difference between the two groups was statistically significant ( χ2 = 3.88, P = 0.049). In 9 patients of GM-CSF group receiving fungal infection prophylaxis and in 15 patients of G-CSF group receiving fungal infection prophylaxis, the incidence of breakthrough invasive fungal infections was 0 and 7 cases, respectively, and the difference between the two groups was statistically significant ( P = 0.022). Conclusions:GM-CSF application in MM patients can reduce the incidence of IFD and breakthrough invasive fungal infections.

Objective:To evaluate the effectiveness of antimicrobial stewardship based on self-developed antibiotic clinical decision support system (aCDSS) in the inpatients at a tertiary hospital for consecutive 6 years, and to provide reference for rational use and antimicrobial stewardship.Methods:aCDSS was self-designed based on information technology and applied in clinical use in our hospital from 2015. Data of inpatient information and antibacterial use from January 2015 to December 2020 were collected from HIS and aCDSS. A retrospective study was conducted in all inpatients on the utilization rate and antibiotic use density.Results:Since 2015, with the comprehensive implementation of antimicrobial stewardship based on the aCDSS,there was a significant decline on the annual rate of antibiotic usage from 44.18% in 2015 to 38.70% in 2020, as well as on the usage rate of extended-spectrum antimicrobial agents including carbapenems, broad-spectrum β-lactam/β-lactamase inhibitors, tigecycline, broad-spectrum cephalosporins, fluoroquinolones, as well as glycopeptide and antifungal drugs. Compared with 2015, the usage of carbapenems, tigecycline and broad-spectrum β-lactam/β-lactamase inhibitors was declined nearly 50% in 2020, and the density of carbapenems and tigecycline were decreased by 29.6% and 7.1%, respectively in 2020. On the other side, the utilization rate and use density of narrow-spectrum cephalosporins continued to increase by year, the use density of narrow-spectrum cephalosporins accounting for 28.2% of all antibiotics in 2020.Conclusions:With the comprehensive implementation of aCDSS, the utilization rate and density of broad-spectrum and high-priced antibacterial drugs in our hospital have decreased continuously to decline in the past 6 years, while the proportion of narrow-spectrum antimicrobials has increased year by year, indicating that the structure of antimicrobial use has been continuously optimized and that antimicrobial stewardship based on the information technology have achieved remarkable results.

Objective:To evaluate the effectiveness of the information management system on the clinical application of special-grade antimicrobial.Methods:Using the established knowledge database, a computer program was designed and developed, which was embedded in the electronic medical record to intervene the clinical use of the special-grade antimicrobial since 2015. The basic information of all discharged patients from the Second Affiliated Hospital of Zhejiang University School of Medicine from January 2013 to December 2020 were extracted from the HIS system, including the medical orders for antibiotics and the drug storehouse dispensing data.The trend analysis was carried out on the changes of the use rates and antibiotic use density (AUD) of the special-grade antimicrobials in the whole hospital and intensive care units (ICU). The data were processed and analyzed using SPSS 24.0.Results:From 2013 to 2015, except for meropenem and amphotericin B, the usage rate of all special-grade antimicrobials in the whole hospital showed an upward trend ( P<0.05). The proportion of special-grade antimicrobials used in the hospital increased year by year ( χ2=7 804.081, P<0.01). The total usage rate of special-grade antimicrobials in ICU showed an upward trend year by year ( χ2=67.028, P<0.01). Since the implementation of the special-grade antimicrobial information management system in 2015, the total use rate of special-grade antimicrobials in the hospital, the use rate of various antibiotics except linezolid, amphotericin B and posaconazole, and the proportion of special-grade antimicrobials used in the hospital have all shown a downward trend year by year ( P<0.01). The total usage rate and total AUD of special-grade antimicrobials in ICU showed a decreasing trend year by year ( χ2=343.514, P<0.01, β=-0.963, P=0.002). Conclusion:The information management system for special-grade antimicrobial can effectively reduce the utilization rate and AUD of most special-grade antibiotics in hospitalized patients including ICU, and has a good clinical application value in antimicrobial stewardship.

Objective To investigate the role of clinical pharmacists in the treatment of a Parkinson′s disease patient with mental disorders.Methods Clinical pharmacists provided appropriate pharmaceutical care and optimized the treatment program based on patient′s symptom, medication history, drug interactions,and adverse drug reactions etc.Results Clinical pharmacists improved rational drug use by participating in the development of patient′s treatment program, giving patient with proper medication instruction and discharge education.Conclusion With their professional knowledge, clinical pharmacists play an important role in rational drug use and helping physicians to optimize the medication regimen.