Artificial intelligence (AI) is an effective tool to accelerate drug discovery and cut costs in discovery processes. Many successful AI applications are reported in the early stages of small molecule drug discovery. However, most of those applications require a deep understanding of software and hardware, and focus on a single field that implies data normalization and transfer between those applications is still a challenge for normal users. It usually limits the application of AI in drug discovery. Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results. MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry. The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness. More than 400 users from industry and academia have used MolProphet in their work. We hope this platform can provide a powerful solution to assist each normal researcher in drug design and related research areas. It is available for everyone at https://www.molprophet.com/.

Zeolite molecular sieves are potential adsorbents for wastewater treatment, characterized by high efficiency, simple process, easy regeneration, and low treatment cost. In this study, zeolite A molecular sieves were prepared using coal fly ash (CFA), which is an effective method for the utilization of CFA. The results showed that the CFA-based zeolite molecular sieves synthesized under optimized conditions exhibited excellent adsorption and removal rates (> 40%) for ammonia–nitrogen in wastewater of different concentrations and properties. The analysis of adsorption kinetics revealed that the adsorption process followed pseudo-second-order kinetics model, indicating that the adsorption of ammonia–nitrogen on zeolite is primarily controlled by chemisorption rather than physisorption. The adsorption process can be divided into two stages, with a higher adsorption rate and a smaller diffusion boundary layer thickness in the first stage, and a lower adsorption rate and an increased diffusion boundary layer thickness in the second stage. This indicates that as the adsorption proceeds, the internal diffusion resistance within the particles gradually increases, leading to a decrease in the adsorption rate until reaching equilibrium, where both the diffusion and adsorption become stable. The adsorption isotherms of ammonia–nitrogen on zeolite A conformed to the assumptions of the Langmuir model, suggesting that the adsorption mechanism primarily involves uniform monolayer adsorption on the surface without intermolecular interactions.

Recently, mesoporous nanomaterials with widespread applications have attracted great interest in the field of drug delivery due to their unique structure and good physiochemical properties. As a biomimetic nanomaterial, mesoporous polydopamine (MPDA) possesses both a superior nature and good compatibility, endowing it with good clinical transformation prospects compared with other inorganic mesoporous nanocarriers. However, the subacute toxicity and underlying mechanisms of biomimetic mesoporous polydopamine nanoparticles remain uncertain. Herein, we prepared MPDAs by a soft template method and evaluated their primary physiochemical properties and metabolite toxicity, as well as potential mechanisms. The results demonstrated that MPDA injection at low (3.61 mg/kg) and medium doses (10.87 mg/kg) did not significantly change the body weight, organ index or routine blood parameters. In contrast, high-dose MPDA injection (78.57 mg/kg) is associated with disturbances in the gut microbiota, activation of inflammatory pathways through the abnormal metabolism of bile acids and unsaturated fatty acids, and potential oxidative stress injury. In sum, the MPDA dose applied should be controlled during the treatment. This study first provides a systematic evaluation of metabolite toxicity and related mechanisms for MPDA-based nanoparticles, filling the gap between their research and clinical transformation as a drug delivery nanoplatform.

Molecular property prediction holds significant importance in drug discovery, enabling the identification of biologically active compounds with favorable drug-like properties. However, the low data problem, arising from the scarcity of labeled data in drug discovery, poses a substantial obstacle for accurate predictions. To address this challenge, we introduce a novel architecture, AttFPGNN-MAML, for few-shot molecular property prediction. The proposed approach incorporates a hybrid feature representation to enrich molecular representations and model intermolecular relationships specific to the task. By leveraging ProtoMAML, a meta-learning strategy, our model is trained and adapted to new tasks. Evaluation on two few-shot data sets, MoleculeNet and FS-Mol, demonstrates our method's superior performance in three out of four tasks and across various support set sizes. These results convincingly validate the effectiveness of our method in the realm of few-shot molecular property prediction. The source code is publicly available at https://github.com/sanomics-lab/AttFPGNN-MAML.

The detection of pathogens in medical wastewater is crucial due to the high content of pathogenic microorganisms that pose significant risks to public health and the environment. Medical wastewater, which includes waste from infectious disease and tuberculosis facilities, as well as comprehensive medical institutions, contains a variety of pathogens such as bacteria, viruses, fungi, and parasites. Traditional detection methods like nucleic acid detection and immunological assays, while effective, are often time-consuming, expensive, and not suitable for rapid detection in underdeveloped areas. Electrochemical biosensors offer a promising alternative with advantages including simplicity, rapid response, portability, and low cost. This paper reviews the sources of pathogens in medical wastewater, highlighting specific bacteria (e.g., E. coli, Salmonella, Staphylococcus aureus), viruses (e.g., enterovirus, respiratory viruses, hepatitis virus), parasites, and fungi. It also discusses various electrochemical biosensing techniques such as voltammetry, conductometry, impedance, photoelectrochemical, and electrochemiluminescent biosensors. These technologies facilitate the rapid, sensitive, and specific detection of pathogens, thereby supporting public health and environmental safety. Future research may should pay more attention on enhancing sensor sensitivity and specificity, developing portable and cost-effective devices, and innovating detection methods for diverse pathogens to improve public health protection and environmental monitoring.