Jian-Zhong Chen

The development of reliable predictive models for nephrotoxic agents remains a critical challenge in drug development, given safety concerns associated with kidney toxicity. Conventional molecular descriptors generally fail to capture essential spatial and electronic features necessary for accurate nephrotoxicity prediction, underscoring the need for novel descriptor approaches. This study presents a novel projection-based method for nephrotoxicity prediction by converting chemical structures into 2D maps for deep learning via 3D spatial transformation to enhance both feature representation and model performance. Both Mollweide and Equirectangular projections were utilized to transform 3D molecular geometries into optimized 2D representations. The 2D molecular maps incorporated three key molecular properties to display the information of atom-based projections showing atomic positions and identities, electrostatic projections visualizing charge distribution, and vdW projections illustrating molecular steric potentials. The Mollweide projection based on atom color demonstrated superior predictive performance, achieving 83% predictive accuracy with an AUC of 0.86, establishing it as the most effective CNN model. The electrostatic and vdW projections transformed atomic spatial data into electrostatically and sterically informative maps, enabling more nuanced molecular pattern recognition and enhanced representation. The reliability of the model was validated through different methods, including independent verification on test set combined with five-fold cross validation as well as comparisons with traditional descriptor-based models using the benchmarking method. Our findings demonstrate that projection-based molecular representations show strong potential for nephrotoxicity screening, opening new possibilities for toxicology prediction and drug safety advancement.

DJ-1 is a multifunctional protein implicated in cancer and autosomal early onset Parkinson's disease. Cys106 of DJ-1 plays a crucial role in its biological functions. The inhibitor bonded to Cys106 needs to be developed with tight binding for the definitive characterization of DJ-1. In this study, we investigate the binding mechanisms of two classes of DJ-1's covalent ligands, isatins and α-chloroamides, using MD simulations, QM/MM calculations, and SAPT analyses. MD simulations indicated that the stable binding process of a ligand in protein would be beneficial to have a good starting point for its covalent binding to DJ-1 in relation to the inhibition. Moreover, the warhead of a covalent inhibitor should be a small group fitting in the narrow space around Cys106, adopting a stable binding pose to facilitate the formation of the C(warhead)-S(Cys106) bond in DJ-1. The covalent bond can enhance the stability of nonbonded interactions between the ligands and DJ-1 during MD simulations. Furthermore, QM/MM calculations demonstrated the two-step nucleophilic addition reaction to form the C(warhead)-S(Cys106) bond for the covalent bindings of isatins and the three-step nucleophilic substitution reaction for the covalent bindings of α-chloroamides in DJ-1. In both reactions, proton transfer from Cys106 to Glu18 is the first step with the highest energy barrier. The electronic characteristics of the phenyl moiety may exert a negligible influence on the formation of the C(warhead)-S(Cys106) bond for the covalent binding to DJ-1. Finally, SAPT analyses revealed the detailed electronic interactions of the compounds with key residues around the active pocket of DJ-1. All the studies shed light on binding mechanisms of covalent inhibitors in the target protein, providing useful clues for the drug design of bioactive compounds.

Reproductive toxicity is one of the important issues in chemical safety. Traditional laboratory testing methods are costly and time-consuming with raised ethical issues. Only a few in silico models have been reported to predict human reproductive toxicity, but none of them make full use of the topological information of compounds. In addition, most existing atom-based graph neural network methods focus on attributing model predictions to individual nodes or edges rather than chemically meaningful fragments or substructures. In current studies, we develop a novel fragment-based graph transformer network (FGTN) approach to generate the QSAR model of human reproductive toxicity by considering internal topological structure information of compounds. In the FGTN model, the compound is represented by a graph architecture using fragments to be nodes and bonds linking two fragments to be edges. A super molecule-level node is further proposed to connect all fragment nodes by undirected edges, obtaining global molecular features from fragment embeddings. The FGTN model achieved an accuracy (ACC) of 0.861 and an area under the receiver operating characteristic curve (AUC) value of 0.914 on nonredundant blind tests, outperforming traditional fingerprint-based machine learning models and atom-based GCN model. The FGTN model can attribute toxic predictions to fragments, generating specific structural alerts for the positive compound. Moreover, FGTN may also have the capability to distinguish various chemical isomers. We believe that FGTN can be used as a reliable and effective tool for human reproductive toxicity prediction in contribution to the advancement of chemical safety assessment.

Background: Chemicals may lead to acute liver injuries, posing a serious threat to human health. Achieving the precise safety profile of a compound is challenging due to the complex and expensive testing procedures. In silico approaches will aid in identifying the potential risk of drug candidates in the initial stage of drug development and thus mitigating the developmental cost.Methods: In current studies, QSAR models were developed for hepatotoxicity predictions using the ensemble strategy to integrate machine learning (ML) and deep learning (DL) algorithms using various molecular features. A large dataset of 2588 chemicals and drugs was randomly divided into training (80%) and test (20%) sets, followed by the training of individual base models using diverse machine learning or deep learning based on three different kinds of descriptors and fingerprints. Feature selection approaches were employed to proceed with model optimizations based on the model performance. Hybrid ensemble approaches were further utilized to determine the method with the best performance.Results: The voting ensemble classifier emerged as the optimal model, achieving an excellent prediction accuracy of 80.26%, AUC of 82.84%, and recall of over 93% followed by bagging and stacking ensemble classifiers method. The model was further verified by an external test set, internal 10-fold cross-validation, and rigorous benchmark training, exhibiting much better reliability than the published models.Conclusion: The proposed ensemble model offers a dependable assessment with a good performance for the prediction regarding the risk of chemicals and drugs to induce liver damage.

Activatable near-infrared (NIR) imaging in the NIR-II range is crucial for deep tissue bioanalyte tracking. However, designing such probes remains challenging due to the limited availability of general chemical strategies. Here, we introduced a foundational platform for activatable probes, using analyte-triggered smart modulation of the π-conjugation system of a NIR-II–emitting rhodamine hybrid. By tuning the nucleophilicity of the ortho-carboxy moiety, we achieved an electronic effect termed “firm-push-to-open and light-push-to-lock,” which enables complete spirocyclization of the probe before sensing and allows for efficient zwitterion formation when the light-pushing aniline carbamate trigger is transformed into a firm-pushing aniline. This platform produces dual-modality NIR-II imaging probes with ~50-fold fluorogenic and activatable photoacoustic signals in live mice, surpassing reported probes with generally below 10-fold activatable signals. Demonstrating generality, we successfully designed probes for hydrogen peroxide (H ₂ O ₂ ) and hydrogen sulfide (H ₂ S). We envision a widespread adoption of the chemical platform for designing activatable NIR-II probes across diverse applications.

An efficient radical cascade cyclization of unactivated alkenes toward the synthesis of a series of ring-fused quinazolinones has been developed in moderate to excellent yields using commercially available ethers, alkanes, and alcohols, respectively, under a base-free condition in a short time without a transition metal as catalyst. Notably, the transformations can be carried out with the advantages of a broad substrate scope and high atomic economy. Density functional theory calculations and wavefunction analyses were performed to elucidate the radical reaction mechanism.

A convenient and efficient approach for the synthesis of indolo[2,1- α ]isoquinoline derivatives from 2-aryl- N -acryloyl indoles and aryl or alkyl α-keto acids is described via radical cascade cyclization under metal-free conditions.