The interest in covalent drugs has resurged in recent decades, spurring the development of numerous specialized computational docking tools to facilitate covalent ligand design and screening. Herein, we present CarsiDock-Cov, a new paradigm distinguishing itself as the first deep learning (DL)-guided approach for covalent docking. CarsiDock-Cov retains the core components of its non-covalent predecessor, leveraging a DL model pretrained on millions of docking complexes to predict protein-ligand distance matrices, along with a dedicated-designed geometric optimization procedure to convert these distances into refined binding poses. Additionally, it incorporates several key enhancements specifically tailored to optimize the protocol for covalent docking applications. Our approach has been extensively validated on multiple public datasets regarding the docking and screening of covalent ligands, and the results indicate that our approach not only achieves comparably improved applicability compared to its non-covalent predecessor, but also exhibits competitive performance against various state-of-the-art covalent docking tools. Collectively, our approach represents a significant advance in covalent docking methodology, offering an automated and efficient solution that shows considerable promise for accelerating covalent drug discovery and design.

P-glycoprotein (P-gp) is a transmembrane protein widely involved in the absorption, distribution, metabolism, excretion, and toxicity (ADMET) of drugs within the human body. Accurate prediction of P-gp inhibitors and substrates is crucial for drug discovery and toxicological assessment. However, existing models rely on limited molecular information, leading to suboptimal model performance for predicting P-gp inhibitors and substrates. To overcome this challenge, we compiled an extensive dataset from public databases and literature, consisting of 5,943 P-gp inhibitors and 4,018 substrates, notable for their high quantity, quality, and structural uniqueness. In addition, we curated two external test sets to validate the model's generalization capability. Subsequently, we developed a multimodal graph contrastive learning (GCL) model for the prediction of P-gp inhibitors and substrates (MC-PGP). This framework integrates three types of features from Simplified Molecular Input Line Entry System (SMILES) sequences, molecular fingerprints, and molecular graphs using an attention-based fusion strategy to generate a unified molecular representation. Furthermore, we employed a GCL approach to enhance structural representations by aligning local and global structures. Extensive experimental results highlight the superior performance of MC-PGP, which achieves improvements in the area under the curve of receiver operating characteristic (AUC-ROC) of 9.82% and 10.62% on the external P-gp inhibitor and external P-gp substrate datasets, respectively, compared with 12 state-of-the-art methods. Furthermore, the interpretability analysis of all three molecular feature types offers comprehensive and complementary insights, demonstrating that MC-PGP effectively identifies key functional groups involved in P-gp interactions. These chemically intuitive insights provide valuable guidance for the design and optimization of drug candidates.

The new generation of artificial intelligence technology,represented by deep learning,has emerged as a crucial driving force in the advancement of new drug research and development.This article creatively proposes a workflow named"Molecular Factory"for the design and optimization of drug molecules based on artificial intelligence technology.This workflow integrates intelligent molecular generation models,high-performance molecular docking algorithms,and accurate protein-ligand binding affinity prediction methods.It has been integrated as a core module into DrugFlow,a one-stop drug design software platform,providing a comprehensive set of mature solutions for the discovery and optimization of lead compounds.Utilizing the"Molecular Factory"module,we conducted the research of second-generation inhibitors against Menin that can combat drug resistance.Through the integration of computational and experimental approaches,we rapidly identified multiple promising compounds.Among them,compound RG-10 exhibited the IC50 values of 9.681 nmol/L,233.2 nmol/L,and 40.09 nmol/L against the wild-type Menin,M327I mutant,and T349M mutant,respectively.Compared to the positive reference molecule SNDX-5613,which has entered Phase Ⅱ clinical trials,RG-10 demonstrated significantly enhanced inhibitory activity against the M327I and T349M mutants.These findings fully demonstrate the unique advantages of the"Molecular Factory"technology in practical drug design and development scenarios.It can rapidly and efficiently generate high-quality active molecules targeting specific protein structures,holding significant value and profound implications for advancing new drug discovery.

Prediction of the interactions between small molecules and their targets play important roles in various applications of drug development, such as lead discovery, drug repurposing and elucidation of potential drug side effects. Therefore, a variety of machine learning-based models have been developed to predict these interactions. In this study, a model called auxiliary multi-task graph isomorphism network with uncertainty weighting (AMGU) was developed to predict the inhibitory activities of small molecules against 204 different kinases based on the multi-task Graph Isomorphism Network (MT-GIN) with the auxiliary learning and uncertainty weighting strategy. The calculation results illustrate that the AMGU model outperformed the descriptor-based models and state-of-the-art graph neural networks (GNN) models on the internal test set. Furthermore, it also exhibited much better performance on two external test sets, suggesting that the AMGU model has enhanced generalizability due to its great transfer learning capacity. Then, a naïve model-agnostic interpretable method for GNN called edges masking was devised to explain the underlying predictive mechanisms, and the consistency of the interpretability results for 5 typical epidermal growth factor receptor (EGFR) inhibitors with their structure‒activity relationships could be observed. Finally, a free online web server called KIP was developed to predict the kinome-wide polypharmacology effects of small molecules (http://cadd.zju.edu.cn/kip).

Acid-base dissociation constant (pK_a) is a key physicochemical parameter in chemical science, especially in organic synthesis and drug discovery. Current methodologies for pK_a prediction still suffer from limited applicability domain and lack of chemical insight. Here we present MF-SuP-pK_a (multi-fidelity modeling with subgraph pooling for pK_a prediction), a novel pK_a prediction model that utilizes subgraph pooling, multi-fidelity learning and data augmentation. In our model, a knowledge-aware subgraph pooling strategy was designed to capture the local and global environments around the ionization sites for micro-pK_a prediction. To overcome the scarcity of accurate pK_a data, low-fidelity data (computational pK_a) was used to fit the high-fidelity data (experimental pK_a) through transfer learning. The final MF-SuP-pK_a model was constructed by pre-training on the augmented ChEMBL data set and fine-tuning on the DataWarrior data set. Extensive evaluation on the DataWarrior data set and three benchmark data sets shows that MF-SuP-pK_a achieves superior performances to the state-of-the-art pK_a prediction models while requires much less high-fidelity training data. Compared with Attentive FP, MF-SuP-pK_a achieves 23.83% and 20.12% improvement in terms of mean absolute error (MAE) on the acidic and basic sets, respectively.

Protein neddylation is catalyzed by a three-enzyme cascade, namely an E1 NEDD8-activating enzyme (NAE), one of two E2 NEDD8 conjugation enzymes and one of several E3 NEDD8 ligases. The physiological substrates of neddylation are the family members of cullin, the scaffold component of cullin RING ligases (CRLs). Currently, a potent E1 inhibitor, MLN4924, also known as pevonedistat, is in several clinical trials for anti-cancer therapy. Here we report the discovery, through virtual screening and structural modifications, of a small molecule compound HA-1141 that directly binds to NAE in both

Chaperone-mediated autophagy (CMA) is a lysosome-dependent selective degradation pathway implicated in the pathogenesis of cancer and neurodegenerative diseases. However, the mechanisms that regulate CMA are not fully understood. Here, using unbiased drug screening approaches, we discover Metformin, a drug that is commonly the first medication prescribed for type 2 diabetes, can induce CMA. We delineate the mechanism of CMA induction by Metformin to be via activation of TAK1-IKKα/β signaling that leads to phosphorylation of Ser85 of the key mediator of CMA, Hsc70, and its activation. Notably, we find that amyloid-beta precursor protein (APP) is a CMA substrate and that it binds to Hsc70 in an IKKα/β-dependent manner. The inhibition of CMA-mediated degradation of APP enhances its cytotoxicity. Importantly, we find that in the APP/PS1 mouse model of Alzheimer's disease (AD), activation of CMA by Hsc70 overexpression or Metformin potently reduces the accumulated brain Aβ plaque levels and reverses the molecular and behavioral AD phenotypes. Our study elucidates a novel mechanism of CMA regulation via Metformin-TAK1-IKKα/β-Hsc70 signaling and suggests Metformin as a new activator of CMA for diseases, such as AD, where such therapeutic intervention could be beneficial.

Androgen receptor (AR) is a ligand-activated transcription factor that plays a pivotal role in the development and progression of many severe diseases such as prostate cancer, muscle atrophy, and osteoporosis. Binding of ligands to AR triggers the conformational changes in AR that may affect the recruitment of coactivators and downstream response of AR signaling pathway. Therefore, AR ligands have great potential to treat these diseases. In this study, we searched for novel AR ligands by performing a docking-based virtual screening (VS) on the basis of the crystal structure of the AR ligand binding domain (LBD) in complex with its agonist. A total of 58 structurally diverse compounds were selected and subjected to LBD affinity assay, with five of them (HBP1-3, HBP1-17, HBP1-38, HBP1-51, and HBP1-58) exhibiting strong binding to AR-LBD. The IC values of HBP1-51 and HBP1-58 are 3.96 µM and 4.92 µM, respectively, which are even lower than that of enzalutamide (Enz, IC = 13.87 µM), a marketed second-generation AR antagonist. Further bioactivity assays suggest that HBP1-51 is an AR agonist, whereas HBP1-58 is an AR antagonist. In addition, molecular dynamics (MD) simulations and principal components analysis (PCA) were carried out to reveal the binding principle of the newly-identified AR ligands toward AR. Our modeling results indicate that the conformational changes of helix 12 induced by the bindings of antagonist and agonist are visibly different. In summary, the current study provides a highly efficient way to discover novel AR ligands, which could serve as the starting point for development of new therapeutics for AR-related diseases.
Androgen Receptor Antagonists ; pharmacology ; Androgens ; metabolism ; pharmacology ; Biological Assay ; Cell Line, Tumor ; Drug Discovery ; methods ; Humans ; Ligands ; Male ; Molecular Docking Simulation ; Molecular Dynamics Simulation ; Phenylthiohydantoin ; analogs & derivatives ; pharmacology ; Principal Component Analysis ; Prostatic Neoplasms ; drug therapy ; Protein Binding ; physiology ; Protein Conformation ; drug effects ; Receptors, Androgen ; metabolism