Explore the vast range of titles available.

Prediction of drug-target interactions (DTI) plays a vital role in drug development in various areas, such as virtual screening, drug repurposing and identification of potential drug side effects. Despite extensive efforts have been invested in perfecting DTI prediction, existing methods still suffer from the high sparsity of DTI datasets and the cold start problem. Here, we develop KGE_NFM, a unified framework for DTI prediction by combining knowledge graph (KG) and recommendation system. This framework firstly learns a low-dimensional representation for various entities in the KG, and then integrates the multimodal information via neural factorization machine (NFM). KGE_NFM is evaluated under three realistic scenarios, and achieves accurate and robust predictions on four benchmark datasets, especially in the scenario of the cold start for proteins. Our results indicate that KGE_NFM provides valuable insight to integrate KG and recommendation system-based techniques into a unified framework for novel DTI discovery. Prediction of drug-target interactions (DTI) plays a vital role in drug development through applications in various areas, such as virtual screening for lead discovery, drug repurposing and identification of potential drug side effects. Here, the authors develop a unified framework for DTI prediction by combining a knowledge graph and a recommendation system.

Graph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various property endpoints, the predictive capacity and computational efficiency of the prediction models developed by eight machine learning (ML) algorithms, including four descriptor-based models (SVM, XGBoost, RF and DNN) and four graph-based models (GCN, GAT, MPNN and Attentive FP), were extensively tested and compared. The results demonstrate that on average the descriptor-based models outperform the graph-based models in terms of prediction accuracy and computational efficiency. SVM generally achieves the best predictions for the regression tasks. Both RF and XGBoost can achieve reliable predictions for the classification tasks, and some of the graph-based models, such as Attentive FP and GCN, can yield outstanding performance for a fraction of larger or multi-task datasets. In terms of computational cost, XGBoost and RF are the two most efficient algorithms and only need a few seconds to train a model even for a large dataset. The model interpretations by the SHAP method can effectively explore the established domain knowledge for the descriptor-based models. Finally, we explored use of these models for virtual screening (VS) towards HIV and demonstrated that different ML algorithms offer diverse VS profiles. All in all, we believe that the off-the-shelf descriptor-based models still can be directly employed to accurately predict various chemical endpoints with excellent computability and interpretability.

Chaperone-mediated autophagy (CMA) is a lysosomedependent 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.

Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to individual nodes, edges or fragments that are not necessarily derived from a chemically meaningful segmentation of molecules. To address this challenge, we propose a method named substructure mask explanation (SME). SME is based on well-established molecular segmentation methods and provides an interpretation that aligns with the understanding of chemists. We apply SME to elucidate how GNNs learn to predict aqueous solubility, genotoxicity, cardiotoxicity and blood–brain barrier permeation for small molecules. SME provides interpretation that is consistent with the understanding of chemists, alerts them to unreliable performance, and guides them in structural optimization for target properties. Hence, we believe that SME empowers chemists to confidently mine structure-activity relationship (SAR) from reliable GNNs through a transparent inspection on how GNNs pick up useful signals when learning from data. Attempts to explain molecular property predictions of neural networks are not always compatible with chemical intuition based on chemical substructures. Here the authors propose the substructure mask explanation method to tackle this challenge.

Cancer expression of PD-L1 suppresses anti-tumor immunity. PD-L1 has emerged as a remarkable therapeutic target. However, the regulation of PD-L1 degradation is not understood. Here, we identify several compounds as inducers of PD-L1 degradation using a high-throughput drug screen. We find EGFR inhibitors promote PD-L1 ubiquitination and proteasomal degradation following GSK3α-mediated phosphorylation of Ser279/Ser283. We identify ARIH1 as the E3 ubiquitin ligase responsible for targeting PD-L1 to degradation. Overexpression of ARIH1 suppresses tumor growth and promotes cytotoxic T cell activation in wild-type, but not in immunocompromised mice, highlighting the role of ARIH1 in anti-tumor immunity. Moreover, combining EGFR inhibitor ES-072 with anti-CTLA4 immunotherapy results in an additive effect on both tumor growth and cytotoxic T cell activation. Our results delineate a mechanism of PD-L1 degradation and cancer escape from immunity via EGFR-GSK3α-ARIH1 signaling and suggest GSK3α and ARIH1 might be potential drug targets to boost anti-tumor immunity and enhance immunotherapies. The regulation of PD-L1 via proteasomal degradation is unclear. Here, the authors show that EGFR inhibition activates GSK3 α to promote PD-L1 phosphorylation, which leads to PD-L1 ubiquitination and proteasome mediated degradation by ARIH1 E3 ligase.

Retrosynthesis is a crucial task in drug discovery and organic synthesis, where artificial intelligence (AI) is increasingly employed to expedite the process. However, existing approaches employ token-by-token decoding methods to translate target molecule strings into corresponding precursors, exhibiting unsatisfactory performance and limited diversity. As chemical reactions typically induce local molecular changes, reactants and products often overlap significantly. Inspired by this fact, we propose reframing single-step retrosynthesis prediction as a molecular string editing task, iteratively refining target molecule strings to generate precursor compounds. Our proposed approach involves a fragment-based generative editing model that uses explicit sequence editing operations. Additionally, we design an inference module with reposition sampling and sequence augmentation to enhance both prediction accuracy and diversity. Extensive experiments demonstrate that our model generates high-quality and diverse results, achieving superior performance with a promising top-1 accuracy of 60.8% on the standard benchmark dataset USPTO-50 K. Retrosynthesis aims to identify synthesis solutions for compounds in drug discovery. Here, the authors frame it as a molecular string editing task and utilize an iterative string editing model to provide high-quality and diverse solutions.

Breast cancer resistance protein (BCRP/ABCG2), an ATP-binding cassette (ABC) efflux transporter, plays a critical role in multi-drug resistance (MDR) to anti-cancer drugs and drug–drug interactions. The prediction of BCRP inhibition can facilitate evaluating potential drug resistance and drug–drug interactions in early stage of drug discovery. Here we reported a structurally diverse dataset consisting of 1098 BCRP inhibitors and 1701 non-inhibitors. Analysis of various physicochemical properties illustrates that BCRP inhibitors are more hydrophobic and aromatic than non-inhibitors. We then developed a series of quantitative structure–activity relationship (QSAR) models to discriminate between BCRP inhibitors and non-inhibitors. The optimal feature subset was determined by a wrapper feature selection method named rfSA (simulated annealing algorithm coupled with random forest), and the classification models were established by using seven machine learning approaches based on the optimal feature subset, including a deep learning method, two ensemble learning methods, and four classical machine learning methods. The statistical results demonstrated that three methods, including support vector machine (SVM), deep neural networks (DNN) and extreme gradient boosting (XGBoost), outperformed the others, and the SVM classifier yielded the best predictions (MCC = 0.812 and AUC = 0.958 for the test set). Then, a perturbation-based model-agnostic method was used to interpret our models and analyze the representative features for different models. The application domain analysis demonstrated the prediction reliability of our models. Moreover, the important structural fragments related to BCRP inhibition were identified by the information gain (IG) method along with the frequency analysis. In conclusion, we believe that the classification models developed in this study can be regarded as simple and accurate tools to distinguish BCRP inhibitors from non-inhibitors in drug design and discovery pipelines.

Machine learning-based generative models can generate novel molecules with desirable physiochemical and pharmacological properties from scratch. Many excellent generative models have been proposed, but multi-objective optimizations in molecular generative tasks are still quite challenging for most existing models. Here we proposed the multi-constraint molecular generation (MCMG) approach that can satisfy multiple constraints by combining conditional transformer and reinforcement learning algorithms through knowledge distillation. A conditional transformer was used to train a molecular generative model by efficiently learning and incorporating the structure–property relations into a biased generative process. A knowledge distillation model was then employed to reduce the model’s complexity so that it can be efficiently fine-tuned by reinforcement learning and enhance the structural diversity of the generated molecules. As demonstrated by a set of comprehensive benchmarks, MCMG is a highly effective approach to traverse large and complex chemical space in search of novel compounds that satisfy multiple property constraints. Combining generative models and reinforcement learning has become a promising direction for computational drug design, but it is challenging to train an efficient model that produces candidate molecules with high diversity. Jike Wang and colleagues present a method, using knowledge distillation, to condense a conditional transformer model to make it usable in reinforcement learning while still generating diverse molecules that optimize multiple molecular properties.

G-protein-coupled receptors (GPCRs) have central roles in intercellular communication 1 , 2 . Structural studies have revealed how GPCRs can activate G proteins. However, whether this mechanism is conserved among all classes of GPCR remains unknown. Here we report the structure of the class-C heterodimeric GABA B receptor, which is activated by the inhibitory transmitter GABA, in its active form complexed with G i1 protein. We found that a single G protein interacts with the GB2 subunit of the GABA B receptor at a site that mainly involves intracellular loop 2 on the side of the transmembrane domain. This is in contrast to the G protein binding in a central cavity, as has been observed with other classes of GPCR. This binding mode results from the active form of the transmembrane domain of this GABA B receptor being different from that of other GPCRs, as it shows no outside movement of transmembrane helix 6. Our work also provides details of the inter- and intra-subunit changes that link agonist binding to G-protein activation in this heterodimeric complex. Cryo-electron microscopy structure of heterodimeric GABA B receptor in complex with G i1 protein reveals that the mode of G-protein binding in this class-C G-protein-coupled receptor differs from that of other classes.