Cytoplasmic DNA sensing by KU complex in aged CD4+ T cell potentiates T cell activation and aging-related autoimmune inflammation.

Aging is associated with DNA accumulation and increased homeostatic proliferation of circulating T cells. Although these attributes are associated with aging-related autoimmunity, their direct contributions remain unclear. Conventionally, KU complex, the regulatory subunit of DNA-dependent protein kinase (DNA-PK), together with the catalytic subunit of DNA-PK (DNA-PKcs), mediates DNA damage repair in the nucleus. Here, we found KU complex abundantly expressed in the cytoplasm, where it recognized accumulated cytoplasmic DNA in aged human and mouse CD4+ T cells. This process enhanced T cell activation and pathology of experimental autoimmune encephalomyelitis (EAE) in aged mice. Mechanistically, KU-mediated DNA sensing facilitated DNA-PKcs recruitment and phosphorylation of the kinase ZAK. This activated AKT and mTOR pathways, promoting CD4+ T cell proliferation and activation. We developed a specific ZAK inhibitor, which dampened EAE pathology in aged mice. Overall, these findings demonstrate a KU-mediated cytoplasmic DNA-sensing pathway in CD4+ T cells that potentiates aging-related autoimmunity.

An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph.

Identifying the potential compound-protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound-protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature. The data and source codes are available at https://github.com/wanxiaozhe/CPI-IGAE.

Multi-instance learning of graph neural networks for aqueous pKa prediction.

MOTIVATION: The acid dissociation constant (pKa) is a critical parameter to reflect the ionization ability of chemical compounds and is widely applied in a variety of industries. However, the experimental determination of pKa is intricate and time-consuming, especially for the exact determination of micro-pKa information at the atomic level. Hence, a fast and accurate prediction of pKa values of chemical compounds is of broad interest. RESULTS: Here, we compiled a large-scale pKa dataset containing 16 595 compounds with 17 489 pKa values. Based on this dataset, a novel pKa prediction model, named Graph-pKa, was established using graph neural networks. Graph-pKa performed well on the prediction of macro-pKa values, with a mean absolute error around 0.55 and a coefficient of determination around 0.92 on the test dataset. Furthermore, combining multi-instance learning, Graph-pKa was also able to automatically deconvolute the predicted macro-pKa into discrete micro-pKa values. AVAILABILITY AND IMPLEMENTATION: The Graph-pKa model is now freely accessible via a web-based interface (https://pka.simm.ac.cn/). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DrugSpaceX: a large screenable and synthetically tractable database extending drug space.

One of the most prominent topics in drug discovery is efficient exploration of the vast drug-like chemical space to find synthesizable and novel chemical structures with desired biological properties. To address this challenge, we created the DrugSpaceX (https://drugspacex.simm.ac.cn/) database based on expert-defined transformations of approved drug molecules. The current version of DrugSpaceX contains >100 million transformed chemical products for virtual screening, with outstanding characteristics in terms of structural novelty, diversity and large three-dimensional chemical space coverage. To illustrate its practical application in drug discovery, we used a case study of discoidin domain receptor 1 (DDR1), a kinase target implicated in fibrosis and other diseases, to show DrugSpaceX performing a quick search of initial hit compounds. Additionally, for ligand identification and optimization purposes, DrugSpaceX also provides several subsets for download, including a 10% diversity subset, an extended drug-like subset, a drug-like subset, a lead-like subset, and a fragment-like subset. In addition to chemical properties and transformation instructions, DrugSpaceX can locate the position of transformation, which will enable medicinal chemists to easily integrate strategy planning and protection design.

Asymmetric C1 Extension of Aldehydes through Biocatalytic Cascades for Stereodivergent Synthesis of Mandelic Acids.

The development of mild, efficient, and enantioselective methods for preparing chiral building blocks from simple, renewable carbon units has been a long-term goal of the sustainable chemical industry. Mandelate derivatives are valuable pharmaceutical intermediates and chiral resolving agents, but their manufacture relies heavily on highly toxic cyanide. Herein, we report (S)-4-hydroxymandelate synthase (HmaS)-centered biocatalytic cascades for the synthesis of mandelates from benzaldehydes and glycine. We show that HmaS can be engineered to perform R-selective hydroxylation by single-point mutation, empowering the stereodivergent synthesis of both (S)- and (R)-mandelate derivatives. These biocatalytic cascades enabled the production of various mandelate derivatives with high atom economy as well as excellent yields (up to 98 %) and ee values (up to >99 %). This methodology offers an effective cyanide-free technology for greener and sustainable production of mandelate derivatives.

Versatile Biocatalytic C(sp3 )-H Oxyfunctionalization for the Site- Selective and Stereodivergent Synthesis of α- and ß-Hydroxy Acids.

C(sp3 )-H oxyfunctionalization, the insertion of an O-atom into C(sp3 )-H bonds, streamlines the synthesis of complex molecules from easily accessible precursors and represents one of the most challenging tasks in organic chemistry with regard to site and stereoselectivity. Biocatalytic C(sp3 )-H oxyfunctionalization has the potential to overcome limitations inherent to small-molecule-mediated approaches by delivering catalyst-controlled selectivity. Through enzyme repurposing and activity profiling of natural variants, we have developed a subfamily of α-ketoglutarate-dependent iron dioxygenases that catalyze the site- and stereodivergent oxyfunctionalization of secondary and tertiary C(sp3 )-H bonds, providing concise synthetic routes towards four types of 92 α- and ß-hydroxy acids with high efficiency and selectivity. This method provides a biocatalytic approach for the production of valuable but synthetically challenging chiral hydroxy acid building blocks.

KinomeX: a web application for predicting kinome-wide polypharmacology effect of small molecules.

MOTIVATION: The large-scale kinome-wide virtual profiling for small molecules is a daunting task by experimental and traditional in silico drug design approaches. Recent advances in deep learning algorithms have brought about new opportunities in promoting this process. RESULTS: KinomeX is an online platform to predict kinome-wide polypharmacology effect of small molecules based solely on their chemical structures. The prediction is made by a multi-task deep neural network model trained with over 140 000 bioactivity data points for 391 kinases. Extensive computational and experimental validations have been performed. Overall, KinomeX enables users to create a comprehensive kinome interaction network for designing novel chemical modulators, and is of practical value on exploring the previously less studied or untargeted kinases. AVAILABILITY AND IMPLEMENTATION: KinomeX is available at: https://kinome.dddc.ac.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Computational chemical biology and drug design: Facilitating protein structure, function, and modulation studies.

Over the past quarter of a century, there has been rapid development in structural biology, which now can provide solid evidence for understanding the functions of proteins. Concurrently, computational approaches with particular relevance to the chemical biology and drug design (CBDD) field have also incrementally and steadily improved. Today, these methods help elucidate detailed working mechanisms and accelerate the discovery of new chemical modulators of proteins. In recent years, integrating computational simulations and predictions with experimental validation has allowed for more effective explorations of the structure, function and modulation of important therapeutic targets. In this review, we summarize the main advancements in computational methodology development, which are then illustrated by several successful applications in CBDD. Finally, we conclude with a discussion of the current major challenges and future directions in the field.

Discovery of a terpene synthase synthesizing a nearly non-flexible eunicellane reveals the basis of flexibility.

Eunicellane diterpenoids, containing a typical 6,10-bicycle, are bioactive compounds widely present in marine corals, but rarely found in bacteria and plants. The intrinsic macrocycle exhibits innate structural flexibility resulting in dynamic conformational changes. However, the mechanisms controlling flexibility remain unknown. The discovery of a terpene synthase, MicA, that is responsible for the biosynthesis of a nearly non-flexible eunicellane skeleton, enable us to propose a feasible theory about the flexibility in eunicellane structures. Parallel studies of all eunicellane synthases in nature discovered to date, including 2Z-geranylgeranyl diphosphate incubations and density functional theory-based Boltzmann population computations, reveale that a trans-fused bicycle with a 2Z-configuration alkene restricts conformational flexibility resulting in a nearly non-flexible eunicellane skeleton. The catalytic route and the enzymatic mechanism of MicA are also elucidated by labeling experiments, density functional theory calculations, structural analysis of the artificial intelligence-based MicA model, and mutational studies.

Transfer learning enhanced graph neural network for aldehyde oxidase metabolism prediction and its experimental application.

Aldehyde oxidase (AOX) is a molybdoenzyme that is primarily expressed in the liver and is involved in the metabolism of drugs and other xenobiotics. AOX-mediated metabolism can result in unexpected outcomes, such as the production of toxic metabolites and high metabolic clearance, which can lead to the clinical failure of novel therapeutic agents. Computational models can assist medicinal chemists in rapidly evaluating the AOX metabolic risk of compounds during the early phases of drug discovery and provide valuable clues for manipulating AOX-mediated metabolism liability. In this study, we developed a novel graph neural network called AOMP for predicting AOX-mediated metabolism. AOMP integrated the tasks of metabolic substrate/non-substrate classification and metabolic site prediction, while utilizing transfer learning from 13C nuclear magnetic resonance data to enhance its performance on both tasks. AOMP significantly outperformed the benchmark methods in both cross-validation and external testing. Using AOMP, we systematically assessed the AOX-mediated metabolism of common fragments in kinase inhibitors and successfully identified four new scaffolds with AOX metabolism liability, which were validated through in vitro experiments. Furthermore, for the convenience of the community, we established the first online service for AOX metabolism prediction based on AOMP, which is freely available at https://aomp.alphama.com.cn.

Fine-tuning large language models for chemical text mining.

Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental and computational chemists. The task is still considered to be extremely challenging due to the complexity of the chemical language and scientific literature. This study explored the power of fine-tuned large language models (LLMs) on five intricate chemical text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data extraction, and the conversion of reaction paragraphs to action sequences. The fine-tuned LLMs demonstrated impressive performance, significantly reducing the need for repetitive and extensive prompt engineering experiments. For comparison, we guided ChatGPT (GPT-3.5-turbo) and GPT-4 with prompt engineering and fine-tuned GPT-3.5-turbo as well as other open-source LLMs such as Mistral, Llama3, Llama2, T5, and BART. The results showed that the fine-tuned ChatGPT models excelled in all tasks. They achieved exact accuracy levels ranging from 69% to 95% on these tasks with minimal annotated data. They even outperformed those task-adaptive pre-training and fine-tuning models that were based on a significantly larger amount of in-domain data. Notably, fine-tuned Mistral and Llama3 show competitive abilities. Given their versatility, robustness, and low-code capability, leveraging fine-tuned LLMs as flexible and effective toolkits for automated data acquisition could revolutionize chemical knowledge extraction.

Identifying compound-protein interactions with knowledge graph embedding of perturbation transcriptomics.

The emergence of perturbation transcriptomics provides a new perspective for drug discovery, but existing analysis methods suffer from inadequate performance and limited applicability. In this work, we present PertKGE, a method designed to deconvolute compound-protein interactions from perturbation transcriptomics with knowledge graph embedding. By considering multi-level regulatory events within biological systems that share the same semantic context, PertKGE significantly improves deconvoluting accuracy in two critical "cold-start" settings: inferring targets for new compounds and conducting virtual screening for new targets. We further demonstrate the pivotal role of incorporating multi-level regulatory events in alleviating representational biases. Notably, it enables the identification of ectonucleotide pyrophosphatase/phosphodiesterase-1 as the target responsible for the unique anti-tumor immunotherapy effect of tankyrase inhibitor K-756 and the discovery of five novel hits targeting the emerging cancer therapeutic target aldehyde dehydrogenase 1B1 with a remarkable hit rate of 10.2%. These findings highlight the potential of PertKGE to accelerate drug discovery.

MolFilterGAN: a progressively augmented generative adversarial network for triaging AI-designed molecules.

Artificial intelligence (AI)-based molecular design methods, especially deep generative models for generating novel molecule structures, have gratified our imagination to explore unknown chemical space without relying on brute-force exploration. However, whether designed by AI or human experts, the molecules need to be accessibly synthesized and biologically evaluated, and the trial-and-error process remains a resources-intensive endeavor. Therefore, AI-based drug design methods face a major challenge of how to prioritize the molecular structures with potential for subsequent drug development. This study indicates that common filtering approaches based on traditional screening metrics fail to differentiate AI-designed molecules. To address this issue, we propose a novel molecular filtering method, MolFilterGAN, based on a progressively augmented generative adversarial network. Comparative analysis shows that MolFilterGAN outperforms conventional screening approaches based on drug-likeness or synthetic ability metrics. Retrospective analysis of AI-designed discoidin domain receptor 1 (DDR1) inhibitors shows that MolFilterGAN significantly increases the efficiency of molecular triaging. Further evaluation of MolFilterGAN on eight external ligand sets suggests that MolFilterGAN is useful in triaging or enriching bioactive compounds across a wide range of target types. These results highlighted the importance of MolFilterGAN in evaluating molecules integrally and further accelerating molecular discovery especially combined with advanced AI generative models.

Drug target inference by mining transcriptional data using a novel graph convolutional network framework.

A fundamental challenge that arises in biomedicine is the need to characterize compounds in a relevant cellular context in order to reveal potential on-target or off-target effects. Recently, the fast accumulation of gene transcriptional profiling data provides us an unprecedented opportunity to explore the protein targets of chemical compounds from the perspective of cell transcriptomics and RNA biology. Here, we propose a novel Siamese spectral-based graph convolutional network (SSGCN) model for inferring the protein targets of chemical compounds from gene transcriptional profiles. Although the gene signature of a compound perturbation only provides indirect clues of the interacting targets, and the biological networks under different experiment conditions further complicate the situation, the SSGCN model was successfully trained to learn from known compound-target pairs by uncovering the hidden correlations between compound perturbation profiles and gene knockdown profiles. On a benchmark set and a large time-split validation dataset, the model achieved higher target inference accuracy as compared to previous methods such as Connectivity Map. Further experimental validations of prediction results highlight the practical usefulness of SSGCN in either inferring the interacting targets of compound, or reversely, in finding novel inhibitors of a given target of interest.

Revisiting Aldehyde Oxidase Mediated Metabolism in Drug-like Molecules: An Improved Computational Model.

Aldehyde oxidase (AOX) is a drug metabolizing molybdo-flavoenzyme that has gained increasing attention because of contribution to the biotransformation in phase I metabolism of xenobiotics. Unfortunately, the intra- and interspecies variations in AOX activity and lack of reliable and predictive animal models make evaluation of AOX-catalyzed metabolism prone to be misleading. In this study, we developed an improved computational model integrating both atom-level and molecule-level features to predict whether a drug-like molecule is a potential human AOX (hAOX) substrate and to identify the corresponding sites of metabolism. Additionally, we combined the proposed computational strategy and in vitro experiments for evaluating the metabolic property of a series of epigenetic-related drug candidates still in the early stage of development. In summary, this study provides an improved strategy to evaluate the liability of molecules toward hAOX and offers useful information for accelerating the drug design and optimization stage.

Deep Learning Enhancing Kinome-Wide Polypharmacology Profiling: Model Construction and Experiment Validation.

The kinome-wide virtual profiling of small molecules with high-dimensional structure-activity data is a challenging task in drug discovery. Here, we present a virtual profiling model against a panel of 391 kinases based on large-scale bioactivity data and the multitask deep neural network algorithm. The obtained model yields excellent internal prediction capability with an auROC of 0.90 and consistently outperforms conventional single-task models on external tests, especially for kinases with insufficient activity data. Moreover, more rigorous experimental validations including 1410 kinase-compound pairs showed a high-quality average auROC of 0.75 and confirmed many novel predicted "off-target" activities. Given the verified generalizability, the model was further applied to various scenarios for depicting the kinome-wide selectivity and the association with certain diseases. Overall, the computational model enables us to create a comprehensive kinome interaction network for designing novel chemical modulators or drug repositioning and is of practical value for exploring previously less studied kinases.

Machine Learning-Based Modeling of Drug Toxicity.

Toxicity is an important reason for the failure of drug research and development (R&D). The traditional experimental testings for chemical toxicity profile are costly and time-consuming. Therefore, it is attractive to develop the effective and accurate alternatives, such as in silico prediction models. In this review, we discuss the practical use of some prediction models on three toxicity end points, including acute toxicity, carcinogenicity, and inhibition of the human ether-a-go-go-related gene ion channel (hERG). Special emphasis is put on the machine learning methods for developing in silico models, and their advantages and weaknesses are discussed. We conclude that machine learning methods are valuable for helping the process of designing new candidates with low toxicity in drug R&D studies. In the future, much still needs to be done to understand more completely the biological mechanisms for toxicity and to develop more accurate prediction models to screen compounds.

Artificial intelligence in drug design.

Thanks to the fast improvement of the computing power and the rapid development of the computational chemistry and biology, the computer-aided drug design techniques have been successfully applied in almost every stage of the drug discovery and development pipeline to speed up the process of research and reduce the cost and risk related to preclinical and clinical trials. Owing to the development of machine learning theory and the accumulation of pharmacological data, the artificial intelligence (AI) technology, as a powerful data mining tool, has cut a figure in various fields of the drug design, such as virtual screening, activity scoring, quantitative structure-activity relationship (QSAR) analysis, de novo drug design, and in silico evaluation of absorption, distribution, metabolism, excretion and toxicity (ADME/T) properties. Although it is still challenging to provide a physical explanation of the AI-based models, it indeed has been acting as a great power to help manipulating the drug discovery through the versatile frameworks. Recently, due to the strong generalization ability and powerful feature extraction capability, deep learning methods have been employed in predicting the molecular properties as well as generating the desired molecules, which will further promote the application of AI technologies in the field of drug design.