ChemMORT: an automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization.

Drug discovery and development constitute a laborious and costly undertaking. The success of a drug hinges not only good efficacy but also acceptable absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties. Overall, up to 50% of drug development failures have been contributed from undesirable ADMET profiles. As a multiple parameter objective, the optimization of the ADMET properties is extremely challenging owing to the vast chemical space and limited human expert knowledge. In this study, a freely available platform called Chemical Molecular Optimization, Representation and Translation (ChemMORT) is developed for the optimization of multiple ADMET endpoints without the loss of potency (https://cadd.nscc-tj.cn/deploy/chemmort/). ChemMORT contains three modules: Simplified Molecular Input Line Entry System (SMILES) Encoder, Descriptor Decoder and Molecular Optimizer. The SMILES Encoder can generate the molecular representation with a 512-dimensional vector, and the Descriptor Decoder is able to translate the above representation to the corresponding molecular structure with high accuracy. Based on reversible molecular representation and particle swarm optimization strategy, the Molecular Optimizer can be used to effectively optimize undesirable ADMET properties without the loss of bioactivity, which essentially accomplishes the design of inverse QSAR. The constrained multi-objective optimization of the poly (ADP-ribose) polymerase-1 inhibitor is provided as the case to explore the utility of ChemMORT.

Comprehensive assessment of nine target prediction web services: which should we choose for target fishing?

Identification of potential targets for known bioactive compounds and novel synthetic analogs is of considerable significance. In silico target fishing (TF) has become an alternative strategy because of the expensive and laborious wet-lab experiments, explosive growth of bioactivity data and rapid development of high-throughput technologies. However, these TF methods are based on different algorithms, molecular representations and training datasets, which may lead to different results when predicting the same query molecules. This can be confusing for practitioners in practical applications. Therefore, this study systematically evaluated nine popular ligand-based TF methods based on target and ligand-target pair statistical strategies, which will help practitioners make choices among multiple TF methods. The evaluation results showed that SwissTargetPrediction was the best method to produce the most reliable predictions while enriching more targets. High-recall similarity ensemble approach (SEA) was able to find real targets for more compounds compared with other TF methods. Therefore, SwissTargetPrediction and SEA can be considered as primary selection methods in future studies. In addition, the results showed that k = 5 was the optimal number of experimental candidate targets. Finally, a novel ensemble TF method based on consensus voting is proposed to improve the prediction performance. The precision of the ensemble TF method outperforms the individual TF method, indicating that the ensemble TF method can more effectively identify real targets within a given top-k threshold. The results of this study can be used as a reference to guide practitioners in selecting the most effective methods in computational drug discovery.

Graph deep learning enabled spatial domains identification for spatial transcriptomics.

Advancing spatially resolved transcriptomics (ST) technologies help biologists comprehensively understand organ function and tissue microenvironment. Accurate spatial domain identification is the foundation for delineating genome heterogeneity and cellular interaction. Motivated by this perspective, a graph deep learning (GDL) based spatial clustering approach is constructed in this paper. First, the deep graph infomax module embedded with residual gated graph convolutional neural network is leveraged to address the gene expression profiles and spatial positions in ST. Then, the Bayesian Gaussian mixture model is applied to handle the latent embeddings to generate spatial domains. Designed experiments certify that the presented method is superior to other state-of-the-art GDL-enabled techniques on multiple ST datasets. The codes and dataset used in this manuscript are summarized at https://github.com/narutoten520/SCGDL.

DKADE: a novel framework based on deep learning and knowledge graph for identifying adverse drug events and related medications.

Adverse drug events (ADEs) are common in clinical practice and can cause significant harm to patients and increase resource use. Natural language processing (NLP) has been applied to automate ADE detection, but NLP systems become less adaptable when drug entities are missing or multiple medications are specified in clinical narratives. Additionally, no Chinese-language NLP system has been developed for ADE detection due to the complexity of Chinese semantics, despite ˃10 million cases of drug-related adverse events occurring annually in China. To address these challenges, we propose DKADE, a deep learning and knowledge graph-based framework for identifying ADEs. DKADE infers missing drug entities and evaluates their correlations with ADEs by combining medication orders and existing drug knowledge. Moreover, DKADE can automatically screen for new adverse drug reactions. Experimental results show that DKADE achieves an overall F1-score value of 91.13%. Furthermore, the adaptability of DKADE is validated using real-world external clinical data. In summary, DKADE is a powerful tool for studying drug safety and automating adverse event monitoring.

Reducing false positive rate of docking-based virtual screening by active learning.

Machine learning-based scoring functions (MLSFs) have become a very favorable alternative to classical scoring functions because of their potential superior screening performance. However, the information of negative data used to construct MLSFs was rarely reported in the literature, and meanwhile the putative inactive molecules recorded in existing databases usually have obvious bias from active molecules. Here we proposed an easy-to-use method named AMLSF that combines active learning using negative molecular selection strategies with MLSF, which can iteratively improve the quality of inactive sets and thus reduce the false positive rate of virtual screening. We chose energy auxiliary terms learning as the MLSF and validated our method on eight targets in the diverse subset of DUD-E. For each target, we screened the IterBioScreen database by AMLSF and compared the screening results with those of the four control models. The results illustrate that the number of active molecules in the top 1000 molecules identified by AMLSF was significantly higher than those identified by the control models. In addition, the free energy calculation results for the top 10 molecules screened out by the AMLSF, null model and control models based on DUD-E also proved that more active molecules can be identified, and the false positive rate can be reduced by AMLSF.

Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction.

Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug-drug interactions (DDIs). DDIs refer to a change in the effect of one drug to the presence of another drug in the human body, which plays an essential role in drug discovery and clinical research. DDIs prediction through traditional clinical trials and experiments is an expensive and time-consuming process. To correctly apply the advanced AI and deep learning, the developer and user meet various challenges such as the availability and encoding of data resources, and the design of computational methods. This review summarizes chemical structure based, network based, natural language processing based and hybrid methods, providing an updated and accessible guide to the broad researchers and development community with different domain knowledge. We introduce widely used molecular representation and describe the theoretical frameworks of graph neural network models for representing molecular structures. We present the advantages and disadvantages of deep and graph learning methods by performing comparative experiments. We discuss the potential technical challenges and highlight future directions of deep and graph learning models for accelerating DDIs prediction.

Assembling spatial clustering framework for heterogeneous spatial transcriptomics data with GRAPHDeep.

MOTIVATION: Spatial clustering is essential and challenging for spatial transcriptomics' data analysis to unravel tissue microenvironment and biological function. Graph neural networks are promising to address gene expression profiles and spatial location information in spatial transcriptomics to generate latent representations. However, choosing an appropriate graph deep learning module and graph neural network necessitates further exploration and investigation. RESULTS: In this article, we present GRAPHDeep to assemble a spatial clustering framework for heterogeneous spatial transcriptomics data. Through integrating 2 graph deep learning modules and 20 graph neural networks, the most appropriate combination is decided for each dataset. The constructed spatial clustering method is compared with state-of-the-art algorithms to demonstrate its effectiveness and superiority. The significant new findings include: (i) the number of genes or proteins of spatial omics data is quite crucial in spatial clustering algorithms; (ii) the variational graph autoencoder is more suitable for spatial clustering tasks than deep graph infomax module; (iii) UniMP, SAGE, SuperGAT, GATv2, GCN, and TAG are the recommended graph neural networks for spatial clustering tasks; and (iv) the used graph neural network in the existent spatial clustering frameworks is not the best candidate. This study could be regarded as desirable guidance for choosing an appropriate graph neural network for spatial clustering. AVAILABILITY AND IMPLEMENTATION: The source code of GRAPHDeep is available at https://github.com/narutoten520/GRAPHDeep. The studied spatial omics data are available at https://zenodo.org/record/8141084.

The F-box Protein KIB1 Mediates Brassinosteroid-Induced Inactivation and Degradation of GSK3-like Kinases in Arabidopsis.

The glycogen synthase kinase-3 (GSK3) family kinases are central cellular regulators highly conserved in all eukaryotes. In Arabidopsis, the GSK3-like kinase BIN2 phosphorylates a range of proteins to control broad developmental processes, and BIN2 is degraded through unknown mechanism upon receptor kinase-mediated brassinosteroid (BR) signaling. Here we identify KIB1 as an F-box E3 ubiquitin ligase that promotes the degradation of BIN2 while blocking its substrate access. Loss-of-function mutations of KIB1 and its homologs abolished BR-induced BIN2 degradation and caused severe BR-insensitive phenotypes. KIB1 directly interacted with BIN2 in a BR-dependent manner and promoted BIN2 ubiquitination in vitro. Expression of an F-box-truncated KIB1 caused BIN2 accumulation but dephosphorylation of its substrate BZR1 and activation of BR responses because KIB1 blocked BIN2 binding to BZR1. Our study demonstrates that KIB1 plays an essential role in BR signaling by inhibiting BIN2 through dual mechanisms of blocking substrate access and promoting degradation.

Creating a zero amylose barley with high soluble sugar content by genome editing.

Amylose biosynthesis is strictly associated with granule-bound starch synthase I (GBSSI) encoded by the Waxy gene. Mutagenesis of single bases in the Waxy gene, which induced by CRISPR/Cas9 genome editing, caused absence of intact GBSSI protein in grain of the edited line. The amylose and amylopectin contents of waxy mutants were zero and 31.73%, while those in the wild type were 33.50% and 39.00%, respectively. The absence of GBSSI protein led to increase in soluble sugar content to 37.30% compared with only 10.0% in the wild type. Sucrose and ß-glucan, were 39.16% and 35.40% higher in waxy mutants than in the wild type, respectively. Transcriptome analysis identified differences between the wild type and waxy mutants that could partly explain the reduction in amylose and amylopectin contents and the increase in soluble sugar, sucrose and ß-glucan contents. This waxy flour, which showed lower final viscosity and setback, and higher breakdown, could provide more option for food processing.

Rational Regulation of the Defect Density in Platinum Nanocrystals for Highly Efficient Hydrogen Evolution Reaction.

Constructing structural defects is a promising way to enhance the catalytic activity toward the hydrogen evolution reaction (HER). However, the relationship between defect density and HER activity has rarely been discussed. In this study, a series of Pt/WOx nanocrystals are fabricated with controlled morphologies and structural defect densities using a facile one-step wet chemical method. Remarkably, compared with polygonal and star structures, the dendritic Pt/WOx (d-Pt/WOx) exhibited a richer structural defect density, including stepped surfaces and atomic defects. Notably, the d-Pt/WOx catalyst required 4 and 16 mV to reach 10 mA cm-2, and its turnover frequency (TOF) values are 11.6 and 22.8 times higher than that of Pt/C under acidic and alkaline conditions, respectively. In addition, d-Pt/WOx//IrO2 displayed a mass activity of 5158 mA mgPt -1 at 2.0 V in proton exchange membrane water electrolyzers (PEMWEs), which is significantly higher than that of the commercial Pt/C//IrO2 system. Further mechanistic studies suggested that the d-Pt/WOx exhibited reduced number of antibonding bands and the lowest dz2-band center, contributing to hydrogen adsorption and release in acidic solution. The highest dz2-band center of d-Pt/WOx facilitated the adsorption of hydrogen from water molecules and water dissociation in alkaline medium. This work emphasizes the key role of the defect density in improving the HER activity of electrocatalysts.

ABC-Net: a divide-and-conquer based deep learning architecture for SMILES recognition from molecular images.

Structural information for chemical compounds is often described by pictorial images in most scientific documents, which cannot be easily understood and manipulated by computers. This dilemma makes optical chemical structure recognition (OCSR) an essential tool for automatically mining knowledge from an enormous amount of literature. However, existing OCSR methods fall far short of our expectations for realistic requirements due to their poor recovery accuracy. In this paper, we developed a deep neural network model named ABC-Net (Atom and Bond Center Network) to predict graph structures directly. Based on the divide-and-conquer principle, we propose to model an atom or a bond as a single point in the center. In this way, we can leverage a fully convolutional neural network (CNN) to generate a series of heat-maps to identify these points and predict relevant properties, such as atom types, atom charges, bond types and other properties. Thus, the molecular structure can be recovered by assembling the detected atoms and bonds. Our approach integrates all the detection and property prediction tasks into a single fully CNN, which is scalable and capable of processing molecular images quite efficiently. Experimental results demonstrate that our method could achieve a significant improvement in recognition performance compared with publicly available tools. The proposed method could be considered as a promising solution to OCSR problems and a starting point for the acquisition of molecular information in the literature.

BioNet: a large-scale and heterogeneous biological network model for interaction prediction with graph convolution.

MOTIVATION: Understanding chemical-gene interactions (CGIs) is crucial for screening drugs. Wet experiments are usually costly and laborious, which limits relevant studies to a small scale. On the contrary, computational studies enable efficient in-silico exploration. For the CGI prediction problem, a common method is to perform systematic analyses on a heterogeneous network involving various biomedical entities. Recently, graph neural networks become popular in the field of relation prediction. However, the inherent heterogeneous complexity of biological interaction networks and the massive amount of data pose enormous challenges. This paper aims to develop a data-driven model that is capable of learning latent information from the interaction network and making correct predictions. RESULTS: We developed BioNet, a deep biological networkmodel with a graph encoder-decoder architecture. The graph encoder utilizes graph convolution to learn latent information embedded in complex interactions among chemicals, genes, diseases and biological pathways. The learning process is featured by two consecutive steps. Then, embedded information learnt by the encoder is then employed to make multi-type interaction predictions between chemicals and genes with a tensor decomposition decoder based on the RESCAL algorithm. BioNet includes 79 325 entities as nodes, and 34 005 501 relations as edges. To train such a massive deep graph model, BioNet introduces a parallel training algorithm utilizing multiple Graphics Processing Unit (GPUs). The evaluation experiments indicated that BioNet exhibits outstanding prediction performance with a best area under Receiver Operating Characteristic (ROC) curve of 0.952, which significantly surpasses state-of-theart methods. For further validation, top predicted CGIs of cancer and COVID-19 by BioNet were verified by external curated data and published literature.

Comprehensive Review of Drug-Drug Interaction Prediction Based on Machine Learning: Current Status, Challenges, and Opportunities.

Detecting drug-drug interactions (DDIs) is an essential step in drug development and drug administration. Given the shortcomings of current experimental methods, the machine learning (ML) approach has become a reliable alternative, attracting extensive attention from the academic and industrial fields. With the rapid development of computational science and the growing popularity of cross-disciplinary research, a large number of DDI prediction studies based on ML methods have been published in recent years. To give an insight into the current situation and future direction of DDI prediction research, we systemically review these studies from three aspects: (1) the classic DDI databases, mainly including databases of drugs, side effects, and DDI information; (2) commonly used drug attributes, which focus on chemical, biological, and phenotypic attributes for representing drugs; (3) popular ML approaches, such as shallow learning-based, deep learning-based, recommender system-based, and knowledge graph-based methods for DDI detection. For each section, related studies are described, summarized, and compared, respectively. In the end, we conclude the research status of DDI prediction based on ML methods and point out the existing issues, future challenges, potential opportunities, and subsequent research direction.

Enhancing Multi-species Liver Microsomal Stability Prediction through Artificial Intelligence.

Liver microsomal stability, a crucial aspect of metabolic stability, significantly impacts practical drug discovery. However, current models for predicting liver microsomal stability are based on limited molecular information from a single species. To address this limitation, we constructed the largest public database of compounds from three common species: human, rat, and mouse. Subsequently, we developed a series of classification models using both traditional descriptor-based and classic graph-based machine learning (ML) algorithms. Remarkably, the best-performing models for the three species achieved Matthews correlation coefficients (MCCs) of 0.616, 0.603, and 0.574, respectively, on the test set. Furthermore, through the construction of consensus models based on these individual models, we have demonstrated their superior predictive performance in comparison with the existing models of the same type. To explore the similarities and differences in the properties of liver microsomal stability among multispecies molecules, we conducted preliminary interpretative explorations using the Shapley additive explanations (SHAP) and atom heatmap approaches for the models and misclassified molecules. Additionally, we further investigated representative structural modifications and substructures that decrease the liver microsomal stability in different species using the matched molecule pair analysis (MMPA) method and substructure extraction techniques. The established prediction models, along with insightful interpretation information regarding liver microsomal stability, will significantly contribute to enhancing the efficiency of exploring practical drugs for development.

CRISPR/Cas9-mediated editing of GmDWF1 brassinosteroid biosynthetic gene induces dwarfism in soybean.

KEY MESSAGE: The study on the GmDWF1-deficient mutant dwf1 showed that GmDWF1 plays a crucial role in determining soybean plant height and yield by influencing the biosynthesis of brassinosteroids. Soybean has not adopted the Green Revolution, such as reduced height for increased planting density, which have proven beneficial for cereal crops. Our research identified the soybean genes GmDWF1a and GmDWF1b, homologous to Arabidopsis AtDWF1, and found that they are widely expressed, especially in leaves, and linked to the cellular transport system, predominantly within the endoplasmic reticulum and intracellular vesicles. These genes are essential for the synthesis of brassinosteroids (BR). Single mutants of GmDWF1a and GmDWF1b, as well as double mutants of both genes generated through CRISPR/Cas9 genome editing, exhibit a dwarf phenotype. The single-gene mutant exhibits moderate dwarfism, while the double mutant shows more pronounced dwarfism. Despite the reduced stature, all types of mutants preserve their node count. Notably, field tests have shown that the single GmDWF1a mutant produced significantly more pods than wild-type plants. Spraying exogenous brassinolide (BL) can compensate for the loss in plant height induced by the decrease in endogenous BRs. Comparing transcriptome analyses of the GmDWF1a mutant and wild-type plants revealed a significant impact on the expression of many genes that influence soybean growth. Identifying the GmDWF1a and GmDWF1b genes could aid in the development of compact, densely planted soybean varieties, potentially boosting productivity.

Characteristics of dissolved organic matter (DOM) in Chinese farmland soils under different climate zone types: A molecular perspective.

Interactions between dissolved organic matter (DOM) and surrounding environments are highly complex. Understanding DOM at the molecular level can contribute to the management of soil pollution and safeguarding agricultural fields. Fourier transform ion cyclotron resonance mass spectrometry (FTICR-MS) has enabled a molecular-level understanding of DOM. Accordingly, in this study, we investigated soil samples from 27 different regions of mainland China with various soil types and climatic characteristics. Based on the geographical features of the four typical climatic zones in mainland China (temperate monsoon, temperate continental, subtropical monsoon, and Qinghai-Tibet Plateau climates), we employed high-resolution mass spectrometry to determine the molecular diversity of DOM under different climatic conditions. The results indicated that lignin and tannin-like substances were the most active categories of DOM in the soils. Collectively, the composition and unsaturation of DOM molecules are influenced by sunlight, precipitation, temperature, and human activity. All climatic regions contained a substantial number of characteristic molecules, with CHO and CHON constituting over 80%, and DOM containing nitrogen and sulfur was relatively more abundant in the monsoon regions. The complex composition of DOM incorporates various active functional groups, such as -NO2 and -ONO2. Furthermore, soil DOM in the monsoon regions showed higher unsaturation and facilitated various (bio) biochemical reactions in the soil.

Induce male sterility by CRISPR/Cas9-mediated mitochondrial genome editing in tobacco.

Genome editing has become more and more popular in animal and plant systems following the emergence of CRISPR/Cas9 technology. However, target sequence modification by CRISPR/Cas9 has not been reported in the plant mitochondrial genome, mtDNA. In plants, a type of male sterility known as cytoplasmic male sterility (CMS) has been associated with certain mitochondrial genes, but few genes have been confirmed by direct mitochondrial gene-targeted modifications. Here, the CMS-associated gene (mtatp9) in tobacco was cleaved using mitoCRISPR/Cas9 with a mitochondrial localization signal. The male-sterile mutant, with aborted stamens, exhibited only 70% of the mtDNA copy number of the wild type and exhibited an altered percentage of heteroplasmic mtatp9 alleles; otherwise, the seed setting rate of the mutant flowers was zero. Transcriptomic analyses showed that glycolysis, tricarboxylic acid cycle metabolism and the oxidative phosphorylation pathway, which are all related to aerobic respiration, were inhibited in stamens of the male-sterile gene-edited mutant. In addition, overexpression of the synonymous mutations dsmtatp9 could restore fertility to the male-sterile mutant. Our results strongly suggest that mutation of mtatp9 causes CMS and that mitoCRISPR/Cas9 can be used to modify the mitochondrial genome of plants.

Interfacial Engineering of Copper-Nickel Selenide Nanodendrites for Enhanced Overall Water Splitting in Alkali Condition.

Fabricating heterogeneous interfaces is an effective approach to improve the intrinsic activity of noble-metal-free catalysts for water splitting. Herein, 3D copper-nickel selenide (CuNi@NiSe) nanodendrites with abundant heterointerfaces are constructed by a precise multi-step wet chemistry method. Notably, CuNi@NiSe only needs 293 and 41 mV at 10 mA cm-2 for oxygen evolution reaction (OER) and hydrogen evolution reaction (HER), respectively. Moreover, the assembled CuNi@NiSe system just requires 2.2 V at 1000 mA cm-2 in anion exchange membrane (AEM) electrolyzer, which is 2.0 times better than Pt/C//IrO2 . Mechanism studies reveal Cu defects on the Cu2-x Se surface boost the electron transfer between Cu atoms and Se atoms of Ni3 Se4 via Cu2-x Se/Ni3 Se4 interface, largely lowering the reaction barrier of rate-determining step for HER. Besides, the intrinsic activity of Ni atoms for in situ generated NiOOH is largely enhanced during OER because of the electron-modulating effect of Se atoms at Ni3 Se4 /NiOOH interface. The unique 3D structure also promotes the mass transfer during catalysis process. This work emphasizes the essential role of interfacial engineering for practical water splitting.

Improving structure-based virtual screening performance via learning from scoring function components.

Scoring functions (SFs) based on complex machine learning (ML) algorithms have gradually emerged as a promising alternative to overcome the weaknesses of classical SFs. However, extensive efforts have been devoted to the development of SFs based on new protein-ligand interaction representations and advanced alternative ML algorithms instead of the energy components obtained by the decomposition of existing SFs. Here, we propose a new method named energy auxiliary terms learning (EATL), in which the scoring components are extracted and used as the input for the development of three levels of ML SFs including EATL SFs, docking-EATL SFs and comprehensive SFs with ascending VS performance. The EATL approach not only outperforms classical SFs for the absolute performance (ROC) and initial enrichment (BEDROC) but also yields comparable performance compared with other advanced ML-based methods on the diverse subset of Directory of Useful Decoys: Enhanced (DUD-E). The test on the relatively unbiased actives as decoys (AD) dataset also proved the effectiveness of EATL. Furthermore, the idea of learning from SF components to yield improved screening power can also be extended to other docking programs and SFs available.

BioMedR: an R/CRAN package for integrated data analysis pipeline in biomedical study.

BACKGROUND: With the increasing development of biotechnology and information technology, publicly available data in chemistry and biology are undergoing explosive growth. Such wealthy information in these resources needs to be extracted and then transformed to useful knowledge by various data mining methods. However, a main computational challenge is how to effectively represent or encode molecular objects under investigation such as chemicals, proteins, DNAs and even complicated interactions when data mining methods are employed. To further explore these complicated data, an integrated toolkit to represent different types of molecular objects and support various data mining algorithms is urgently needed. RESULTS: We developed a freely available R/CRAN package, called BioMedR, for molecular representations of chemicals, proteins, DNAs and pairwise samples of their interactions. The current version of BioMedR could calculate 293 molecular descriptors and 13 kinds of molecular fingerprints for small molecules, 9920 protein descriptors based on protein sequences and six types of generalized scale-based descriptors for proteochemometric modeling, more than 6000 DNA descriptors from nucleotide sequences and six types of interaction descriptors using three different combining strategies. Moreover, this package realized five similarity calculation methods and four powerful clustering algorithms as well as several useful auxiliary tools, which aims at building an integrated analysis pipeline for data acquisition, data checking, descriptor calculation and data modeling. CONCLUSION: BioMedR provides a comprehensive and uniform R package to link up different representations of molecular objects with each other and will benefit cheminformatics/bioinformatics and other biomedical users. It is available at: https://CRAN.R-project.org/package=BioMedR and https://github.com/wind22zhu/BioMedR/.