Search

Artificial intelligence (AI)-aided drug design has demonstrated unprecedented effects on modern drug discovery, but there is still an urgent need for user-friendly interfaces that bridge the gap between these sophisticated tools and scientists, particularly those who are less computer savvy. Herein, we present DrugFlow, an AI-driven one-stop platform that offers a clean, convenient, and cloud-based interface to streamline early drug discovery workflows. By seamlessly integrating a range of innovative AI algorithms, covering molecular docking, quantitative structure–activity relationship modeling, molecular generation, ADMET (absorption, distribution, metabolism, excretion and toxicity) prediction, and virtual screening, DrugFlow can offer effective AI solutions for almost all crucial stages in early drug discovery, including hit identification and hit/lead optimization. We hope that the platform can provide sufficiently valuable guidance to aid real-word drug design and discovery. The platform is available at https://drugflow.com.

The application of Explainable Artificial Intelligence (XAI) in the field of chemistry has garnered growing interest for its potential to justify the prediction of black-box machine learning models and provide actionable insights. We first survey a range of XAI techniques adapted for chemical applications and categorize them based on the technical details of each methodology. We then present a few case studies to illustrate the practical utility of XAI, such as identifying carcinogenic molecules and guiding molecular optimizations, in order to provide chemists with concrete examples of ways to take full advantage of XAI-augmented machine learning for chemistry. Despite the initial success of XAI in chemistry, we still face the challenges of developing more reliable explanations, assuring robustness against adversarial actions, and customizing the explanation for different applications and needs of the diverse scientific community. Finally, we discuss the emerging role of large language models like GPT in generating natural language explanations and discusses the specific challenges associated with them. We advocate that addressing the aforementioned challenges and actively embracing new techniques may contribute to establishing machine learning as an indispensable technique for chemistry in this digital era.

Nucleic acid (NA)–ligand interactions are of paramount importance in a variety of biological processes, including cellular reproduction and protein biosynthesis, and therefore, NAs have been broadly recognized as potential drug targets. Understanding NA–ligand interactions at the atomic scale is essential for investigating the molecular mechanism and further assisting in NA-targeted drug discovery. Molecular docking is one of the predominant computational approaches for predicting the interactions between NAs and small molecules. Despite the availability of versatile docking programs, their performance profiles for NA–ligand complexes have not been thoroughly characterized. In this study, we first compiled the largest structure-based NA–ligand binding data set to date, containing 800 noncovalent NA–ligand complexes with clearly identified ligands. Based on this extensive data set, eight frequently used docking programs, including six protein–ligand docking programs (LeDock, Surflex-Dock, UCSF Dock6, AutoDock, AutoDock Vina, and PLANTS) and two specific NA–ligand docking programs (rDock and RLDOCK), were systematically evaluated in terms of binding pose and binding affinity predictions. The results demonstrated that some protein–ligand docking programs, specifically PLANTS and LeDock, produced more promising or comparable results compared with the specialized NA–ligand docking programs. Among the programs evaluated, PLANTS, rDock, and LeDock showed the highest performance in binding pose prediction, and their top-1 and best root-mean-square deviation (rmsd) success rates were as follows: PLANTS (35.93 and 76.05%), rDock (27.25 and 72.16%), and LeDock (27.40 and 64.37%). Compared with the moderate level of binding pose prediction, few programs were successful in binding affinity prediction, and the best correlation (Rp= −0.461) was observed with PLANTS. Finally, further comparison with the latest NA–ligand docking program (NLDock) on four well-established data sets revealed that PLANTS and LeDock outperformed NLDock in terms of binding pose prediction on all data sets, demonstrating their significant potential for NA–ligand docking. To the best of our knowledge, this study is the most comprehensive evaluation of popular molecular docking programs for NA–ligand systems.

Hydrogel is an ideal material for flexible electrochemical energy storage components due to its good conductivity and softer texture, which is expected to promote electrochemical energy storage technology toward high efficiency, durability, environmental protection, etc., and expand the application range. Currently, hydrogels are used as electrolytes, electrodes or films in various supercapacitors and secondary batteries, and their energy storage feasibility has been demonstrated in the invention and even application of some energy storage components. However, they have low electrical conductivity, mechanical fragility, poor self-healing capacity, low energy density, and are not suitable for long-term, high-power use. Therefore, how to improve the conductivity and mechanical properties of hydrogels and extend the service life of energy storage components has become a research hotspot. This review is devoted to analyzing the internal structure and fundamental properties of hydrogels, and elaborating their electrochemical energy storage mechanism and advantages. From the perspective of structural and material innovation, the key technologies of hydrogels as electrolyte and electrode materials in recent years are summarized. Meanwhile, the development focus of hydrogel electrochemical energy storage technology is summarized and the future development prospects are reviewed. For the application of electrochemical energy storage technology in the field of flexible electronics, this review will provide new ideas and insights.

Lipophilicity (logD) and aqueous solubility (logSw) play a central role in drug development. The accurate prediction of these properties remains to be solved due to data scarcity. Current methodologies neglect the intrinsic relationships between physicochemical properties and usually ignore the ionization effects. Here, we propose an attention-driven mixture-of-experts (MoE) model named ALipSol, which explicitly reproduces the hierarchy of task relationships. We adopt the principle of divide-and-conquer by breaking down the complex end point (logDor logSw) into simpler ones (acidic pKa, basic pKa, and logP) and allocating a specific expert network for each subproblem. Subsequently, we implement transfer learning to extract knowledge from related tasks, thus alleviating the dilemma of limited data. Additionally, we substitute the gating network with an attention mechanism to better capture the dynamic task relationships on a per-example basis. We adopt local fine-tuning and consensus prediction to further boost model performance. Extensive evaluation experiments verify the success of the ALipSol model, which achieves RMSE improvement of 8.04%, 2.49%, 8.57%, 12.8%, and 8.60% on the Lipop, ESOL, AqSolDB, external logD, and external logSdata sets, respectively, compared with Attentive FP and the state-of-the-art in silicotools. In particular, our model yields more significant advantages (Welch’s t-test) for small training data, implying its high robustness and generalizability. The interpretability analysis proves that the atom contributions learned by ALipSol are more reasonable compared with the vanilla Attentive FP, and the substitution effects in benzene derivatives agreed well with empirical constants, revealing the potential of our model to extract useful patterns from data and provide guidance for lead optimization.

Many deep learning (DL)-based molecular generative models have been proposed to design novel molecules. These models may perform well on benchmarks, but they usually do not take real-world constraints into account, such as available training data set, synthetic accessibility, and scaffold diversity in drug discovery. In this study, a new algorithm, ChemistGA, was proposed by combining the traditional heuristic algorithm with DL, in which the crossover of the traditional genetic algorithm (GA) was redefined by DL in conjunction with GA, and an innovative backcrossing operation was implemented to generate desired molecules. Our results clearly show that ChemistGA not only retains the strength of the traditional GA but also greatly enhances the synthetic accessibility and success rate of the generated molecules with desired properties. Calculations on the two benchmarks illustrate that ChemistGA achieves impressive performance among the state-of-the-art baselines, and it opens a new avenue for the application of generative models to real-world drug discovery scenarios.

Development of accurate machine-learning-based scoring functions (MLSFs) for structure-based virtual screening against a given target requires a large unbiased dataset with structurally diverse actives and decoys. However, most datasets for the development of MLSFs were designed for traditional SFs and may suffer from hidden biases and data insufficiency. Hereby, we developed a new approach named Topology-based and Conformation-based decoys generation (TocoDecoy), which integrates two strategies to generate decoys by tweaking the actives for a specific target, to generate unbiased and expandable datasets for training and benchmarking MLSFs. For hidden bias evaluation, the performance of InteractionGraphNet (IGN) trained on the TocoDecoy, LIT-PCBA, and DUD-E-like datasets was assessed. The results illustrate that the IGN model trained on the TocoDecoy dataset is competitive with that trained on the LIT-PCBA dataset but remarkably outperforms that trained on the DUD-E dataset, suggesting that the decoys in TocoDecoy are unbiased for training and benchmarking MLSFs.

Adverse effects induced by drug–drug interactions may result in early termination of drug development or even withdrawal of drugs from the market, and many drug–drug interactions are caused by the inhibition of cytochrome P450 (CYP450) enzymes. Therefore, the accurate prediction of the inhibition capability of a given compound against a specific CYP450 isoform is highly desirable. In this study, three ensemble learning methods, including random forest, gradient boosting decision tree, and eXtreme gradient boosting (XGBoost), and two deep learning methods, including deep neural networks and convolutional neural networks, were used to develop classification models to discriminate inhibitors and noninhibitors for five major CYP450 isoforms (1A2, 2C9, 2C19, 2D6, and 3A4). The results demonstrate that the ensemble learning models generally give better predictions than the deep learning models for the external test sets. Among all of the models, the XGBoost models achieve the best classification capability (average prediction accuracy of 90.4%) for the test sets, which even outperform the previously reported model developed by the multitask deep autoencoder neural network (88.5%). The Shapley additive explanation method was then used to interpret the models and analyze the misclassified molecules. The important molecular descriptors given by our models are consistent with the structural preferences for inhibitors of different CYP450 isoforms, which may provide valuable clues to detect potential drug–drug interactions in the early stage of drug discovery.

The DNase domain-containing protein TATDN1 is a conserved nuclease in both prokaryotes and eukaryotes. It was previously implicated to play a role in apoptotic DNA fragmentation in yeast and C. elegans. However, its biological function in higher organisms, such as vertebrates, is unknown. Here, we report that zebrafish TATDN1 (zTATDN1) possesses a novel endonuclease activity, which first makes a nick at the DNA duplex and subsequently converts the nick into a DNA double-strand break in vitro. This biochemical property allows zTATDN1 to catalyze decatenation of catenated kinetoplast DNA to produce separated linear DNA in vitro. We further determine that zTATDN1 is predominantly expressed in eye cells during embryonic development. Knockdown of TATDN1 in zebrafish embryos results in an abnormal cell cycle progression, formation of polyploidy and aberrant chromatin structures. Consequently, the TATDN1-deficient morphants have disordered eye cell layers and significantly smaller eyes compared with the WT control. Altogether, our current studies suggest that zTATDN1 plays an important role in chromosome segregation and eye development in zebrafish.

► We investigate whether FEN1 mutations cause individuals to be more sensitive to tobacco compounds such as B[α]P. ► We demonstrate that FEN1 is involved in processing of B[α]P lesions and the GEN activity of FEN1 is important for this process. ► Individuals carrying FEN1 mutations that impair its GEN activity will have high risk to develop tobacco-induced cancer.

Creating a wide range of new compounds that not only have ideal pharmacological properties but also easily pass long-term toxicity evaluation is still a challenging task in current drug discovery. In this study, we developed a conditional generative model by combining a semisupervised variational autoencoder (SSVAE) with an MGA toxicity predictor. Our aim is to generate molecules with low toxicity, good drug-like properties, and structural diversity. For multiobjective optimization, we have developed a method with hierarchical constraints on the toxicity space of small molecules to generate drug-like small molecules, which can also minimize the effect on the diversity of generated results. The evaluation results of the metrics indicate that the developed model has good effectiveness, novelty, and diversity. The generated molecules by this model are mainly distributed in low-toxicity regions, which suggests that our model can efficiently constrain the generation of toxic structures. In contrast to simply filtering toxic ones after generation, the low-toxicity molecular generative model can generate molecules with structural diversity. Our strategy can be used in target-based drug discovery to improve the quality of generated molecules with low-toxicity, drug-like, and highly active properties.

Background: Circular RNAs (circRNA) have been shown to be involved in the pathogenesis of colorectal cancer (CRC). CircCTNNA1 was found to be one of the upregulated circRNAs in CRC. However, there are few studies on circCTNNA1, so it is necessary to carry out further studies. Methods: The expression of circCTNNA1, microRNA (miR)-363-3p, and chemokine C-X-C motif ligand 5 (CXCL5) was detected by quantitative real-time PCR (qRT-PCR). The protein levels of CXCL5 and metastasis markers were measured using western blot (WB) analysis. Cell proliferation, apoptosis, cell cycle, migration, and invasion were determined by cell counting kit 8 (CCK8) assay, colony formation assay, flow cytometry, and transwell assay. The relationship between miR-363-3p and circCTNNA1 or CXCL5 was evaluated via dual-luciferase reporter assay and RNA immunoprecipitation assay. Animal study was performed to explore the function of circCTNNA1 on CRC tumorigenesis. Results: CircCTNNA1 and CXCL5 were highly expressed in CRC. Knockdown of circCTNNA1 could inhibit the proliferation, cell cycle, metastasis, and promote the apoptosis of CRC cells. MiR-363-3p could be sponged by circCTNNA1, and the inhibition effect of circCTNNA1 silencing on CRC progression could be reversed by miR-363-3p inhibitor. Moreover, miR-363-3p could interact with CXCL5, and CXCL5 overexpression also could reverse the suppressive effect of miR-363-3p on CRC progression. Downregulation of circCTNNA1 also could hinder the tumor growth of CRC in vivo. Conclusion: CircCTNNA1 enhanced CRC progression via regulating the miR-363-3p/CXCL5 axis.

Accurate quantification of protein–ligand interactions remains a key challenge to structure-based drug design. However, traditional machine learning (ML)-based methods based on handcrafted descriptors, one-dimensional protein sequences, and/or two-dimensional graph representations limit their capability to learn the generalized molecular interactions in 3D space. Here, we proposed a novel deep graph representation learning framework named InteractionGraphNet (IGN) to learn the protein–ligand interactions from the 3D structures of protein–ligand complexes. In IGN, two independent graph convolution modules were stacked to sequentially learn the intramolecular and intermolecular interactions, and the learned intermolecular interactions can be efficiently used for subsequent tasks. Extensive binding affinity prediction, large-scale structure-based virtual screening, and pose prediction experiments demonstrated that IGN achieved better or competitive performance against other state-of-the-art ML-based baselines and docking programs. More importantly, such state-of-the-art performance was proven from the successful learning of the key features in protein–ligand interactions instead of just memorizing certain biased patterns from data.

Safety is a main reason for drug failures, and therefore, the detection of compound toxicity and potential adverse effects in the early stage of drug development is highly desirable. However, accurate prediction of many toxicity endpoints is extremely challenging due to low accessibility of sufficient and reliable toxicity data, as well as complicated and diversified mechanisms related to toxicity. In this study, we proposed the novel multitask graph attention (MGA) framework to learn the regression and classification tasks simultaneously. MGA has shown excellent predictive power on 33 toxicity data sets and has the capability to extract general toxicity features and generate customized toxicity fingerprints. In addition, MGA provides a new way to detect structural alerts and discover the relationship between different toxicity tasks, which will be quite helpful to mine toxicity information from large amounts of toxicity data.