Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures

Inductive bias in machine learning (ML) is the set of assumptions describing how a model makes predictions. Different ML-based methods for protein-ligand binding affinity (PLA) prediction have different inductive biases, leading to different levels of generalization capability and interpretability. Intuitively, the inductive bias of an ML-based model for PLA prediction should fit in with biological mechanisms relevant for binding to achieve good predictions with meaningful reasons. To this end, we propose an interaction-based inductive bias to restrict neural networks to functions relevant for binding with two assumptions: (1) A protein-ligand complex can be naturally expressed as a heterogeneous graph with covalent and non-covalent interactions; (2) The predicted PLA is the sum of pairwise atom-atom affinities determined by non-covalent interactions. The interaction-based inductive bias is embodied by an explainable heterogeneous interaction graph neural network (EHIGN) for explicitly modeling pairwise atom-atom interactions to predict PLA from 3D structures. Extensive experiments demonstrate that EHIGN achieves better generalization capability than other state-of-the-art ML-based baselines in PLA prediction and structure-based virtual screening. More importantly, comprehensive analyses of distance-affinity, pose-affinity, and substructure-affinity relations suggest that the interaction-based inductive bias can guide the model to learn atomic interactions that are consistent with physical reality. As a case study to demonstrate practical usefulness, our method is tested for predicting the efficacy of Nirmatrelvir against SARS-CoV-2 variants. EHIGN successfully recognizes the changes in the efficacy of Nirmatrelvir for different SARS-CoV-2 variants with meaningful reasons.

MFTrans: A multi-feature transformer network for protein secondary structure prediction

In the rapidly evolving field of computational biology, accurate prediction of protein secondary structures is crucial for understanding protein functions, facilitating drug discovery, and advancing disease diagnostics. In this paper, we propose MFTrans, a deep learning-based multi-feature fusion network aimed at enhancing the precision and efficiency of Protein Secondary Structure Prediction (PSSP). This model employs a Multiple Sequence Alignment (MSA) Transformer in combination with a multi-view deep learning architecture to effectively capture both global and local features of protein sequences. MFTrans integrates diverse features generated by protein sequences, including MSA, sequence information, evolutionary information, and hidden state information, using a multi-feature fusion strategy. The MSA Transformer is utilized to interleave row and column attention across the input MSA, while a Transformer encoder and decoder are introduced to enhance the extracted high-level features. A hybrid network architecture, combining a convolutional neural network with a bidirectional Gated Recurrent Unit (BiGRU) network, is used to further extract high-level features after feature fusion. In independent tests, our experimental results show that MFTrans has superior generalization ability, outperforming other state-of-the-art PSSP models by 3 % on average on public benchmarks including CASP12, CASP13, CASP14, TEST2016, TEST2018, and CB513. Case studies further highlight its advanced performance in predicting mutation sites. MFTrans contributes significantly to the protein science field, opening new avenues for drug discovery, disease diagnosis, and protein.

Parkinson's severity diagnosis explainable model based on 3D multi-head attention residual network

The severity evaluation of Parkinson's disease (PD) is of great significance for the treatment of PD. However, existing methods either have limitations based on prior knowledge or are invasive methods. To propose a more generalized severity evaluation model, this paper proposes an explainable 3D multi-head attention residual convolution network. First, we introduce the 3D attention-based convolution layer to extract video features. Second, features will be fed into LSTM and residual backbone networks, which can be used to capture the contextual information of the video. Finally, we design a feature compression module to condense the learned contextual features. We develop some interpretable experiments to better explain this black-box model so that it can be better generalized. Experiments show that our model can achieve state-of-the-art diagnosis performance. The proposed lightweight but effective model is expected to serve as a suitable end-to-end deep learning baseline in future research on PD video-based severity evaluation and has the potential for large-scale application in PD telemedicine. The source code is available at https://github.com/JackAILab/MARNet.

Discovery of Kinetin in inhibiting colorectal cancer progression via enhancing PSMB1-mediated RAB34 degradation

Colorectal cancer (CRC) is one of the most prevalent malignancies worldwide. Understanding the underlying mechanism driving CRC progression and identifying potential therapeutic drug targets are of utmost urgency. We previously utilized LC-MS-based proteomic profiling to identify proteins associated with postoperative progression in stage II/III CRC. Here, we revealed that proteasome subunit beta type-1 (PSMB1) is an independent predictor for postoperative progression in stage II/III CRC. Mechanistically, PSMB1 binds directly to onco-protein RAB34 and promotes its proteasome-dependent degradation, potentially leading to the inactivation of the MEK/ERK signaling pathway and inhibition of CRC progression. To further identify potential anticancer drugs, we screened a library of 2509 FDA-approved drugs using computer-aided drug design (CADD) and identified Kinetin as a potentiating agent for PSMB1. Functional assays confirmed that Kinetin enhanced the interaction between PSMB1 and RAB34, hence facilitated the degradation of RAB34 protein and decreased the MEK/ERK phosphorylation. Kinetin suppresses CRC progression in patient-derived xenograft (PDX) and liver metastasis models. Conclusively, our study identifies PSMB1 as a potential biomarker and therapeutic target for CRC, and Kinetin as an anticancer drug by enhancing proteasome-dependent onco-protein degradation.

MRI-based automated machine learning model for preoperative identification of variant histology in muscle-invasive bladder carcinoma

OBJECTIVES

It is essential yet highly challenging to preoperatively diagnose variant histologies such as urothelial carcinoma with squamous differentiation (UC w/SD) from pure UC in patients with muscle-invasive bladder carcinoma (MIBC), as their treatment strategy varies significantly. We developed a non-invasive automated machine learning (AutoML) model to preoperatively differentiate UC w/SD from pure UC in patients with MIBC.

METHODS

A total of 119 MIBC patients who underwent baseline bladder MRI were enrolled in this study, including 38 patients with UC w/SD and 81 patients with pure UC. These patients were randomly assigned to a training set or a test set (3:1). An AutoML model was built from the training set, using 13 selected radiomic features from T2-weighted imaging, semantic features (ADC values), and clinical features (tumor length, tumor stage, lymph node metastasis status), and subsequent ten-fold cross-validation was performed. A test set was used to validate the proposed model. The AUC of the ROC curve was then calculated for the model.

RESULTS

This AutoML model enabled robust differentiation of UC w/SD and pure UC in patients with MIBC in both training set (ten-fold cross-validation AUC = 0.955, 95% confidence interval [CI]: 0.944-0.965) and test set (AUC = 0.932, 95% CI: 0.812-1.000).

CONCLUSION

The presented AutoML model, that incorporates the radiomic, semantic, and clinical features from baseline MRI, could be useful for preoperative differentiation of UC w/SD and pure UC.

CLINICAL RELEVANCE STATEMENT

This MRI-based automated machine learning (AutoML) study provides a non-invasive and low-cost preoperative prediction tool to identify the muscle-invasive bladder cancer patients with variant histology, which may serve as a useful tool for clinical decision-making.

KEY POINTS

• It is important to preoperatively diagnose variant histology from urothelial carcinoma in patients with muscle-invasive bladder carcinoma (MIBC), as their treatment strategy varies significantly. • An automated machine learning (AutoML) model based on baseline bladder MRI can identify the variant histology (squamous differentiation) from urothelial carcinoma preoperatively in patients with MIBC. • The developed AutoML model is a non-invasive and low-cost preoperative prediction tool, which may be useful for clinical decision-making.

LDCNet: Lightweight dynamic convolution network for laparoscopic procedures image segmentation

Medical image segmentation is fundamental for modern healthcare systems, especially for reducing the risk of surgery and treatment planning. Transanal total mesorectal excision (TaTME) has emerged as a recent focal point in laparoscopic research, representing a pivotal modality in the therapeutic arsenal for the treatment of colon & rectum cancers. Real-time instance segmentation of surgical imagery during TaTME procedures can serve as an invaluable tool in assisting surgeons, ultimately reducing surgical risks. The dynamic variations in size and shape of anatomical structures within intraoperative images pose a formidable challenge, rendering the precise instance segmentation of TaTME images a task of considerable complexity. Deep learning has exhibited its efficacy in Medical image segmentation. However, existing models have encountered challenges in concurrently achieving a satisfactory level of accuracy while maintaining manageable computational complexity in the context of TaTME data. To address this conundrum, we propose a lightweight dynamic convolution Network (LDCNet) that has the same superior segmentation performance as the state-of-the-art (SOTA) medical image segmentation network while running at the speed of the lightweight convolutional neural network. Experimental results demonstrate the promising performance of LDCNet, which consistently exceeds previous SOTA approaches. Codes are available at github.com/yinyiyang416/LDCNet.

Equivariant Flexible Modeling of the Protein-Ligand Binding Pose with Geometric Deep Learning

Flexible modeling of the protein-ligand complex structure is a fundamental challenge for in silico drug development. Recent studies have improved commonly used docking tools by incorporating extra-deep learning-based steps. However, such strategies limit their accuracy and efficiency because they retain massive sampling pressure and lack consideration for flexible biomolecular changes. In this study, we propose FlexPose, a geometric graph network capable of direct flexible modeling of complex structures in Euclidean space without the following conventional sampling and scoring strategies. Our model adopts two key designs: scalar-vector dual feature representation and SE(3)-equivariant network, to manage dynamic structural changes, as well as two strategies: conformation-aware pretraining and weakly supervised learning, to boost model generalizability in unseen chemical space. Benefiting from these paradigms, our model dramatically outperforms all tested popular docking tools and recently advanced deep learning methods, especially in tasks involving protein conformation changes. We further investigate the impact of protein and ligand similarity on the model performance with two conformation-aware strategies. Moreover, FlexPose provides an affinity estimation and model confidence for postanalysis.

TCMBank: bridges between the largest herbal medicines, chemical ingredients, target proteins, and associated diseases with intelligence text mining

Traditional Chinese Medicine (TCM) has long been viewed as a precious source of modern drug discovery. AI-assisted drug discovery (AIDD) has been investigated extensively. However, there are still two challenges in applying AIDD to guide TCM drug discovery: the lack of a large amount of standardized TCM-related information and AIDD is prone to pathological failures in out-of-domain data. We have released TCM Database@Taiwan in 2011, and it has been widely disseminated and used. Now, we developed TCMBank, the largest systematic free TCM database, which is an extension of TCM Database@Taiwan. TCMBank contains 9192 herbs, 61 966 ingredients (unduplicated), 15 179 targets, 32 529 diseases, and their pairwise relationships. By integrating multiple data sources, TCMBank provides 3D structure information of ingredients and provides a standard list and detailed information on herbs, ingredients, targets and diseases. TCMBank has an intelligent document identification module that continuously adds TCM-related information retrieved from the literature in PubChem. In addition, driven by TCMBank big data, we developed an ensemble learning-based drug discovery protocol for identifying potential leads and drug repurposing. We take colorectal cancer and Alzheimer's disease as examples to demonstrate how to accelerate drug discovery by artificial intelligence. Using TCMBank, researchers can view literature-driven relationship mapping between herbs/ingredients and genes/diseases, allowing the understanding of molecular action mechanisms for ingredients and identification of new potentially effective treatments. TCMBank is available at https://TCMBank.CN/.

3D graph neural network with few-shot learning for predicting drug-drug interactions in scaffold-based cold start scenario

Understanding drug-drug interactions (DDI) of new drugs is critical for minimizing unexpected adverse drug reactions. The modeling of new drugs is called a cold start scenario. In this scenario, Only a few structural information or physicochemical information about new drug is available. The 3D conformation of drug molecules usually plays a crucial role in chemical properties compared to the 2D structure. 3D graph network with few-shot learning is a promising solution. However, the 3D heterogeneity of drug molecules and the discretization of atomic distributions lead to spatial confusion in few-shot learning. Here, we propose a 3D graph neural network with few-shot learning, Meta3D-DDI, to predict DDI events in cold start scenario. The 3DGNN ensures rotation and translation invariance by calculating atomic pairwise distances, and incorporates 3D structure and distance information in the information aggregation stage. The continuous filter interaction module can continuously simulate the filter to obtain the interaction between the target atom and other atoms. Meta3D-DDI further develops a FSL strategy based on bilevel optimization to transfer meta-knowledge for DDI prediction tasks from existing drugs to new drugs. In addition, the existing cold start setting may cause the scaffold structure information in the training set to leak into the test set. We design scaffold-based cold start scenario to ensure that the drug scaffolds in the training set and test set do not overlap. The extensive experiments demonstrate that our architecture achieves the SOTA performance for DDI prediction under scaffold-based cold start scenario on two real-world datasets. The visual experiment shows that Meta3D-DDI significantly improves the learning for DDI prediction of new drugs. We also demonstrate how Meta3D-DDI can reduce the amount of data required to make meaningful DDI predictions.

Hybrid neural network approaches to predict drug-target binding affinity for drug repurposing: screening for potential leads for Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disease that primarily affects elderly individuals. Recent studies have found that sigma-1 receptor (S1R) agonists can maintain endoplasmic reticulum stress homeostasis, reduce neuronal apoptosis, and enhance mitochondrial function and autophagy, making S1R a target for AD therapy. Traditional experimental methods are costly and inefficient, and rapid and accurate prediction methods need to be developed, while drug repurposing provides new ways and options for AD treatment. In this paper, we propose HNNDTA, a hybrid neural network for drug-target affinity (DTA) prediction, to facilitate drug repurposing for AD treatment. The study combines protein-protein interaction (PPI) network analysis, the HNNDTA model, and molecular docking to identify potential leads for AD. The HNNDTA model was constructed using 13 drug encoding networks and 9 target encoding networks with 2506 FDA-approved drugs as the candidate drug library for S1R and related proteins. Seven potential drugs were identified using network pharmacology and DTA prediction results of the HNNDTA model. Molecular docking simulations were further performed using the AutoDock Vina tool to screen haloperidol and bromperidol as lead compounds for AD treatment. Absorption, distribution, metabolism, excretion, and toxicity (ADMET) evaluation results indicated that both compounds had good pharmacokinetic properties and were virtually non-toxic. The study proposes a new approach to computer-aided drug design that is faster and more economical, and can improve hit rates for new drug compounds. The results of this study provide new lead compounds for AD treatment, which may be effective due to their multi-target action. HNNDTA is freely available at https://github.com/lizhj39/HNNDTA.

NHGNN-DTA: a node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction

MOTIVATION

Large-scale prediction of drug-target affinity (DTA) plays an important role in drug discovery. In recent years, machine learning algorithms have made great progress in DTA prediction by utilizing sequence or structural information of both drugs and proteins. However, sequence-based algorithms ignore the structural information of molecules and proteins, while graph-based algorithms are insufficient in feature extraction and information interaction.

RESULTS

In this article, we propose NHGNN-DTA, a node-adaptive hybrid neural network for interpretable DTA prediction. It can adaptively acquire feature representations of drugs and proteins and allow information to interact at the graph level, effectively combining the advantages of both sequence-based and graph-based approaches. Experimental results have shown that NHGNN-DTA achieved new state-of-the-art performance. It achieved the mean squared error (MSE) of 0.196 on the Davis dataset (below 0.2 for the first time) and 0.124 on the KIBA dataset (3% improvement). Meanwhile, in the case of cold start scenario, NHGNN-DTA proved to be more robust and more effective with unseen inputs than baseline methods. Furthermore, the multi-head self-attention mechanism endows the model with interpretability, providing new exploratory insights for drug discovery. The case study on Omicron variants of SARS-CoV-2 illustrates the efficient utilization of drug repurposing in COVID-19.

AVAILABILITY AND IMPLEMENTATION

The source code and data are available at https://github.com/hehh77/NHGNN-DTA.

Retrosynthesis prediction using an end-to-end graph generative architecture for molecular graph editing

Retrosynthesis planning, the process of identifying a set of available reactions to synthesize the target molecules, remains a major challenge in organic synthesis. Recently, computer-aided synthesis planning has gained renewed interest and various retrosynthesis prediction algorithms based on deep learning have been proposed. However, most existing methods are limited to the applicability and interpretability of model predictions, and further improvement of predictive accuracy to a more practical level is still required. In this work, inspired by the arrow-pushing formalism in chemical reaction mechanisms, we present an end-to-end architecture for retrosynthesis prediction called Graph2Edits. Specifically, Graph2Edits is based on graph neural network to predict the edits of the product graph in an auto-regressive manner, and sequentially generates transformation intermediates and final reactants according to the predicted edits sequence. This strategy combines the two-stage processes of semi-template-based methods into one-pot learning, improving the applicability in some complicated reactions, and also making its predictions more interpretable. Evaluated on the standard benchmark dataset USPTO-50k, our model achieves the state-of-the-art performance for semi-template-based retrosynthesis with a promising 55.1% top-1 accuracy.

Meta Learning With Graph Attention Networks for Low-Data Drug Discovery

Finding candidate molecules with favorable pharmacological activity, low toxicity, and proper pharmacokinetic properties is an important task in drug discovery. Deep neural networks have made impressive progress in accelerating and improving drug discovery. However, these techniques rely on a large amount of label data to form accurate predictions of molecular properties. At each stage of the drug discovery pipeline, usually, only a few biological data of candidate molecules and derivatives are available, indicating that the application of deep neural networks for low-data drug discovery is still a formidable challenge. Here, we propose a meta learning architecture with graph attention network, Meta-GAT, to predict molecular properties in low-data drug discovery. The GAT captures the local effects of atomic groups at the atom level through the triple attentional mechanism and implicitly captures the interactions between different atomic groups at the molecular level. GAT is used to perceive molecular chemical environment and connectivity, thereby effectively reducing sample complexity. Meta-GAT further develops a meta learning strategy based on bilevel optimization, which transfers meta knowledge from other attribute prediction tasks to low-data target tasks. In summary, our work demonstrates how meta learning can reduce the amount of data required to make meaningful predictions of molecules in low-data scenarios. Meta learning is likely to become the new learning paradigm in low-data drug discovery. The source code is publicly available at: https://github.com/lol88/Meta-GAT.

Geometric Interaction Graph Neural Network for Predicting Protein-Ligand Binding Affinities from 3D Structures (GIGN)

Predicting protein-ligand binding affinities (PLAs) is a core problem in drug discovery. Recent advances have shown great potential in applying machine learning (ML) for PLA prediction. However, most of them omit the 3D structures of complexes and physical interactions between proteins and ligands, which are considered essential to understanding the binding mechanism. This paper proposes a geometric interaction graph neural network (GIGN) that incorporates 3D structures and physical interactions for predicting protein-ligand binding affinities. Specifically, we design a heterogeneous interaction layer that unifies covalent and noncovalent interactions into the message passing phase to learn node representations more effectively. The heterogeneous interaction layer also follows fundamental biological laws, including invariance to translations and rotations of the complexes, thus avoiding expensive data augmentation strategies. GIGN achieves state-of-the-art performance on three external test sets. Moreover, by visualizing learned representations of protein-ligand complexes, we show that the predictions of GIGN are biologically meaningful.

DSIL-DDI: A Domain-Invariant Substructure Interaction Learning for Generalizable Drug-Drug Interaction Prediction

Drug-drug interactions (DDIs) trigger unexpected pharmacological effects in vivo, often with unknown causal mechanisms. Deep learning methods have been developed to better understand DDI. However, learning domain-invariant representations for DDI remains a challenge. Generalizable DDI predictions are closer to reality than source domain predictions. For existing methods, it is difficult to achieve out-of-distribution (OOD) predictions. In this article, focusing on substructure interaction, we propose DSIL-DDI, a pluggable substructure interaction module that can learn domain-invariant representations of DDIs from source domain. We evaluate DSIL-DDI on three scenarios: the transductive setting (all drugs in test set appear in training set), the inductive setting (test set contains new drugs that were not present in training set), and OOD generalization setting (training set and test set belong to two different datasets). The results demonstrate that DSIL-DDI improve the generalization and interpretability of DDI prediction modeling and provides valuable insights for OOD DDI predictions. DSIL-DDI can help doctors ensuring the safety of drug administration and reducing the harm caused by drug abuse.

Learning size-adaptive molecular substructures for explainable drug-drug interaction prediction by substructure-aware graph neural network

Drug-drug interactions (DDIs) can trigger unexpected pharmacological effects on the body, and the causal mechanisms are often unknown. Graph neural networks (GNNs) have been developed to better understand DDIs. However, identifying key substructures that contribute most to the DDI prediction is a challenge for GNNs. In this study, we presented a substructure-aware graph neural network, a message passing neural network equipped with a novel substructure attention mechanism and a substructure-substructure interaction module (SSIM) for DDI prediction (SA-DDI). Specifically, the substructure attention was designed to capture size- and shape-adaptive substructures based on the chemical intuition that the sizes and shapes are often irregular for functional groups in molecules. DDIs are fundamentally caused by chemical substructure interactions. Thus, the SSIM was used to model the substructure-substructure interactions by highlighting important substructures while de-emphasizing the minor ones for DDI prediction. We evaluated our approach in two real-world datasets and compared the proposed method with the state-of-the-art DDI prediction models. The SA-DDI surpassed other approaches on the two datasets. Moreover, the visual interpretation results showed that the SA-DDI was sensitive to the structure information of drugs and was able to detect the key substructures for DDIs. These advantages demonstrated that the proposed method improved the generalization and interpretation capability of DDI prediction modeling.

3DGT-DDI: 3D graph and text based neural network for drug-drug interaction prediction

MOTIVATION

Drug-drug interactions (DDIs) occur during the combination of drugs. Identifying potential DDI helps us to study the mechanism behind the combination medication or adverse reactions so as to avoid the side effects. Although many artificial intelligence methods predict and mine potential DDI, they ignore the 3D structure information of drug molecules and do not fully consider the contribution of molecular substructure in DDI.

RESULTS

We proposed a new deep learning architecture, 3DGT-DDI, a model composed of a 3D graph neural network and pre-trained text attention mechanism. We used 3D molecular graph structure and position information to enhance the prediction ability of the model for DDI, which enabled us to deeply explore the effect of drug substructure on DDI relationship. The results showed that 3DGT-DDI outperforms other state-of-the-art baselines. It achieved an 84.48% macro F1 score in the DDIExtraction 2013 shared task dataset. Also, our 3D graph model proves its performance and explainability through weight visualization on the DrugBank dataset. 3DGT-DDI can help us better understand and identify potential DDI, thereby helping to avoid the side effects of drug mixing.

AVAILABILITY

The source code and data are available at https://github.com/hehh77/3DGT-DDI.

Multitask deep learning with dynamic task balancing for quantum mechanical properties prediction

Predicting quantum mechanical properties (QMPs) is very important for the innovation of material and chemistry science. Multitask deep learning models have been widely used in QMPs prediction. However, existing multitask learning models often train multiple QMPs prediction tasks simultaneously without considering the internal relationships and differences between tasks, which may cause the model to overfit easy tasks. In this study, we first proposed a multiscale dynamic attention graph neural network (MDGNN) for molecular representation learning. The MDGNN was designed in a multitask learning fashion that can solve multiple learning tasks at the same time. We then introduced a dynamic task balancing (DTB) strategy combining task differences and difficulties to reduce overfitting across multiple tasks. Finally, we adopted gradient-weighted class activation mapping (Grad-CAM) to analyze a deep learning model for frontier molecular orbital, highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) energy level predictions. We evaluated our approach using two large QMPs datasets and compared the proposed method to the state-of-the-art multitask learning models. The MDGNN outperforms other multitask learning approaches on two datasets. The DTB strategy can further improve the performance of MDGNN significantly. Moreover, we show that Grad-CAM creates explanations that are consistent with the molecular orbitals theory. These advantages demonstrate that the proposed method improves the generalization and interpretation capability of QMPs prediction modeling.

MGraphDTA: deep multiscale graph neural network for explainable drug-target binding affinity prediction

Predicting drug-target affinity (DTA) is beneficial for accelerating drug discovery. Graph neural networks (GNNs) have been widely used in DTA prediction. However, existing shallow GNNs are insufficient to capture the global structure of compounds. Besides, the interpretability of the graph-based DTA models highly relies on the graph attention mechanism, which can not reveal the global relationship between each atom of a molecule. In this study, we proposed a deep multiscale graph neural network based on chemical intuition for DTA prediction (MGraphDTA). We introduced a dense connection into the GNN and built a super-deep GNN with 27 graph convolutional layers to capture the local and global structure of the compound simultaneously. We also developed a novel visual explanation method, gradient-weighted affinity activation mapping (Grad-AAM), to analyze a deep learning model from the chemical perspective. We evaluated our approach using seven benchmark datasets and compared the proposed method to the state-of-the-art deep learning (DL) models. MGraphDTA outperforms other DL-based approaches significantly on various datasets. Moreover, we show that Grad-AAM creates explanations that are consistent with pharmacologists, which may help us gain chemical insights directly from data beyond human perception. These advantages demonstrate that the proposed method improves the generalization and interpretation capability of DTA prediction modeling.

Machine learning and graph neural network for finding potential drugs related to multiple myeloma

An innovative voting mechanism for virtual drug screening.

FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction

The prediction of drug-target affinity (DTA) plays an increasingly important role in drug discovery. Nowadays, lots of prediction methods focus on feature encoding of drugs and proteins, but ignore the importance of feature aggregation. However, the increasingly complex encoder networks lead to the loss of implicit information and excessive model size. To this end, we propose a deep-learning-based approach namely FusionDTA. For the loss of implicit information, a novel muti-head linear attention mechanism was utilized to replace the rough pooling method. This allows FusionDTA aggregates global information based on attention weights, instead of selecting the largest one as max-pooling does. To solve the redundancy issue of parameters, we applied knowledge distillation in FusionDTA by transfering learnable information from teacher model to student. Results show that FusionDTA performs better than existing models for the test domain on all evaluation metrics. We obtained concordance index (CI) index of 0.913 and 0.906 in Davis and KIBA dataset respectively, compared with 0.893 and 0.891 of previous state-of-art model. Under the cold-start constrain, our model proved to be more robust and more effective with unseen inputs than baseline methods. In addition, the knowledge distillation did save half of the parameters of the model, with only 0.006 reduction in CI index. Even FusionDTA with half the parameters could easily exceed the baseline on all metrics. In general, our model has superior performance and improves the effect of drug-target interaction (DTI) prediction. The visualization of DTI can effectively help predict the binding region of proteins during structure-based drug design.

Mol2Context-vec: learning molecular representation from context awareness for drug discovery

With the rapid development of proteomics and the rapid increase of target molecules for drug action, computer-aided drug design (CADD) has become a basic task in drug discovery. One of the key challenges in CADD is molecular representation. High-quality molecular expression with chemical intuition helps to promote many boundary problems of drug discovery. At present, molecular representation still faces several urgent problems, such as the polysemy of substructures and unsmooth information flow between atomic groups. In this research, we propose a deep contextualized Bi-LSTM architecture, Mol2Context-vec, which can integrate different levels of internal states to bring dynamic representations of molecular substructures. And the obtained molecular context representation can capture the interactions between any atomic groups, especially a pair of atomic groups that are topologically distant. Experiments show that Mol2Context-vec achieves state-of-the-art performance on multiple benchmark datasets. In addition, the visual interpretation of Mol2Context-vec is very close to the structural properties of chemical molecules as understood by humans. These advantages indicate that Mol2Context-vec can be used as a reliable and effective tool for molecular expression. Availability: The source code is available for download in https://github.com/lol88/Mol2Context-vec.

Enhancing adversarial defense for medical image analysis systems with pruning and attention mechanism

PURPOSE

Deep learning has achieved impressive performance across a variety of tasks, including medical image processing. However, recent research has shown that deep neural networks (DNNs) are susceptible to small adversarial perturbations in the image, which raise safety concerns about the deployment of these systems in clinical settings.

METHODS

To improve the defense of the medical imaging system against adversarial examples, we propose a new model-based defense framework for medical image DNNs model equipped with pruning and attention mechanism module based on the analysis of the reason why existing medical image DNNs models are vulnerable to attacks from adversarial examples is that complex biological texture of medical imaging and overparameterized medical image DNNs model.

RESULTS

Three benchmark medical image datasets have verified the effectiveness of our method in improving the robustness of medical image DNNs models. In the chest X-ray datasets, our defending method can even achieve up 77.18% defense rate for projected gradient descent attack and 69.49% defense rate for DeepFool attack. And through ablation experiments on the pruning module and the attention mechanism module, it is verified that the use of pruning and attention mechanism can effectively improve the robustness of the medical image DNNs model.

CONCLUSIONS

Compared with the existing model-based defense methods proposed for natural images, our defense method is more suitable for medical images. Our method can be a general strategy to approach the design of more explainable and secure medical deep learning systems, and can be widely used in various medical image tasks to improve the robustness of medical models.

Predicting Drug-Target Interactions with Deep-Embedding Learning of Graphs and Sequences

Computational approaches for predicting drug-target interactions (DTIs) play an important role in drug discovery since conventional screening experiments are time-consuming and expensive. In this study, we proposed end-to-end representation learning of a graph neural network with an attention mechanism and an attentive bidirectional long short-term memory (BiLSTM) to predict DTIs. For efficient training, we introduced a bidirectional encoder representations from transformers (BERT) pretrained method to extract substructure features from protein sequences and a local breadth-first search (BFS) to learn subgraph information from molecular graphs. Integrating both models, we developed a DTI prediction system. As a result, the proposed method achieved high performances with increases of 2.4% and 9.4% for AUC and recall, respectively, on unbalanced datasets compared with other methods. Extensive experiments showed that our model can relatively screen potential drugs for specific protein. Furthermore, visualizing the attention weights provides biological insight.

Graph convolutional network approach to investigate potential selective Limk1 inhibitors

Since the Limk1 is a promising drug target and few inhibitors with good Limk1/ROCK2 selectivity have been reported, discovering potential and selective Limk1 inhibitors with novel scaffolds is becoming an urgent need to develop new treatments for the related diseases. Here, we utilized molecular docking to screen potential compounds of Limk1 from Traditional Chinese Medicine (TCM) database. Meanwhile, we performed a three-dimensional graph convolutional network (3DGCN), based on 3D molecular graph, to predict the inhibitory activity of Limk1 and ROCK2. Compared with the baseline models (RF, GCN and Weave), the 3DGCN achieved higher accuracy and the averaged RMSE values on test sets for Limk1 and ROCK2 were 0.721 and 0.852 respectively. In 3DGCN, above 80% of the test-set molecules from both two datasets were predicted within absolute error of 1.0 and the feature visualization suggested that it could automatically learn relevant structure features including 3D molecular information from a specific task for prediction. Furthermore, molecular dynamics (MD) simulations within 100 ns were employed to verify the stability of ligand-protein complexes and reveal the binding modes of the potential selective lead compounds of Limk1. Finally, integrating docking results, the predicted values by the 3DGCN and the MD analysis, we found that 7549 and 2007_15649 might be the potential and selective inhibitors for Limk1 receptor.

Lung Lesion Localization of COVID-19 From Chest CT Image: A Novel Weakly Supervised Learning Method

Chest computed tomography (CT) image data is necessary for early diagnosis, treatment, and prognosis of Coronavirus Disease 2019 (COVID-19). Artificial intelligence has been tried to help clinicians in improving the diagnostic accuracy and working efficiency of CT. Whereas, existing supervised approaches on CT image of COVID-19 pneumonia require voxel-based annotations for training, which take a lot of time and effort. This paper proposed a weakly-supervised method for COVID-19 lesion localization based on generative adversarial network (GAN) with image-level labels only. We first introduced a GAN-based framework to generate normal-looking CT slices from CT slices with COVID-19 lesions. We then developed a novel feature match strategy to improve the reality of generated images by guiding the generator to capture the complex texture of chest CT images. Finally, the localization map of lesions can be easily obtained by subtracting the output image from its corresponding input image. By adding a classifier branch to the GAN-based framework to classify localization maps, we can further develop a diagnosis system with improved classification accuracy. Three CT datasets from hospitals of Sao Paulo, Italian Society of Medical and Interventional Radiology, and China Medical University about COVID-19 were collected in this article for evaluation. Our weakly supervised learning method obtained AUC of 0.883, dice coefficient of 0.575, accuracy of 0.884, sensitivity of 0.647, specificity of 0.929, and F1-score of 0.640, which exceeded other widely used weakly supervised object localization methods by a significant margin. We also compared the proposed method with fully supervised learning methods in COVID-19 lesion segmentation task, the proposed weakly supervised method still leads to a competitive result with dice coefficient of 0.575. Furthermore, we also analyzed the association between illness severity and visual score, we found that the common severity cohort had the largest sample size as well as the highest visual score which suggests our method can help rapid diagnosis of COVID-19 patients, especially in massive common severity cohort. In conclusion, we proposed this novel method can serve as an accurate and efficient tool to alleviate the bottleneck of expert annotation cost and advance the progress of computer-aided COVID-19 diagnosis.

ML-DTI: Mutual Learning Mechanism for Interpretable Drug-Target Interaction Prediction

Deep learning (DL) provides opportunities for the identification of drug-target interactions (DTIs). The challenges of applying DL lie primarily with the lack of interpretability. Also, most of the existing DL-based methods formulate the drug and target encoder as two independent modules without considering the relationship between them. In this study, we propose a mutual learning mechanism to bridge the gap between the two encoders. We formulated the DTI problem from a global perspective by inserting mutual learning layers between the two encoders. The mutual learning layer was achieved by multihead attention and position-aware attention. The neural attention mechanism also provides effective visualization, which makes it easier to analyze a model. We evaluated our approach using three benchmark kinase data sets under different experimental settings and compared the proposed method to three baseline models. We found that the four methods yielded similar results in the random split setting (training and test sets share common drugs and targets), while the proposed method increases the predictive performance significantly in the orphan-target and orphan-drug split setting (training and test sets share only targets or drugs). The experimental results demonstrated that the proposed method improved the generalization and interpretation capability of DTI modeling.

A Novel Graph Neural Network Methodology to Investigate Dihydroorotate Dehydrogenase Inhibitors in Small Cell Lung Cancer

Small cell lung cancer (SCLC) is a particularly aggressive tumor subtype, and dihydroorotate dehydrogenase (DHODH) has been demonstrated to be a therapeutic target for SCLC. Network pharmacology analysis and virtual screening were utilized to find out related proteins and investigate candidates with high docking capacity to multiple targets. Graph neural networks (GNNs) and machine learning were used to build reliable predicted models. We proposed a novel concept of multi-GNNs, and then built three multi-GNN models called GIAN, GIAT, and SGCA, which achieved satisfactory results in our dataset containing 532 molecules with all R^{^2} values greater than 0.92 on the training set and higher than 0.8 on the test set. Compared with machine learning algorithms, random forest (RF), and support vector regression (SVR), multi-GNNs had a better modeling effect and higher precision. Furthermore, the long-time 300 ns molecular dynamics simulation verified the stability of the protein–ligand complexes. The result showed that ZINC8577218, ZINC95618747, and ZINC4261765 might be the potentially potent inhibitors for DHODH. Multi-GNNs show great performance in practice, making them a promising field for future research. We therefore suggest that this novel concept of multi-GNNs is a promising protocol for drug discovery.

Novel and versatile artificial intelligence algorithms for investigating possible GHSR1α and DRD1 agonists for Alzheimer's disease

Hippocampal lesions are recognized as the earliest pathological changes in Alzheimer's disease (AD). Recent researches have shown that the co-activation of growth hormone secretagogue receptor 1α (GHSR1α) and dopamine receptor D1 (DRD1) could recover the function of hippocampal synaptic and cognition. We combined traditional virtual screening technology with artificial intelligence models to screen multi-target agonists for target proteins from TCM database and a novel boost Generalized Regression Neural Network (GRNN) model was proposed in this article to improve the poor adjustability of GRNN. R-square was chosen to evaluate the accuracy of these artificial intelligent models. For the GHSR1α agonist dataset, Adaptive Boosting (AdaBoost), Linear Ridge Regression (LRR), Support Vector Machine (SVM), and boost GRNN achieved good results; the R-square of the test set of these models reached 0.900, 0.813, 0.708, and 0.802, respectively. For the DRD1 agonist dataset, Gradient Boosting (GB), Random Forest (RF), SVM, and boost GRNN achieved good results; the R-square of the test set of these models reached 0.839, 0.781, 0.763, and 0.815, respectively. According to these values of R-square, it is obvious that boost GRNN and SVM have better adaptability for different data sets and boost GRNN is more accurate than SVM. To evaluate the reliability of screening results, molecular dynamics (MD) simulation experiments were performed to make sure that candidates were docked well in the protein binding site. By analyzing the results of these artificial intelligent models and MD experiments, we suggest that 2007_17103 and 2007_13380 are the possible dual-target drugs for Alzheimer's disease (AD).

Artificial Intelligence-Based Application to Explore Inhibitors of Neurodegenerative Diseases

Neuroinflammation is a common factor in neurodegenerative diseases, and it has been demonstrated that galectin-3 activates microglia and astrocytes, leading to inflammation. This means that inhibition of galectin-3 may become a new strategy for the treatment of neurodegenerative diseases. Based on this motivation, the objective of this study is to explore an integrated new approach for finding lead compounds that inhibit galectin-3, by combining universal artificial intelligence algorithms with traditional drug screening methods. Based on molecular docking method, potential compounds with high binding affinity were screened out from Chinese medicine database. Manifold artificial intelligence algorithms were performed to validate the docking results and further screen compounds. Among all involved predictive methods, the deep learning-based algorithm made 500 modeling attempts, and the square correlation coefficient of the best trained model on the test sets was 0.9. The XGBoost model reached a square correlation coefficient of 0.97 and a mean square error of only 0.01. We switched to the ZINC database and performed the same experiment, the results showed that the compounds in the former database showed stronger affinity. Finally, we further verified through molecular dynamics simulation that the complex composed of the candidate ligand and the target protein showed stable binding within 100 ns of simulation time. In summary, combined with the application based on artificial intelligence algorithms, we unearthed the active ingredients 1,2-Dimethylbenzene and Typhic acid contained in Crataegus pinnatifida and Typha angustata might be the effective inhibitors of neurodegenerative diseases. The high prediction accuracy of the models shows that it has practical application value on small sample data sets such as drug screening.

A novel artificial intelligence protocol to investigate potential leads for Parkinson's disease

Previous studies have shown that small molecule inhibitors of NLRP3 may be a potential treatment for Parkinson's disease (PD). NACHT, LRR and PYD domains-containing protein 3 (NLRP3), heat shock protein HSP 90-beta (HSP90AB1), caspase-1 (CASP1) and cellular tumor antigen p53 (TP53) have significant involvement in the pathogenesis pathway of PD. Molecular docking was used to screen the traditional Chinese medicine database TCM Database@Taiwan. Top traditional Chinese medicine (TCM) compounds with high affinities based on Dock Score were selected to form the drug-target interaction network to investigate potential candidates targeting NLRP3, HSP90AB1, CASP1, and TP53 proteins. Artificial intelligence model, 3D-Quantitative Structure-Activity Relationship (3D-QSAR) were constructed respectively utilizing training sets of inhibitors against the four proteins with known inhibitory activities (pIC50). The results showed that 2007_22057 (an indole derivative), 2007_22325 (a valine anhydride) and 2007_15317 (an indole derivative) might be a potential medicine formula for the treatment of PD. Then there are three candidate compounds identified by the result of molecular dynamics.

A novel artificial intelligence protocol for finding potential inhibitors of acute myeloid leukemia

There is currently no effective treatment for acute myeloid leukemia, and surgery is also ineffective as an important treatment for most tumors. Rapidly developing artificial intelligence technology can be applied to different aspects of drug development, and it plays a key role in drug discovery. Based on network pharmacology and virtual screening, candidates were selected from the molecular database. Nine artificial intelligence algorithm models were used to further verify the candidates' potential. The 350 training results of the deep learning model showed higher credibility, and the R-square of the training set and test set of the optimal model reached 0.89 and 0.84, respectively. The random forest model has an R-square of 0.91 and a mean square error of only 0.003. The R-square of the Adaptive Boosting model and the Bagging model reached 0.92 and 0.88, respectively. Molecular dynamics simulation evaluated the stability of the ligand-protein complex and achieved good results. Artificial intelligence models had unearthed the promising candidates for STAT3 inhibitors, and the good performance of most models showed that they still had practical value on small data sets.

A Multi-Task Group Bi-LSTM Networks Application on Electrocardiogram Classification

BACKGROUND

Cardiovascular diseases (CVD) are the leading cause of death globally. Electrocardiogram (ECG) analysis can provide thoroughly assessment for different CVDs efficiently. We propose a multi-task group bidirectional long short-term memory (MTGBi-LSTM) framework to intelligent recognize multiple CVDs based on multi-lead ECG signals.

METHODS

This model employs a Group Bi-LSTM (GBi-LSTM) and Residual Group Convolutional Neural Network (Res-GCNN) to learn the dual feature representation of ECG space and time series. GBi-LSTM is divided into Global Bi-LSTM and Intra-Group Bi-LSTM, which can learn the features of each ECG lead and the relationship between leads. Then, through attention mechanism, the different lead information of ECG is integrated to make the model to possess the powerful feature discriminability. Through multi-task learning, the model can fully mine the association information between diseases and obtain more accurate diagnostic results. In addition, we propose a dynamic weighted loss function to better quantify the loss to overcome the imbalance between classes.

RESULTS

Based on more than 170,000 clinical 12-lead ECG analysis, the MTGBi-LSTM method achieved accuracy, precision, recall and F1 of 88.86%, 90.67%, 94.19% and 92.39%, respectively. The experimental results show that the proposed MTGBi-LSTM method can reliably realize ECG analysis and provide an effective tool for computer-aided diagnosis of CVD.

Artificial Intelligence Approach To Investigate the Longevity Drug

Longevity is a very important and interesting topic, and Klotho has been demonstrated to be related to longevity. We combined network pharmacology, machine learning, deep learning, and molecular dynamics (MD) simulation to investigate potent lead drugs. Related protein insulin-like growth factor 1 receptor (IGF1R) and insulin receptor (IR) were docked with the traditional Chinese medicine (TCM) database to screen out several novel candidates. Besides, nine different machine learning algorithms were performed to build reliable and accurate predicted models. Moreover, we used the novel deep learning algorithm to build predicted models. All of these models obtained significant R², which are all greater than 0.87 on the training set and higher than 0.88 for the test set, respectively. The long time 500 ns molecular dynamics simulation was also performed to verify protein-ligand properties and stability. Finally, we obtained Antifebrile Dichroa, Holarrhena antidysenterica, and Gelsemium sempervirens, which might be potent TCMs for two targets.

Artificial Intelligence Approach to Find Lead Compounds for Treating Tumors

It has been demonstrated that MMP13 enzyme is related to most cancer cell tumors. The world's largest traditional Chinese medicine database was applied to screen for structure-based drug design and ligand-based drug design. To predict drug activity, machine learning models (Random Forest (RF), AdaBoost Regressor (ABR), Gradient Boosting Regressor (GBR)), and Deep Learning models were utilized to validate the Docking results, and we obtained an R² of 0.922 on the training set and 0.804 on the test set in the RF algorithm. For the Deep Learning algorithm, R² of the training set is 0.90, and R² of the test set is 0.810. However, these TCM compounds fly away during the molecular dynamics (MD) simulation. We seek another method: peptide design. All peptide database were screened by the Docking process. Modification peptides were optimized the interaction modes, and the affinities were assessed with ZDOCK protocol and Refine Docked protein protocol. The 300 ns MD simulation evaluated the stability of receptor-peptide complexes. The double-site effect appeared on S2, a designed peptide based on a known inhibitor, when complexed with BCL2. S3, a designed peptide referred from endogenous inhibitor P16, competed against cyclin when binding with CDK6. The MDM2 inhibitors S5 and S6 were derived from the P53 structure and stable binding with MDM2. A flexible region of peptides S5 and S6 may enhance the binding ability by changing its own conformation, which was unforeseen. These peptides (S2, S3, S5, and S6) are potentially interesting to treat cancer; however, these findings need to be affirmed by biological testing, which will be conducted in the near future.

Deep Learning and Random Forest Approach for Finding the Optimal Traditional Chinese Medicine Formula for Treatment of Alzheimer's Disease

It has demonstrated that glycogen synthase kinase 3β (GSK3β) is related to Alzheimer's disease (AD). On the basis of the world largest traditional Chinese medicine (TCM) database, a network-pharmacology-based approach was utilized to investigate TCM candidates that can dock well with multiple targets. Support vector machine (SVM) and multiple linear regression (MLR) methods were utilized to obtain predicted models. In particular, the deep learning method and the random forest (RF) algorithm were adopted. We achieved R² values of 0.927 on the training set and 0.862 on the test set with deep learning and 0.869 on the training set and 0.890 on the test set with RF. Besides, comparative molecular similarity indices analysis (CoMSIA) was performed to get a predicted model. All of the training models achieved good results on the test set. The stability of GSK3β protein-ligand complexes was evaluated using 100 ns of MD simulation. Methyl 3- O-feruloylquinate and cynanogenin A induced both more compactness to the GSK3β complex and stable conditions at all simulation times, and the GSK3β complex also had no substantial fluctuations after a simulation time of 5 ns. For TCM molecules, we used the trained models to calculate predicted bioactivity values, and the optimum TCM candidates were obtained by ranking the predicted values. The results showed that methyl 3- O-feruloylquinate contained in Phellodendron amurense and cynanogenin A contained in Cynanchum atratum are capable of forming stable interactions with GSK3β.

Insight into two antioxidants binding to the catalase NADPH binding site from traditional Chinese medicines

The two TCM compounds, hesperidin and THSG, might help to keep catalase active during the decomposition of hydrogen peroxide.

Developing hypothetical inhibition mechanism of novel urea transporter B inhibitor

Urea transporter B (UT-B) is a membrane channel protein that specifically transports urea. UT-B null mouse exhibited urea selective urine concentrating ability deficiency, which suggests the potential clinical applications of the UT-B inhibitors as novel diuretics. Primary high-throughput virtual screening (HTVS) of 50000 small-molecular drug-like compounds identified 2319 hit compounds. These 2319 compounds were screened by high-throughput screening using an erythrocyte osmotic lysis assay. Based on the pharmacological data, putative UT-B binding sites were identified by structure-based drug design and validated by ligand-based and QSAR model. Additionally, UT-B structural and functional characteristics under inhibitors treated and untreated conditions were simulated by molecular dynamics (MD). As the result, we identified four classes of compounds with UT-B inhibitory activity and predicted a human UT-B model, based on which computative binding sites were identified and validated. A novel potential mechanism of UT-B inhibitory activity was discovered by comparing UT-B from different species. Results suggest residue PHE198 in rat and mouse UT-B might block the inhibitor migration pathway. Inhibitory mechanisms of UT-B inhibitors and the functions of key residues in UT-B were proposed. The binding site analysis provides a structural basis for lead identification and optimization of UT-B inhibitors.

In silico investigation of potential pyruvate kinase M2 regulators from traditional Chinese medicine against cancers

A recent research in cancer research demonstrates that tumor-specific pyruvate kinase M2 (PKM2) plays an important role in chromosome segregation and mitosis progression of tumor cells. To improve the drug development of TCM compounds, we aim to identify potent TCM compounds as lead compounds of PKM2 regulators. PONDR-Fit protocol was utilized to predict the disordered disposition in the binding domain of PKM2 protein before virtual screening as the disordered structure in the protein may cause the side effect and downregulation of the possibility of ligand to bind with target protein. MD simulation was performed to validate the stability of interactions between PKM2 proteins and each ligand after virtual screening. The top TCM compounds, saussureamine C and precatorine, extracted from Lycium chinense Mill. and Abrus precatorius L., respectively, have higher binding affinities with target protein in docking simulation than control. They have stable H-bonds with residues A:Lys311 and some other residues in both chains of PKM2 protein. Hence, we propose the TCM compounds, saussureamine C and precatorine, as potential candidates as lead compounds for further study in drug development process with the PKM2 protein against cancer.

In silico investigation of traditional Chinese medicine compounds to inhibit human histone deacetylase 2 for patients with Alzheimer's disease

Human histone deacetylase 2 (HDAC2) has been identified as being associated with Alzheimer's disease (AD), a neuropathic degenerative disease. In this study, we screen the world's largest Traditional Chinese Medicine (TCM) database for natural compounds that may be useful as lead compounds in the search for inhibitors of HDAC2 function. The technique of molecular docking was employed to select the ten top TCM candidates. We used three prediction models, multiple linear regression (MLR), support vector machine (SVM), and the Bayes network toolbox (BNT), to predict the bioactivity of the TCM candidates. Molecular dynamics simulation provides the protein-ligand interactions of compounds. The bioactivity predictions of pIC50 values suggest that the TCM candidatesm, (-)-Bontl ferulate, monomethylcurcumin, and ningposides C, have a greater effect on HDAC2 inhibition. The structure variation caused by the hydrogen bonds and hydrophobic interactions between protein-ligand interactions indicates that these compounds have an inhibitory effect on the protein.

Lead discovery for Alzheimer's disease related target protein RbAp48 from traditional Chinese medicine

Deficiency or loss of function of Retinoblastoma-associated proteins (RbAp48) is related with Alzheimer's disease (AD), and AD disease is associated with age-related memory loss. During normal function, RbAp48 forms a complex with the peptide FOG-1 (friend of GATA-1) and has a role in gene transcription, but an unstable complex may affect the function of RbAp48. This study utilizes the world's largest traditional Chinese medicine (TCM) database and virtual screening to provide potential compounds for RbAp48 binding. A molecular dynamics (MD) simulation was employed to understand the variations after protein-ligand interaction. FOG1 was found to exhibit low stability after RbAp48 binding; the peptide displayed significant movement from the initial docking position, a phenomenon which matched the docking results. The protein structure of the other TCM candidates was not variable during MD simulation and had a greater stable affinity for RbAp48 binding than FOG1. Our results reveal that the protein structure does not affect ligand binding, and the top three TCM candidates Bittersweet alkaloid II, Eicosandioic acid, and Perivine might resolve the instability of the RbAp48-FOG1 complex and thus be used in AD therapy.

In Silico Identification of Potent PPAR-γ Agonists from Traditional Chinese Medicine: A Bioactivity Prediction, Virtual Screening, and Molecular Dynamics Study

The peroxisome proliferator-activated receptors (PPARs) related to regulation of lipid metabolism, inflammation, cell proliferation, differentiation, and glucose homeostasis by controlling the related ligand-dependent transcription of networks of genes. They are used to be served as therapeutic targets against metabolic disorder, such as obesity, dyslipidemia, and diabetes; especially, PPAR-γ is the most extensively investigated isoform for the treatment of dyslipidemic type 2 diabetes. In this study, we filter compounds of traditional Chinese medicine (TCM) using bioactivities predicted by three distinct prediction models before the virtual screening. For the top candidates, the molecular dynamics (MD) simulations were also utilized to investigate the stability of interactions between ligand and PPAR-γ protein. The top two TCM candidates, 5-hydroxy-L-tryptophan and abrine, have an indole ring and carboxyl group to form the H-bonds with the key residues of PPAR-γ protein, such as residues Ser289 and Lys367. The secondary amine group of abrine also stabilized an H-bond with residue Ser289. From the figures of root mean square fluctuations (RMSFs), the key residues were stabilized in protein complexes with 5-Hydroxy-L-tryptophan and abrine as control. Hence, we propose 5-hydroxy-L-tryptophan and abrine as potential lead compounds for further study in drug development process with the PPAR-γ protein.

Computational design of apolipoprotein E4 inhibitors for Alzheimer's disease therapy from traditional Chinese medicine

Apolipoprotein E4 (Apo E4) is the major genetic risk factor in the causation of Alzheimer's disease (AD). In this study we utilize virtual screening of the world's largest traditional Chinese medicine (TCM) database and investigate potential compounds for the inhibition of ApoE4. We present the top three TCM candidates: Solapalmitine, Isodesacetyluvaricin, and Budmunchiamine L5 for further investigation. Dynamics analysis and molecular dynamics (MD) simulation were used to simulate protein-ligand complexes for observing the interactions and protein variations. Budmunchiamine L5 did not have the highest score from virtual screening; however, the dynamics pose is similar to the initial docking pose after MD simulation. Trajectory analysis reveals that Budmunchiamine L5 was stable over all simulation times. The migration distance of Budmunchiamine L5 illustrates that docked ligands are not variable from the initial docked site. Interestingly, Arg158 was observed to form H-bonds with Budmunchiamine L5 in the docking pose and MD snapshot, which indicates that the TCM compounds could stably bind to ApoE4. Our results show that Budmunchiamine L5 has good absorption, blood brain barrier (BBB) penetration, and less toxicity according to absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction and could, therefore, be safely used for developing novel ApoE4 inhibitors.

Finding inhibitors of mutant superoxide dismutase-1 for amyotrophic lateral sclerosis therapy from traditional chinese medicine

Superoxide dismutase type 1 (SOD1) mutations cause protein aggregation and decrease protein stability, which are linked to amyotrophic lateral sclerosis (ALS) disease. This research utilizes the world's largest traditional Chinese medicine (TCM) database to search novel inhibitors of mutant SOD1, and molecular dynamics (MD) simulations were used to analyze the stability of protein that interacted with docked ligands. Docking results show that hesperidin and 2,3,5,4'-tetrahydroxystilbene-2-O- β -D-glucoside (THSG) have high affinity to mutant SOD1 and then dopamine. For MD simulation analysis, hesperidin and THSG displayed similar value of RMSD with dopamine, and the migration analysis reveals stable fluctuation at the end of MD simulation time. Interestingly, distance between the protein and ligand has distinct difference, and hesperidin changes the position from initial binding site to the other place. In flexibility of residues analysis, the secondary structure among all complexes does not change, indicating that the structure are not affect ligand binding. The binding poses of hesperidin and THSG are similar to dopamine after molecular simulation. Our result indicated that hesperidin and THSG might be potential lead compound to design inhibitors of mutant SOD1 for ALS therapy.