It has become impossible to imagine the fields of biochemistry and medicinal chemistry without computational chemistry and molecular modelling techniques. In many steps of the drug development process in silico methods have become indispensable. Virtual screening (VS) can tremendously expedite the early discovery phase, whilst the use of molecular dynamics (MD) simulations forms a powerful additional tool to in vitro methods throughout the entire drug discovery process. In the field of biochemistry, MD has also become a compelling method for studying biophysical systems (e.g., protein folding) complementary to experimental techniques. However, both VS and MD come with their own limitations and methodological difficulties, from hardware limitations to restrictions in algorithmic capabilities. One solution to overcoming these difficulties lies in the field of machine learning (ML), and more specifically deep learning (DL). There are many ways in which DL can be applied to these molecular modelling techniques to achieve more accurate results in a more efficient manner or expedite the data analysis of the acquired results. Despite steadily increasing interest in DL amidst computational chemists, knowledge is still limited and scattered over different resources. This review is aimed at computational chemists with knowledge of molecular modelling, who wish to possibly integrate DL approaches in their research and already have a basic understanding of the fundamentals of DL. This review focusses on a survey of recent applications of DL in molecular modelling techniques. The different sections are logically subdivided, based on where DL is integrated in the research: (1) for the improvement of VS workflows, (2) for the improvement of certain workflows in MD simulations, (3) for aiding in the calculations of interatomic forces, or (4) for data analysis of MD trajectories. It will become clear that DL has the capacity to completely transform the way molecular modelling is carried out.

The role of LOXL2 in cancer has been widely demonstrated, but current therapies targeting LOXL2 are not yet fully developed. We believe that selective nature-derived inhibition of LOXL2 may provide a better therapeutic approach for the treatment of cancer. Therefore, we adopted a comprehensive approach combining deep learning and traditional computer-aided drug design methods to screen LOXL2 selective inhibitors. Bioactivity and affinity of the potential LOXL2 inhibitors were determined by molecular docking and virtual screening. At the same time, we experimentally tested the effect of potential LOXL2 inhibitors on cancer cells. Validation showed that it could inhibit proliferation and migration, promote apoptosis of CT26 cells, and reduce the expression level of LOXL2 protein. As a result, we identified a potent LOXL2 inhibitor: the natural product Forsythoside A, and demonstrated that Forsythoside A has an inhibitory effect on tumors.

Protein-protein interactions (PPIs) are central to the mechanisms of signaling pathways and immune responses, which can help us understand disease etiology. Therefore, there is a significant need for efficient and rapid automated approaches to predict changes in PPIs. In recent years, there has been a significant increase in applying deep learning techniques to predict changes in binding affinity between the original protein complex and its mutant variants. Particularly, the adoption of graph neural networks (GNNs) has gained prominence for their ability to learn representations of protein-protein complexes. However, the conventional GNNs have mainly concentrated on capturing local features, often disregarding the interactions among distant elements that hold potential important information. In this study, we have developed a transformer-based graph neural network to extract features of the mutant segment from the three-dimensional structure of protein-protein complexes. By embracing both local and global features, the approach ensures a more comprehensive understanding of the intricate relationships, thus promising more accurate predictions of binding affinity changes. To enhance the representation capability of protein features, we incorporate a large-scale pre-trained protein language model into our approach and employ the global protein feature it provides. The proposed model is shown to be able to predict the mutation changes in binding affinity with a root mean square error of 1.10 and a Pearson correlation coefficient of near 0.71, as demonstrated by performance on test and validation cases. Our experiments on all five datasets, including both single mutant and multiple mutant cases, demonstrate that our model outperforms four state-of-the-art baseline methods, and the efficacy was subjected to comprehensive experimental evaluation. Our study introduces a transformer-based graph neural network approach to accurately predict changes in protein-protein interactions (PPIs). By integrating local and global features and leveraging pretrained protein language models, our model outperforms state-of-the-art methods across diverse datasets. The results of this study can provide new views for studying immune responses and disease etiology related to protein mutations. Furthermore, this approach may contribute to other biological or biochemical studies related to PPIs.Scientific contribution Our scientific contribution lies in the development of a novel transformer-based graph neural network tailored to predict changes in protein-protein interactions (PPIs) with excellent accuracy. By seamlessly integrating both local and global features extracted from the three-dimensional structure of protein-protein complexes, and leveraging the rich representations provided by pretrained protein language models, our approach surpasses existing methods across diverse datasets. Our findings may offer novel insights for the understanding of complex disease etiology associated with protein mutations. The novel tool can be applicable to various biological and biochemical investigations involving protein mutations.

Natural Language Processing (NLP) has revolutionized the way computers are used to study and interact with human languages and is increasingly influential in the study of protein and ligand binding, which is critical for drug discovery and development. This review examines how NLP techniques have been adapted to decode the "language" of proteins and small molecule ligands to predict protein-ligand interactions (PLIs). We discuss how methods such as long short-term memory (LSTM) networks, transformers, and attention mechanisms can leverage different protein and ligand data types to identify potential interaction patterns. Significant challenges are highlighted including the scarcity of high-quality negative data, difficulties in interpreting model decisions, and sampling biases in existing data sets. We argue that focusing on improving data quality, enhancing model robustness, and fostering both collaboration and competition could catalyze future advances in machine-learning-based predictions of PLIs.

Phytophthora root and stem rot in soybeans results in substantial economic losses worldwide. In this study, a machine learning model based on a heterogeneous interaction graph attention network model was constructed. The PDBbind data set, comprising 13,285 complexes with experimental pKa or pKi values, was utilized to train and evaluate the model, which was subsequently employed to screen candidate compounds against chitin synthase of Phytophthora sojae (PsChs1) in the Traditional Chinese Medicine Systems Pharmacology database, comprising 14,249 compounds. High-scoring candidate compounds were docked with PsChs1 protein using Discovery Studio, and their interaction energies were evaluated. Molecular dynamic simulations spanning 50 ns were performed using GROMACS to explore the stability of the complexes, trajectory analysis was conducted with root-mean-square deviations, and the hydrogen bonds, radius of gyration, MMPBSA binding free energy, and binding modes were analyzed. MOL011832 and MOL011833 were identified as potential pesticides, both of which were present in the herb Schizonepeta through database retrieval. The inhibitory effects of an ethanol extract of Schizonepeta against P. sojae were subsequently explored and confirmed in biological experiments. Overall, this study proves the feasibility and high efficiency of pesticide discovery using graph neural network-based models.

In the realm of drug discovery and design, the accurate prediction of protein-ligand binding affinity is of paramount importance as it underpins the functional interactions within biological systems. This study introduces a novel self-supervised learning (SSL) framework that combines contrastive learning and graph neural networks (CL-GNN) for predicting protein-ligand binding affinities, which is a critical aspect of drug discovery. Traditional methods for affinity prediction are expensive and time-consuming, prompting the development of more efficient computational approaches. CL-GNN utilizes a contrastive learning strategy, a form of SSL, to learn from a large data set of 371 458 unique unlabeled protein-ligand complexes. By employing graph neural networks and molecular graph enhancement techniques, the model effectively captures protein-ligand interactions in a self-supervised manner. The fine-tuned model demonstrates competitive performance, achieving high Pearson's correlation coefficients and low root-mean-square errors on benchmark data sets. The proposed method outperforms existing machine learning models, showcasing its potential for accelerating the drug development process. The method effectively quantifies the similarity between protein-ligand complex representations learned in the pretraining and downstream testing phases through cosine similarity assessment. This approach not only revealed potential connections between complexes in their binding properties but also provided new insights into the understanding of drug mechanisms of action. In addition, the transparency of the model is significantly improved by visualizing the importance of key protein residues and ligand atoms. This visualization tool provides insight into the model's predictive decision-making process, providing key biological insights for drug design and optimization.

A novel concept of quantifying graph non-isomorphism is introduced to measure structural differences between graphs, and thus overcoming the strict limitations of traditional graph isomorphism tests. This paper trains Graph Neural Networks (GNNs) and graph kernels to classify urban road networks and proposes using graph classification accuracy as a metric to quantify graph non-isomorphism. Experimental results demonstrate that Edge Convolutional Neural Network (EdgeCNN) not only leverages node attributes effectively but also fully utilizes edge features, achieving an 85% classification accuracy, which surpasses that of the Weisfeiler-Lehman (WL) kernel algorithm (80%). This finding challenges the claim that "GNNs are at most as powerful as the WL test in distinguishing graph structures." Furthermore, the paper explores the non-isomorphism of 10,361 road networks from 30 cities worldwide, providing valuable insights for future urban development.

The binding between proteins and ligands plays a crucial role in the field of drug discovery. However, this area currently faces numerous challenges. On one hand, existing methods are constrained by the limited availability of labeled data, often performing inadequately when addressing complex protein-ligand interactions. On the other hand, many models struggle to effectively capture the flexible variations and relative spatial relationships between proteins and ligands. These issues not only significantly hinder the advancement of protein-ligand binding research but also adversely affect the accuracy and efficiency of drug discovery. Therefore, in response to these challenges, our study aims to enhance predictive capabilities through innovative approaches, providing more reliable support for drug discovery efforts.

This study leverages a pre-trained model with spatial awareness to enhance the prediction of protein-ligand binding affinity. By perturbing the structures of small molecules in a manner consistent with physical constraints and employing self-supervised tasks, we improve the representation of small molecule structures, allowing for better adaptation to affinity predictions. Meanwhile, our approach enables the identification of potential binding sites on proteins.

Our model demonstrates a significantly higher correlation coefficient in binding affinity predictions. Extensive evaluation on the PDBBind v2019 refined set, CASF, and Merck FEP benchmarks confirms the model's robustness and strong generalization across diverse datasets. Additionally, the model achieves over 95% in classification ROC for binding site identification, underscoring its high accuracy in pinpointing protein-ligand interaction regions.

This research presents a novel approach that not only enhances the accuracy of binding affinity predictions but also facilitates the identification of binding sites, showcasing the potential of pre-trained models in computational drug design. Data and code are available at https://github.com/MIALAB-RUC/SableBind .

Molecular Docking is a critical task in structure-based virtual screening. Recent advancements have showcased the efficacy of diffusion-based generative models for blind docking tasks. However, these models do not inherently estimate protein-ligand binding strength thus cannot be directly applied to virtual screening tasks. Protein-ligand scoring functions serve as fast and approximate computational methods to evaluate the binding strength between the protein and ligand. In this work, we introduce normalized mixture density network (NMDN) score, a deep learning (DL)-based scoring function learning the probability density distribution of distances between protein residues and ligand atoms. The NMDN score addresses limitations observed in existing DL scoring functions and performs robustly in both pose selection and virtual screening tasks. Additionally, we incorporate an interaction module to predict the experimental binding affinity score to fully utilize the learned protein and ligand representations. Finally, we present an end-to-end blind docking and virtual screening protocol named DiffDock-NMDN. For each protein-ligand pair, we employ DiffDock to sample multiple poses, followed by utilizing the NMDN score to select the optimal binding pose, and estimating the binding affinity using scoring functions. Our protocol achieves an average enrichment factor of 4.96 on the LIT-PCBA data set, proving effective in real-world drug discovery scenarios where binder information is limited. This work not only presents a robust DL-based scoring function with superior pose selection and virtual screening capabilities but also offers a blind docking protocol and benchmarks to guide future scoring function development.

Molecular Property Prediction (MPP) is a fundamental task in important research fields such as chemistry, materials, biology, and medicine, where traditional computational chemistry methods based on quantum mechanics often consume substantial time and computing power. In recent years, machine learning has been increasingly used in computational chemistry, in which graph neural networks have shown good performance in molecular property prediction tasks, but they have some limitations in terms of generalizability, interpretability, and certainty. In order to address the above challenges, a Multiscale Molecular Structural Neural Network (MMSNet) is proposed in this paper, which obtains rich multiscale molecular representations through the information fusion between bonded and non-bonded "message passing" structures at the atomic scale and spatial feature information "encoder-decoder" structures at the molecular scale; a multi-level attention mechanism is introduced on the basis of theoretical analysis of molecular mechanics in order to enhance the model's interpretability; the prediction results of MMSNet are used as label values and clustered in the molecular library by the K-NN (K-Nearest Neighbors) algorithm to reverse match the spatial structure of the molecules, and the certainty of the model is quantified by comparing virtual screening results across different K-values. Experimental results in the authoritative small molecule dataset QM9 and the macromolecular protein database PDBbind demonstrate that MMSNet has optimal prediction accuracy, model complexity, and generalizability compared with more than ten existing state-of-the-art (SOTA) models in a variety of different types of prediction tasks; it has a great potential for downstream tasks such as chemical research, drug discovery, and material design.

Protein-protein interactions (PPIs) play a crucial role in numerous biochemical and biological processes. Although several structure-based molecular generative models have been developed, PPI interfaces and compounds targeting PPIs exhibit distinct physicochemical properties compared to traditional binding pockets and small-molecule drugs. As a result, generating compounds that effectively target PPIs, particularly by considering PPI complexes or interface hotspot residues, remains a significant challenge. In this work, we constructed a comprehensive dataset of PPI interfaces with active and inactive compound pairs. Based on this, we propose a novel molecular generative framework tailored to PPI interfaces, named GENiPPI. Our evaluation demonstrates that GENiPPI captures the implicit relationships between the PPI interfaces and the active molecules, and can generate novel compounds that target these interfaces. Moreover, GENiPPI can generate structurally diverse novel compounds with limited PPI interface modulators. To the best of our knowledge, this is the first exploration of a structure-based molecular generative model focused on PPI interfaces, which could facilitate the design of PPI modulators. The PPI interface-based molecular generative model enriches the existing landscape of structure-based (pocket/interface) molecular generative model. SCIENTIFIC CONTRIBUTION: This study introduces GENiPPI, a protein-protein interaction (PPI) interface-aware molecular generative framework. The framework first employs Graph Attention Networks to capture atomic-level interaction features at the protein complex interface. Subsequently, Convolutional Neural Networks extract compound representations in voxel and electron density spaces. These features are integrated into a Conditional Wasserstein Generative Adversarial Network, which trains the model to generate compound representations targeting PPI interfaces. GENiPPI effectively captures the relationship between PPI interfaces and active/inactive compounds. Furthermore, in fewshot molecular generation, GENiPPI successfully generates compounds comparable to known disruptors. GENiPPI provides an efficient tool for structure-based design of PPI modulators.

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.

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Accurate prediction of protein-ligand binding affinities can significantly advance the development of drug discovery. Several graph neural network (GNN)-based methods learn representations of protein-ligand complexes via modeling intermolecule interactions and spatial structures (e.g., distances and angles) of complexes. However, these methods fail to emphasize the importance of bonds and learn hierarchical structures of complexes, which are significant for binding affinity prediction. In this article, we propose the structure-aware graph attention diffusion network (SGADN) to incorporate both distance and angle information for efficient spatial structure learning. We model complexes as line graphs with distance and angle information, focusing on bonds as nodes. Then we perform line graph attention diffusion layers (LGADLs) on line graphs to explore long-range bond node interactions and enhance spatial structure learning. Furthermore, we propose an attentive pooling layer (APL) to refine the hierarchical structures in complexes. Extensive experimental studies on two benchmarks demonstrate the superiority of SGADN for binding affinity prediction.

The prediction of drug-target interactions (DTI) is a crucial preliminary stage in drug discovery and development, given the substantial risk of failure and the prolonged validation period associated with in vitro and in vivo experiments. In the contemporary landscape, various machine learning-based methods have emerged as indispensable tools for DTI prediction. This paper begins by placing emphasis on the data representation employed by these methods, delineating five representations for drugs and four for proteins. The methods are then categorized into traditional machine learning-based approaches and deep learning-based ones, with a discussion of representative approaches in each category and the introduction of a novel taxonomy for deep neural network models in DTI prediction. Additionally, we present a synthesis of commonly used datasets and evaluation metrics to facilitate practical implementation. In conclusion, we address current challenges and outline potential future directions in this research field.

The investigation of molecular interactions between ligands and their target molecules is becoming more significant as protein structure data continues to develop. In this study, we introduce PLA-STGCNnet, a deep fusion spatial-temporal graph neural network designed to study protein-ligand interactions based on the 3D structural data of protein-ligand complexes. Unlike 1D protein sequences or 2D ligand graphs, the 3D graph representation offers a more precise portrayal of the complex interactions between proteins and ligands. Research studies have shown that our fusion model, PLA-STGCNnet, outperforms individual algorithms in accurately predicting binding affinity. The advantage of a fusion model is the ability to fully combine the advantages of multiple different models and improve overall performance by combining their features and outputs. Our fusion model shows satisfactory performance on different data sets, which proves its generalization ability and stability. The fusion-based model showed good performance in protein-ligand affinity prediction, and we successfully applied the model to drug screening. Our research underscores the promise of fusion spatial-temporal graph neural networks in addressing complex challenges in protein-ligand affinity prediction. The Python scripts for implementing various model components are accessible at https://github.com/ligaili01/PLA-STGCN.

Deep learning-based drug-target affinity (DTA) prediction methods have shown impressive performance, despite a high number of training parameters relative to the available data. Previous studies have highlighted the presence of dataset bias by suggesting that models trained solely on protein or ligand structures may perform similarly to those trained on complex structures. However, these studies did not propose solutions and focused solely on analyzing complex structure-based models. Even when ligands are excluded, protein-only models trained on complex structures still incorporate some ligand information at the binding sites. Therefore, it is unclear whether binding affinity can be accurately predicted using only compound or protein features due to potential dataset bias. In this study, we expanded our analysis to comprehensive databases and investigated dataset bias through compound and protein feature-based methods using multilayer perceptron models. We assessed the impact of this bias on current prediction models and proposed the binding affinity similarity explorer (BASE) web service, which provides bias-reduced datasets.

By analyzing eight binding affinity databases using multilayer perceptron models, we confirmed a bias where the compound-protein binding affinity can be accurately predicted using compound features alone. This bias arises because most compounds show consistent binding affinities due to high sequence or functional similarity among their target proteins. Our Uniform Manifold Approximation and Projection analysis based on compound fingerprints further revealed that low and high variation compounds do not exhibit significant structural differences. This suggests that the primary factor driving the consistent binding affinities is protein similarity rather than compound structure. We addressed this bias by creating datasets with progressively reduced protein similarity between the training and test sets, observing significant changes in model performance. We developed the BASE web service to allow researchers to download and utilize these datasets. Feature importance analysis revealed that previous models heavily relied on protein features. However, using bias-reduced datasets increased the importance of compound and interaction features, enabling a more balanced extraction of key features.

We propose the BASE web service, providing both the affinity prediction results of existing models and bias-reduced datasets. These resources contribute to the development of generalized and robust predictive models, enhancing the accuracy and reliability of DTA predictions in the drug discovery process. BASE is freely available online at https://synbi2024.kaist.ac.kr/base .

Accurate prediction of protein-ligand binding affinities is an essential challenge in structure-based drug design. Despite recent advances in data-driven methods for affinity prediction, their accuracy is still limited, partially because they only take advantage of static crystal structures while the actual binding affinities are generally determined by the thermodynamic ensembles between proteins and ligands. One effective way to approximate such a thermodynamic ensemble is to use molecular dynamics (MD) simulation. Here, an MD dataset containing 3,218 different protein-ligand complexes is curated, and Dynaformer, a graph-based deep learning model is further developed to predict the binding affinities by learning the geometric characteristics of the protein-ligand interactions from the MD trajectories. In silico experiments demonstrated that the model exhibits state-of-the-art scoring and ranking power on the CASF-2016 benchmark dataset, outperforming the methods hitherto reported. Moreover, in a virtual screening on heat shock protein 90 (HSP90) using Dynaformer, 20 candidates are identified and their binding affinities are further experimentally validated. Dynaformer displayed promising results in virtual drug screening, revealing 12 hit compounds (two are in the submicromolar range), including several novel scaffolds. Overall, these results demonstrated that the approach offer a promising avenue for accelerating the early drug discovery process.

The rapidly advancing field of artificial intelligence (AI) has garnered substantial attention for its potential application in drug discovery and development. This opinion review critically examined the feasibility and prospects of integrating AI as a transformative tool in the pharmaceutical industry. AI, encompassing machine learning algorithms, deep learning, and data analytics, offers unprecedented opportunities to streamline and enhance various stages of drug development. This opinion review delved into the current landscape of AI-driven approaches, discussing their utilization in target identification, lead optimization, and predictive modeling of pharmacokinetics and toxicity. We aimed to scrutinize the integration of large-scale omics data, electronic health records, and chemical informatics, highlighting the power of AI in uncovering novel therapeutic targets and accelerating drug repurposing strategies. Despite the considerable potential of AI, the review also addressed inherent challenges, including data privacy concerns, interpretability of AI models, and the need for robust validation in real-world clinical settings. Additionally, we explored ethical considerations surrounding AI-driven decision-making in drug development. This opinion review provided a nuanced perspective on the transformative role of AI in drug discovery by discussing the existing literature and emerging trends, presenting critical insights and addressing potential hurdles. In conclusion, this study aimed to stimulate discourse within the scientific community and guide future endeavors to harness the full potential of AI in drug development.

Due to its essential roles in cell proliferation and apoptosis, the precise regulation of the Hippo pathway through LATS presents a viable biological target for developing new drugs for cancer and regenerative diseases. However, currently available probes for selective and highly drug-like inhibition of LATS require further improvement in terms of both activity, selectivity and drug-like properties. Through scaffold hopping aided by docking studies and AI-assisted prediction of metabolic stabilities, we successfully identified an advanced LATS inhibitor demonstrating potent kinase activity, exceptional selectivity against other kinases, and superior oral pharmacokinetic profiles.

Drug target interaction prediction is a crucial stage in drug discovery. However, brute-force search over a compound database is financially infeasible. We have witnessed the increasing measured drug-target interactions records in recent years, and the rich drug/protein-related information allows the usage of graph machine learning. Despite the advances in deep learning-enabled drug-target interaction, there are still open challenges: (1) rich and complex relationship between drugs and proteins can be explored; (2) the intermediate node is not calibrated in the heterogeneous graph. To tackle with above issues, this paper proposed a framework named DSG-DTI. Specifically, DSG-DTI has the heterogeneous graph autoencoder and heterogeneous attention network-based Matrix Completion. Our framework ensures that the known types of nodes (e.g., drug, target, side effects, diseases) are precisely embedded into high-dimensional space with our pretraining skills. Also, the attention-based heterogeneous graph-based matrix completion achieves highly competitive results via effective long-range dependencies extraction. We verify our model on two public benchmarks. The result of two publicly available benchmark application programs show that the proposed scheme effectively predicts drug-target interactions and can generalize to newly registered drugs and targets with slight performance degradation, outperforming the best accuracy compared with other baselines.

Binding affinity prediction of three-dimensional (3D) protein-ligand complexes is critical for drug repositioning and virtual drug screening. Existing approaches usually transform a 3D protein-ligand complex to a two-dimensional (2D) graph, and then use graph neural networks (GNNs) to predict its binding affinity. However, the node and edge features of the 2D graph are extracted based on invariant local coordinate systems of the 3D complex. As a result, these approaches can not fully learn the global information of the complex, such as the physical symmetry and the topological information of bonds. To address these issues, we propose a novel Equivariant Line Graph Network (ELGN) for binding affinity prediction of 3D protein-ligand complexes. The proposed ELGN firstly adds a super node to the 3D complex, and then builds a line graph based on the 3D complex. After that, ELGN uses a new E(3)-equivariant network layer to pass the messages between nodes and edges based on the global coordinate system of the 3D complex. Experimental results on two real datasets demonstrate the effectiveness of ELGN over several state-of-the-art baselines.

Identification of interactions between chemical compounds and proteins is crucial for various applications, including drug discovery, target identification, network pharmacology, and elucidation of protein functions. Deep neural network-based approaches are becoming increasingly popular in efficiently identifying compound-protein interactions with high-throughput capabilities, narrowing down the scope of candidates for traditional labor-intensive, time-consuming and expensive experimental techniques. In this study, we proposed an end-to-end approach termed SPVec-SGCN-CPI, which utilized simplified graph convolutional network (SGCN) model with low-dimensional and continuous features generated from our previously developed model SPVec and graph topology information to predict compound-protein interactions. The SGCN technique, dividing the local neighborhood aggregation and nonlinearity layer-wise propagation steps, effectively aggregates K-order neighbor information while avoiding neighbor explosion and expediting training. The performance of the SPVec-SGCN-CPI method was assessed across three datasets and compared against four machine learning- and deep learning-based methods, as well as six state-of-the-art methods. Experimental results revealed that SPVec-SGCN-CPI outperformed all these competing methods, particularly excelling in unbalanced data scenarios. By propagating node features and topological information to the feature space, SPVec-SGCN-CPI effectively incorporates interactions between compounds and proteins, enabling the fusion of heterogeneity. Furthermore, our method scored all unlabeled data in ChEMBL, confirming the top five ranked compound-protein interactions through molecular docking and existing evidence. These findings suggest that our model can reliably uncover compound-protein interactions within unlabeled compound-protein pairs, carrying substantial implications for drug re-profiling and discovery. In summary, SPVec-SGCN demonstrates its efficacy in accurately predicting compound-protein interactions, showcasing potential to enhance target identification and streamline drug discovery processes.Scientific contributionsThe methodology presented in this work not only enables the comparatively accurate prediction of compound-protein interactions but also, for the first time, take sample imbalance which is very common in real world and computation efficiency into consideration simultaneously, accelerating the target identification and drug discovery process.

Predicting protein-ligand binding affinity is crucial in new drug discovery and development. However, most existing models rely on acquiring 3D structures of elusive proteins. Combining amino acid sequences with ligand sequences and better highlighting active sites are also significant challenges.

We propose an innovative neural network model called DEAttentionDTA, based on dynamic word embeddings and a self-attention mechanism, for predicting protein-ligand binding affinity. DEAttentionDTA takes the 1D sequence information of proteins as input, including the global sequence features of amino acids, local features of the active pocket site, and linear representation information of the ligand molecule in the SMILE format. These three linear sequences are fed into a dynamic word-embedding layer based on a 1D convolutional neural network for embedding encoding and are correlated through a self-attention mechanism. The output affinity prediction values are generated using a linear layer. We compared DEAttentionDTA with various mainstream tools and achieved significantly superior results on the same dataset. We then assessed the performance of this model in the p38 protein family.

The resource codes are available at https://github.com/whatamazing1/DEAttentionDTA.

Identifying drug-target interactions (DTI) is crucial in drug discovery. Fragments are less complex and can accurately characterize local features, which is important in DTI prediction. Recently, deep learning (DL)-based methods predict DTI more efficiently. However, two challenges remain in existing DL-based methods: (i) some methods directly encode drugs and proteins into integers, ignoring the substructure representation; (ii) some methods learn the features of the drugs and proteins separately instead of considering their interactions.

In this article, we propose a fragment-oriented method based on a multihead cross attention mechanism for predicting DTI, named FMCA-DTI. FMCA-DTI obtains multiple types of fragments of drugs and proteins by branch chain mining and category fragment mining. Importantly, FMCA-DTI utilizes the shared-weight-based multihead cross attention mechanism to learn the complex interaction features between different fragments. Experiments on three benchmark datasets show that FMCA-DTI achieves significantly improved performance by comparing it with four state-of-the-art baselines.

The code for this workflow is available at: https://github.com/jacky102022/FMCA-DTI.

Developing new pharmaceuticals is a costly and time-consuming endeavor fraught with significant safety risks. A critical aspect of drug research and disease therapy is discerning the existence of interactions between drugs and proteins. The evolution of deep learning (DL) in computer science has been remarkably aided in this regard in recent years. Yet, two challenges remain: (i) balancing the extraction of profound, local cohesive characteristics while warding off gradient disappearance and (ii) globally representing and understanding the interactions between the drug and target local attributes, which is vital for delivering molecular level insights indispensable to drug development. In response to these challenges, we propose a DL network structure, MolLoG, primarily comprising two modules: local feature encoders (LFE) and global interactive learning (GIL). Within the LFE module, graph convolution networks and leap blocks capture the local features of drug and protein molecules, respectively. The GIL module enables the efficient amalgamation of feature information, facilitating the global learning of feature structural semantics and procuring multihead attention weights for abstract features stemming from two modalities, providing biologically pertinent explanations for black-box results. Finally, predictive outcomes are achieved by decoding the unified representation via a multilayer perceptron. Our experimental analysis reveals that MolLoG outperforms several cutting-edge baselines across four data sets, delivering superior overall performance and providing satisfactory results when elucidating various facets of drug-target interaction predictions.

Accurate prediction of protein-ligand binding affinity (PLA) is important for drug discovery. Recent advances in applying graph neural networks have shown great potential for PLA prediction. However, existing methods usually neglect the geometric information (i.e. bond angles), leading to difficulties in accurately distinguishing different molecular structures. In addition, these methods also pose limitations in representing the binding process of protein-ligand complexes. To address these issues, we propose a novel geometry-enhanced mid-fusion network, named GEMF, to learn comprehensive molecular geometry and interaction patterns. Specifically, the GEMF consists of a graph embedding layer, a message passing phase, and a multi-scale fusion module. GEMF can effectively represent protein-ligand complexes as graphs, with graph embeddings based on physicochemical and geometric properties. Moreover, our dual-stream message passing framework models both covalent and non-covalent interactions. In particular, the edge-update mechanism, which is based on line graphs, can fuse both distance and angle information in the covalent branch. In addition, the communication branch consisting of multiple heterogeneous interaction modules is developed to learn intricate interaction patterns. Finally, we fuse the multi-scale features from the covalent, non-covalent, and heterogeneous interaction branches. The extensive experimental results on several benchmarks demonstrate the superiority of GEMF compared with other state-of-the-art methods.

Binding of blood components to collagen was proved to be a key step in thrombus formation. Intelligent Design of Protein Matcher (IDProMat), a neural network model, was then developed based on the principle of seq2seq to design an antithrombotic peptide targeting collagen. The encoding and decoding of peptide sequence data and the interaction patterns of peptide chains at the interface were studied, and then, IDProMat was applied to the design of peptides to cover collagen. The 99.3% decrease in seq2seq loss and 58.3% decrease in MLP loss demonstrated that IDProMat learned the interaction patterns between residues at the binding interface. An efficient peptide, LRWNSYY, was then designed using this model. Validations on its binding on collagen and its inhibition of platelet adhesion were obtained using docking, MD simulations, and experimental approaches.

Developing new drugs is costly, time-consuming, and risky. Drug-target affinity (DTA), indicating the binding capability between drugs and target proteins, is a crucial indicator for drug development. Accurately predicting interaction strength between new drug-target pairs by analyzing previous experiments aids in screening potential drug molecules, repurposing them, and developing safe and effective medicines. Existing computational models for DTA prediction rely on strings or single-graph neural networks, lacking consideration of protein structure and molecular semantic information, leading to limited accuracy. Our experiments demonstrate that string-based methods may overlook protein conformations, causing a high root mean square error (RMSE) of 3.584 in affinity due to a lack of spatial context. Single graph networks also underperform on topology features, with a 6% lower confidence interval (CI) for activity classification. Absent semantic information also limits generalization across diverse compounds, resulting in 18% increment in RMSE and 5% in misclassifications within quantifications study, restricting potential drug discovery. To address these limitations, we propose G-K BertDTA, a novel framework for accurate DTA prediction incorporating protein features, molecular semantic features, and molecular structural information. In this proposed model, we represent drugs as graphs, with a GIN employed to learn the molecular topological information. For the extraction of protein structural features, we utilize a DenseNet architecture. A knowledge-based BERT semantic model is incorporated to obtain rich pre-trained semantic embeddings, thereby enhancing the feature information. We extensively evaluated our proposed approach on the publicly available benchmark datasets (i.e., KIBA and Davis), and experimental results demonstrate the promising performance of our method, which consistently outperforms previous state-of-the-art approaches. Code is available at https://github.com/AmbitYuki/G-K-BertDTA.

Virtual screening (VS) is an integral and ever-evolving domain of drug discovery framework. The VS is traditionally classified into ligand-based (LB) and structure-based (SB) approaches. Machine intelligence or artificial intelligence has wide applications in the drug discovery domain to reduce time and resource consumption. In combination with machine intelligence algorithms, VS has emerged into revolutionarily progressive technology that learns within robust decision orders for data curation and hit molecule screening from large VS libraries in minutes or hours. The exponential growth of chemical and biological data has evolved as "big-data" in the public domain demands modern and advanced machine intelligence-driven VS approaches to screen hit molecules from ultra-large VS libraries. VS has evolved from an individual approach (LB and SB) to integrated LB and SB techniques to explore various ligand and target protein aspects for the enhanced rate of appropriate hit molecule prediction. Current trends demand advanced and intelligent solutions to handle enormous data in drug discovery domain for screening and optimizing hits or lead with fewer or no false positive hits. Following the big-data drift and tremendous growth in computational architecture, we presented this review. Here, the article categorized and emphasized individual VS techniques, detailed literature presented for machine learning implementation, modern machine intelligence approaches, and limitations and deliberated the future prospects.

Protein-ligand binding affinity prediction plays an important role in the field of drug discovery. Existing deep learning-based approaches have significantly improved the efficiency of protein-ligand binding affinity prediction through their excellent inductive bias capability. However, these methods only focus on fragmented three-dimensional data, which truncates the integrity of pocket data, leading to the neglect of potential long-range interactions. In this paper, we propose a dual-stream framework, with amino acid sequence assisting the atomic data fusion for graph neural network (termed SadNet), to fuse both 3D atomic data and sequence data for more accurate prediction results. In detail, SadNet consists of a pocket module and a sequence module. The sequence module expands the "receptive field" of the pocket module through a mid-term virtual node fusion. To better integrate sequence-level information from the sequence module and 3D structural information from the pocket module, we incorporate structural information for each amino acid within the sequence module. Besides, to better understand the intrinsic relationship between sequences and 3D atomic information, our SadNet utilizes information stacking from both the early stage and later stage. Experimental results on publicly available benchmark datasets demonstrate the superiority of the proposed dual-stream approach over the state-of-the-art alternatives. The code of this work is available online at https://github.com/wardhong/SadNet.

A central problem in drug discovery is to identify the interactions between drug-like compounds and protein targets. Over the past few decades, various quantitative structure-activity relationship (QSAR) and proteo-chemometric (PCM) approaches have been developed to model and predict these interactions. While QSAR approaches solely utilize representations of the drug compound, PCM methods incorporate both representations of the protein target and the drug compound, enabling them to achieve above-chance predictive accuracy on previously unseen protein targets. Both QSAR and PCM approaches have recently been improved by machine learning and deep neural networks, that allow the development of drug-target interaction prediction models from measurement data. However, deep neural networks typically require large amounts of training data and cannot robustly adapt to new tasks, such as predicting interaction for unseen protein targets at inference time. In this work, we propose to use HyperNetworks to efficiently transfer information between tasks during inference and thus to accurately predict drug-target interactions on unseen protein targets. Our HyperPCM method reaches state-of-the-art performance compared to previous methods on multiple well-known benchmarks, including Davis, DUD-E, and a ChEMBL derived data set, and particularly excels at zero-shot inference involving unseen protein targets. Our method, as well as reproducible data preparation, is available at https://github.com/ml-jku/hyper-dti.

Water network rearrangement from the ligand-unbound state to the ligand-bound state is known to have significant effects on the protein-ligand binding interactions, but most of the current machine learning-based scoring functions overlook these effects. In this study, we endeavor to construct a comprehensive and realistic deep learning model by incorporating water network information into both ligand-unbound and -bound states. In particular, extended connectivity interaction features were integrated into graph representation, and graph transformer operator was employed to extract features of the ligand-unbound and -bound states. Through these efforts, we developed a water network-augmented two-state model called ECIFGraph::HM-Holo-Apo. Our new model exhibits satisfactory performance in terms of scoring, ranking, docking, screening, and reverse screening power tests on the CASF-2016 benchmark. In addition, it can achieve superior performance in large-scale docking-based virtual screening tests on the DEKOIS2.0 data set. Our study highlights that the use of a water network-augmented two-state model can be an effective strategy to bolster the robustness and applicability of machine learning-based scoring functions, particularly for targets with hydrophilic or solvent-exposed binding pockets.

The pKa of C-H acids is an important parameter in the fields of organic synthesis, drug discovery, and materials science. However, the prediction of pKa is still a great challenge due to the limit of experimental data and the lack of chemical insight. Here, a new model for predicting the pKa values of C-H acids is proposed on the basis of graph neural networks (GNNs) and data augmentation. A message passing unit (MPU) was used to extract the topological and target-related information from the molecular graph data, and a readout layer was utilized to retrieve the information on the ionization site C atom. The retrieved information then was adopted to predict pKa by a fully connected network. Furthermore, to increase the diversity of the training data, a knowledge-infused data augmentation technique was established by replacing the H atoms in a molecule with substituents exhibiting different electronic effects. The MPU was pretrained with the augmented data. The efficacy of data augmentation was confirmed by visualizing the distribution of compounds with different substituents and by classifying compounds. The explainability of the model was studied by examining the change of pKa values when a specific atom was masked. This explainability was used to identify the key substituents for pKa. The model was evaluated on two data sets from the iBonD database. Dataset1 includes the experimental pKa values of C-H acids measured in DMSO, while dataset2 comprises the pKa values measured in water. The results show that the knowledge-infused data augmentation technique greatly improves the predictive accuracy of the model, especially when the number of samples is small.

Predicting protein-ligand binding affinity is a central issue in drug design. Various deep learning models have been published in recent years, where many of them rely on 3D protein-ligand complex structures as input and tend to focus on the single task of reproducing binding affinity. In this study, we have developed a graph neural network model called PLANET (Protein-Ligand Affinity prediction NETwork). This model takes the graph-represented 3D structure of the binding pocket on the target protein and the 2D chemical structure of the ligand molecule as input. It was trained through a multi-objective process with three related tasks, including deriving the protein-ligand binding affinity, protein-ligand contact map, and ligand distance matrix. Besides the protein-ligand complexes with known binding affinity data retrieved from the PDBbind database, a large number of non-binder decoys were also added to the training data for deriving the final model of PLANET. When tested on the CASF-2016 benchmark, PLANET exhibited a scoring power comparable to the best result yielded by other deep learning models as well as a reasonable ranking power and docking power. In virtual screening trials conducted on the DUD-E benchmark, PLANET's performance was notably better than several deep learning and machine learning models. As on the LIT-PCBA benchmark, PLANET achieved comparable accuracy as the conventional docking program Glide, but it only spent less than 1% of Glide's computation time to finish the same job because PLANET did not need exhaustive conformational sampling. Considering the decent accuracy and efficiency of PLANET in binding affinity prediction, it may become a useful tool for conducting large-scale virtual screening.

Nucleic acid-based therapies are seeing a spiralling surge. Stimuli-responsive polymers, especially pH-responsive ones, are gaining widespread attention because of their ability to efficiently deliver nucleic acids. These polymers can be synthesized and modified according to target requirements, such as delivery sites and the nature of nucleic acids. In this regard, the endosomal escape mechanism of polymer-nucleic acid complexes (polyplexes) remains a topic of considerable interest owing to various plausible escape mechanisms. This review describes current progress in the endosomal escape mechanism of polyplexes and state-of-the-art chemical designs for pH-responsive polymers. The importance is also discussed of the acid dissociation constant (i.e., pKa) in designing the new generation of pH-responsive polymers, along with assays to monitor and quantify the endosomal escape behavior. Further, the use of machine learning is addressed in pKa prediction and polymer design to find novel chemical structures for pH responsiveness. This review will facilitate the design of new pH-responsive polymers for advanced and efficient nucleic acid delivery.

Improving the generalization ability of scoring functions remains a major challenge in protein-ligand binding affinity prediction. Many machine learning methods are limited by their reliance on single-modal representations, hindering a comprehensive understanding of protein-ligand interactions. We introduce a graph-neural-network-based scoring function that utilizes a triplet contrastive learning loss to improve protein-ligand representations. In this model, three-dimensional complex representations and the fusion of two-dimensional ligand and coarse-grained pocket representations converge while distancing from decoy representations in latent space. After rigorous validation on multiple external data sets, our model exhibits commendable generalization capabilities compared to those of other deep learning-based scoring functions, marking it as a promising tool in the realm of drug discovery. In the future, our training framework can be extended to other biophysical- and biochemical-related problems such as protein-protein interaction and protein mutation prediction.

Atomic structure prediction and associated property calculations are the bedrock of chemical physics. Since high-fidelity ab initio modeling techniques for computing the structure and properties can be prohibitively expensive, this motivates the development of machine-learning (ML) models that make these predictions more efficiently. Training graph neural networks over large atomistic databases introduces unique computational challenges, such as the need to process millions of small graphs with variable size and support communication patterns that are distinct from learning over large graphs, such as social networks. We demonstrate a novel hardware-software codesign approach to scale up the training of atomistic graph neural networks (GNN) for structure and property prediction. First, to eliminate redundant computation and memory associated with alternative padding techniques and to improve throughput via minimizing communication, we formulate the effective coalescing of the batches of variable-size atomistic graphs as the bin packing problem and introduce a hardware-agnostic algorithm to pack these batches. In addition, we propose hardware-specific optimizations, including a planner and vectorization for the gather-scatter operations targeted for Graphcore's Intelligence Processing Unit (IPU), as well as model-specific optimizations such as merged communication collectives and optimized softplus. Putting these all together, we demonstrate the effectiveness of the proposed codesign approach by providing an implementation of a well-established atomistic GNN on the Graphcore IPUs. We evaluate the training performance on multiple atomistic graph databases with varying degrees of graph counts, sizes, and sparsity. We demonstrate that such a codesign approach can reduce the training time of atomistic GNNs and can improve their performance by up to 1.5× compared to the baseline implementation of the model on the IPUs. Additionally, we compare our IPU implementation with a Nvidia GPU-based implementation and show that our atomistic GNN implementation on the IPUs can run 1.8× faster on average compared to the execution time on the GPUs.

Rational structure-based drug design relies on accurate predictions of protein-ligand binding affinity from structural molecular information. Although deep learning-based methods for predicting binding affinity have shown promise in computational drug design, certain approaches have faced criticism for their potential to inadequately capture the fundamental physical interactions between ligands and their macromolecular targets or for being susceptible to dataset biases. Herein, we propose to include bond-critical points based on the electron density of a protein-ligand complex as a fundamental physical representation of protein-ligand interactions. Employing a geometric deep learning model, we explore the usefulness of these bond-critical points to predict absolute binding affinities of protein-ligand complexes, benchmark model performance against existing methods, and provide a critical analysis of this new approach. The models achieved root-mean-squared errors of 1.4-1.8 log units on the PDBbind dataset, and 1.0-1.7 log units on the PDE10A dataset, not indicating significant advantages over benchmark methods, and thus rendering the utility of electron density for deep learning models context-dependent. The relationship between intermolecular electron density and corresponding binding affinity was analyzed, and Pearson correlation coefficients r > 0.7 were obtained for several macromolecular targets.

Numerous investigations increasingly indicate the significance of microRNA (miRNA) in human diseases. Hence, unearthing associations between miRNA and diseases can contribute to precise diagnosis and efficacious remediation of medical conditions. The detection of miRNA-disease linkages via computational techniques utilizing biological information has emerged as a cost-effective and highly efficient approach. Here, we introduced a computational framework named ReHoGCNES, designed for prospective miRNA-disease association prediction (ReHoGCNES-MDA). This method constructs homogenous graph convolutional network with regular graph structure (ReHoGCN) encompassing disease similarity network, miRNA similarity network and known MDA network and then was tested on four experimental tasks. A random edge sampler strategy was utilized to expedite processes and diminish training complexity. Experimental results demonstrate that the proposed ReHoGCNES-MDA method outperforms both homogenous graph convolutional network and heterogeneous graph convolutional network with non-regular graph structure in all four tasks, which implicitly reveals steadily degree distribution of a graph does play an important role in enhancement of model performance. Besides, ReHoGCNES-MDA is superior to several machine learning algorithms and state-of-the-art methods on the MDA prediction. Furthermore, three case studies were conducted to further demonstrate the predictive ability of ReHoGCNES. Consequently, 93.3% (breast neoplasms), 90% (prostate neoplasms) and 93.3% (prostate neoplasms) of the top 30 forecasted miRNAs were validated by public databases. Hence, ReHoGCNES-MDA might serve as a dependable and beneficial model for predicting possible MDAs.

Drug discovery is time-consuming, expensive, and predominantly follows the "one drug → one target → one disease" paradigm. With the rapid development of systems biology and network pharmacology, a novel drug discovery paradigm, "multidrug → multitarget → multidisease", has emerged. This new holistic paradigm of drug discovery aligns well with the essence of networks, leading to the emergence of network-based methods in the field of drug discovery. In this Perspective, we initially introduce the concept and data sources of networks and highlight classical methodologies employed in network-based methods. Subsequently, we focus on the practical applications of network-based methods across various areas of drug discovery, such as target prediction, virtual screening, prediction of drug therapeutic effects or adverse drug events, and elucidation of molecular mechanisms. In addition, we provide representative web servers for researchers to use network-based methods in specific applications. Finally, we discuss several challenges of network-based methods and the directions for future development. In a word, network-based methods could serve as powerful tools to accelerate drug discovery.

The launch of AlphaFold series has brought deep-learning techniques into the molecular structural science. As another crucial problem, structure-based prediction of protein-ligand binding affinity urgently calls for advanced computational techniques. Is deep learning ready to decode this problem? Here we review mainstream structure-based, deep-learning approaches for this problem, focusing on molecular representations, learning architectures and model interpretability. A model taxonomy has been generated. To compensate for the lack of valid comparisons among those models, we realized and evaluated representatives from a uniform basis, with the advantages and shortcomings discussed. This review will potentially benefit structure-based drug discovery and related areas.

Drug discovery is a complex and expensive procedure involving several timely and costly phases through which new potential pharmaceutical compounds must pass to get approved. One of these critical steps is the identification and optimization of lead compounds, which has been made more accessible by the introduction of computational methods, including deep learning (DL) techniques. Diverse DL model architectures have been put forward to learn the vast landscape of interaction between proteins and ligands and predict their affinity, helping in the identification of lead compounds.

This survey fills a gap in previous research by comprehensively analyzing the most commonly used datasets and discussing their quality and limitations. It also offers a comprehensive classification of the most recent DL methods in the context of protein-ligand binding affinity prediction (BAP), providing a fresh perspective on this evolving field.

We thoroughly examine commonly used datasets for BAP and their inherent characteristics. Our exploration extends to various preprocessing steps and DL techniques, including graph neural networks, convolutional neural networks, and transformers, which are found in the literature. We conducted extensive literature research to ensure that the most recent deep learning approaches for BAP were included by the time of writing this manuscript.

The systematic approach used for the present study highlighted inherent challenges to BAP via DL, such as data quality, model interpretability, and explainability, and proposed considerations for future research directions. We present valuable insights to accelerate the development of more effective and reliable DL models for BAP within the research community.

The present study can considerably enhance future research on predicting affinity between protein and ligand molecules, hence further improving the overall drug development process.

Drug development is a challenging and costly process, yet it plays a crucial role in improving healthcare outcomes. Drug development requires extensive research and testing to meet the demands for economic efficiency, cures, and pain relief.

Drug development is a vital research area that necessitates innovation and collaboration to achieve significant breakthroughs. Computer-aided drug design provides a promising avenue for drug discovery and development by reducing costs and improving the efficiency of drug design and testing.

In this study, a novel model, namely LSTM-SAGDTA, capable of accurately predicting drug-target binding affinity, was developed. We employed SeqVec for characterizing the protein and utilized the graph neural networks to capture information on drug molecules. By introducing self-attentive graph pooling, the model achieved greater accuracy and efficiency in predicting drug-target binding affinity.

Moreover, LSTM-SAGDTA obtained superior accuracy over current state-of-the-art methods only by using less training time. The results of experiments suggest that this method represents a highprecision solution for the DTA predictor.

The overexpression or mutation of the kinase domain of the epidermal growth factor receptor (EGFR) is strongly associated with non-small-cell lung cancer (NSCLC). EGFR tyrosine kinase inhibitors (TKIs) have proven to be effective in treating NSCLC patients. However, EGFR mutations can result in drug resistance. To elucidate the mechanisms underlying this resistance and inform future drug development, we examined the binding affinities of BLU-945, a recently reported fourth-generation TKI, to wild-type EGFR (EGFRWT) and its double-mutant (L858R/T790M; EGFRDM) and triple-mutant (L858R/T790M/C797S; EGFRTM) forms. We compared the binding affinities of BLU-945, BLU-945 analogues, CH7233163 (another fourth-generation TKI), and erlotinib (a first-generation TKI) using absolute binding free energy calculations. Our findings reveal that BLU-945 and CH7233163 exhibit binding affinities to both EGFRDM and EGFRTM stronger than those of erlotinib, corroborating experimental data. We identified K745 and T854 as the key residues in the binding of fourth-generation EGFR TKIs. Electrostatic forces were the predominant driving force for the binding of fourth-generation TKIs to EGFR mutants. Furthermore, we discovered that the incorporation of piperidinol and sulfone groups in BLU-945 substantially enhanced its binding capacity to EGFR mutants. Our study offers valuable theoretical insights for optimizing fourth-generation EGFR TKIs.

Drug-target affinity (DTA) prediction as an emerging and effective method is widely applied to explore the strength of drug-target interactions in drug development research. By predicting these interactions, researchers can assess the potential efficacy and safety of candidate drugs at an early stage, narrowing down the search space for therapeutic targets and accelerating the discovery and development of new drugs. However, existing DTA prediction models mainly use graphical representations of drug molecules, which lack information on interactions between individual substructures, thus affecting prediction accuracy and model interpretability. Therefore, transformer and diffusion on drug graphs in DTA prediction (TDGraphDTA) are introduced to predict drug-target interactions using multi-scale information interaction and graph optimization. An interactive module is integrated into feature extraction of drug and target features at different granularity levels. A diffusion model-based graph optimization module is proposed to improve the representation of molecular graph structures and enhance the interpretability of graph representations while obtaining optimal feature representations. In addition, TDGraphDTA improves the accuracy and reliability of predictions by capturing relationships and contextual information between molecular substructures. The performance of the proposed TDGraphDTA in DTA prediction was verified on three publicly available benchmark datasets (Davis, Metz, and KIBA). Compared with state-of-the-art baseline models, it achieved better results in terms of consistency index, R-squared, etc. Furthermore, compared with some existing methods, the proposed TDGraphDTA is demonstrated to have better structure capturing capabilities by visualizing the feature capturing capabilities of the model using Grad-AAM toxicity labels in the ToxCast dataset. The corresponding source codes are available at https://github.com/Lamouryz/TDGraph.

Predicting protein stability change upon variation through a computational approach is a valuable tool to unveil the mechanisms of mutation-induced drug failure and develop immunotherapy strategies. Some previous machine learning-based techniques exhibit anti-symmetric bias toward destabilizing situations, whereas others struggle with generalization to unseen examples. To address these issues, we propose a gated graph neural network-based approach to predict changes in protein stability upon mutation. The model uses message passing to encode the links between the molecular structure and property after eliminating the non-mutant structure and creating input feature vectors. While doing so, it also incorporates the coordinates of the raw atoms to provide spatial insights into the chemical systems. We test the model on the Ssym, Myoglobin, Broom, and p53 datasets to demonstrate the generalization performance. Compared to existing approaches, our proposed method achieves improved linearity with symmetry in less time. The code for this study is available at: https://github.com/HongzhouTang/Pros-GNN.

Data-driven deep learning algorithms provide accurate prediction of high-level quantum-chemical molecular properties. However, their inputs must be constrained to the same quantum-chemical level of geometric relaxation as the training dataset, limiting their flexibility. Adopting alternative cost-effective conformation generative methods introduces domain-shift problems, deteriorating prediction accuracy. Here we propose a deep contrastive learning-based domain-adaptation method called Local Atomic environment Contrastive Learning (LACL). LACL learns to alleviate the disparities in distribution between the two geometric conformations by comparing different conformation-generation methods. We found that LACL forms a domain-agnostic latent space that encapsulates the semantics of an atom's local atomic environment. LACL achieves quantum-chemical accuracy while circumventing the geometric relaxation bottleneck and could enable future application scenarios such as inverse molecular engineering and large-scale screening. Our approach is also generalizable from small organic molecules to long chains of biological and pharmacological molecules.

Gathering information from multi-perspective graphs is an essential issue for many applications especially for protein-ligand-binding affinity prediction. Most of traditional approaches obtained such information individually with low interpretability. In this paper, we harness the rich information from multi-perspective graphs with a general model, which abstractly represents protein-ligand complexes with better interpretability while achieving excellent predictive performance. In addition, we specially analyze the protein-ligand-binding affinity problem, taking into account the heterogeneity of proteins and ligands. Experimental evaluations demonstrate the effectiveness of our data representation strategy on public datasets by fusing information from different perspectives. All codes are available in the https://github.com/Jthy-af/HaPPy .

Protein kinases regulate various cellular functions and hold significant pharmacological promise in cancer and other diseases. Although kinase inhibitors are one of the largest groups of approved drugs, much of the human kinome remains unexplored but potentially druggable. Computational approaches, such as machine learning, offer efficient solutions for exploring kinase-compound interactions and uncovering novel binding activities. Despite the increasing availability of three-dimensional (3D) protein and compound structures, existing methods predominantly focus on exploiting local features from one-dimensional protein sequences and two-dimensional molecular graphs to predict binding affinities, overlooking the 3D nature of the binding process. Here we present KDBNet, a deep learning algorithm that incorporates 3D protein and molecule structure data to predict binding affinities. KDBNet uses graph neural networks to learn structure representations of protein binding pockets and drug molecules, capturing the geometric and spatial characteristics of binding activity. In addition, we introduce an algorithm to quantify and calibrate the uncertainties of KDBNet's predictions, enhancing its utility in model-guided discovery in chemical or protein space. Experiments demonstrated that KDBNet outperforms existing deep learning models in predicting kinase-drug binding affinities. The uncertainties estimated by KDBNet are informative and well-calibrated with respect to prediction errors. When integrated with a Bayesian optimization framework, KDBNet enables data-efficient active learning and accelerates the exploration and exploitation of diverse high-binding kinase-drug pairs.