Affinity Prediction Research Articles

DeepRSMA: a cross-fusion based deep learning method for RNA-small molecule binding affinity prediction.

RNA is implicated in numerous aberrant cellular functions and disease progressions, highlighting the crucial importance of RNA-targeted drugs. To accelerate the discovery of such drugs, it is essential to develop an effective computational method for predicting RNA-small molecule affinity (RSMA). Recently, deep learning based computational methods have been promising due to their powerful nonlinear modeling ability. However, the leveraging of advanced deep learning methods to mine the diverse information of RNAs, small molecules and their interaction still remains a great challenge. In this study, we present DeepRSMA, an innovative cross-attention-based deep learning method for RSMA prediction. To effectively capture fine-grained features from RNA and small molecules, we developed nucleotide-level and atomic-level feature extraction modules for RNA and small molecules, respectively. Additionally, we incorporated both sequence and graph views into these modules to capture features from multiple perspectives. Moreover, a Transformer-based cross-fusion module is introduced to learn the general patterns of interactions between RNAs and small molecules. To achieve effective RSMA prediction, we integrated the RNA and small molecule representations from the feature extraction and cross-fusion modules. Our results show that DeepRSMA outperforms baseline methods in multiple test settings. The interpretability analysis and the case study on spinal muscular atrophy (SMA) demonstrate that DeepRSMA has the potential to guide RNA-targeted drug design. The codes and data are publicly available at https://github.com/Hhhzj-7/DeepRSMA. Supplementary data are available at Bioinformatics online.

Predicting Protein-Ligand Binding Affinity Using Fusion Model of Spatial-Temporal Graph Neural Network and 3D Structure-Based Complex Graph.

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.

DDDR-15. UTILIZING DEEP DOCKING AND ARTIFICIAL INTELLIGENCE FOR THE DISCOVERY OF NOVEL PARP1-SELECTIVE INHIBITORS FOR USE AGAINST BRAIN TUMORS

Abstract Brain tumors, including primary brain tumors and central nervous system (CNS) metastases, remain among the most challenging malignancies to treat, with therapeutic options often limited by the inability of drugs to penetrate the blood-brain barrier. Poly(ADP-ribose) polymerase (PARP) is a key enzyme in DNA repair, and inhibition of PARP1 specifically drives synthetic lethality in BRCA-mutated disease. While they’ve achieved commercial success, first generation PARP inhibitors are limited in their utility as they cannot readily pass through the blood-brain barrier and have adverse side effects, likely driven by the collateral inhibition of PARP2. Development of a PARP1-selective, CNS penetrant inhibitor could reduce toxicity, while providing a new therapeutic option for brain tumors. Traditional drug discovery methods are time-consuming and costly, necessitating innovative approaches. Here, we describe the application of Deep Docking, an advanced artificial intelligence (AI) approach, to discover a novel, PARP1-selective inhibitor for use against brain tumors. Deep Docking utilizes deep learning to accelerate the prediction of the binding affinity of a large number of compounds to target proteins, streamlining the virtual screening process and allowing for rapid docking of billions of compounds against the PARP1 protein. Additionally, state-of-the-art generative algorithms and deep learning techniques for predicting drug-like properties such as metabolism, permeability, and safety profiles, can be combined to rapidly perform hit-to-lead optimization. We will present preliminary Deep Docking screening results from billions of compounds, identifying several with predicted high binding affinities for PARP-1. Validating in vitro and in vivo data, including PARP1 selectivity, metabolic stability, pharmacokinetic profile, CNS penetration and safety profile, will be described. Application of the Deep Docking AI platform is being used to significantly accelerate the discovery of a selective PARP-1 inhibitor for brain tumors. This approach will not only improve the efficiency of drug discovery but also enhance the specificity and efficacy of potential therapeutics.

Investigation of Novel Quinoline Derivatives Targeting Epidermal Growth Factor Receptors as Anticancer Agents a Computational Approach

Background: Newer chemical entities are created and synthesis has been made feasible by a variety of computer-aided drug design (CAAD) techniques. In addition to facilitating the visualisation of the ligand-target binding process, the application of in silico methodologies and structure-based drug design (SBDD) allows for the prediction of receptor affinities and significant binding pocket locations. Objective: The goal of the current study was to identify new quinoline derivatives by computational methods specially designed to bind the EGFR receptor in the treatment of breast cancer. Materials and Methods: ChemAxon Marvin Sketch 5.11.5 was used to create derivatives of quinolines. The admetSAR online web tools and SwissADME were utilised to forecast the toxicity and pharmacokinetic characteristics of several substances. A multitude of software programmes, such as Autodock 1.1.2, MGL Tools 1.5.6, Procheck, Protparam ExPasy tool, PyMOL, and Biovia Discovery Studio Visualizer v20.1.0.19295 were also employed to ascertain the ligand-receptor interactions between quinoline derivatives and the target receptor (PDB -5GNK). Result: Almost all components were shown to be less hazardous, orally consumable and to have the appropriate pharmacokinetic characteristics based on in silico study. All newly generated derivative compounds have higher docking scores when compared to the widely used medication sorafenib. Conclusion: Interactions with quinoline analogues boost binding energy and the number of Hbonds produced, making them a suitable place to start when creating compounds for further exploration. The quinoline moiety increases its potential as a novel therapy alternative for breast cancer and could facilitate more comprehensive in vivo, in vitro, chemical-based, and pharma studies by medicinal chemists.

Mayer-Homology Learning Prediction of Protein-Ligand Binding Affinities

Artificial intelligence-assisted drug design is revolutionizing the pharmaceutical industry. Effective molecular features are crucial for accurate machine learning predictions, and advanced mathematics plays a key role in designing these features. Persistent homology theory, which equips topological invariants with persistence, provides valuable insights into molecular structures. The standard homology theory is based on a differential rule for the boundary operator that satisfies [Formula: see text] = 0. Our recent work has extended this rule by employing Mayer homology with generalized differentials that satisfy [Formula: see text] = 0 for [Formula: see text] 2, leading to the development of persistent Mayer homology (PMH) theory and richer topological information across various scales. In this study, we utilize PMH to create a novel multiscale topological vectorization for molecular representation, offering valuable tools for descriptive and predictive analyses in molecular data and machine learning prediction. Specifically, benchmark tests on established protein-ligand datasets, including PDBbind-v2007, PDBbind-v2013, and PDBbind-v2016, demonstrate the superior performance of our Mayer homology models in predicting protein-ligand binding affinities.

Accurate prediction of protein–ligand interactions by combining physical energy functions and graph-neural networks

We introduce an advanced model for predicting protein–ligand interactions. Our approach combines the strengths of graph neural networks with physics-based scoring methods. Existing structure-based machine-learning models for protein–ligand binding prediction often fall short in practical virtual screening scenarios, hindered by the intricacies of binding poses, the chemical diversity of drug-like molecules, and the scarcity of crystallographic data for protein–ligand complexes. To overcome the limitations of existing machine learning-based prediction models, we propose a novel approach that fuses three independent neural network models. One classification model is designed to perform binary prediction of a given protein–ligand complex pose. The other two regression models are trained to predict the binding affinity and root-mean-square deviation of a ligand conformation from an input complex structure. We trained the model to account for both deviations in experimental and predicted binding affinities and pose prediction uncertainties. By effectively integrating the outputs of the triplet neural networks with a physics-based scoring function, our model showed a significantly improved performance in hit identification. The benchmark results with three independent decoy sets demonstrate that our model outperformed existing models in forward screening. Our model achieved top 1% enrichment factors of 32.7 and 23.1 with the CASF2016 and DUD-E benchmark sets, respectively. The benchmark results using the LIT-PCBA set further confirmed its higher average enrichment factors, emphasizing the model’s efficiency and generalizability. The model’s efficiency was further validated by identifying 23 active compounds from 63 candidates in experimental screening for autotaxin inhibitors, demonstrating its practical applicability in hit discovery.Scientific contributionOur work introduces a novel training strategy for a protein–ligand binding affinity prediction model by integrating the outputs of three independent sub-models and utilizing expertly crafted decoy sets. The model showcases exceptional performance across multiple benchmarks. The high enrichment factors in the LIT-PCBA benchmark demonstrate its potential to accelerate hit discovery.

BASE: a web service for providing compound-protein binding affinity prediction datasets with reduced similarity bias.

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 .

GPT4Kinase: High-accuracy prediction of inhibitor-kinase binding affinity utilizing large language model

The accurate prediction of inhibitor-kinase binding affinity is crucial in biological research and medical applications. Particularly, kinases play a pivotal role in numerous cellular processes and are essential enzymes in Mitogen-Activated Protein Kinase (MAPK) signaling pathway. This present study harnesses the capabilities of Large Language Models (LLMs), specifically GPT-4, to predict the binding affinity between inhibitors and kinases within the MAPK pathway, including Raf protein kinase (RAF), Mitogen-activated protein kinase kinase (MEK) and Extracellular Signal-Regulated Kinase (ERK). Remarkably, GPT-4 achieved an impressive 87.31 % accuracy in prediction on RAF binding affinity, and 77.00 % accuracy in comprehensive prediction tasks, substantially outperforming existing mainstream methods such as Autodock Vina (21.21 %), BatchDTA (52.00 %) and KIPP (59.60 %). Furthermore, GPT-4 was employed to delineate the features of high-affinity and low-affinity molecules, as well as their contributing functional groups. These contributing groups were subsequently validated through molecular docking. Additionally, to validate the generalizability of the method, we applied it to six other kinases and achieved a maximum accuracy of 83.78 %. Also, we utilized a dataset comprising over 200 kinases, obtaining a high accuracy of 66.20 %. The study showcases the transformative impact of LLMs on molecular binding affinity prediction, with major implications for biological sciences and therapeutic development.

Designing an adaptive learning framework for predicting drug-target affinity using reinforcement learning and graph neural networks

In the field of biomedical engineering, predicting Drug-Target Affinities (DTA) is crucial. However, current affinity prediction models are predominantly manually designed, which is a complex, time-consuming process that may not effectively accommodate the diversity and complexity of datasets. To address this challenge, we propose an adaptive learning framework for predicting drug-target affinity, called Adaptive-DTA, which integrates reinforcement learning with graph neural networks to automate the design of affinity prediction models. Adaptive-DTA defines the architecture search space using directed acyclic graphs and employs an reinforcement learning algorithm to guide the architecture search, optimizing parameters based on the entropy of sampled architectures and model performance metrics. Additionally, we enhance efficiency with a two-stage training and validation strategy, incorporating low-fidelity and high-fidelity evaluations. Our framework not only alleviates the challenges associated with manual model design but also significantly improves model performance and generalization. To evaluate the performance of our method, we conducted extensive experiments on DTA benchmark datasets and compared the results with nine state-of-the-art methods. The experimental outcomes demonstrate that our proposed framework outperforms these methods, exhibiting outstanding performance in predicting drug-target affinities. Our innovative approach streamlines the design of affinity prediction model, reduces reliance on manual crafting, and enhances model generalization. Its ability to automatically optimize network architectures represents a major step forward in the automation of computational drug discovery processes.

Ensembling methods for protein-ligand binding affinity prediction

Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 13 deep learning models from combinations of 5 input features. Then, we explore all possible ensembles of the trained models to find the best ensembles. Our deep learning models use cross-attention and self-attention layers to extract short and long-range interactions. Our method is named Ensemble Binding Affinity (EBA). EBA extracts information from various models using different combinations of input features, such as simple 1D sequential and structural features of the protein-ligand complexes rather than 3D complex features. EBA is implemented to accurately predict the binding affinity of a protein-ligand complex. One of our ensembles achieves the highest Pearson correlation coefficient (R) value of 0.914 and the lowest root mean square error (RMSE) value of 0.957 on the well-known benchmark test set CASF2016. Our ensembles show significant improvements of more than 15% in R-value and 19% in RMSE on both well-known benchmark CSAR-HiQ test sets over the second-best predictor named CAPLA. Furthermore, the superior performance of the ensembles across all metrics compared to existing state-of-the-art protein-ligand binding affinity prediction methods on all five benchmark test datasets demonstrates the effectiveness and robustness of our approach. Therefore, our approach to improving binding affinity prediction between proteins and ligands can contribute to improving the success rate of potential drugs and accelerate the drug development process.

Assessment of Binding Affinity in the Complexes of CoV-S-Protein’s RBD and the ACE2 Using Convolutional Neural Networks

The experimentally obtained structures of 48 complexes of the ACE2 receptor with the S protein’s RBD of the coronaviruses SARS-CoV and SARS-CoV-2 (including mutant forms of the latter) were assessed and the dissociation constant was calculated for them. Prediction of binding affinity was carried out using ProBAN, a neural network algorithm, previously developed by the authors, and a number of other algorithms for estimating the Gibbs free energy such as Prodigy, FoldX, DFIRE and RosettaDock. A comparison of the evaluation results shows that ProBAN has the best prediction quality (Pearson correlation − 0.56, MAE − 0.7 kcal/mol) of all the analyzed algorithms. The results obtained suggest better quality of affinity prediction for other protein-protein complexes. Information about the complexes under study and prediction results are available in the repository at the link: https://github.com/EABogdanova/ProBAN_RBD-ACE2.

ERL-ProLiGraph: Enhanced representation learning on protein-ligand graph structured data for binding affinity prediction.

Predicting Protein-Ligand Binding Affinity (PLBA) is pivotal in drug development, as accurate estimations of PLBA expedite the identification of promising drug candidates for specific targets, thereby accelerating the drug discovery process. Despite substantial advancements in PLBA prediction, developing an efficient and more accurate method remains non-trivial. Unlike previous computer-aid PLBA studies which primarily using ligand SMILES and protein sequences represented as strings, this research introduces a Deep Learning-based method, the Enhanced Representation Learning on Protein-Ligand Graph Structured data for Binding Affinity Prediction (ERL-ProLiGraph). The unique aspect of this method is the use of graph representations for both proteins and ligands, intending to learn structural information continued from both to enhance the accuracy of PLBA predictions. In these graphs, nodes represent atomic structures, while edges depict chemical bonds and spatial relationship. The proposed model, leveraging deep-learning algorithms, effectively learns to correlate these graphical representations with binding affinities. This graph-based representations approach enhances the model's ability to capture the complex molecular interactions critical in PLBA. This work represents a promising advancement in computational techniques for protein-ligand binding prediction, offering a potential path toward more efficient and accurate predictions in drug development. Comparative analysis indicates that the proposed ERL-ProLiGraph outperforms previous models, showcasing notable efficacy and providing a more suitable approach for accurate PLBA predictions.

In silico analysis of the melamine structural analogues interaction with calcium-sensing receptor: A potential for nephrotoxicity

In recent years, melamine, and its structural analogues, as adulterants in various food products including protein supplements,have been widely studied for their nephrotoxic effects. Previous research has presented evidence that certain small molecules can alter the calcium-sensing receptor (CaSR) function, contributing to nephrotoxicity. Melamine, for example, has been observed in in vitro settings to interact with the allosteric binding site of CaSR, resulting in uncontrolled CaSR activation. This activation results in the production of reactive oxygen species, which eventually causes kidney cell apoptosis and/or necrosis. The present research used the in silico molecular modelling to evaluate the CaSR binding profilesof four common adulterants in protein supplements: melamine, cyanuric acid, uric acid, and melamine cyanurate. Using Schrödinger’s Maestro docking software (version 13.2.128), the docking studies coupled a noncovalent extra precision mode with the molecular mechanics-generalized born surface area (MM-GBSA) simulation for enhanced binding affinity prediction accuracy. This study identified that cyanuric acid, uric acid, and melamine cyanurate have greater CaSR binding affinities than melamine. Interestingly, melamine cyanurate had the highest binding potential to CaSR. Previous animal studies have reported high concentrations of melamine cyanurate complex in rat kidneys following melamine administration. These findings demonstrate a molecular explanation melamine cyanurate complex-induced nephrotoxicity. This research offers new insight regarding the probable mechanism through which melamine, its analogues, and complexes may cause nephrotoxicity.

Leveraging Transfer Learning for Predicting Protein-Small Molecule Interactions.

A complex web of intermolecular interactions defines and regulates biological processes. Understanding this web has been particularly challenging because of the sheer number of actors in biological systems: ∼10 4 proteins in a typical human cell offer a plausible 10 8 interactions. This number grows rapidly if we consider metabolites, drugs, nutrients, and other biological molecules. The relative strength of interactions also critically affects these biological processes. However, the small and often incomplete datasets (10 3 -10 4 protein-ligand interactions) traditionally used for binding affinity predictions limit the ability to capture the full complexity of these interactions. To overcome this challenge, we developed Yuel 2, a novel neural network-based approach that leverages transfer learning to address the limitations of small datasets. Yuel 2 is pre-trained on a large-scale dataset to learn intricate structural features and then fine-tuned on specialized datasets like PDBbind to enhance the predictive accuracy and robustness. We show that Yuel 2 predicts multiple binding affinity metrics - Kd, Ki, and IC50 - between proteins and small molecules, offering a comprehensive representation of molecular interactions crucial for drug design and development.

MREDTA: A BERT and transformer-based molecular representation encoder for predicting drug-target binding affinity.

Drug-target binding affinity (DTA) prediction is vital for drug repositioning. The accuracy and generalizability of DTA models remain a major challenge. Here, we develop a model composed of BERT-Trans Block, Multi-Trans Block, and DTI Learning modules, referred to as Molecular Representation Encoder-based DTA prediction (MREDTA). MREDTA has three advantages: (1) extraction of both local and global molecular features simultaneously through skip connections; (2) improved sensitivity to molecular structures through the Multi-Trans Block; (3) enhanced generalizability through the introduction of BERT. Compared with 12 advanced models, benchmark testing of KIBA and Davis datasets demonstrated optimal performance of MREDTA. In case study, we applied MREDTA to 2034 FDA-approved drugs for treating non-small-cell lung cancer (NSCLC), all of which act on mutant EGFRT790M protein. The corresponding molecular docking results demonstrated the robustness of MREDTA.

MVSF-AB: Accurate antibody-antigen binding affinity prediction via multi-view sequence feature learning.

Predicting the binding affinity between antigens and antibodies accurately is crucial for assessing therapeutic antibody effectiveness and enhancing antibody engineering and vaccine design. Traditional machine learning methods have been widely used for this purpose, relying on interfacial amino acids' structural information. Nevertheless, due to technological limitations and high costs of acquiring structural data, the structures of most antigens and antibodies are unknown, and sequence-based methods have gained attention. Existing sequence-based approaches designed for protein-protein affinity prediction exhibit a significant drop in performance when applied directly to antibody-antigen affinity prediction due to imbalanced training data and lacking design in the model framework specifically for antibody-antigen, hindering the learning of key features of antibodies and antigens. Therefore, we propose MVSF-AB, a Multi-View Sequence Feature learning for accurate Antibody-antigen Binding affinity prediction. MVSF-AB designs a multi-view method that fuses semantic features and residue features to fully utilize the sequence information of antibody-antigen and predicts the binding affinity. Experimental results demonstrate that MVSF-AB outperforms existing approaches in predicting unobserved natural antibody-antigen affinity and maintains its effectiveness when faced with mutant strains of antibodies. Datasets we used and source code are available on our public GitHub repository https://github.com/TAI-Medical-Lab/MVSF-AB.

ANTIPASTI: Interpretable prediction of antibody binding affinity exploiting normal modes and deep learning.

The high binding affinity of antibodies toward their cognate targets is key to eliciting effective immune responses, as well as to the use of antibodies as research and therapeutic tools. Here, we propose ANTIPASTI, a convolutional neural network model that achieves state-of-the-art performance in the prediction of antibody binding affinity using as input a representation of antibody-antigen structures in terms of normal mode correlation maps derived from elastic network models. This representation captures not only structural features but energetic patterns of local and global residue fluctuations. The learnt representations are interpretable: they reveal similarities of binding patterns among antibodies targeting the same antigen type, and can be used to quantify the importance of antibody regions contributing to binding affinity. Our results show the importance of the antigen imprint in the normal mode landscape, and the dominance of cooperative effects and long-range correlations between antibody regions to determine binding affinity.

DTA Atlas: A massive-scale drug repurposing database

The drug development process is costly and time-consuming. Repurposing existing approved drugs, an efficient and cost-effective strategy, involves assessing numerous drug-protein pairs to uncover new interactions. While modern in silico methods enhance scalability, an open database for projected drug-target interactions across the entire human proteome is still lacking. In this work, we introduce an open database of predicted drug-target interactions, termed DTA Atlas, covering the entire human proteome as well as a wide range of marketed drugs, resulting in over 220 million drug-target pairs. The database integrates 4 billion affinity predictions from advanced deep neural networks and offers a user-friendly web interface, enabling users to explore drug-target affinity predictions for the human proteome. To the best of our knowledge, DTA Atlas represents the first comprehensive collection of drug-target binding strength predictions. It is open-source and can serve as an important resource for drug development, drug repurposing, toxicity studies and more.

Structural investigation, DNA/Mpox/COVID-19 molecular docking, and biological assays of two novel Co(II) and Cu(II) complexes derived from tri- and bi-dentate pyridyl-functionalized phosphoramide ligand [Ph]P(O)[NH-2Py]2

Phosphoramides have recently gained significant attention in medical and pharmaceutical research due to their diverse biological applications, including anticancer and antiviral drugs. Here, novel phosphoramide complexes [Co(II){(O)P[NH-2Py]2[Ph]}2][CoCl4] (1) and [Cu(II){(O)P[O][NH-2Py][Ph]}2{OH2}].2H2O (2) derived from [Ph]P(O)[NH-2Py]2 were synthesized and characterized by FT-IR, CHN elemental analysis and single crystal X-ray diffraction. In these discrete chelate complexes the phosphoramide [Ph]P(O)[NH-2Py]2 moiety acts as a flexible tridentate O,N,N-donor ligand for 1 or bidentate N,O-donor ligand for 2. The metal cation has a hexa-coordinate M(N)4(O)2 environment adopting a distorted octahedral geometry for 1 and a penta-coordinate M(N)2(O)3 environment with a distorted square pyramidal geometry for 2. The supramolecular assemblies have 1D linear arrangements along the [201] axis formed via NH…Cl hydrogen bond interactions for 1 and 2D arrangements parallel to the ab plane formed via classical NH…O and OH…O hydrogen bonds for 2. The in vitro anticancer activity of 1 and 2 was assessed against MDA-MB-231 breast cancer cell line showing a good inhibitory effect for both compounds, especially for the Cu(II) complex 2 with a IC50 of 29 ± 2.1 nmolar. Antioxidant and anti-hemolytic potential of 1 and 2 was experimentally evaluated using the DPPH technique showing suitable performance for both compounds. The binding capacity of 1 and 2 to DNA was investigated using molecular docking simulations showing a good correlation with the experimental in vitro results. The results reveal mixed modes of interactions between the compounds with the DNA receptor confirming a suitable DNA-binding ability for both 1 and 2. In silico molecular docking technique was also employed to provide a detailed prediction of the binding affinity of the studied compounds for SARS-CoV-2 (−6.5 kcal/mol) and Monkeypox (−8.4 kcal/mol)) which competes with current effective drugs.

PocketDTA: an advanced multimodal architecture for enhanced prediction of drug-target affinity from 3D structural data of target binding pockets.

Accurately predicting the drug-target binding affinity (DTA) is crucial to drug discovery and repurposing. Although deep learning has been widely used in this field, it still faces challenges with insufficient generalization performance, inadequate use of 3D information, and poor interpretability. To alleviate these problems, we developed the PocketDTA model. This model enhances the generalization performance by pre-trained models ESM-2 and GraphMVP. It ingeniously handles the first 3 (top-3) target binding pockets and drug 3D information through customized GVP-GNN Layers and GraphMVP-Decoder. In addition, it uses a bilinear attention network to enhance interpretability. Comparative analysis with state-of-the-art (SOTA) methods on the optimized Davis and KIBA datasets reveals that the PocketDTA model exhibits significant performance advantages. Further, ablation studies confirm the effectiveness of the model components, whereas cold-start experiments illustrate its robust generalization capabilities. In particular, the PocketDTA model has shown significant advantages in identifying key drug functional groups and amino acid residues via molecular docking and literature validation, highlighting its strong potential for interpretability. Code and data are available at: https://github.com/zhaolongNCU/PocketDTA.