Drug-target Prediction Research Articles

Dual modality feature fused neural network integrating binding site information for drug target affinity prediction

Accurately predicting binding affinities between drugs and targets is crucial for drug discovery but remains challenging due to the complexity of modeling interactions between small drug and large targets. This study proposes DMFF-DTA, a dual-modality neural network model integrates sequence and graph structure information from drugs and proteins for drug-target affinity prediction. The model introduces a binding site-focused graph construction approach to extract binding information, enabling more balanced and efficient modeling of drug-target interactions. Comprehensive experiments demonstrate DMFF-DTA outperforms state-of-the-art methods with significant improvements. The model exhibits excellent generalization capabilities on completely unseen drugs and targets, achieving an improvement of over 8% compared to existing methods. Model interpretability analysis validates the biological relevance of the model. A case study in pancreatic cancer drug repurposing demonstrates its practical utility. This work provides an interpretable, robust approach to integrate multi-view drug and protein features for advancing computational drug discovery.

MAI-TargetFisher: A proteome-wide drug target prediction method synergetically enhanced by artificial intelligence and physical modeling.

Computational target identification plays a pivotal role in the drug development process. With the significant advancements of deep learning methods for protein structure prediction, the structural coverage of human proteome has increased substantially. This progress inspired the development of the first genome-wide small molecule targets scanning method. Our method aims to localize drug targets and detect potential off-target effects early in the drug discovery process, thereby improving the success rate of drug development. We have constructed a high-quality database of protein structures with annotated potential binding sites, covering 82% of the protein-coding genome. On the basis of this database, to enhance our search capabilities, we have integrated computational techniques, including both artificial intelligence-based and biophysical model-based methods. This integration led to the development of a target identification method called Multi-Algorithm Integrated Target Fisher (MAI-TargetFisher). MAI-TargetFisher leverages the complementary strengths of various methods while minimizing their weaknesses, enabling precise database navigation to generate a reliably ranked set of candidate targets for an active query molecule. Importantly, our work is the first comprehensive scan of protein surfaces across the entire human genome, aimed at evaluating potential small molecule binding sites on each protein. Through a series of evaluations on benchmark and a target identification task, the results demonstrate the high hit rates and good reliability of our method under the validation of wet experiments. We have also made available a freely accessible web server at https://bailab.siais.shanghaitech.edu.cn/mai-targetfisher for non-commercial use.

Prediction of potential drug targets and key inhibitors (ZINC67974679, ZINC67982856, and ZINC05668040) against Rickettsia felis using integrated computational approaches

Prediction of potential drug targets and key inhibitors (ZINC67974679, ZINC67982856, and ZINC05668040) against Rickettsia felis using integrated computational approaches

Target Discovery Driven by Chemical Biology and Computational Biology.

Target identification is crucial for drug screening and development because it can reveal the mechanism of drug action and ensure the reliability and accuracy of the results. Chemical biology, an interdisciplinary field combining chemistry and biology, can assist in this process by studying the interactions between active molecular compounds and proteins and their physiological effects. It can also help predict potential drug targets or candidates, develop new biomarker assays and diagnostic reagents, and evaluate the selectivity and range of active compounds to reduce the risk of off-target effects. Chemical biology can achieve these goals using techniques such as changing protein thermal stability, enzyme sensitivity, and molecular structure and applying probes, isotope labeling and mass spectrometry. Concurrently, computational biology employs a diverse array of computational models to predict drug targets. This approach also offers innovative avenues for repurposing existing drugs. In this paper, we review the reported chemical biology and computational biology techniques for identifying different types of targets that can provide valuable insights for drug target discovery.

Drug-target binding affinity prediction based on power graph and word2vec

BackgroundDrug and protein targets affect the physiological functions and metabolic effects of the body through bonding reactions, and accurate prediction of drug-protein target interactions is crucial for drug development. In order to shorten the drug development cycle and reduce costs, machine learning methods are gradually playing an important role in the field of drug-target interactions.ResultsCompared with other methods, regression-based drug target affinity is more representative of the binding ability. Accurate prediction of drug target affinity can effectively reduce the time and cost of drug retargeting and new drug development. In this paper, a drug target affinity prediction model (WPGraphDTA) based on power graph and word2vec is proposed.ConclusionsIn this model, the drug molecular features in the power graph module are extracted by a graph neural network, and then the protein features are obtained by the Word2vec method. After feature fusion, they are input into the three full connection layers to obtain the drug target affinity prediction value. We conducted experiments on the Davis and Kiba datasets, and the experimental results showed that WPGraphDTA exhibited good prediction performance.

Identifying MTHFD1 and LGALS4 as Potential Therapeutic Targets in Prostate Cancer Through Multi-Omics Mendelian Randomization Analysis.

Background: Prostate cancer remains one of the leading causes of cancer-related mortality in men worldwide. The treatment of it is currently based on surgical removal, radiotherapy, and hormone therapy. It is crucial to improve therapeutic prospects for the diagnosis and treatment of prostate cancer via drug target screening. Methods: We integrated eQTL data from the eQTLGen Consortium and pQTL data from UK Biobank Proteome Plasma Proteins (UKB-PPP) and deCODE health datasets. MR analyses (SMR, heterogeneity in dependent instruments (HEIDI), IVW, Wald ratio, weighted median, and MR-Egger) were used to screen candidate genes associated with prostate adenocarcinoma (PRAD) risk. Candidate genes were further verified through TCGA-based gene expression profile, survival analysis, and immune microenvironment evaluations. TIDE analysis was utilized to investigate gene immunotherapy response. Single-cell RNA sequencing data from the GSE176031 dataset were used to investigate the gene expression patterns. The Drug Bank, Therapeutic Target Database and Drug Signatures Database were utilized to predict targeted drugs for candidate genes. Results: MTHFD1 and LGALS4 were identified as promising therapeutic targets for PRAD, with evidence provided at multi-omics levels. LGALS4 was predominantly expressed in malignant cells and was correlated with enhanced immune checkpoint pathways, increased TIDE scores, and immunotherapy resistance. In contrast, MTHFD1was expressed in both tumor and microenvironmental cells and was associated with poor survival. Drug target prediction suggested that there are no currently approved drugs specifically targeting MTHFD1 and LGALS4. Conclusions: Our study identified MTHFD1 and LGALS4 as potential preventive targets for PRAD. However, future experiments are warranted to assess the utility and effectiveness of these candidate proteins.

MCF-DTI: Multi-Scale Convolutional Local-Global Feature Fusion for Drug-Target Interaction Prediction.

Predicting drug-target interactions (DTIs) is a crucial step in the development of new drugs and drug repurposing. In this paper, we propose a novel drug-target prediction model called MCF-DTI. The model utilizes the SMILES representation of drugs and the sequence features of targets, employing a multi-scale convolutional neural network (MSCNN) with parallel shared-weight modules to extract features from the drug side. For the target side, it combines MSCNN with Transformer modules to capture both local and global features effectively. The extracted features are then weighted and fused, enabling comprehensive feature representation to enhance the predictive power of the model. Experimental results on the Davis dataset demonstrate that MCF-DTI achieves an AUC of 0.9746 and an AUPR of 0.9542, outperforming other state-of-the-art models. Our case study demonstrates that our model effectively validated several known drug-target relationships in lung cancer and predicted the therapeutic potential of certain preclinical compounds in treating lung cancer. These findings contribute valuable insights for subsequent drug repurposing efforts and novel drug development.

GraphkmerDTA: integrating local sequence patterns and topological information for drug-target binding affinity prediction and applications in multi-target anti-Alzheimer's drug discovery.

Identifying drug-target binding affinity (DTA) plays a critical role in early-stage drug discovery. Despite the availability of various existing methods, there are still two limitations. Firstly, sequence-based methods often extract features from fixed length protein sequences, requiring truncation or padding, which can result in information loss or the introduction of unwanted noise. Secondly, structure-based methods prioritize extracting topological information but struggle to effectively capture sequence features. To address these challenges, we propose a novel deep learning model named GraphkmerDTA, which integrates Kmer features with structural topology. Specifically, GraphkmerDTA utilizes graph neural networks to extract topological features from both molecules and proteins, while fully connected networks learn local sequence patterns from the Kmer features of proteins. Experimental results indicate that GraphkmerDTA outperforms existing methods on benchmark datasets. Furthermore, a case study on lung cancer demonstrates the effectiveness of GraphkmerDTA, as it successfully identifies seven known EGFR inhibitors from a screening library of over two thousand compounds. To further assess the practical utility of GraphkmerDTA, we integrated it with network pharmacology to investigate the mechanisms underlying the therapeutic effects of Lonicera japonica flower in treating Alzheimer's disease. Through this interdisciplinary approach, three potential compounds were identified and subsequently validated through molecular docking studies. In conclusion, we present not only a novel AI model for the DTA task but also demonstrate its practical application in drug discovery by integrating modern AI approaches with traditional drug discovery methodologies.

Improving generalizability of drug-target binding prediction by pre-trained multi-view molecular representations.

Most drugs start on their journey inside the body by binding the right target proteins. This is the reason that numerous efforts have been devoted to predicting the drug-target binding during drug development. However, the inherent diversity among molecular properties, coupled with limited training data availability, poses challenges to the accuracy and generalizability of these methods beyond their training domain. In this work, we proposed a neural networks construction for high accurate and generalizable drug-target binding prediction, named Pre-trained Multi-view Molecular Representations (PMMR). The method uses pre-trained models to transfer representations of target proteins and drugs to the domain of drug-target binding prediction, mitigating the issue of poor generalizability stemming from limited data. Then, two typical representations of drug molecules, Graphs and SMILES strings, are learned respectively by a Graph Neural Network and a Transformer to achieve complementarity between local and global features. PMMR was evaluated on drug-target affinity and interaction benchmark datasets, and it derived preponderant performance contrast to peer methods, especially generalizability in cold-start scenarios. Furthermore, our state-of-the-art method was indicated to have the potential for drug discovery by a case study of cyclin-dependent kinase 2. https://github.com/NENUBioCompute/PMMR.

Sappanone A alleviates metabolic dysfunction-associated steatohepatitis by decreasing hepatocyte lipotoxicity via targeting Mup3 in mice.

Metabolic dysfunction-associated steatohepatitis (MASH) is an inflammatory lipotoxic disorder marked by hepatic steatosis, hepatocyte damage, inflammation, and varying stages of fibrosis. Sappanone A (SA), a flavonoid, exhibits anti-inflammatory and hepatoprotection activities. Nevertheless, the effects of SA on MASH remain ambiguous. We evaluated the effects of SA on hepatocyte lipotoxicity, inflammation, and fibrosis conditions in MASH mice, as well as the underlying mechanisms. A conventional murine MASH model fed a methionine-choline-deficient (MCD) diet was utilized to assess the role of SA on MASH in vivo. Drug target prediction and liver transcriptomics were employed to elucidate the potential actions of SA. AML12 cells were applied to further explore the effects and mechanisms of SA in vitro. The in silico prediction indicated that SA could modulate inflammation, insulin resistance, lipid metabolism, and collagen catabolic process. Treating with SA dose-dependently lessened the elevated levels of serum ALT and AST in mice with diet-triggered MASH, and high-dose SA treatment exhibited a similar effect to silymarin. Additionally, SA treatment significantly reduced lipid deposition, inflammation, and fibrosis subjected to metabolic stress in a dose-dependent manner. Besides, SA mitigated palmitate-triggered lipotoxicity in hepatocytes. Liver transcriptomics further confirmed the aforementioned findings. Of note, mRNA-sequencing analysis and molecular biology experiments demonstrated that SA statistically up-regulated the hepatic expression of major urinary protein 3 (Mup3), thereby facilitating lipid transportation and inhibiting lipotoxicity. Furthermore, Mup3 knockdown in hepatocytes significantly abolished the hepatoprotection provided by SA. SA alleviates MASH by decreasing lipid accumulation and lipotoxicity in hepatocytes, at least partially by targeting Mup3, and subsequently blocks MASH process. Therefore, SA could be a promising hepatoprotective agent in the context of MASH.

Study of the naturally occurring lignan brachangobinan A as antiplasmodial agent: Synthesis, biological evaluation, and in silico prediction.

This study focused on the synthesis, structural validation, and evaluation of the antiplasmodial efficacy of brachangobinan A (BA) and its enantiomers, (+)-BA and (-)-BA, as potential antimalarial agents. BA, (+)-BA, and (-)-BA were synthesized through chemical processes and validated via advanced spectroscopic techniques. In vitro studies were conducted to assess their efficacy against Plasmodium falciparum strains 3D7 and K1 by determining their half maximal inhibitory concentration (IC50) values, cytotoxicity profiles, and selectivity indices. Additional evaluations examined the impacts of exposure to these compounds on stage-specific effects, parasite morphology, and parasitemia levels, as well as potential mechanisms of action through in silico drug target prediction and molecular docking simulations. In vivo efficacy was tested in a mouse model of malaria caused by P. yoelii 17XNL. The results revealed that BA, (+)-BA, and (-)-BA exhibited promising in vitro antiplasmodial activity and selectivity, inducing morphological changes and demonstrating cidal effects. Drug-likeness predictions indicated favorable safety profiles but challenges in terms of bioavailability. In silico analyses identified Pf HSP90, Pf CDK2H, and Pf MAPK as key targets of (+)-BA and (-)-BA. In vivo studies confirmed the efficacy of BA in reducing parasitemia levels (trial 1: 19.72%; trial 2: 15.00%) compared with the untreated group (trial 1: 29.95%; trial 2: 28.27%) without adverse effects. These findings suggest that BA and its enantiomers have potential as seed compounds for development of antimalarial agents.

Unbiased Drug Target Prediction Reveals Sensitivity to Ferroptosis Inducers, HDAC and RTK Inhibitors in Melanoma Subtypes.

The utilization of PD1 and CTLA4 inhibitors has revolutionized the treatment of malignant melanoma (MM). However, resistance to targeted and immune-checkpoint-based therapies still poses a significant problem. Here, we mine large-scale MM proteogenomic data to identify druggable targets and forecast treatment efficacy and resistance. Leveraging protein profiles from established MM subtypes and molecular structures of 82 cancer treatment drugs, we identified nine candidate hub proteins, mTOR, FYN, PIK3CB, EGFR, MAPK3, MAP4K1, MAP2K1, SRC, and AKT1, across five distinct MM subtypes. These proteins are potential drug targets applicable to one or multiple MM subtypes. Additionally, by integrating proteogenomic profiles obtained from MM subtypes with MM cell line dependency and drug sensitivity data, we identified a total of 162 potentially targetable genes. Lastly, we identified 20 compounds exhibiting potential drug impact in at least one melanoma subtype. Employing these unbiased approaches, we have uncovered compounds targeting ferroptosis demonstrating a striking 30× fold difference in sensitivity among different subtypes. Our results suggest innovative and novel therapeutic strategies by stratifying melanoma samples through proteomic profiling, offering a spectrum of novel therapeutic interventions and prospects for combination therapy.

SeqDPI: A 1D-CNN approach for predicting binding affinity of kinase inhibitors.

Predicting drug target binding affinity has huge relevance in Modern drug discovery and drug repositioning processes which assist doctors to come up with new drugs or even use the existing drugs for new target proteins. In silico models, using advanced deep learning techniques could further assist these prediction tasks by providing most prominent drug target pairs. Considering these factors, a deep learning based algorithmic framework is developed in this study to support drug target interaction prediction. The proposed SeqDPI model extract the relevant drug and protein features from the one dimensional Sequential representation of the dataset considered using optimized CNN networks that deploy convolutions on varying length of amino acid subsequence's to capture hidden pattern, the convolved drug- protein features obtained are then used as an input to L2 penalized feed forward neural network which matches the local residue patterns in protein classes with molecular fingerprints of drugs to predict the binding strength for all drug target pairs. The proposed model reduces the convolution strain typically encountered in existing in silico models that utilize complex 3D structures of drug protein datasets. The result shows that the SeqDPI model achieves a mean square error MSE of (0.167) across cross validation folds, outperforming baseline models such as KronRLS (0.406), Simboost (0.226), and DeepPS (0.214). Additionally, SeqDPI attains a high CI score of 0.9114 on the benchmark KIBA dataset, demonstrating its statistical significance and computational efficiency compared to existing methods. This gives the relevance and effectiveness of SeqDPI model in accurately predicting binding affinities while working with simpler one-dimensional data, making it a robust and computationally cost-effective solution for drug-target interaction prediction.

Sanguinarine identified as a natural dual inhibitor of AURKA and CDK2 through network pharmacology and bioinformatics approaches

Cervical cancer (CA) continues to be a female malignant tumor with limited therapeutic options, resulting in a high mortality rate. Sanguinarine (SANG), a naturally occurring alkaloid, has demonstrated notable efficacy in preclinical treatment of CA. However, the mechanism through which SANG acts against CA is not fully understood. To address this, utilizing nine drug target prediction databases, we have successfully identified 379 potential targets for SANG. Venn diagram analysis compared 2367 CA-related targets from the GeneCards disease database, 2618 CA-closely related targets derived from multiple datasets in GEO through WGCNA analysis, and the 379 potential targets of SANG, resulting in 35 shared targets. Subsequently, by employing PPI network analysis, the Cytohubba plugin, the Human Protein Atlas, TCGA database data, and ROC curve analysis, we have identified AURKA and CDK2 as key targets of SANG in combating CA. Single-gene GSEA results suggest that the overexpression of AURKA and CDK2 is closely correlated with DNA replication, cell cycle progression, and various DNA repair pathways in CA. Molecular docking and molecular simulation dynamics analyses have confirmed the stable binding of both AURKA and CDK2 to SANG. In summary, by integrating diverse methodological approaches, this study discovered that SANG potentially inhibits the malignant features of CA by targeting AURKA and CDK2, thereby regulating DNA replication, cell cycle progression, and multiple DNA repair pathways. This lays a solid foundation for further exploring the pharmacological role of SANG in CA therapy. However, further in-depth in vitro and in vivo experiments are required to corroborate our findings.

Drug–target interaction prediction by integrating heterogeneous information with mutual attention network

BackgroundIdentification of drug–target interactions is an indispensable part of drug discovery. While conventional shallow machine learning and recent deep learning methods based on chemogenomic properties of drugs and target proteins have pushed this prediction performance improvement to a new level, these methods are still difficult to adapt to novel structures. Alternatively, large-scale biological and pharmacological data provide new ways to accelerate drug–target interaction prediction.MethodsHere, we propose DrugMAN, a deep learning model for predicting drug–target interaction by integrating multiplex heterogeneous functional networks with a mutual attention network (MAN). DrugMAN uses a graph attention network-based integration algorithm to learn network-specific low-dimensional features for drugs and target proteins by integrating four drug networks and seven gene/protein networks collected by a certain screening conditions, respectively. DrugMAN then captures interaction information between drug and target representations by a mutual attention network to improve drug–target prediction.ResultsDrugMAN achieved the best performance compared with cheminformation-based methods SVM, RF, DeepPurpose and network-based deep learing methods DTINet and NeoDT in four different scenarios, especially in real-world scenarios. Compared with SVM, RF, deepurpose, DTINet, and NeoDT, DrugMAN showed the smallest decrease in AUROC, AUPRC, and F1-Score from warm-start to Both-cold scenarios. This result is attributed to DrugMAN’s learning from heterogeneous data and indicates that DrugMAN has a good generalization ability. Taking together, DrugMAN spotlights heterogeneous information to mine drug–target interactions and can be a powerful tool for drug discovery and drug repurposing.

Identification of core genes and molecular prediction of drug targets for countering BPA-induced olfactory bulb neurotoxicity in male mice

Bisphenol A (BPA) is ubiquitous in plastics, which can modify and improve the applicability and durability of plastics. Previous laboratory studies have shown that BPA can trigger cognitive impairment and depression. The olfactory bulb (OB) is significantly related to cognition and depression. However, there is a deficiency in information on BPA-induced OB neurotoxicity. Therefore, we analyzed the OB tissues of male mice at the transcriptional level after BPA poisoning at four different levels of concentration (0, 0.01, 0.1, and 1 μg/mL). Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and weighted gene co-expression network analysis (WGCNA) were used to screen critical pathways and core genes. The result demonstrated that the PI3K-AKT signaling pathway might play a crucial role in the effects of BPA on the OB. In addition, two genes of the PI3K-AKT signaling pathway, the colony stimulating factor-1 receptor (Csf1r) and the toll-like receptor 2 (Tlr2), were screened by the protein-protein interaction networks. Furthermore, molecular docking identified ceftolozane as a potential drug candidate that could counteract BPA-related OB neurotoxicity. Conclusively, our results confirmed that BPA induced OB damage in male mice through the PI3K-AKT pathway and proposed that ceftolozane might reduce BPA-induced OB neurotoxicity.

A molecular video-derived foundation model for scientific drug discovery

Accurate molecular representation of compounds is a fundamental challenge for prediction of drug targets and molecular properties. In this study, we present a molecular video-based foundation model, named VideoMol, pretrained on 120 million frames of 2 million unlabeled drug-like and bioactive molecules. VideoMol renders each molecule as a video with 60-frame and designs three self-supervised learning strategies on molecular videos to capture molecular representation. We show high performance of VideoMol in predicting molecular targets and properties across 43 drug discovery benchmark datasets. VideoMol achieves high accuracy in identifying antiviral molecules against common diverse disease-specific drug targets (i.e., BACE1 and EP4). Drugs screened by VideoMol show better binding affinity than molecular docking, revealing the effectiveness in understanding the three-dimensional structure of molecules. We further illustrate interpretability of VideoMol using key chemical substructures.

MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction.

The prediction of drug-target affinity (DTA) plays a crucial role in drug development and the identification of potential drug targets. In recent years, computer-assisted DTA prediction has emerged as a significant approach in this field. In this study, we propose a multi-modal deep learning framework called MMD-DTA for predicting drug-target binding affinity and binding regions. The model can predict DTA while simultaneously learning the binding regions of drug-target interactions through unsupervised learning. To achieve this, MMD-DTA first uses graph neural networks and target structural feature extraction network to extract multi-modal information from the sequences and structures of drugs and targets. It then utilizes the feature interaction and fusion modules to generate interaction descriptors for predicting DTA and interaction strength for binding region prediction. Our experimental results demonstrate that MMD-DTA outperforms existing models based on key evaluation metrics. Furthermore, external validation results indicate that MMD-DTA enhances the generalization capability of the model by integrating sequence and structural information of drugs and targets. The model trained on the benchmark dataset can effectively generalize to independent virtual screening tasks. The visualization of drug-target binding region prediction showcases the interpretability of MMD-DTA, providing valuable insights into the functional regions of drug molecules that interact with proteins.

Network-based hub biomarker discovery for glaucoma

ObjectiveGlaucoma is an optic neuropathy and the leading cause of irreversible blindness worldwide. However, the early detection of glaucoma remains challenging, as chronic forms of glaucoma remain largely asymptomatic until...

Drug-Target Prediction Based on Dynamic Heterogeneous Graph Convolutional Network.

Novel drug-target interaction (DTI) prediction is crucial in drug discovery and repositioning. Recently, graph neural network (GNN) has shown promising results in identifying DTI by using thresholds to construct heterogeneous graphs. However, an empirically selected threshold can lead to loss of valuable information, especially in sparse networks, a common scenario in DTI prediction. To make full use of insufficient information, we propose a DTI prediction model based on Dynamic Heterogeneous Graph (DT-DHG). And progressive learning is introduced to adjust the receptive fields of node. The experimental results show that our method significantly improves the performance of the original GNNs and is robust against the choices of backbones. Meanwhile, DT-DHG outperforms the state-of-the-art methods and effectively predicts novel DTIs.