Novel vanadyl complexes synthesis, characterization and interactions with bovine serum albumin-effects on STZ- diabetes rats.

Drug-protein interactions are essential since most administered drugs bind abundantly and reversibly to serum albumin and are delivered mainly as a complex with protein. The nature and strength of drug-protein interactions have a big impact on how a drug works biologically. The binding parameters are useful in studying the pharmacological response of drugs and the designing of dosage forms. Serum albumin is regarded as optimal model for in vitro research on drug-protein interaction since it is the main protein that binds medicines and other physiological components. In this perspective, binary complex have been synthesized and characterized, from vanadium metal and acetylacetone(4,4,4-trifluoro-1-(2-theonyl)-1,3-butanedione). Imidazole, 2-Methyl-imidazole, and 2-Ethyl-imidazole auxiliary ligands were employed for the synthesis of ternary complexes. Additionally, UV absorption and fluorescence emission spectroscopy were used to examine the binding interactions between vanadium complexes and Bovine Serum Albumin. The outcomes of the binding studies and spectral approaches were in strong agreement with one another. These complexes upon inoculation into diabetes-induced Wistar rats stabilized their serum glucose levels within 3 days. From various studies, it was discovered that the ordering of glucose-lowering actions of these metal complexes were equivalent. The vanadium ternary metal complex derived from (4,4,4-trifluoro-1-(2-theonyl)-1,3-butanedione) and imidazole as ligands is the best among the other metal vanadium complexes.

Exploring Tau Fibril-Disaggregating and Antioxidating Molecules Binding to Membrane-Bound Amyloid Oligomers Using Machine Learning-Enhanced Docking and Molecular Dynamics.

Intracellular tau fibrils are sources of neurotoxicity and oxidative stress in Alzheimer's. Current drug discovery efforts have focused on molecules with tau fibril disaggregation and antioxidation functions. However, recent studies suggest that membrane-bound tau-containing oligomers (mTCOs), smaller and less ordered than tau fibrils, are neurotoxic in the early stage of Alzheimer's. Whether tau fibril-targeting molecules are effective against mTCOs is unknown. The binding of epigallocatechin-3-gallate (EGCG), CNS-11, and BHT-CNS-11 to in silico mTCOs and experimental tau fibrils was investigated using machine learning-enhanced docking and molecular dynamics simulations. EGCG and CNS-11 have tau fibril disaggregation functions, while the proposed BHT-CNS-11 has potential tau fibril disaggregation and antioxidation functions like EGCG. Our results suggest that the three molecules studied may also bind to mTCOs. The predicted binding probability of EGCG to mTCOs increases with the protein aggregate size. In contrast, the predicted probability of CNS-11 and BHT-CNS-11 binding to the dimeric mTCOs is higher than binding to the tetrameric mTCOs for the homo tau but not for the hetero tau-amylin oligomers. Our results also support the idea that anionic lipids may promote the binding of molecules to mTCOs. We conclude that tau fibril-disaggregating and antioxidating molecules may bind to mTCOs, and that mTCOs may also be useful targets for Alzheimer's drug design.

DeepMPF: deep learning framework for predicting drug-target interactions based on multi-modal representation with meta-path semantic analysis.

BACKGROUND: Drug-target interaction (DTI) prediction has become a crucial prerequisite in drug design and drug discovery. However, the traditional biological experiment is time-consuming and expensive, as there are abundant complex interactions present in the large size of genomic and chemical spaces. For alleviating this phenomenon, plenty of computational methods are conducted to effectively complement biological experiments and narrow the search spaces into a preferred candidate domain. Whereas, most of the previous approaches cannot fully consider association behavior semantic information based on several schemas to represent complex the structure of heterogeneous biological networks. Additionally, the prediction of DTI based on single modalities cannot satisfy the demand for prediction accuracy. METHODS: We propose a multi-modal representation framework of 'DeepMPF' based on meta-path semantic analysis, which effectively utilizes heterogeneous information to predict DTI. Specifically, we first construct protein-drug-disease heterogeneous networks composed of three entities. Then the feature information is obtained under three views, containing sequence modality, heterogeneous structure modality and similarity modality. We proposed six representative schemas of meta-path to preserve the high-order nonlinear structure and catch hidden structural information of the heterogeneous network. Finally, DeepMPF generates highly representative comprehensive feature descriptors and calculates the probability of interaction through joint learning. RESULTS: To evaluate the predictive performance of DeepMPF, comparison experiments are conducted on four gold datasets. Our method can obtain competitive performance in all datasets. We also explore the influence of the different feature embedding dimensions, learning strategies and classification methods. Meaningfully, the drug repositioning experiments on COVID-19 and HIV demonstrate DeepMPF can be applied to solve problems in reality and help drug discovery. The further analysis of molecular docking experiments enhances the credibility of the drug candidates predicted by DeepMPF. CONCLUSIONS: All the results demonstrate the effectively predictive capability of DeepMPF for drug-target interactions. It can be utilized as a useful tool to prescreen the most potential drug candidates for the protein. The web server of the DeepMPF predictor is freely available at http://120.77.11.78/DeepMPF/ , which can help relevant researchers to further study.

Molecular Mechanism of Interaction of Curcumin with BSA, Surfactants and Live E. Coli Cell Membrane Revealed by Fluorescence Spectroscopy and Confocal Microscopy.

Clinical trials on the therapeutic effect of curcumin have proven to be highly effective against many diseases including cancer and Alzheimer's. However, the molecular mechanism of interaction of curcumin with protein and live cell membrane is poorly understood. Here, we report the mechanism of interaction of curcumin with bovine serum albumin (BSA) and live E. coli cell membrane in the presence of organized assemblies of sodium dodecyl sulfate (SDS) and cetrimonium bromide (CTAB) by fluorescence spectroscopy, laser-scanning confocal microscopy, and computation. Enhanced binding constant, blue-shifted emission spectra, and imaging of heterogeneous FRET on live bacteria cell membrane strongly indicate the complex formation of curcumin with strong hydrophobic interaction, which is further validated by computation. Finally, our results may shed light on the efficient strategy of applications of curcumin as a natural therapeutic lead in clinical trials against many life-threatening diseases.

Mechanistic Insight into Binding of Huperzine A with Human Serum Albumin: Computational and Spectroscopic Approaches.

Human serum albumin (HSA) is the most abundant protein in plasma synthesized by the liver and the main modulator of fluid distribution between body compartments. It has an amazing capacity to bind with multiple ligands, offering a store and transporter for various endogenous and exogenous compounds. Huperzine A (HpzA) is a natural sesquiterpene alkaloid found in Huperzia serrata and used in various neurological conditions, including Alzheimer's disease (AD). This study elucidated the binding of HpzA with HSA using advanced computational approaches such as molecular docking and molecular dynamic (MD) simulation followed by fluorescence-based binding assays. The molecular docking result showed plausible interaction between HpzA and HSA. The MD simulation and principal component analysis (PCA) results supported the stable interactions of the protein-ligand complex. The fluorescence assay further validated the in silico study, revealing significant binding affinity between HpzA and HSA. This study advocated that HpzA acts as a latent HSA binding partner, which may be investigated further in AD therapy in experimental settings.

A neural network-based method for polypharmacy side effects prediction.

BACKGROUND: Polypharmacy is a type of treatment that involves the concurrent use of multiple medications. Drugs may interact when they are used simultaneously. So, understanding and mitigating polypharmacy side effects are critical for patient safety and health. Since the known polypharmacy side effects are rare and they are not detected in clinical trials, computational methods are developed to model polypharmacy side effects. RESULTS: We propose a neural network-based method for polypharmacy side effects prediction (NNPS) by using novel feature vectors based on mono side effects, and drug-protein interaction information. The proposed method is fast and efficient which allows the investigation of large numbers of polypharmacy side effects. Our novelty is defining new feature vectors for drugs and combining them with a neural network architecture to apply for the context of polypharmacy side effects prediction. We compare NNPS on a benchmark dataset to predict 964 polypharmacy side effects against 5 well-established methods and show that NNPS achieves better results than the results of all 5 methods in terms of accuracy, complexity, and running time speed. NNPS outperforms about 9.2% in Area Under the Receiver-Operating Characteristic, 12.8% in Area Under the Precision-Recall Curve, 8.6% in F-score, 10.3% in Accuracy, and 18.7% in Matthews Correlation Coefficient with 5-fold cross-validation against the best algorithm among other well-established methods (Decagon method). Also, the running time of the Decagon method which is 15 days for one fold of cross-validation is reduced to 8 h by the NNPS method. CONCLUSIONS: The performance of NNPS is benchmarked against 5 well-known methods, Decagon, Concatenated drug features, Deep Walk, DEDICOM, and RESCAL, for 964 polypharmacy side effects. We adopt the 5-fold cross-validation for 50 iterations and use the average of the results to assess the performance of the NNPS method. The evaluation of the NNPS against five well-known methods, in terms of accuracy, complexity, and running time speed shows the performance of the presented method for an essential and challenging problem in pharmacology. Datasets and code for NNPS algorithm are freely accessible at https://github.com/raziyehmasumshah/NNPS .

Review and comparative assessment of similarity-based methods for prediction of drug-protein interactions in the druggable human proteome.

Drug-protein interactions (DPIs) underlie the desired therapeutic actions and the adverse side effects of a significant majority of drugs. Computational prediction of DPIs facilitates research in drug discovery, characterization and repurposing. Similarity-based methods that do not require knowledge of protein structures are particularly suitable for druggable genome-wide predictions of DPIs. We review 35 high-impact similarity-based predictors that were published in the past decade. We group them based on three types of similarities and their combinations that they use. We discuss and compare key aspects of these methods including source databases, internal databases and their predictive models. Using our novel benchmark database, we perform comparative empirical analysis of predictive performance of seven types of representative predictors that utilize each type of similarity individually and all possible combinations of similarities. We assess predictive quality at the database-wide DPI level and we are the first to also include evaluation over individual drugs. Our comprehensive analysis shows that predictors that use more similarity types outperform methods that employ fewer similarities, and that the model combining all three types of similarities secures area under the receiver operating characteristic curve of 0.93. We offer a comprehensive analysis of sensitivity of predictive performance to intrinsic and extrinsic characteristics of the considered predictors. We find that predictive performance is sensitive to low levels of similarities between sequences of the drug targets and several extrinsic properties of the input drug structures, drug profiles and drug targets. The benchmark database and a webserver for the seven predictors are freely available at http://biomine.cs.vcu.edu/servers/CONNECTOR/.

Recent advances in magnetic digital microfluidic platforms.

Magnetic Digital microfluidics (DMF), which enables the manipulation of droplets containing different types of samples and reagents by permanent magnets or electromagnet arrays, has been used as a promising platform technology for bioanalytical and preparative assays. This is due to its unique advantages such as simple and "power free" operation, easy assembly, great compatibility with auto control systems, and dual functionality of magnetic particles (actuation and target attachment). Over the past decades, magnetic DMF technique has gained a widespread attention in many fields such as sample-to-answer molecular diagnostics, immunoassays, cell assays, on-demand chemical synthesis, and single-cell manipulation. In the first part of this review, we summarised features of magnetic DMF. Then, we introduced the actuation mechanisms and fabrication of magnetic DMF. Furthermore, we discussed five main applications of magnetic DMF, namely drug screening, protein assays, polymerase chain reaction (PCR), cell manipulation, and chemical analysis and synthesis. In the last part of the review, current challenges and limitations with magnetic DMF technique were discussed, such as biocompatibility, automation of microdroplet control systems, and microdroplet evaporation, with an eye on towards future development.

Label-Free Bioelectrochemical Methods for Evaluation of Anticancer Drug Effects at a Molecular Level.

Cancer is a multifactorial family of diseases that is still a leading cause of death worldwide. More than 100 different types of cancer affecting over 60 human organs are known. Chemotherapy plays a central role for treating cancer. The development of new anticancer drugs or new uses for existing drugs is an exciting and increasing research area. This is particularly important since drug resistance and side effects can limit the efficacy of the chemotherapy. Thus, there is a need for multiplexed, cost-effective, rapid, and novel screening methods that can help to elucidate the mechanism of the action of anticancer drugs and the identification of novel drug candidates. This review focuses on different label-free bioelectrochemical approaches, in particular, impedance-based methods, the solid supported membranes technique, and the DNA-based electrochemical sensor, that can be used to evaluate the effects of anticancer drugs on nucleic acids, membrane transporters, and living cells. Some relevant examples of anticancer drug interactions are presented which demonstrate the usefulness of such methods for the characterization of the mechanism of action of anticancer drugs that are targeted against various biomolecules.

Characterization of solution-phase drug-protein interactions by ultrafast affinity extraction.

A number of tools based on high-performance affinity separations have been developed for studying drug-protein interactions. An example of one recent approach is ultrafast affinity extraction. This method has been employed to examine the free (or non-bound) fractions of drugs and other solutes in simple or complex samples that contain soluble binding agents. These free fractions have also been used to determine the binding constants and rate constants for the interactions of drugs with these soluble agents. This report describes the general principles of ultrafast affinity extraction and the experimental conditions under which it can be used to characterize such interactions. This method will be illustrated by utilizing data that have been obtained when using this approach to measure the binding and dissociation of various drugs with the serum transport proteins human serum albumin and alpha1-acid glycoprotein. A number of practical factors will be discussed that should be considered in the design and optimization of this approach for use with single-column or multi-column systems. Techniques will also be described for analyzing the resulting data for the determination of free fractions, rate constants and binding constants. In addition, the extension of this method to complex samples, such as clinical specimens, will be considered.

Unlocking the potential of beta sitosterol: Augmenting the suppression of oral cancer cells through extrinsic and intrinsic signalling mechanisms.

The global increase in the prevalence of oral neoplasms and related deaths can be attributed to social development and lifestyle factors, leading to poor prognosis and a lack of early clinical detection. Oral cancer ranks ranked sixth mostly diagnosed cancer and is a leading cause of cancer-related deaths. In light of these circumstances, our objective was to assess the potential of ß-sitosterol, a naturally occurring herbal compound, as an anticancer agent against KB cells, a representative cell line for oral cancer. Our study primarily focused on evaluating the cytotoxic effect and mRNA expression of apoptotic proteins by ß-sitosterol on KB cells. The results demonstrated a remarkable cytotoxic effect, leading to cell death. Further investigation using flow cytometric analysis revealed that this cell death was mediated through the initiation of the apoptotic signalling by ß-sitosterol. The use of the bioinformatic tool, STITCH, supported our study by predicting drug-protein interactions and suggesting that ß-sitosterol may play a significant role in targeting apoptotic pathways. Additionally, docking results were employed to validate the findings demonstrating high binding affinity of ß-sitosterol with apoptotic-mediated signalling targets. To gain deeper insights into the molecular insights, we measured mRNA levels for BAX, BCL-2, MCL-1, P53, P21, MDM2, caspase3, and caspase9. Based on our comprehensive findings, our study concludes that ß-sitosterol holds significant therapeutic potential against oral cancer cells. These results strongly suggest that this herbal compound should be further explored as a potential treatment option for oral cancer for clinical trial.

The Specific Binding and Promotion Effect of Azoles on Human Aldo-Keto Reductase 7A2.

Human AKR 7A2 broadly participates in the metabolism of a number of exogenous and endogenous compounds. Azoles are a class of clinically widely used antifungal drugs, which are usually metabolized by CYP 3A4, CYP2C19, and CYP1A1, etc. in vivo. The azole-protein interactions that human AKR7A2 participates in remain unreported. In this study, we investigated the effect of the representative azoles (miconazole, econazole, ketoconazole, fluconazole, itraconazole, voriconazole, and posaconazole) on the catalysis of human AKR7A2. The steady-state kinetics study showed that the catalytic efficiency of AKR7A2 enhanced in a dose-dependent manner in the presence of posaconazole, miconazole, fluconazole, and itraconazole, while it had no change in the presence of econazole, ketoconazole, and voriconazole. Biacore assays demonstrated that all seven azoles were able to specifically bind to AKR7A2, among which itraconazole, posaconazole, and voriconazole showed the strongest binding. Blind docking predicted that all azoles were apt to preferentially bind at the entrance of the substrate cavity of AKR7A2. Flexible docking showed that posaconazole, located at the region, can efficiently lower the binding energy of the substrate 2-CBA in the cavity compared to the case of no posaconazole. This study demonstrates that human AKR7A2 can interact with some azole drugs, and it also reveals that the enzyme activity can be regulated by some small molecules. These findings will enable a better understanding of azole-protein interactions.

Specifics of Metabolite-Protein Interactions and Their Computational Analysis and Prediction.

Computational approaches to the characterization and prediction of compound-protein interactions have a long research history and are well established, driven primarily by the needs of drug development. While, in principle, many of the computational methods developed in the context of drug development can also be applied directly to the investigation of metabolite-protein interactions, the interactions of metabolites with proteins (enzymes) are characterized by a number of particularities that result from their natural evolutionary origin and their biological and biochemical roles, as well as from a different problem setting when investigating them. In this review, these special aspects will be highlighted and recent research on them and developed computational approaches presented, along with available resources. They concern, among others, binding promiscuity, allostery, the role of posttranslational modifications, molecular steering and crowding effects, and metabolic conversion rate predictions. Recent breakthroughs in the field of protein structure prediction and newly developed machine learning techniques are being discussed as a tremendous opportunity for developing a more detailed molecular understanding of metabolism.

Drug-protein interaction prediction via variational autoencoders and attention mechanisms.

During the process of drug discovery, exploring drug-protein interactions (DPIs) is a key step. With the rapid development of biological data, computer-aided methods are much faster than biological experiments. Deep learning methods have become popular and are mainly used to extract the characteristics of drugs and proteins for further DPIs prediction. Since the prediction of DPIs through machine learning cannot fully extract effective features, in our work, we propose a deep learning framework that uses variational autoencoders and attention mechanisms; it utilizes convolutional neural networks (CNNs) to obtain local features and attention mechanisms to obtain important information about drugs and proteins, which is very important for predicting DPIs. Compared with some machine learning methods on the C.elegans and human datasets, our approach provides a better effect. On the BindingDB dataset, its accuracy (ACC) and area under the curve (AUC) reach 0.862 and 0.913, respectively. To verify the robustness of the model, multiclass classification tasks are performed on Davis and KIBA datasets, and the ACC values reach 0.850 and 0.841, respectively, thus further demonstrating the effectiveness of the model.

Analytical methods for obtaining binding parameters of drug-protein interactions: A review.

The study of drug-protein interactions can reveal the corresponding binding mechanisms, providing valuable information for the early phase drug development and development of new drugs. This article reviews the methods used for obtaining the binding parameters of drug-protein systems. The methods include equilibrium dialysis, high-performance affinity chromatography, capillary electrophoresis, spectroscopy, calorimetry, competition and displacement, mass spectrometry, fluorescence resonance energy transfer, and thermal stability shift analysis. Relevant parameters include the association constant, number of binding sites, thermodynamic properties, binding force types, binding site types, binding distances, changes in protein conformation, and changes in protein stability. In addition, the review also summarizes the principles, advantages, and limitations of each method in detail. The comparison of parameter information can not only guide method selection but also provide valuable reference information for in-depth exploration of drug-protein interaction mechanisms.

A role of salt bridges in mediating drug potency: A lesson from the N-myristoyltransferase inhibitors.

The salt bridge is the strongest non-covalent interaction in nature and is known to participate in protein folding, protein-protein interactions, and molecular recognition. However, the role of salt bridges in the context of drug design has remained not well understood. Here, we report that a common feature in the mechanism of inhibition of the N-myristoyltransferases (NMT), promising targets for the treatment of protozoan infections and cancer, is the formation of a salt bridge between a positively charged chemical group of the small molecule and the negatively charged C-terminus of the enzyme. Substituting the inhibitor positively charged amine group with a neutral methylene group prevents the formation of the salt bridge and leads to a dramatic activity loss. Molecular dynamics simulations have revealed that salt bridges stabilize the NMT-ligand complexes by functioning as molecular clips that stabilize the conformation of the protein structure. As such, the creation of salt bridges between the ligands and their protein targets may find an application as a valuable tool in rational drug design.

Stimulation of Ca2+ -ATPase Transport Activity by a Small-Molecule Drug.

The sarco(endo)plasmic reticulum Ca2+ -ATPase (SERCA) hydrolyzes ATP to transport Ca2+ from the cytoplasm to the sarcoplasmic reticulum (SR) lumen, thereby inducing muscle relaxation. Dysfunctional SERCA has been related to various diseases. The identification of small-molecule drugs that can activate SERCA may offer a therapeutic approach to treat pathologies connected with SERCA malfunction. Herein, we propose a method to study the mechanism of interaction between SERCA and novel SERCA activators, i. e. CDN1163, using a solid supported membrane (SSM) biosensing approach. Native SR vesicles or reconstituted proteoliposomes containing SERCA were adsorbed on the SSM and activated by ATP concentration jumps. We observed that CDN1163 reversibly interacts with SERCA and enhances ATP-dependent Ca2+ translocation. The concentration dependence of the CDN1163 effect provided an EC50 =6.0±0.3 µM. CDN1163 was shown to act directly on SERCA and to exert its stimulatory effect under physiological Ca2+ concentrations. These results suggest that CDN1163 interaction with SERCA can promote a protein conformational state that favors Ca2+ release into the SR lumen.

Evaluation of the Interactions between Human Serum Albumin (HSA) and Non-Steroidal Anti-Inflammatory (NSAIDs) Drugs by Multiwavelength Molecular Fluorescence, Structural and Computational Analysis.

The interaction between drugs and transport proteins, such as albumins, is a key factor in drug bioavailability. One of the techniques commonly used for the evaluation of the drug-protein complex formation is fluorescence. This work studies the interaction of human serum albumin (HSA) with four non-steroidal anti-inflammatory drugs (NSAIDs)-ibuprofen, flurbiprofen, naproxen, and diflunisal-by monitoring the fluorescence quenching when the drug-albumin complex is formed. Two approaches-the double logarithm Stern-Volmer equation and the STAR program-are used to evaluate the binding parameters. The results are analyzed considering the binding properties, determined by using other complementary techniques and the available structural information of albumin complexes with NSAID-related compounds. Finally, this combined analysis has been synergistically used to interpret the binding of flurbiprofen to HSA.

Ligand-protein interactions of plant-isolated (9z,12z)-octadeca-9,12-dienoic acid with Β-ketoacyl-Acp synthase (KasA) in potential anti-tubercular drug designing.

Mycobacterium tuberculosis remains one of the world's contributors to mortality. With the emergence of SARS-CoV-2 coinfections, patients with TB are predisposed to being more heavily weighed down by COVID-19 disease and its opportunistic coinfections. The severity of the disease coupled with drug resistance on the currently used drugs warrants for the search for alternative remedies from synthetic agents, semisynthetics and natural products that include plants. Africa is rich in plant diversity with a promise as sources of drug agents, one of which is Eichhornia crassipes. This work aimed at isolating a fatty acid and dock it to ß-ketoacyl-ACP synthase for possible anti-TB drug development prospects using computational tools. (9z,12z)-Octadeca-9,12-dienoic acid was isolated from Eichhornia crassipes for the first time using chromatographic techniques and identified using 1D and 2D NMR spectroscopic methods (1H NMR, COSY, HSQC, HMBC and 13C NMR). The compound was then docked to ß-ketoacyl-ACP synthase (KasA), an essential member of the b-ketoacyl synthases encoded in the M. tuberculosis genome in comparison with its co-crystallized ligand JSF-3285, also for the first time. (9z,12z)-Octadeca-9,12-dienoic acid interacted with only phenylalanine239 and proline201 while JSF-3285 interacted with proline201, glutamine120, alanine119, leucine116, glutamine199, histadine345, phenylalanine239, glycine240 and glycine200. (9z,12z)-Octadeca-9,12-dienoic acid had a ligand efficiency of 0.24, compared to the co-crystallized ligand's 0.36. The compound was too flexible and elongated with -4.72 KCalmol-1 binding energy. Despite some unfavourable physico-chemical properties, the compound still provides reliable interactions that only require logical structural modifications by the addition of polar regions amongst others to increase interactions and ligand efficiency, which can consequently stand to be a better potential drug lead. For the first time, plant-based (9z,12z)-Octadeca-9,12-dienoic acid isolated from Eichhornia crassipes was shown to interact fairly well with ß-ketoacyl-ACP synthase and proved to be a potential starting material from which anti-tubercular drugs can be designed.

DLS: A Link Prediction Method Based on Network Local Structure for Predicting Drug-Protein Interactions.

The studies on drug-protein interactions (DPIs) had significant for drug repositioning, drug discovery, and clinical medicine. The biochemical experimentation (in vitro) requires a long time and high cost to be confirmed because it is difficult to estimate. Therefore, a feasible solution is to predict DPIs efficiently with computers. We propose a link prediction method based on drug-protein interaction (DPI) local structural similarity (DLS) for predicting the DPIs. The DLS method combines link prediction and binary network structure to predict DPIs. The ten-fold cross-validation method was applied in the experiment. After comparing the predictive capability of DLS with the improved similarity-based network prediction method, the results of DLS on the test set are significantly better. Moreover, several candidate proteins were predicted for three approved drugs, namely captopril, desferrioxamine and losartan, and these predictions are further validated by the literature. In addition, the combination of the Common Neighborhood (CN) method and the DLS method provides a new idea for the integrated application of the link prediction method.