Submit to CIMB Review for CIMB Propose a Special Issue

Journal Menu

Journal Browser

New Sight: Enzymes as Targets for Drug Development

Special Issue Editors
Special Issue Information
Published Papers

A special issue of Current Issues in Molecular Biology (ISSN 1467-3045). This special issue belongs to the section "Molecular Pharmacology".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 24204

Share This Special Issue

Special Issue Editor

Prof. Dr. Sung-Kun (Sean) Kim

E-Mail Website
Guest Editor

Department of Natural Sciences, Northeastern State University, Broken Arrow, OK 74014, USA
Interests: biochemistry; enzymology; drug discovery; SELEX (systematic evolution of ligands by exponential enrichment); in vitro selection technique
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The most attractive targets for drug development are considered enzymes in the pharmaceutical community. Characterization of enzymes is, therefore, critical in understanding their reactions. Many analytical methods are needed to complete characterization such as purification; kinetics; protein stabilization; optimal conditions for pH; temperature; ionic strength; subtract or product binding; ligand/inhibitor/protein interactions; three-dimensional structure; and conformational changes. Recently, in silico analysis has made a huge contribution in enzyme characterization. Molecular docking and molecular dynamics should be included as major techniques. This Special Issue brings together a large number of intriguing subjects to promote ideas on enzymes as targets for drug development.

It is envisioned that the following topics would be included in the Special Issue:

Improvement of enzyme purification;
Development of novel inhibitors;
Investigation of enzyme mechanism;
Understanding enzyme conformation changes.

Prof. Dr. Sung-Kun (Sean) Kim
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Current Issues in Molecular Biology is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (12 papers)

Download All Papers

Editorial

Jump to: Research

3 pages, 198 KiB

Open AccessEditorial

New Sight: Enzymes as Targets for Drug Development

by Sung-Kun Kim

Curr. Issues Mol. Biol. 2023, 45(9), 7650-7652; https://doi.org/10.3390/cimb45090482 - 20 Sep 2023

Viewed by 974

Abstract

In the dynamic realm of medical research, a resounding chord is struck by recent studies that have propelled drug discovery to new horizons across a spectrum of disciplines [...] Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

Research

Jump to: Editorial

13 pages, 3497 KiB

Open AccessArticle

Recombinant Soybean Lipoxygenase 2 (GmLOX2) Acts Primarily as a ω6(S)-Lipoxygenase

by Elena O. Smirnova, Alevtina M. Egorova, Natalia V. Lantsova, Ivan R. Chechetkin, Yana Y. Toporkova and Alexander N. Grechkin

Curr. Issues Mol. Biol. 2023, 45(8), 6283-6295; https://doi.org/10.3390/cimb45080396 - 28 Jul 2023

Cited by 1 | Viewed by 1139

Abstract

The lipoxygenase (LOX) cascade is a source of bioactive oxylipins that play a regulatory role in plants, animals, and fungi. Soybean (Glycine max (L.) Merr.) LOXs are the classical models for LOX research. Progress in genomics has uncovered a large diversity of GmLOX isoenzymes. Most of them await biochemical investigations. The catalytic properties of recombinant soybean LOX2 (GmLOX2) are described in the present work. The GmLOX2 gene has been cloned before, but only for nucleotide sequencing, while the recombinant protein was not prepared and studied. In the present work, the recombinant GmLOX2 behavior towards linoleic, α-linolenic, eicosatetraenoic (20:4), eicosapentaenoic (20:5), and hexadecatrienoic (16:3) acids was examined. Linoleic acid was a preferred substrate. Oxidation of linoleic acid afforded 94% optically pure (13S)-hydroperoxide and 6% racemic 9-hydroperoxide. GmLOX2 was less active on other substrates but possessed an even higher degree of regio- and stereospecificity. For example, it converted α-linolenic acid into (13S)-hydroperoxide at about 98% yield. GmLOX2 showed similar specificity towards other substrates, producing (15S)-hydroperoxides (with 20:4 and 20:5) or (11S)-hydroperoxide (with 16:3). Thus, the obtained data demonstrate that soybean GmLOX2 is a specific (13S)-LOX. Overall, the catalytic properties of GmLOX2 are quite similar to those of GmLOX1, but pH is optimum. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Graphical abstract

12 pages, 2317 KiB

Open AccessArticle

Different Directions of Effects of Polyclonal IgG Antibodies from Patients with Schizophrenia and Healthy Individuals on Cell Death In Vitro: A Pilot Study

by Elena V. Epimakhova, Liudmila P. Smirnova, Daria V. Kazantseva, Daria A. Kamaeva and Svetlana A. Ivanova

Curr. Issues Mol. Biol. 2023, 45(4), 3168-3179; https://doi.org/10.3390/cimb45040206 - 6 Apr 2023

Cited by 1 | Viewed by 1291

Abstract

Numerous studies indicate the involvemen of oxidative stress in the pathogenesis of schizophrenia. It has been shown that the serum pool of antibodies in patients with schizophrenia contains catalytically active antibodies (abzymes) that have a wide range of activities, including redox properties. In the present work, the effects of IgGs—having oxidoreductase activities—isolated from the serum of patients with schizophrenia and healthy individuals were studied in vitro. The IgGs were purified by affinity chromatography followed by an SDS-PAGE analysis of homogeneity in a 4–18% gradient gel. The catalase and superoxide dismutase (SOD) activities of the IgGs were measured spectrophotometrically using a kinetic module. Human neuroblastoma SH-SY5Y cells were cultured with IgG at a final concentration of 0.2 mg/mL for 24 h. In a parallel experiment, tert-butyl hydroperoxide was used as an oxidative stressor. The number of dead cells after incubation was determined with fluorescent dyes, propidium iodide and Hoechst, by high-throughput screening on the CellInsight CX7 platform. A cytotoxic effect of the IgG from the schizophrenia patients on SH-SY5Y cells was detected after 24 h incubation. A correlation was found between the SOD activity of the IgGs and IgG-induced cell death. Under the induced oxidative stress, the cytotoxic effect of the IgG from the patients with schizophrenia on the SH-SY5Y cell line was five times stronger. Meanwhile, the IgG from the healthy individuals exerted a cytoprotective effect on the cultured cells, accompanied by high catalase activity. Thus, the observed influence on cell viability depends on the catalytic properties of the abzymes. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

21 pages, 4414 KiB

Open AccessArticle

The Potential of Stilbene Compounds to Inhibit M^pro Protease as a Natural Treatment Strategy for Coronavirus Disease-2019

by Ayesha Naseem, Fatima Rasool, Abrar Ahmed and Wayne G. Carter

Curr. Issues Mol. Biol. 2023, 45(1), 12-32; https://doi.org/10.3390/cimb45010002 - 20 Dec 2022

Cited by 3 | Viewed by 1721

Abstract

COVID-19 disease has had a global impact on human health with increased levels of morbidity and mortality. There is an unmet need to design and produce effective antivirals to treat COVID-19. This study aimed to explore the potential ability of natural stilbenes to inhibit the M^pro protease, an acute respiratory syndrome coronavirus-2 (SARS-CoV-2) enzyme involved in viral replication. The binding affinities of stilbene compounds against M^pro were scrutinized using molecular docking, prime molecular mechanics-generalized Born surface area (MM-GBSA) energy calculations, and molecular dynamic simulations. Seven stilbene molecules were docked with M^pro and compared with GC376 and N3, antivirals with demonstrated efficacy against M^pro. Ligand binding efficiencies and polar and non-polar interactions between stilbene compounds and M^pro were analyzed. The binding affinities of astringin, isorhapontin, and piceatannol were −9.319, −8.166, and −6.291 kcal/mol, respectively, and higher than either GC376 or N3 at −6.976 and −6.345 kcal/mol, respectively. Prime MM-GBSA revealed that these stilbene compounds exhibited useful ligand efficacy and binding affinity to M^pro. Molecular dynamic simulation studies of astringin, isorhapontin, and piceatannol showed their stability at 300 K throughout the simulation time. Collectively, these results suggest that stilbenes such as astringin, isorhapontin, and piceatannol could provide useful natural inhibitors of M^pro and thereby act as novel treatments to limit SARS-CoV-2 replication. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

10 pages, 2040 KiB

Open AccessArticle

Phosphodiesterase 5 Inhibitor Potentiates Epigallocatechin 3-O-Gallate-Induced Apoptotic Cell Death via Activation of the cGMP Signaling Pathway in Caco-2 Cells

by Jaehoon Bae, Kwanwoo Lee, Ji-Sun Park, Jinseok Jung, Hirofumi Tachibana, Yoshinori Fujimura, Motofumi Kumazoe, Jae Sung Lim, Young-Chang Cho, Seung-Jae Lee and Su-Jin Park

Curr. Issues Mol. Biol. 2022, 44(12), 6247-6256; https://doi.org/10.3390/cimb44120426 - 9 Dec 2022

Cited by 1 | Viewed by 2012

Abstract

Epigallocatechin 3-O-gallate (EGCG) is a predominant component in green tea with various health benefits. The 67 kDa laminin receptor (67LR) is a nonintegrin cell surface receptor that is overexpressed in various types of cancer; 67LR was identified a cell surface EGCG target that plays a pivotal role in tumor growth, metastasis, and resistance to chemotherapy. However, the plasma concentration of EGCG is limited, and its molecular mechanisms remain unelucidated in colon cancer. In this study, we found that the phosphodiesterase 5 (PDE5) inhibitor, vardenafil (VDN), potentiates EGCG-induced apoptotic cell death in colon cancer cells. The combination of EGCG and VDN induced apoptosis via activation of the endothelial nitric oxide synthase/cyclic guanosine monophosphate/protein kinase Cδ signaling pathway. In conclusion, the PDE5 inhibitor, VDN, may reduce the intracellular PDE5 enzyme activity that potentiates EGCG-induced apoptotic cell death in Caco-2 cells. These results suggest that PDE5 inhibitors can be used to elevate cGMP levels to induce 67LR-mediated, cancer-specific cell death. Therefore, EGCG may be employed as a therapeutic candidate for colon cancer. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

40 pages, 17704 KiB

Open AccessArticle

In Silico Identification of Promising New Pyrazole Derivative-Based Small Molecules for Modulating CRMP2, C-RAF, CYP17, VEGFR, C-KIT, and HDAC—Application towards Cancer Therapeutics

by Fatima Ezzahra Bennani, Khalid Karrouchi, Latifa Doudach, Mario Scrima, Noor Rahman, Luca Rastrelli, Trina Ekawati Tallei, Christopher E. Rudd, My El Abbes Faouzi and M’hammed Ansar

Curr. Issues Mol. Biol. 2022, 44(11), 5312-5351; https://doi.org/10.3390/cimb44110361 - 31 Oct 2022

Cited by 5 | Viewed by 2184

Abstract

Despite continual efforts being made with multiple clinical studies and deploying cutting-edge diagnostic tools and technologies, the discovery of new cancer therapies remains of severe worldwide concern. Multiple drug resistance has also emerged in several cancer cell types, leaving them unresponsive to the many cancer treatments. Such a condition always prompts the development of next-generation cancer therapies that have a better chance of inhibiting selective target macromolecules with less toxicity. Therefore, in the present study, extensive computational approaches were implemented combining molecular docking and dynamic simulation studies for identifying potent pyrazole-based inhibitors or modulators for CRMP2, C-RAF, CYP17, c-KIT, VEGFR, and HDAC proteins. All of these proteins are in some way linked to the development of numerous forms of cancer, including breast, liver, prostate, kidney, and stomach cancers. In order to identify potential compounds, 63 in-house synthesized pyrazole-derivative compounds were docked with each selected protein. In addition, single or multiple standard drug compounds of each protein were also considered for docking analyses and their results used for comparison purposes. Afterward, based on the binding affinity and interaction profile of pyrazole compounds of each protein, potentially strong compounds were filtered out and further subjected to 1000 ns MD simulation analyses. Analyzing parameters such as RMSD, RMSF, RoG and protein–ligand contact maps were derived from trajectories of simulated protein–ligand complexes. All these parameters turned out to be satisfactory and within the acceptable range to support the structural integrity and interaction stability of the protein–ligand complexes in dynamic state. Comprehensive computational analyses suggested that a few identified pyrazole compounds, such as M33, M36, M72, and M76, could be potential inhibitors or modulators for HDAC, C-RAF, CYP72 and VEGFR proteins, respectively. Another pyrazole compound, M74, turned out to be a very promising dual inhibitor/modulator for CRMP2 and c-KIT proteins. However, more extensive study may be required for further optimization of the selected chemical framework of pyrazole derivatives to yield improved inhibitory activity against each studied protein receptor. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

13 pages, 2284 KiB

Open AccessArticle

Hydrogen Peroxide Induced Toxicity Is Reversed by the Macrocyclic IRAP-Inhibitor HA08 in Primary Hippocampal Cell Cultures

by Frida Stam, Sara Florén Lind, Anja Schroff, Sofia Zelleroth, Erik Nylander, Johan Gising, Alfhild Grönbladh, Mats Larhed and Mathias Hallberg

Curr. Issues Mol. Biol. 2022, 44(10), 5000-5012; https://doi.org/10.3390/cimb44100340 - 18 Oct 2022

Cited by 1 | Viewed by 2316

Abstract

Angiotensin IV (Ang IV), a metabolite of Angiotensin II, is a bioactive hexapeptide that inhibits the insulin-regulated aminopeptidase (IRAP). This transmembrane zinc metallopeptidase with many biological functions has in recent years emerged as a new pharmacological target. IRAP is expressed in a variety of tissues and can be found in high density in the hippocampus and neocortex, brain regions associated with cognition. Ang IV is known to improve memory tasks in experimental animals. One of the most potent IRAP inhibitors known today is the macrocyclic compound HA08 that is significantly more stable than the endogenous Ang IV. HA08 combines structural elements from Ang IV and the physiological substrates oxytocin and vasopressin, and binds to the catalytic site of IRAP. In the present study we evaluate whether HA08 can restore cell viability in rat primary cells submitted to hydrogen peroxide damage. After damaging the cells with hydrogen peroxide and subsequently treating them with HA08, the conceivable restoring effects of the IRAP inhibitor were assessed. The cellular viability was determined by measuring mitochondrial activity and lactate dehydrogenase (LDH) release. The mitochondrial activity was significantly higher in primary hippocampal cells, whereas the amount of LDH was unaffected. We conclude that the cell viability can be restored in this cell type by blocking IRAP with the potent macrocyclic inhibitor HA08, although the mechanism by which HA08 exerts its effects remains unclear. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

21 pages, 7987 KiB

Open AccessArticle

Pharmacophore-Model-Based Virtual-Screening Approaches Identified Novel Natural Molecular Candidates for Treating Human Neuroblastoma

by F A Dain Md Opo, Saleh Alkarim, Ghadeer I. Alrefaei, Mohammad Habibur Rahman Molla, Nouf H. Alsubhi, Faisal Alzahrani and Foysal Ahammad

Curr. Issues Mol. Biol. 2022, 44(10), 4838-4858; https://doi.org/10.3390/cimb44100329 - 13 Oct 2022

Cited by 7 | Viewed by 2432

Abstract

The mortality of cancer patients with neuroblastoma is increasing due to the limited availability of specific treatment options. Few drug candidates for combating neuroblastoma have been developed, and identifying novel therapeutic candidates against the disease is an urgent issue. It has been found that muc-N protein is amplified in one-third of human neuroblastomas and expressed as an attractive drug target against the disease. The myc-N protein interferes with the bromodomain and extraterminal (BET) family proteins. Pharmacologically inhibition of the protein potently depletes MYCN in neuroblastoma cells. BET inhibitors target MYCN transcription and show therapeutic efficacy against neuroblastoma. Therefore, the study aimed to identify potential inhibitors against the BET family protein, specifically Brd4 (brodamine-containing protein 4), to hinder the activity of neuroblastoma cells. To identify effective molecular candidates against the disease, a structure-based pharmacophore model was created for the binding site of the Brd4 protein. The pharmacophore model generated from the protein Brd4 was validated to screen potential natural active compounds. The compounds identified through the pharmacophore-model-based virtual-screening process were further screened through molecular docking, ADME (absorption, distribution, metabolism, and excretion), toxicity, and molecular dynamics (MD) simulation approach. The pharmacophore-model-based screening process initially identified 136 compounds, further evaluated based on molecular docking, ADME analysis, and toxicity approaches, identifying four compounds with good binding affinity and lower side effects. The stability of the selected compounds was also confirmed by dynamic simulation and molecular mechanics with generalized Born and surface area solvation (MM-GBSA) methods. Finally, the study identified four natural lead compounds, ZINC2509501, ZINC2566088, ZINC1615112, and ZINC4104882, that will potentially inhibit the activity of the desired protein and help to fight against neuroblastoma and related diseases. However, further evaluations through in vitro and in vivo assays are suggested to identify their efficacy against the desired protein and disease. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

8 pages, 1819 KiB

Open AccessArticle

Inhibitory Activity of Quaternary Isoquinoline Alkaloids on Soluble Epoxide Hydrolase

by Jang Hoon Kim, Chong Woon Cho, Mok Hur, Woo Tae Park, Youn-Ho Moon, Sung-Cheol Koo, Yun-Chan Hur, Jong Seong Kang and Ik Soo Lee

Curr. Issues Mol. Biol. 2022, 44(9), 4282-4289; https://doi.org/10.3390/cimb44090294 - 16 Sep 2022

Cited by 2 | Viewed by 1585

Abstract

The quaternary isoquinoline alkaloids of palmatine (1), berberine (2), and jatrorrhizine (3) were evaluated in terms of their ability to inhibit soluble epoxide hydrolase (sEH). They had similar inhibitory activities, with IC₅₀ values of 29.6 ± 0.5, 33.4 ± 0.8, and 27.3 ± 0.4 μM, respectively. Their respective Ki values of 26.9, 46.8, and 44.5 μM—determined by enzyme kinetics—indicated that they inhibited the catalytic reaction by binding noncompetitively with sEH. The application of computational chemistry to the in vitro results revealed the site of the receptor to which the ligand would likely bind. Accordingly, three alkaloids were identified as having a suitable basic skeleton for lead compound development of sEH inhibitors. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

13 pages, 1496 KiB

Open AccessArticle

Clinico-Immunological Effects of a Single-Agent CDK4/6 Inhibitor in Advanced HR+/HER2− Breast Cancer Based on a Window of Opportunity Study

by Alberto D’Angelo, Fabiola Giudici, Robert Chapman, Jacob Darlow, Huseyin Kilili, Navid Sobhani, Mattia Cinelli, Maria Rosa Cappelletti, Carla Strina, Manuela Milani and Daniele Generali

Curr. Issues Mol. Biol. 2022, 44(9), 4255-4267; https://doi.org/10.3390/cimb44090292 - 15 Sep 2022

Viewed by 2198

Abstract

Background: Cyclin-dependent kinase 4/6 inhibitors (CDK4/6 i), abemaciclib, palbociclib, and ribociclib, have been FDA-approved for the treatment of hormone receptor-positive (HR+), HER2−negative (HER2−) advanced breast cancer (aBC). This targeted therapy has revived hope in those aBC patients who did not respond to standard therapies. Interestingly, when administered as a single agent, CDK4/6 modulated several peripheral blood cells after a short-course treatment of 28 days. However, the impact of these immune effects has yet to be thoroughly investigated. Methods: We administered abemaciclib, palbociclib, and ribociclib monotherapy to 23 patients with HR+/HER2− metastatic breast cancer. The aim is to investigate the impact of on-treatment modifications on peripheral blood cells and their composite scores in patients after a 28-day course of CDK4/6 i alone. Results: In the current study, we observed a significant decrease in neutrophils (p-value < 0.001) for patients treated with abemaciclib, palbociclib, and ribociclib. An overall decrease of T_regs was observed and potentially linked to palbociclib treatment. The neutrophile to lymphocyte (N/L) ratio was also decreased overall and potentially linked to abemaciclib and palbociclib treatment. Platelets were decreased in patients administered with abemaciclib. Notably, the radiometabolic response was available only for those patients treated with ribociclib and abemaciclib, and only those lesions treated with ribociclib reached statistical relevance. Conclusions: Our study strongly supports the notion that CDK4/6 inhibitors induce tumour immune modulation. N/L ratio and platelet levels decreased due to treatment. Future studies should test whether patients would benefit from immunomodulators in association with CDK4/6 agents in a larger clinical trial. Moreover, the CDK4/6-induced immune modulation could also be considered a potential predictive clinical factor in HR+/HER2− advanced breast cancer. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

17 pages, 3211 KiB

Open AccessArticle

Identification of Putative Plant-Based ALR-2 Inhibitors to Treat Diabetic Peripheral Neuropathy

by Mohd Saeed, Munazzah Tasleem, Ambreen Shoib, Mohd Adnan Kausar, Abdel Moneim E. Sulieman, Nadiyah M. Alabdallah, Zeina El Asmar, Abdelmuhsin Abdelgadir, Asma Al-Shammary, Md Jahoor Alam, Riadh Badroui and Maryam Zahin

Curr. Issues Mol. Biol. 2022, 44(7), 2825-2841; https://doi.org/10.3390/cimb44070194 - 29 Jun 2022

Cited by 6 | Viewed by 2148

Abstract

Diabetic peripheral neuropathy (DPN) is a common diabetes complication (DM). Aldose reductase -2 (ALR-2) is an oxidoreductase enzyme that is most extensively studied therapeutic target for diabetes-related complications that can be inhibited by epalrestat, which has severe adverse effects; hence the discovery of potent natural inhibitors is desired. In response, a pharmacophore model based on the properties of eplarestat was generated. The specified pharmacophore model searched the NuBBE_DB database of natural compounds for prospective lead candidates. To assess the drug-likeness and ADMET profile of the compounds, a series of in silico filtering procedures were applied. The compounds were then put through molecular docking and interaction analysis. In comparison to the reference drug, four compounds showed increased binding affinity and demonstrated critical residue interactions with greater stability and specificity. As a result, we have identified four potent inhibitors: ZINC000002895847, ZINC000002566593, ZINC000012447255, and ZINC000065074786, that could be used as pharmacological niches to develop novel ALR-2 inhibitors. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

13 pages, 841 KiB

Open AccessArticle

DeepMHADTA: Prediction of Drug-Target Binding Affinity Using Multi-Head Self-Attention and Convolutional Neural Network

by Lei Deng, Yunyun Zeng, Hui Liu, Zixuan Liu and Xuejun Liu

Curr. Issues Mol. Biol. 2022, 44(5), 2287-2299; https://doi.org/10.3390/cimb44050155 - 19 May 2022

Cited by 9 | Viewed by 2990

Abstract

Drug-target interactions provide insight into the drug-side effects and drug repositioning. However, wet-lab biochemical experiments are time-consuming and labor-intensive, and are insufficient to meet the pressing demand for drug research and development. With the rapid advancement of deep learning, computational methods are increasingly applied to screen drug-target interactions. Many methods consider this problem as a binary classification task (binding or not), but ignore the quantitative binding affinity. In this paper, we propose a new end-to-end deep learning method called DeepMHADTA, which uses the multi-head self-attention mechanism in a deep residual network to predict drug-target binding affinity. On two benchmark datasets, our method outperformed several current state-of-the-art methods in terms of multiple performance measures, including mean square error (MSE), consistency index (CI),

r_{m}^{2}

, and PR curve area (AUPR). The results demonstrated that our method achieved better performance in predicting the drug–target binding affinity. Full article

(This article belongs to the Special Issue New Sight: Enzymes as Targets for Drug Development)

► Show Figures

Figure 1

Journal Menu

Journal Browser

New Sight: Enzymes as Targets for Drug Development

Share This Special Issue

Special Issue Editor

Special Issue Information

Published Papers (12 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI