Displaying publications 41 - 60 of 162 in total

Abstract:
Sort:
  1. Hasan WNW, Chin KY, Jolly JJ, Ghafar NA, Soelaiman IN
    PMID: 29683099 DOI: 10.2174/1871530318666180423122409
    BACKGROUND: Osteoporosis is a silent skeletal disease characterized by low bone mass and destruction of skeletal microarchitecture, leading to an increased fracture risk. This occurs due to an imbalance in bone remodelling, whereby the rate of bone resorption is greater than bone formation. Mevalonate pathway, previously known to involve in cholesterol synthesis, is an important regulatory pathway for bone remodelling.

    OBJECTIVE: This review aimed to provide an overview of the relationship between mevalonate pathway and bone metabolism, as well as agents which act through this pathway to achieve their therapeutic potential.

    DISCUSSION: Mevalonate pathway produces farnesyl pyrophosphate and geranylgeranyl pyrophosphate essential in protein prenylation. An increase in protein prenylation favours bone resorption over bone formation. Non-nitrogen containing bisphosphonates inhibit farnesyl diphosphate synthase which produces farnesyl pyrophosphate. They are used as the first line therapy for osteoporosis. Statins, a well-known class of cholesterol-lowering agents, inhibit 3-hydroxy-3-methyl-glutaryl-coenzyme A (HMG-CoA) reductase, the rate-determining enzyme in the mevalonate pathway. It was shown to increase bone mineral density and prevent fracture in humans. Tocotrienol is a group of vitamin E commonly found in palm oil, rice bran and annatto bean. It causes degradation of HMG-CoA reductase. Many studies demonstrated that tocotrienol prevented bone loss in animal studies but its efficacy has not been tested in humans.

    CONCLUSION: Mevalonate pathway can be exploited to develop effective antiosteoporosis agents.

    Matched MeSH terms: Drug Discovery/methods*
  2. Spreafico A, Hansen AR, Abdul Razak AR, Bedard PL, Siu LL
    Cancer Discov, 2021 Apr;11(4):822-837.
    PMID: 33811119 DOI: 10.1158/2159-8290.CD-20-1301
    Clinical trials represent a fulcrum for oncology drug discovery and development to bring safe and effective medicines to patients in a timely manner. Clinical trials have shifted from traditional studies evaluating cytotoxic chemotherapy in largely histology-based populations to become adaptively designed and biomarker-driven evaluations of molecularly targeted agents and immune therapies in selected patient subsets. This review will discuss the scientific, methodological, practical, and patient-focused considerations to transform clinical trials. A call to action is proposed to establish the framework for next-generation clinical trials that strikes an optimal balance of operational efficiency, scientific impact, and value to patients. SIGNIFICANCE: The future of cancer clinical trials requires a framework that can efficiently transform scientific discoveries to clinical utility through applications of innovative technologies and dynamic design methodologies. Next-generation clinical trials will offer individualized strategies which ultimately contribute to globalized knowledge and collective learning, through the joint efforts of all key stakeholders including investigators and patients.
    Matched MeSH terms: Drug Discovery/trends
  3. Dahari DE, Salleh RM, Mahmud F, Chin LP, Embi N, Sidek HM
    Trop Life Sci Res, 2016 Aug;27(2):53-71.
    PMID: 27688851 MyJurnal DOI: 10.21315/tlsr2016.27.2.5
    Exploiting natural resources for bioactive compounds is an attractive drug discovery strategy in search for new anti-malarial drugs with novel modes of action. Initial screening efforts in our laboratory revealed two preparations of soil-derived actinomycetes (H11809 and FH025) with potent anti-malarial activities. Both crude extracts showed glycogen synthase kinase 3β (GSK3β)-inhibitory activities in a yeast-based kinase assay. We have previously shown that the GSK3 inhibitor, lithium chloride (LiCl), was able to suppress parasitaemia development in a rodent model of malarial infection. The present study aims to evaluate whether anti-malarial activities of H11809 and FH025 involve the inhibition of GSK3β. The acetone crude extracts of H11809 and FH025 each exerted strong inhibition on the growth of Plasmodium falciparum 3D7 in vitro with 50% inhibitory concentration (IC50) values of 0.57 ± 0.09 and 1.28 ± 0.11 µg/mL, respectively. The tested extracts exhibited Selectivity Index (SI) values exceeding 10 for the 3D7 strain. Both H11809 and FH025 showed dosage-dependent chemo-suppressive activities in vivo and improved animal survivability compared to non-treated infected mice. Western analysis revealed increased phosphorylation of serine (Ser 9) GSK3β (by 6.79 to 6.83-fold) in liver samples from infected mice treated with H11809 or FH025 compared to samples from non-infected or non-treated infected mice. A compound already identified in H11809 (data not shown), dibutyl phthalate (DBP) showed active anti-plasmodial activity against 3D7 (IC50 4.87 ± 1.26 µg/mL which is equivalent to 17.50 µM) and good chemo-suppressive activity in vivo (60.80% chemo-suppression at 300 mg/kg body weight [bw] dosage). DBP administration also resulted in increased phosphorylation of Ser 9 GSK3β compared to controls. Findings from the present study demonstrate that the potent anti-malarial activities of H11809 and FH025 were mediated via inhibition of host GSK3β. In addition, our study suggests that DBP is in part the bioactive component contributing to the anti-malarial activity displayed by H11809 acting through the inhibition of GSK3β.
    Matched MeSH terms: Drug Discovery
  4. Soopramanien M, Khan N, Neerooa BNHM, Sagathevan K, Siddiqui R
    Asian Pac J Cancer Prev, 2021 Mar 01;22(3):733-740.
    PMID: 33773536 DOI: 10.31557/APJCP.2021.22.3.733
    OBJECTIVES: The overall aim was to determine whether gut bacteria of Columbia livia are a potential source of antitumour molecules.

    METHODS: Faecal and gut microbiota of Columbia livia were isolated, identified and conditioned media were prepared containing metabolites. Growth inhibition, lactate dehydrogenase cytotoxicity and cell survival assays were accomplished against cervical cancer cells. Next, liquid-chromatography mass spectrometry was conducted to elucidate the molecules present.

    RESULTS: A plethora of bacteria from faecal matter and gastrointestinal tract were isolated. Selected conditioned media exhibited potent anticancer effects and displayed cytotoxicity to cervical cancer cells at IC50 concentration of 10.65 and 15.19 µg/ml. Moreover, cells treated with conditioned media exhibited morphological changes, including cell shrinking and rounding; indicative of apoptosis, when compared to untreated cells. A total of 111 and 71 molecules were revealed from these gut and faecal metabolites. The identity of 60 molecules were revealed including, dihydroxymelphalan. Nonetheless, 122 molecules remain unidentified and are the subject of future studies.

    CONCLUSION: These findings suggest that gut bacteria of Columbia livia possess molecules, which may have anticancer activities. Further in silico testing and/or high throughput screening will determine potential anticancer properties of these molecules.
    .

    Matched MeSH terms: Drug Discovery
  5. Khan NA, Anwar A, Siddiqui R
    ACS Chem Neurosci, 2017 11 15;8(11):2355.
    PMID: 28933530 DOI: 10.1021/acschemneuro.7b00343
    Brain-eating amoebae (Acanthamoeba spp., Balamuthia mandrillaris, and Naegleria fowleri) can cause opportunistic infections involving the central nervous system. It is troubling that the mortality rate is more than 90% despite advances in antimicrobial chemotherapy over the last few decades. Here, we describe urgent key priorities for improving outcomes from infections due to brain-eating amoebae.
    Matched MeSH terms: Drug Discovery
  6. Anwar A, Khan NA, Siddiqui R
    Parasit Vectors, 2018 01 09;11(1):26.
    PMID: 29316961 DOI: 10.1186/s13071-017-2572-z
    Acanthamoeba spp. are protist pathogens and causative agents of serious infections including keratitis and granulomatous amoebic encephalitis. Its ability to convert into dormant and highly resistant cysts form limits effectiveness of available therapeutic agents and presents a pivotal challenge for drug development. During the cyst stage, Acanthamoeba is protected by the presence of hardy cyst walls, comprised primarily of carbohydrates and cyst-specific proteins, hence synthesis inhibition and/or degradation of cyst walls is of major interest. This review focuses on targeting of Acanthamoeba cysts by identifying viable therapeutic targets.
    Matched MeSH terms: Drug Discovery/methods*; Drug Discovery/trends
  7. Patra JK, Das G, Fraceto LF, Campos EVR, Rodriguez-Torres MDP, Acosta-Torres LS, et al.
    J Nanobiotechnology, 2018 Sep 19;16(1):71.
    PMID: 30231877 DOI: 10.1186/s12951-018-0392-8
    Nanomedicine and nano delivery systems are a relatively new but rapidly developing science where materials in the nanoscale range are employed to serve as means of diagnostic tools or to deliver therapeutic agents to specific targeted sites in a controlled manner. Nanotechnology offers multiple benefits in treating chronic human diseases by site-specific, and target-oriented delivery of precise medicines. Recently, there are a number of outstanding applications of the nanomedicine (chemotherapeutic agents, biological agents, immunotherapeutic agents etc.) in the treatment of various diseases. The current review, presents an updated summary of recent advances in the field of nanomedicines and nano based drug delivery systems through comprehensive scrutiny of the discovery and application of nanomaterials in improving both the efficacy of novel and old drugs (e.g., natural products) and selective diagnosis through disease marker molecules. The opportunities and challenges of nanomedicines in drug delivery from synthetic/natural sources to their clinical applications are also discussed. In addition, we have included information regarding the trends and perspectives in nanomedicine area.
    Matched MeSH terms: Drug Discovery/methods
  8. Dahiya R, Dahiya S, Fuloria NK, Kumar S, Mourya R, Chennupati SV, et al.
    Mar Drugs, 2020 Jun 24;18(6).
    PMID: 32599909 DOI: 10.3390/md18060329
    Peptides are distinctive biomacromolecules that demonstrate potential cytotoxicity and diversified bioactivities against a variety of microorganisms including bacteria, mycobacteria, and fungi via their unique mechanisms of action. Among broad-ranging pharmacologically active peptides, natural marine-originated thiazole-based oligopeptides possess peculiar structural features along with a wide spectrum of exceptional and potent bioproperties. Because of their complex nature and size divergence, thiazole-based peptides (TBPs) bestow a pivotal chemical platform in drug discovery processes to generate competent scaffolds for regulating allosteric binding sites and peptide-peptide interactions. The present study dissertates on the natural reservoirs and exclusive structural components of marine-originated TBPs, with a special focus on their most pertinent pharmacological profiles, which may impart vital resources for the development of novel peptide-based therapeutic agents.
    Matched MeSH terms: Drug Discovery
  9. Sabetian S, Shamsir MS
    Bioinformation, 2019;15(7):513-522.
    PMID: 31485137 DOI: 10.6026/97320630015513
    Proteins can interact in various ways, ranging from direct physical relationships to indirect interactions in a formation of protein-protein interaction network. Diagnosis of the protein connections is critical to identify various cellular pathways. Today constructing and analyzing the protein interaction network is being developed as a powerful approach to create network pharmacology toward detecting unknown genes and proteins associated with diseases. Discovery drug targets regarding therapeutic decisions are exciting outcomes of studying disease networks. Protein connections may be identified by experimental and recent new computational approaches. Due to difficulties in analyzing in-vivo proteins interactions, many researchers have encouraged improving computational methods to design protein interaction network. In this review, the experimental and computational approaches and also advantages and disadvantages of these methods regarding the identification of new interactions in a molecular mechanism have been reviewed. Systematic analysis of complex biological systems including network pharmacology and disease network has also been discussed in this review.
    Matched MeSH terms: Drug Discovery
  10. Lokesh BVS, Prasad YR, Shaik AB
    Infect Disord Drug Targets, 2019;19(3):310-321.
    PMID: 30556506 DOI: 10.2174/1871526519666181217120626
    BACKGROUND: Many synthetic procedures were reported till date to prepare pyrazoline derivatives. Some have published pyrazolines from different chalcone derivatives in the literature.

    OBJECTIVE: A series of new pyrazolines containing novel 2,5-dichloro-3-acetylthiophene chalcone moiety (PZT1-PZT20) have been synthesized, characterized by 1HNMR and 13CNMR and evaluated for them in vitro antitubercular activity against M. tuberculosis H37Rv strain and in vitro anticancer activity against DU-145 prostate cancer cell lines and all compounds were also screened for molecular docking studies against specific targeted protein domains.

    METHODS: All compounds were screened for potential activity against Mycobacterium tuberculosis H37Rv (MTB) strain and anticancer activity against DU-149 prostate cancer cell lines using MTT cytotoxicity assay.

    RESULTS: Among the series, compound PZT5 with 2", 4"-dichlorophenyl group at 5-position on the pyrazoline ring exhibited the most potent antitubercular activity (MIC=1.60 µg/mL) and compounds PZT2, PZT9, PZT11, PZT15, and PZT20 showed similar antitubercular activity against standard pyrazinamide (MIC=3.12 µg/mL) by broth dilution assay. PZT15 and PZT17 with 4"- pyridinyl and 2"-pyrrolyl groups on pyrazoline ring were found to exhibit better anticancer activity against DU-149 prostate cancer cell lines with IC50 values of 2.0±0.2 µg/mL and 6.0±0.3 µg/mL respectively by MTT assay. The preliminary structure-activity relationship has been summarized. The molecular docking studies with crystalline structures of enoyl acyl carrier protein reductase InhA interaction with target protein (2NSD; PDB and 3FNG; PDB) of Mycobacterium tuberculosis H37Rv (MTB) strain have also exhibited good ligand interaction and binding affinity. Ligand interaction and binding affinity were estimated using crystal structures of both types of enoyl acyl carrier protein reductase InhA (3FNG.pdb) and found to be much higher (-16.70 to - 19.20 kcal/mol) compared with pyrazinamide (-10.70 kcal/mol) as a standard target molecule. Whereas the binding affinities of six active compounds with crystal structure of other type of enoyl acyl carrier protein reductase InhA (2NSD.pdb) were much similar and higher (-9.30 to - 11.20 kcal/mole) than pyrazinamide (-11.10 kcal/mole).

    CONCLUSION: These new pyrazolines would be promising potent inhibitors of drug sensitive and drug resistant Mycobacterium tuberculosis strain and potential anticancer agents against prostate cancer and other prototypes of cancers.

    Matched MeSH terms: Drug Discovery
  11. El-Far AH, Badria FA, Shaheen HM
    Curr Drug Discov Technol, 2016;13(3):123-143.
    PMID: 27515456
    Costus speciosus is native to South East Asia, especially found in India, Srilanka, Indonesia and Malaysia. C. speciosus have numerous therapeutic potentials against a wide variety of complains. The therapeutic properties of C. speciosus are attributed to the presence of various ingredients such as alkaloids, flavonoids, glycosides, phenols, saponins, sterols and sesquiterpenes. This review presented the past, present, and the future status of C. speciosus active ingredients to propose a future use as a potential anticancer agent. All possible up-regulation of cellular apoptotic molecules as p53, p21, p27, caspases, reactive oxygen species (ROS) generation and others attribute to the anticancer activity of C. speciosus along the down-regulation of anti-apoptotic agents such as Akt, Bcl2, NFKB, STAT3, JAK, MMPs, actin, surviving and vimentin. Eventually, we recommend further investigation of different C. speciosus extracts, using some active ingredients and evaluate the anticancer effect of these chemicals against different cancers.
    Matched MeSH terms: Drug Discovery
  12. Daood U, Gopinath D, Pichika MR, Mak KK, Seow LL
    Molecules, 2021 Apr 12;26(8).
    PMID: 33921378 DOI: 10.3390/molecules26082214
    To determine whether quaternary ammonium (k21) binds to Severe Acute Respiratory Syndrome-Coronavirus 2 (SARS-CoV-2) spike protein via computational molecular docking simulations, the crystal structure of the SARS-CoV-2 spike receptor-binding domain complexed with ACE-2 (PDB ID: 6LZG) was downloaded from RCSB PD and prepared using Schrodinger 2019-4. The entry of SARS-CoV-2 inside humans is through lung tissues with a pH of 7.38-7.42. A two-dimensional structure of k-21 was drawn using the 2D-sketcher of Maestro 12.2 and trimmed of C18 alkyl chains from all four arms with the assumption that the core moiety k-21 was without C18. The immunogenic potential of k21/QA was conducted using the C-ImmSim server for a position-specific scoring matrix analyzing the human host immune system response. Therapeutic probability was shown using prediction models with negative and positive control drugs. Negative scores show that the binding of a quaternary ammonium compound with the spike protein's binding site is favorable. The drug molecule has a large Root Mean Square Deviation fluctuation due to the less complex geometry of the drug molecule, which is suggestive of a profound impact on the regular geometry of a viral protein. There is high concentration of Immunoglobulin M/Immunoglobulin G, which is concomitant of virus reduction. The proposed drug formulation based on quaternary ammonium to characterize affinity to the SARS-CoV-2 spike protein using simulation and computational immunological methods has shown promising findings.
    Matched MeSH terms: Drug Discovery*
  13. Shiammala PN, Duraimutharasan NKB, Vaseeharan B, Alothaim AS, Al-Malki ES, Snekaa B, et al.
    Methods, 2023 Nov;219:82-94.
    PMID: 37778659 DOI: 10.1016/j.ymeth.2023.09.010
    Artificial intelligence (AI), particularly deep learning as a subcategory of AI, provides opportunities to accelerate and improve the process of discovering and developing new drugs. The use of AI in drug discovery is still in its early stages, but it has the potential to revolutionize the way new drugs are discovered and developed. As AI technology continues to evolve, it is likely that AI will play an even greater role in the future of drug discovery. AI is used to identify new drug targets, design new molecules, and predict the efficacy and safety of potential drugs. The inclusion of AI in drug discovery can screen millions of compounds in a matter of hours, identifying potential drug candidates that would have taken years to find using traditional methods. AI is highly utilized in the pharmaceutical industry by optimizing processes, reducing waste, and ensuring quality control. This review covers much-needed topics, including the different types of machine-learning techniques, their applications in drug discovery, and the challenges and limitations of using machine learning in this field. The state-of-the-art of AI-assisted pharmaceutical discovery is described, covering applications in structure and ligand-based virtual screening, de novo drug creation, prediction of physicochemical and pharmacokinetic properties, drug repurposing, and related topics. Finally, many obstacles and limits of present approaches are outlined, with an eye on potential future avenues for AI-assisted drug discovery and design.
    Matched MeSH terms: Drug Discovery/methods
  14. Che Abdullah CA, Azad CL, Ovalle-Robles R, Fang S, Lima MD, Lepró X, et al.
    ACS Appl Mater Interfaces, 2014 Jul 9;6(13):10373-80.
    PMID: 24933259 DOI: 10.1021/am5018489
    Here, we explore the use of two- and three-dimensional scaffolds of multiwalled-carbon nanotubes (MWNTs) for hepatocyte cell culture. Our objective is to study the use of these scaffolds in liver tissue engineering and drug discovery. In our experiments, primary rat hepatocytes, the parenchymal (main functional) cell type in the liver, were cultured on aligned nanogrooved MWNT sheets, MWNT yarns, or standard 2-dimensional culture conditions as a control. We find comparable cell viability between all three culture conditions but enhanced production of the hepatocyte-specific marker albumin for cells cultured on MWNTs. The basal activity of two clinically relevant cytochrome P450 enzymes, CYP1A2 and CYP3A4, are similar on all substrates, but we find enhanced induction of CYP1A2 for cells on the MWNT sheets. Our data thus supports the use of these substrates for applications including tissue engineering and enhancing liver-specific functions, as well as in in vitro model systems with enhanced predictive capability in drug discovery and development.
    Matched MeSH terms: Drug Discovery*
  15. Faheem, Kumar BK, Sekhar KVGC, Kunjiappan S, Jamalis J, Balaña-Fouce R, et al.
    Mini Rev Med Chem, 2021;21(4):398-425.
    PMID: 33001013 DOI: 10.2174/1389557520666201001130114
    β-Carboline, a naturally occurring indole alkaloid, holds a momentous spot in the field of medicinal chemistry due to its myriad of pharmacological actions like anticancer, antiviral, antibacterial, antifungal, antileishmanial, antimalarial, neuropharmacological, anti-inflammatory and antithrombotic among others. β-Carbolines exhibit their pharmacological activity via diverse mechanisms. This review provides a recent update (2015-2020) on the anti-infective potential of natural and synthetic β-carboline analogs focusing on its antibacterial, antifungal, antiviral, antimalarial, antileishmanial and antitrypanosomal properties. In cases where enough details are available, a note on its mechanism of action is also added.
    Matched MeSH terms: Drug Discovery
  16. Faheem, Kumar BK, Sekhar KVGC, Kunjiappan S, Jamalis J, Balaña-Fouce R, et al.
    Bioorg Chem, 2020 Nov;104:104269.
    PMID: 32947136 DOI: 10.1016/j.bioorg.2020.104269
    COVID-19 caused by the novel SARS-CoV-2 has been declared a pandemic by the WHO is causing havoc across the entire world. As of May end, about 6 million people have been affected, and 367 166 have died from COVID-19. Recent studies suggest that the SARS-CoV-2 genome shares about 80% similarity with the SARS-CoV-1 while their protein RNA dependent RNA polymerase (RdRp) shares 96% sequence similarity. Remdesivir, an RdRp inhibitor, exhibited potent activity against SARS-CoV-2 in vitro. 3-Chymotrypsin like protease (also known as Mpro) and papain-like protease, have emerged as the potential therapeutic targets for drug discovery against coronaviruses owing to their crucial role in viral entry and host-cell invasion. Crystal structures of therapeutically important SARS-CoV-2 target proteins, namely, RdRp, Mpro, endoribonuclease Nsp15/NendoU and receptor binding domain of CoV-2 spike protein has been resolved, which have facilitated the structure-based design and discovery of new inhibitors. Furthermore, studies have indicated that the spike proteins of SARS-CoV-2 use the Angiotensin Converting Enzyme-2 (ACE-2) receptor for its attachment similar to SARS-CoV-1, which is followed by priming of spike protein by Transmembrane protease serine 2 (TMPRSS2) which can be targeted by a proven inhibitor of TMPRSS2, camostat. The current treatment strategy includes repurposing of existing drugs that were found to be effective against other RNA viruses like SARS, MERS, and Ebola. This review presents a critical analysis of druggable targets of SARS CoV-2, new drug discovery, development, and treatment opportunities for COVID-19.
    Matched MeSH terms: Drug Discovery*
  17. Saeed F, Ahmed A, Shamsir MS, Salim N
    J Comput Aided Mol Des, 2014 Jun;28(6):675-84.
    PMID: 24830925 DOI: 10.1007/s10822-014-9750-2
    The cluster-based compound selection is used in the lead identification process of drug discovery and design. Many clustering methods have been used for chemical databases, but there is no clustering method that can obtain the best results under all circumstances. However, little attention has been focused on the use of combination methods for chemical structure clustering, which is known as consensus clustering. Recently, consensus clustering has been used in many areas including bioinformatics, machine learning and information theory. This process can improve the robustness, stability, consistency and novelty of clustering. For chemical databases, different consensus clustering methods have been used including the co-association matrix-based, graph-based, hypergraph-based and voting-based methods. In this paper, a weighted cumulative voting-based aggregation algorithm (W-CVAA) was developed. The MDL Drug Data Report (MDDR) benchmark chemical dataset was used in the experiments and represented by the AlogP and ECPF_4 descriptors. The results from the clustering methods were evaluated by the ability of the clustering to separate biologically active molecules in each cluster from inactive ones using different criteria, and the effectiveness of the consensus clustering was compared to that of Ward's method, which is the current standard clustering method in chemoinformatics. This study indicated that weighted voting-based consensus clustering can overcome the limitations of the existing voting-based methods and improve the effectiveness of combining multiple clusterings of chemical structures.
    Matched MeSH terms: Drug Discovery*
  18. Abdo A, Salim N
    ChemMedChem, 2009 Feb;4(2):210-8.
    PMID: 19072820 DOI: 10.1002/cmdc.200800290
    Many methods have been developed to capture the biological similarity between two compounds for use in drug discovery. A variety of similarity metrics have been introduced, the Tanimoto coefficient being the most prominent. Many of the approaches assume that molecular features or descriptors that do not relate to the biological activity carry the same weight as the important aspects in terms of biological similarity. Herein, a novel similarity searching approach using a Bayesian inference network is discussed. Similarity searching is regarded as an inference or evidential reasoning process in which the probability that a given compound has biological similarity with the query is estimated and used as evidence. Our experiments demonstrate that the similarity approach based on Bayesian inference networks is likely to outperform the Tanimoto similarity search and offer a promising alternative to existing similarity search approaches.
    Matched MeSH terms: Drug Discovery
  19. Babajide Mustapha I, Saeed F
    Molecules, 2016 Jul 28;21(8).
    PMID: 27483216 DOI: 10.3390/molecules21080983
    Following the explosive growth in chemical and biological data, the shift from traditional methods of drug discovery to computer-aided means has made data mining and machine learning methods integral parts of today's drug discovery process. In this paper, extreme gradient boosting (Xgboost), which is an ensemble of Classification and Regression Tree (CART) and a variant of the Gradient Boosting Machine, was investigated for the prediction of biological activity based on quantitative description of the compound's molecular structure. Seven datasets, well known in the literature were used in this paper and experimental results show that Xgboost can outperform machine learning algorithms like Random Forest (RF), Support Vector Machines (LSVM), Radial Basis Function Neural Network (RBFN) and Naïve Bayes (NB) for the prediction of biological activities. In addition to its ability to detect minority activity classes in highly imbalanced datasets, it showed remarkable performance on both high and low diversity datasets.
    Matched MeSH terms: Drug Discovery/methods*
  20. Al-Dabbagh MM, Salim N, Himmat M, Ahmed A, Saeed F
    J Comput Aided Mol Des, 2017 Apr;31(4):365-378.
    PMID: 28220440 DOI: 10.1007/s10822-016-0003-4
    Chemical libraries contain thousands of compounds that need screening, which increases the need for computational methods that can rank or prioritize compounds. The tools of virtual screening are widely exploited to enhance the cost effectiveness of lead drug discovery programs by ranking chemical compounds databases in decreasing probability of biological activity based upon probability ranking principle (PRP). In this paper, we developed a novel ranking approach for molecular compounds inspired by quantum mechanics, called quantum probability ranking principle (QPRP). The QPRP ranking criteria would make an attempt to draw an analogy between the physical experiment and molecular structure ranking process for 2D fingerprints in ligand based virtual screening (LBVS). The development of QPRP criteria in LBVS has employed the concepts of quantum at three different levels, firstly at representation level, this model makes an effort to develop a new framework of molecular representation by connecting the molecular compounds with mathematical quantum space. Secondly, estimate the similarity between chemical libraries and references based on quantum-based similarity searching method. Finally, rank the molecules using QPRP approach. Simulated virtual screening experiments with MDL drug data report (MDDR) data sets showed that QPRP outperformed the classical ranking principle (PRP) for molecular chemical compounds.
    Matched MeSH terms: Drug Discovery/methods*
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links