Efficient machine learning model for predicting drug-target interactions with case study for Covid-19

BackgroundDiscover possible Drug Target Interactions (DTIs) is a decisive step in the detection of the effects of drugs as well as drug repositioning. There is a strong incentive to develop effective computational methods that can effectively predict potential DTIs, as traditional DTI laboratory experiments are expensive, time-consuming, and labor-intensive. Some technologies have been developed for this purpose, however large numbers of interactions have not yet been detected, the accuracy of their prediction still low, and protein sequences and structured data are rarely used together in the prediction process.MethodsThis paper presents DTIs prediction model that takes advantage of the special capacity of the structured form of proteins and drugs. Our model obtains features from protein amino-acid sequences using physical and chemical properties, and from drugs smiles (Simplified Molecular Input Line Entry System) strings using encoding techniques. Comparing the proposed model with different existing methods under K-fold cross validation, empirical results show that our model based on ensemble learning algorithms for DTI prediction provide more accurate results from both structures and features data.ResultsThe proposed model is applied on two datasets:Benchmark (feature only) datasets and DrugBank (Structure data) datasets. Experimental results obtained by Light-Boost and ExtraTree using structures and feature data results in 98 % accuracy and 0.97 f-score comparing to 94 % and 0.92 achieved by the existing methods. Moreover, our model can successfully predict more yet undiscovered interactions, and hence can be used as a practical tool to drug repositioning.A case study of applying our prediction model on the proteins that are known to be affected by Corona viruses in order to predict the possible interactions among these proteins and existing drugs is performed. Also, our model is applied on Covid-19 related drugs announced on DrugBank. The results show that some drugs like DB00691 and DB05203 are predicted with 100 % accuracy to interact with ACE2 protein. This protein is a self-membrane protein that enables Covid-19 infection. Hence, our model can be used as an effective tool in drug reposition to predict possible drug treatments for Covid-19.     

Establishing an Analogue Based In Silico Pipeline in the Pursuit of Novel Inhibitory Scaffolds against the SARS Coronavirus 2 Papain-Like Protease

The ongoing coronavirus pandemic has been a burden on the worldwide population, with mass fatalities and devastating socioeconomic consequences. It has particularly drawn attention to the lack of approved small-molecule drugs to inhibit SARS coronaviruses. Importantly, lessons learned from the SARS outbreak of 2002–2004, caused by severe acute respiratory syndrome coronavirus 1 (SARS-CoV-1), can be applied to current drug discovery ventures. SARS-CoV-1 and SARS-CoV-2 both possess two cysteine proteases, the main protease (M^pro) and the papain-like protease (PL^pro), which play a significant role in facilitating viral replication, and are important drug targets. The non-covalent inhibitor, GRL-0617, which was found to inhibit replication of SARS-CoV-1, and more recently SARS-CoV-2, is the only PL^pro inhibitor co-crystallised with the recently solved SARS-CoV-2 PL^pro crystal structure. Therefore, the GRL-0617 structural template and pharmacophore features are instrumental in the design and development of more potent PL^pro inhibitors. In this work, we conducted scaffold hopping using GRL-0617 as a reference to screen over 339,000 ligands in the chemical space using the ChemDiv, MayBridge, and Enamine screening libraries. Twenty-four distinct scaffolds with structural and electrostatic similarity to GRL-0617 were obtained. These proceeded to molecular docking against PL^pro using the AutoDock tools. Of two compounds that showed the most favourable predicted binding affinities to the target site, as well as comparable protein-ligand interactions to GRL-0617, one was chosen for further analogue-based work. Twenty-seven analogues of this compound were further docked against the PL^pro, which resulted in two additional hits with promising docking profiles. Our in silico pipeline consisted of an integrative four-step approach: (1) ligand-based virtual screening (scaffold-hopping), (2) molecular docking, (3) an analogue search, and, (4) evaluation of scaffold drug-likeness, to identify promising scaffolds and eliminate those with undesirable properties. Overall, we present four novel, and lipophilic, scaffolds obtained from an exhaustive search of diverse and uncharted regions of chemical space, which may be further explored in vitro through structure-activity relationship (SAR) studies in the search for more potent inhibitors. Furthermore, these scaffolds were predicted to have fewer off-target interactions than GRL-0617. Lastly, to our knowledge, this work contains the largest ligand-based virtual screen performed against GRL-0617.     

Molecular Dynamic Simulation Search for Possible Amphiphilic Drug Discovery for Covid-19

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.     

Una nota sui gruppi policiclici che ammettono un automorfismo con numero di Reidemeister finito

LetG be a group and ϕ an automorphism ofG. Two elementsx, y ∈ G are called ϕ-conjugate if there existsg ∈ G such thatx=g ⁻¹ yg ^θ. It is easily verified that the ϕ-conjugation is an equivalence relation; the numberR(ϕ) of ϕ-classes ofG is called the Reidemeister number of the automorphism ϕ. In this paper we prove that if a polycyclic groupsG admits an automorphism ϕ of ordern such thatR(ϕ)<∞, thenG contains a subgroup of finite index with derived length at most 2 ⁿ⁻¹ .

     

Paths for $${\mathcal{Z}}_k$$ Parafermionic Models

We present a simple bijection between restricted Bressoud lattice paths and paths in regime II of the Andrews–Baxter–Forrester restricted solid–on–solid model. Both types of paths describe states in parafermionic irreducible modules. The bijection implies a direct correspondence between a RSOS path and a parafermionic state in a quasi-particle basis.      

Reaction of 2-hydroxyethylhydrazine with a trifluoromethyl-β-diketone: Study and structural characterization of a new 5-hydroxy-5-trifluoromethyl-4,5-dihydropyrazole intermediate

The reaction of the β-diketone 4,4,4-trifluoro-1-pyridin-2-yl-butane-1,3-dione and the monosubstituted hydrazine 2-hydroxyethylhydrazine has been investigated. Two products have been identified, 2-(2-hydroxyethyl)-3-pyridin-2-yl-5-trifluoromethyl-4,5-dihydropyrazole (P) and 2-(3-pyridin-2-yl-5-trifluoromethylpyrazol-1-yl)ethanol (L) in proportion 2:8, when the reaction was done at room temperature in ethanol for 15 h. The preparation of P as a pure product was performed in ethanol at 0 °C for 7 h. P has been characterized by ¹H, ¹³C{¹H} and ¹⁹F{¹H} NMR spectroscopy and by other techniques as appropriate.     

<Superscript>19</Superscript>F NMR spectroscopic characterization of the interaction of niflumic acid with human serum albumin

The interaction of a non-steroidal anti-inflammatory drug, niflumic acid (NFA), with human serum albumin (HSA) has been investigated by ¹⁹F nuclear magnetic resonance (NMR) spectroscopy. A ¹⁹F NMR spectrum of NFA in a buffered (pH 7.4) solution of NaCl (0.1 mol L⁻¹) contained a single sharp signal of its CF₃ group 14.33 ppm from the internal reference 2,2,2-trifluoroethanol. Addition of 0.6 mmol L⁻¹ HSA to the NFA buffer solution caused splitting of the CF₃ signal into two broadened signals, shifted to the lower fields of 14.56 and 15.06 ppm, with an approximate intensity ratio of 1:3. Denaturation of HSA by addition of 3.0 mol L⁻¹ guanidine hydrochloride (GU) restored a single sharp signal of CF₃ at 14.38 ppm, indicating complete liberation of NFA from HSA as a result of its denaturation. These results suggest that the binding is reversible and occurs in at least two HSA regions. Competitive ¹⁹F NMR experiments using warfarin, dansyl-l-asparagine, and benzocaine (site I ligands), and l-tryptophan and ibuprofen (site II ligands) revealed that NFA binds to site I at two different regions, Ia and Ib, in the ratio 1:3. By use of ¹⁹F NMR with NFA as an ¹⁹F NMR probe the nonfluorinated site I-binding drugs sulfobromophthalein and iophenoxic acid were also found to bind sites Ia and Ib, respectively. These results illustrate the usefulness and convenience of ¹⁹F NMR for investigation of the HSA binding of both fluorinated and nonfluorinated drugs.     

Spin-spin coupling and substituent and halogen isotope shift effects in the fluorine NMR spectra of fluorinated cyclopropanes and cyclopropyl ethers

The (19)F NMR spectra of a series of fluorinated cyclopropanes, most of which contain chlorine or bromine on the ring, have been observed and analyzed. A scheme has been developed to assign the resonances and the molecular stereochemistry, based on substituent effects, comparison of related molecules, and isotope shifts induced by the halogens. Replacement of fluorine by chlorine shifts cis fluorine resonances to lower field, and bromine has an even greater downfield influence. However, the shift effect of bromine compared to chlorine on gem or trans fluorines is variable. The magnitude of the isotope shifts is found to be regularly related to the geometrical relationship of the halogen to the observed fluorine and thus makes a significant contribution to the fluorine assignments. The three-bond spin-spin coupling constants between fluorine atoms in cyclopropanes display unusual behavior and are not helpful for assignment of the fluorine resonances. The signs of the coupling constants have been investigated by spin-tickling experiments, and the previously developed relation of the coupling constant sign to its temperature dependence has been found to be violated for some molecules.     

ki67、Cytokeratin19在口腔粘膜扁平苔藓及口腔鳞癌上皮组织中表达的研究

目的研究口腔粘膜扁平苔藓及口腔鳞癌患者口腔粘膜上皮ki67,Cytokeratin19的表达,探讨012发病的可能机理及是否为癌前病变。方法用免疫组化SABC法检测20例口腔粘膜扁平苔藓患者口腔粘膜组织及30例OSCC13腔粘膜组织中ki67,Cytokeratin19的表达并行细胞计数,其中对Cytokeratin19的表达行半定量统计分析。结果（1）OLP与正常组中ki67中阳性表达率有显著差异,P〈0.05;（2）Cytokeratin19行半定量分析发现OLP组与OSCC组有显著差异,P〈0.05。结论（1）ki67,Cytokeratin19的异常表达可能是OLP,OSCC的发病原因。（2）Cytokertin19、ki67的高表达均提示OLP可能是一种癌前病变。（3）Cytokertin19、ki67可作为口腔鳞癌检测的指标。     

Pigment study by Raman microscopy of 23 paintings by the Portuguese artist Henrique Pousão (1859–1884)

Twenty‐three paintings by Henrique Pousão—a 19th century Portuguese painter—belonging to the collection of Museu Nacional Soares dos Reis, Porto, Portugal, were analysed by Raman microscopy. The fine focus of a 100× objective allowed the visualisation and individual identification of small grains. As a result, thirty‐seven compounds, namely, anatase, barium white, basic lead sulfate, brochantite, cadmium red, cadmium yellow, calcium carbonate, carbon‐based black, celadonite, chrome green, chrome orange, chrome yellow, cobalt blue, cochineal lake, copper sulfide, emerald green, iron(III) oxyhydroxide, iron(III) oxide, kaolinite, lead antimonate yellow, lead carbonate, lead white, lead sulfate, madder lake, malachite, Prussian blue, quartz, realgar/pararealgar, red lead, rutile, Scheele's green, strontium yellow, ultramarine blue, vermilion, viridian, zinc white and zinc yellow, were identified. Not all these compounds are pigments; some are extenders, others trace components and others probably products of reactions between pigments. Special attention was given to the Raman characterisation of celadonite, chrome orange, basic lead sulfate and lead antimonate yellow. Complementary techniques were used to confirm the identities of certain pigments and to characterise reference samples. Pousão, whose work has not previously been studied spectroscopically, was found to have used a remarkably wide range of pigments over his painting periods, without showing significant preference for any particular set of pigments. Copyright © 2007 John Wiley & Sons, Ltd.