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.     

Diversity-oriented regioselective domino Michael/Aldol reaction of 3-ylideneoxindoles: A direct access to indanol-fused 3-oxindoles

A diversity-oriented molecular hybridization strategy has been utilized for the synthesis of 2,3-disubstituted 1-indanol-fused 3-oxindoles through a regioselective domino Michael/Aldol reaction of 3-ylideneoxindoles 1 with malononitrile or cyanacetate ethyle 2. Products bearing consecutive stereocenters consist of an oxindole moiety and an indanol core, were smoothly obtained in high yields (up to 92% yield) with good diastereoselectivity (up to 20:1). This protocol also represents the first construction of indanol-fused 3-oxindole scaffolds, thus leading to new knowledge in the fields of both molecular complexity and diversity-oriented synthesis (DOS) and the lead compound discovery. It is also worth mentioning that the reaction was completely regioselective and the competitive regioisomeric products 4 or 5 were not obtained in any case.     

Molecular hybridization-guided annulation reactions of isatins with 4-methylpent-3-en-2-one: A direct access to spirooxindole tetrahydropyranones

An efficient molecular hybridization strategy has been utilized for the synthesis of pirooxindole tetrahydropyranones 3 through annulation reactions of isatins 1 with 4-methylpent-3-en-2-one 2. Products consist of a pirooxindole tetrahydropyranone scaffold and propan-2-ether unit were smoothly obtained in moderate yields (up to 56% yield). The one-pot, two-step reaction, avoiding the isolation and purification of intermediates C, has proved to be a practical protocol. This protocol leads to new knowledge in the fields of both molecular complexity and the lead compound discovery.     

An improved synthesis of ‘octa-acid’ deep-cavity cavitand

An improved synthesis of a water-soluble deep-cavity cavitand (octa-acid, 1) is presented. Previously (Gibb, C.L.D.; Gibb, B.C. J. Am. Chem. Soc. 2004, 126, 11408–11409), we documented access to host 1 in eight (non-linear) steps starting from resorcinol; a synthesis that required four steps involving chromatographic purification. Here, we reveal a modified synthesis of host 1. Consisting of seven (non-linear) steps, this new synthesis involves only one chromatographic step, and avoids a minor impurity observed in the original approach. This improved synthesis is therefore useful for the laboratories that are investigating the properties of these types of host.     

Diversity-oriented TsOH catalysis-enabled construction of tanshinone-substituted bis(indolyl/pyrrolyl)methanes and their biological evaluation for anticancer activities

We have developed an efficient and straightforward methodology for the synthesis of novel tanshinone-substituted bis(indolyl/pyrrolyl)methane scaffolds 3 through TsOH catalysis-enabled addition of indoles or pyrroles 1 with tanshinones 2 based on molecular hybridization strategy. Products were smoothly obtained in good yields (up to 81% yield). This protocol also represents the first construction of tanshinone skeleton-fused bis(indolyl/pyrrolyl)methane scaffolds, thus leading to new knowledge in the fields of both molecular complexity and diversity-oriented synthesis and the lead compound discovery. Furthermore, their biological activities against human leukemia cells K562, human prostate cancer cells PC-3, and human lung cancer cells A549 have been preliminarily demonstrated by in vitro assays. The results demonstrated that most of these compounds 3 obtained by this protocol showed comparable activity to the positive control of cisplatin.     

Simultaneous feature selection and parameter optimisation using an artificial ant colony: case study of melting point prediction

Background  

We present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models. The WAAC algorithm is an extension of the modified ant colony algorithm of Shen et al. (J Chem Inf Model 2005, 45: 1024–1029). We test the ability of the algorithm to develop a predictive partial least squares model for the Karthikeyan dataset (J Chem Inf Model 2005, 45: 581–590) of melting point values. We also test its ability to perform feature selection on a support vector machine model for the same dataset.     

Constant Potential Pretreatment of Carbon Fiber Electrodes for in Vivo Electrochemistry

Abstract

A constant potential procedure to pretreat carbon fiber electrodes is described. This essentially consists of two steps: +3.0 V for 30 s and -2.0 V for 10 s. The anodic potential treatment enhances sensitivity for catechols, and cathodic potential treatment improves selectivity, which results in a potential shift of AA from catechols. The optimum parameters and experimental conditions for electrochemical treatment were explored. Treated carbon fiber electrode used in rat brain showed well-defined and separated peaks of AA and catechols.     

The Path of Carbon in Photosynthesis: How to Discover a Biochemical Pathway

Abstract

This paper traces the discovery of the so-called Calvin–Benson cycle of photosynthesis, that is, the cyclic sequence of reactions through which the reduction of carbon dioxide to carbohydrates is accomplished in the green organs of plants. This pathway, which herein is understood to be the model of a mechanism, was elucidated by a research team of the University of California at Berkeley in the years 1946–1954. The sequence of working hypotheses is described, with a focus on the methodology and heuristic strategies of the research group. While it has often been underlined that the group’s innovative mixture of new techniques (radiotracers and paper chromatography) was the secret of its success, this paper describes how these techniques were applied: it transpires that the group combined the classic difference test, the interpretation of which was guided by additional heuristic assumptions and mechanistic thinking, with a specific kind of analogical inference, namely, the transfer of causal knowledge from one context to another.     

Ligand based virtual screening using SVM on GPU

In silico methods play an essential role in modern drug discovery methods. Virtual screening, an in silico method, is used to filter out the chemical space on which actual wet lab experiments are need to be conducted. Ligand based virtual screening is a computational strategy using which one can build a model of the target protein based on the knowledge of the ligands that bind successfully to the target. This model is then used to predict if the new molecule is likely to bind to the target. Support vector machine, a supervised learning algorithm used for classification, can be utilized for virtual screening the ligand data. When used for virtual screening purpose, SVM could produce interesting results. But since we have a huge ligand data, the time taken for training the SVM model is quite high compared to other learning algorithms. By parallelizing these algorithms on multi-core processors, one can easily expedite these discoveries. In this paper, a GPU based ligand based virtual screening tool (GpuSVMScreen) which uses SVM have been proposed and bench-marked. This data parallel virtual screening tool provides high throughput by running in short time. The proposed GpuSVMScreen can successfully screen large number of molecules (billions) also. The source code of this tool is available at http://ccc.nitc.ac.in/project/GPUSVMSCREEN.     

Expeditious Synthesis of Ramipril: An Angiotensin Converting Enzyme (ACE) Inhibitor

We document an efficient and cost‐effective synthesis of ramipril 1 utilizing (i) an environmentally benign process for the esterification of racemic 2‐aza‐bicyclo‐[3.3.0]‐octane‐3‐carboxylic acid hydrochloride 2 using boric acid as a catalyst and (ii) a robust resolution process for the synthesis of 3a by means of inexpensive and recyclable L‐(+)‐mandelic acid as key steps.     

Energy landscape study of water splitting and H2 evolution at a ruthenium(II) pincer complex

A bird's-eye view of the water splitting and H₂ generation at a ruthenium(II) pincer complex is presented. Using a combination of density functional theory and efficient algorithms for exploration of potential energy hypersurface (PES), a total of 197 local minima and 186 transition states are identified, and a new mechanism for water splitting and H₂ evolution via hydroxycarbonyl intermediates is presented. Furthermore, a global feature of the reaction PES, so-called potential energy landscape, is discussed on analyzing the obtained structures. As a result, the landscape is characterized by hierarchical structure, namely, PES consists of many “superbasins (SBs)” that are separated by relatively high energy barriers corresponding to bond breaking around Ru(II) center. Each SB involves a set of conformational isomers that can be interchanged with each other through relatively small barriers. To the best of our best knowledge, this is the first report on the quantum chemical computation of the hierarchical structure of PES for a realistic, catalytic reaction system.     

Kinetic and Thermodynamic Studies of Facial and Meridional uns-cis-[Co(eddp)gly] Complexes

Thermal properties of facial and meridional uns-cis-[Co(eddp)gly]0.5H₂O complexes were investigated by means of DSC and TG techniques. It wasshown that the processes of thermal decomposition of these complexes are multi-stepdegradation processes, which can also be well separated into individual steps, depending onthe molecular symmetry. Thus, the process of thermal degradation of the meridional isomerof the above complex consists of 4 well-separated steps in the temperature interval from 100to 500°C. The corresponding kinetic and thermodynamic parameters of this process weredetermined, and a possible mechanism is discussed. This revised version was published online in July 2006 with corrections to the Cover Date.     

Analysis of a Mixture of Polychlorinated Biphenyls,DDT and its Analogues by High-Performance Liquid Chromatography

Abstract

A simple and rapid method for separation and quantitative analysis of polychlorinated biphenyis (PCBs) and chlorinated pesticides (DDT and its analogues DDE and DDD in their o, o'-and p, p'-isomers) is described. The procedure consists of two steps: a) transformation of DDT and its analogues in o, p'-and p, p'-dichlorobenzophenone (DCBP); b)determination of the amount of PCBs and ∑DDT as DCBP by HPLC. Results obtained confirm that HPLC can be considered as an alternative or a supplementary methodology to conventional methods such as gas chromatography. The method is applied to marine organisms.     

Integration of chemical data using XML

Internet resources for the toxicological and pharmacological communities offer considerable information, however, the data is generally not amenable to machine-driven reuse. Adoption of XML standards by these (and related) communities will revolutionize the process of sharing information, promoting collaboration and discovery.     

A Practical Manufacturing Synthesis of 1-(R)-Hydroxymethyl-Dtpa: An Important Intermediate in the Synthesis of MRI Contrast Agents

An efficient synthesis of alcohol 2 is described from L-Serine (OMe) in four synthetic steps. The process uses readily available reagents and is suitable for manufacturing.     

Kinetic modelling and inverse treatment of the radical mechanism of the liquid-phase autoxidation of 1,2,3,4-tetrahydronaphthalene

A kinetic model to account for the overall radical mechanism of the self-initiated liquid-phase autoxidation of 1,2,3,4-tetrahydronaphthalene (tetralin RH₂) without solvent and without catalyst at 60°C under normal pressure is presented. The model was constructed following a heuristic approach and it consists of 16 elementary steps and a species space including 6 radical and 7 nonradical compounds. Applying inverse computations, the model can be assigned to experimentally observed data within very good agreement where most of the computed values for the kinetic parameters are found to be close to literature values. The respective experimental data is characterized by an autocatalytic time-evolution of tetralin hydroperoxide (HROOH) and of α-tetralone (RO) where in the first stage of autoxidation a remarkable very slow rate of the RO formation in respect to that of the HROOH formation can be observed. This effect is explicitly expressed by the transformation process of tetralyloxy radicals (HRO˙) into α-tetralol radicals (˙ROH) which react with oxygen yielding RO. The transformation is suggested to be catalyzed by α-tetralol (HROH) which accumulates autocatalytically during the radical chain process. Hence, the nonlinear formation of HROH leads to a switching in the transformation of HRO˙ into ˙ROH radicals which causes a growing rate of RO evolution. The autocatalytic nature of the overall process is explained by degenerate branching of one molecule of HROOH yielding radical species finally resulting into 2 tetralyl radicals (RH˙). This process leads to a growing number of chain propagating reaction sequences involving RH˙ and tetralylperoxy radicals (HROO˙) in which RH₂ and O₂ are consumed and HROOH is formed. Based on the fitting of experimental data the suggested general dynamic structure of the model is validated by computing the reaction fluxes vs. time of several mechanistic key steps. By computer simulations the model is also shown to predict the increase of product accumulation which can be observed experimentally if the autoxidation of RH₂ is started after an initial addition of HROH. © 1996 John Wiley & Sons, Inc.     

Automated affinity selection for rapid discovery of peptide binders

In-solution affinity selection (AS) of large synthetic peptide libraries affords identification of binders to protein targets through access to an expanded chemical space. Standard affinity selection methods, however, can be time-consuming, low-throughput, or provide hits that display low selectivity to the target. Here we report an automated bio-layer interferometry (BLI)-assisted affinity selection platform. When coupled with tandem mass spectrometry (MS), this method enables both rapid de novo discovery and affinity maturation of known peptide binders with high selectivity. The BLI-assisted AS-MS technology also features real-time monitoring of the peptide binding during the library selection process, a feature unattainable by current selection approaches. We show the utility of the BLI AS-MS platform toward rapid identification of novel nanomolar (dissociation constant, K_D < 50 nM) non-canonical binders to the leukemia-associated oncogenic protein menin. To our knowledge, this is the first application of BLI to the affinity selection of synthetic peptide libraries. We believe our approach can significantly accelerate the use of synthetic peptidomimetic libraries in drug discovery.

This work reports an automated affinity selection-mass spectrometry (AS-MS) approach amenable to both de novo peptide binder discovery and affinity maturation of known binders in a high-throughput and selective manner.     

Collection and preparation of molecular databases for virtual screening

Drug discovery and development research is undergoing a paradigm shift from a linear and sequential nature of the various steps involved in the drug discovery process of the past to the more parallel approach of the present, due to a lack of sufficient correlation between activities estimated by in vitro and in vivo assays. This is attributed to the non-drug-likeness of the lead molecules, which has often been detected at advanced drug development stages. Thus a striking aspect of this paradigm shift has been early/parallel in silico prioritization of drug-like molecular databases (also database pre-processing), in addition to prioritizing compounds with high affinity and selectivity for a protein target. In view of this, a drug-like database useful for virtual screening has been created by prioritizing molecules from 36 catalog suppliers, using our recently derived binary QSAR based drug-likeness model as a filter. The performance of this model was assessed by a comparative evaluation with respect to commonly used filters implemented by the ZINC database. Since the model was derived considering all the limitations that have plagued the existing rules and models, it performs better than the existing filters and thus the molecules prioritized by this filter represent a better subset of drug-like compounds. The application of this model on exhaustive subsets of 4,972,123 molecules, many of which have passed the ZINC database filters for drug-likeness, led to a further prioritization of 2,920,551 drug-like molecules. This database may have a great potential for in silico virtual screening for discovering molecules, which may survive the later stages of the drug development research.     

Conditional GWAS revealing genetic impacts of lifestyle behaviors on low-density lipoprotein (LDL)

BackgroundAccumulation of LDL cholesterol (LDL-c) within artery walls is strongly associated with the initiation and progression of atherosclerosis development. This complex trait is affected by multifactor involving polygenes, environments, and their interactions. Uncovering genetic architecture of LDL may help to increase the understanding of the genetic mechanism of cardiovascular diseases.MethodsWe used a genetic model to analyze genetic effects including additive, dominance, epistasis, and ethnic interactions for data from the Multi-Ethnic Study of Atherosclerosis (MESA). Three lifestyle behaviors (reading, intentional exercising, smoking) were used as cofactor in conditional models.ResultsWe identified 156 genetic effects of 10 quantitative trait SNPs (QTSs) in base model and three conditional models. The total estimated heritability of these genetic effects was approximately 72.88% in the base model. Five genes (CELSR2, MARK2, ADAMTS12, PFDN4, and MAGI2) have biological functions related to LDL.ConclusionsCompared with the based model LDL, the results in three conditional models revealed that intentional exercising and smoking could have impacts for causing and suppressing some of genetic effects and influence the levels of LDL. Furthermore, these two lifestyles could have different genetic effects for each ethnic group on a specific QTS. As most of the heritability in based model LDL and conditional model LDL|Smk was contributed from epistasis effects, our result indicated that epistasis effects played important roles in determining LDL levels. Our study provided useful insight into the biological mechanisms underlying regulation of LDL and might help in the discovery of novel therapeutic targets for cardiovascular disease.