Enhanced ranking of PknB Inhibitors using data fusion methods

Identification of novel human nicotinamide N-methyltransferase inhibitors: a structure-based pharmacophore modeling and molecular dynamics approach

Human nicotinamide N-methyltransferase (hNNMT) is a cytosolic enzyme associated in the phase-II metabolism, belonging to the S-adenosyl-L-methionine (SAM)-dependent methyltransferases family. Overexpression of hNNMT was observed in diseases such as metabolic disorders and different types of cancers, which suggest NNMT as a prospective therapeutic target. In this study we propose a structure-based pharmacophore model to understand the structural features responsible for the pharmacological activity. The generated model was validated using the ROC curve (AUC), goodness of hit score (GH), specificity, sensitivity and enrichment factor (EF). The pharmacophore was employed to retrieve active molecules from the ZINC database, followed by virtual-screening and molecular docking. Six molecules with the best pharmfit score, binding energy and ADMET properties were identified in this study. A 150 ns molecular dynamics simulation was performed on the selected molecules complexed with hNNMT protein to validate the results. The molecules ZINC35464499, ZINC13311192, ZINC31159282, ZINC14650833, ZINC14819515 and ZINC00303881 were identified, which could be act as the potential hNNMT inhibitors and can also be used as direct hits for developing novel hNNMT antagonists.Communicated by Ramaswamy H. Sarma.

Systematic comparison of ligand-based and structure-based virtual screening methods on poly (ADP-ribose) polymerase-1 inhibitors

The poly (ADP-ribose) polymerase-1 (PARP1) has been regarded as a vital target in recent years and PARP1 inhibitors can be used for ovarian and breast cancer therapies. However, it has been realized that most of PARP1 inhibitors have disadvantages of low solubility and permeability. Therefore, by discovering more molecules with novel frameworks, it would have greater opportunities to apply it into broader clinical fields and have a more profound significance. In the present study, multiple virtual screening (VS) methods had been employed to evaluate the screening efficiency of ligand-based, structure-based and data fusion methods on PARP1 target. The VS methods include 2D similarity screening, structure-activity relationship (SAR) models, docking and complex-based pharmacophore screening. Moreover, the sum rank, sum score and reciprocal rank were also adopted for data fusion methods. The evaluation results show that the similarity searching based on Torsion fingerprint, six SAR models, Glide docking and pharmacophore screening using Phase have excellent screening performance. The best data fusion method is the reciprocal rank, but the sum score also performs well in framework enrichment. In general, the ligand-based VS methods show better performance on PARP1 inhibitor screening. These findings confirmed that adding ligand-based methods to the early screening stage will greatly improve the screening efficiency, and be able to enrich more highly active PARP1 inhibitors with diverse structures.

Pharmacophore model, docking, QSAR, and molecular dynamics simulation studies of substituted cyclic imides and herbal medicines as COX-2 inhibitors

Cyclooxygenase-2 (COX-2) enzyme inhibitors have not eliminated the necessity for developed drugs not only in the nonsteroidal anti-inflammatory drug (NSAIDs) area, but also in other therapeutic applications including prevention of cancer and Alzheimer's disease. A series of novel substituted cyclic imides have been reported as selective COX-2 inhibitors. To understand the structural features responsible for their activity, a 3D validated pharmacophore and quantitative structure−activity relationship (QSAR) model have been developed. The values of enrichment factor (EF), goodness of hit score (GH), area under the ROC curve (AUC), sensitivity, and specificity refer to the good ability of the pharmacophore model to identify active compounds. Multiple linear regression (MLR) produced statistically significant QSAR model with (R²_training = 0.763, R²_test = 0.96) and predictability (Q²_training = 0.66, Q²_test = 0.84). Then, using the pharmacophore and QSAR models, eight authenticated botanicals in two herbal medicines and the ZINC compounds database, were virtually screened for ligands to COX-2. The retrieved hits which also obey lipinski's rule of five (RO5) were docked in the COX-2 3D structure to investigate their binding mode and affinity. Finally, based on the docking results, nine molecules were prioritized as promising hits that could be used as leads to discover novel COX-2 inhibitors. COX-2 inhibition of most of these hits has not been reported previously. Ten-nanosecond molecular dynamics simulation (10-ns MD) was performed on the initial structure COX-2 complex with ZINC000113253375 and ZINC000043170560 resulted from the docking. Our utilization of the 3D pharmacophore model, QSAR, molecular docking, and molecular dynamics simulation trials can be a potent strategy to successfully predict activity, efficiently design drugs, and screen large numbers of new compounds as active drug candidates.

Development and validation of a sensitive LC-MS/MS method for the quantitation of IMB-YH-4py5-2H, an antituberculosis candidate, and its application to the pharmacokinetic study

(E)-N,N-dimethyl-4-oxo-4-(4-(pyridin-4-yl)phenyl)but-2-enamide hydrochloride (IMB-YH-4py5-2H) is a novel Protein Kinase B (PknB) inhibitor with potent activity against Mycobacterium tuberculosis strains. In the present study, a sensitive and specific liquid chromatography/tandem mass spectrometry (LC-MS/MS) method was developed and validated to determine IMB-YH-4py5-2H in rat plasma. Sample pretreatment was achieved by liquid-liquid extraction with ethyl acetate, and separation was performed on an XTerra MS C₁₈ column (2.1×50 mm, 3.5 μm) with gradient elution (methanol and 0.1% formic acid) at a flow rate of 0.3 mL/min. Detection was performed in multiple reaction monitoring (MRM) mode. Linear calibration curves were obtained over a concentration range of 1−100 ng/mL. The intra-day and inter-day precisions were lower than 8.46%, and the accuracies ranged from -8.71% to 12.36% at all quality control levels. The extraction recoveries were approximately 70%, and the matrix effects were negligible. All quality control samples were stable under different storage conditions. The validated method was successfully applied to a preclinical pharmacokinetic study in Sprague-Dawley rats. IMB-YH-4py5-2H demonstrated improved pharmacokinetic properties (higher exposure level) compared with its leading compound. IMB-YH-4py5-2H was also distributed throughout the lung pronouncedly, especially inside alveolar macrophages, indicating its effectiveness against lower respiratory infections.

In Silico Methods for the Discovery of Orthosteric GABAB Receptor Compounds

The GABAB receptor (GABAB-R) is a heterodimeric class C G protein-coupled receptor comprised of the GABAB1a/b and GABAB2 subunits. The endogenous orthosteric agonist γ-amino-butyric acid (GABA) binds within the extracellular Venus flytrap (VFT) domain of the GABAB1a/b subunit. The receptor is associated with numerous neurological and neuropsychiatric disorders including learning and memory deficits, depression and anxiety, addiction and epilepsy, and is an interesting target for new drug development. Ligand- and structure-based virtual screening (VS) are used to identify hits in preclinical drug discovery. In the present study, we have evaluated classical ligand-based in silico methods, fingerprinting and pharmacophore mapping and structure-based in silico methods, structure-based pharmacophores, docking and scoring, and linear interaction approximation (LIA) for their aptitude to identify orthosteric GABAB-R compounds. Our results show that the limited number of active compounds and their high structural similarity complicate the use of ligand-based methods. However, by combining ligand-based methods with different structure-based methods active compounds were identified in front of DUDE-E decoys and the number of false positives was reduced, indicating that novel orthosteric GABAB-R compounds may be identified by a combination of ligand-based and structure-based in silico methods.

Real-Time Weighted Data Fusion Algorithm for Temperature Detection Based on Small-Range Sensor Network

Biological oxidation pretreatment, which can improve the yield of gold, is the main gold extraction technology for disposing refractory gold ore with high arsenic and sulfur. The temperature of the oxidation tank influences the oxidation efficiency between the ore pulp and bacteria, including the yield of gold. Therefore, measurement has consistently been an important subject for researchers. As an effective data processing method, data fusion has been used extensively in many fields of industrial production. However, the interference of equipment or external factors such as the diurnal temperature difference or powerful wind may constantly increase measurement errors and damage certain sensors, which may transmit error data. These problems can be solved by following a pretreatment process. First, we establish a heat transfer mechanism model. Second, we design a small-range sensor network for the pretreatment process and present a layered fusion structure of sharing sensors using a multi-connected fusion structure. Third, we introduce the idea of iterative operation in data processing. In addition, we use prior data for predicting state values twice in order to improve the effectiveness of extended Kalman filtering in one time step. This study also proposes multi-fading factors on the basis of a weighted fading memory index to adjust the prediction error covariance. Finally, the state estimation accuracy of each sensor can be used as a weighting principle for the predictive confidence of each sensor by adding a weighting factor. In this study, the performance of the proposed method is verified by simulation and compared with the traditional single-sensor method. Actual industrial measurement data are processed by the proposed method for the equipment experiment. The performance index of the simulation and the experiment shows that the proposed method has a higher global accuracy than the traditional single-sensor method. Simulation results show that the accuracy of the proposed method has a 55% improvement upon that of the traditional single-sensor method, on average. In the equipment experiment, the accuracy of the industrial measurement improved by 37% when using the proposed method.

In Silico Screen and Structural Analysis Identifies Bacterial Kinase Inhibitors which Act with β-Lactams To Inhibit Mycobacterial Growth

New tools and concepts are needed to combat antimicrobial resistance. Actinomycetes and firmicutes share several eukaryotic-like Ser/Thr kinases (eSTK) that offer antibiotic development opportunities, including PknB, an essential mycobacterial eSTK. Despite successful development of potent biochemical PknB inhibitors by many groups, clinically useful microbiologic activity has been elusive. Additionally, PknB kinetics are not fully described, nor are structures with specific inhibitors available to inform inhibitor design. We used computational modeling with available structural information to identify human kinase inhibitors predicted to bind PknB, and we selected hits based on drug-like characteristics intended to increase the likelihood of cell entry. The computational model suggested a family of inhibitors, the imidazopyridine aminofurazans (IPAs), bind PknB with high affinity. We performed an in-depth characterization of PknB and found that these inhibitors biochemically inhibit PknB, with potency roughly following the predicted models. A novel X-ray structure confirmed that the inhibitors bound as predicted and made favorable protein contacts with the target. These inhibitors also have antimicrobial activity toward mycobacteria and nocardia. We demonstrated that the inhibitors are uniquely potentiated by β-lactams but not antibiotics traditionally used to treat mycobacteria, consistent with PknB's role in sensing cell wall stress. This is the first demonstration in the phylum actinobacteria that some β-lactam antibiotics could be more effective if paired with a PknB inhibitor. Collectively, our data show that in silico modeling can be used as a tool to discover promising drug leads, and the inhibitors we discovered can act with clinically relevant antibiotics to restore their efficacy against bacteria with limited treatment options.

Discovery of natural product inhibitors of phosphodiesterase 10A as novel therapeutic drug for schizophrenia using a multistep virtual screening

The major complaint that most of the schizophrenic patients' face is the cognitive impairment which affects the patient's quality of life. The current antipsychotic drugs treat only the positive symptoms without alleviating the negative or cognitive symptoms of the disease. In addition, the existing therapies are known to produce extrapyramidal side effects that affect the patient adherence to the treatment. PDE10A inhibitor is the new therapeutic approach which has been proven to be effective in alleviating the negative and cognitive symptoms of the disease. A number of PDE10A inhibitors have been developed, but no inhibitor has made it beyond the clinical trials so far. Thus, the present study has been conducted to identify a PDE10A inhibitor from natural sources to be used as a lead compound for the designing of novel selective PDE10A inhibitors. Ligand and structure-based pharmacophore models for PDE10A inhibitors were generated and employed for virtual screening of universal natural products database. From the virtual screening results, 37 compounds were docked into the active site of the PDE10A. Out of 37 compounds, three inhibitors showed the highest affinity for PDE10A where UNPD216549 showed the lowest binding energy and has been chosen as starting point for designing of novel PDE10A inhibitors. The structure-activity-relationship studies assisted in designing of selective PDE10A inhibitors. The optimization of the substituents on the phenyl ring resulted in 26 derivatives with lower binding energy with PDE10A as compared to the lead compound. Among these, MA 8 and MA 98 exhibited the highest affinity for PDE10A with binding energy (-10.90 Kcal/mol).

Toward a hierarchical virtual screening and toxicity risk analysis for identifying novel CA XII inhibitors

Carbonic anhydrase isoform XII (CA XII) is a potential target for cancer treatment. In this study, pharmacophore modeling, hierarchical virtual screening, and toxicity risk analysis were performed for identifying novel CA XII inhibitors. A pharmacophore model of two classes of CA XII inhibitors was generated. The pharmacophore model indicated the important features of inhibitors for the binding with the CA XII. The model was then utilized to screen the ZINC and CoCoCo databases for retrieving potential hit compounds of CA XII. For accurate conclusions about the selectivity of inhibitors, the retrieved molecules which obey of Lipinski's rule of five (RO5) and have no toxicity risk were docked in a CA XII 3D structure by smina. Finally, on the basis of binding affinity and the binding mode of the molecules, twelve molecules were prioritized as promising hits. It should be noted that two of hits H5 and H6 were previously reported in the CHEMBL database. This hierarchical method is worthy of reducing the time and using almost all information available. The final hits may be used as a lead to discovery novel CA XII inhibitors.

Quantum probability ranking principle for ligand-based virtual screening

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.

Substituted 4-oxo-crotonic acid derivatives as a new class of protein kinase B (PknB) inhibitors: synthesis and SAR study

Structure–activity relationship (SAR) study of a series of unsaturated crotonic acid derivatives as potential PknB inhibitors.

Pharmacophore modeling and in silico toxicity assessment of potential anticancer agents from African medicinal plants

Molecular modeling has been employed in the search for lead compounds of chemotherapy to fight cancer. In this study, pharmacophore models have been generated and validated for use in virtual screening protocols for eight known anticancer drug targets, including tyrosine kinase, protein kinase B β, cyclin-dependent kinase, protein farnesyltransferase, human protein kinase, glycogen synthase kinase, and indoleamine 2,3-dioxygenase 1. Pharmacophore models were validated through receiver operating characteristic and Güner–Henry scoring methods, indicating that several of the models generated could be useful for the identification of potential anticancer agents from natural product databases. The validated pharmacophore models were used as three-dimensional search queries for virtual screening of the newly developed AfroCancer database (~400 compounds from African medicinal plants), along with the Naturally Occurring Plant-based Anticancer Compound-Activity-Target dataset (comprising ~1,500 published naturally occurring plant-based compounds from around the world). Additionally, an in silico assessment of toxicity of the two datasets was carried out by the use of 88 toxicity end points predicted by the Lhasa’s expert knowledge-based system (Derek), showing that only an insignificant proportion of the promising anticancer agents would be likely showing high toxicity profiles. A diversity study of the two datasets, carried out using the analysis of principal components from the most important physicochemical properties often used to access drug-likeness of compound datasets, showed that the two datasets do not occupy the same chemical space.

Search for Potent and Selective Aurora A Inhibitors Based on General Ser/Thr Kinase Pharmacophore Model

Based on the data for compounds known from the literature to be active against various types of Ser/Thr kinases, a general pharmachophore model for these types of kinases was developed. The search for the molecules fitting to this pharmacophore among the ASINEX proprietary library revealed a number of compounds, which were tested and appeared to possess some activity against Ser/Thr kinases such as Aurora A, Aurora B and Haspin. Our work on the optimization of these molecules against Aurora A kinase allowed us to achieve several hits in a 3–5 nM range of activity with rather good selectivity and Absorption, Distribution, Metabolism, and Excretion (ADME) properties, and cytotoxicity against 16 cancer cell lines. Thus, we showed the possibility to fine-tune the general Ser/Thr pharmacophore to design active and selective compounds against desired types of kinases.

General Ser/Thr Kinases Pharmacophore Approach for Selective Kinase Inhibitors Search as Exemplified by Design of Potent and Selective Aurora A Inhibitors

A general pharmachophore model for various types of Ser/Thr kinases was developed. Search for the molecules fitting to this pharmacophore among ASINEX proprietary library revealed a number of compounds, which were tested and appeared to possess some activity against several Ser/Thr kinases such as Aurora A, Aurora B and Haspin. The possibility of performing the fine-tuning of the general Ser/Thr pharmacophore to desired types of kinase to get active and selective inhibitors was exemplified by Aurora A kinase. As a result, several hits in 3-5 nm range of activity against Aurora A kinase with rather good selectivity and ADME properties were obtained.

In silico and in vitro screening to identify structurally diverse non-azole CYP51 inhibitors as potent antifungal agent

The problem of resistance to azole class of antifungals is a serious cause of concern to the medical fraternity and thus there is an urgent need to identify non-azole scaffolds with high affinity for lanosterol 14α-demethylase (CYP51). In view of this we have attempted to identify novel non-azole CYP51 inhibitors through the application of pharmacophore based virtual screening and in vitro evaluation. A rigorously validated pharmacophore model comprising of 2 hydrogen bond acceptor and 2 hydrophobic features has been developed and used to mine NCI database. Out of 265 retrieved hits, NSC 1215 and 1520 have been chosen on the basis of Lipinski's rule of five, fit and estimated values. Both the hits were docked into the active site of CYP51. In view of high fit value and CDocker score, NSC 1215 and 1520 have been subjected to in vitro microbiological assay. The result reveals that NSC 1215 and 1520 are active against Candida albicans, Candida parapsilosis, Candida tropicalis, and Aspergillus niger. In addition to this the absorption characteristics of both the hits have also been determined using the rat sac technique and permeation in order of NSC 1520>NSC 1215 has been observed.

Validated LC--MS/MS method for determination of YH-8, a novel PKnB inhibitor, in rat plasma and its application to pharmacokinetic study

(E)-Methyl-4-aryl-4-oxabut-2-enoate (YH-8) is a novel PKnB protein kinase inhibitor with good anti-tuberculosis activity. To evaluate its pharmacokinetics in rats, a sensitive and selective high performance liquid chromatography–tandem mass spectrometric (LC--MS/MS) method has been developed and validated for the quantification of YH-8 in rat plasma for the first time. Samples were pre-treated using a liquid--liquid extraction with ethyl acetate and the chromatographic separation was performed on a C18 column by gradient elution with methanol--water as the mobile phase. YH-8 was detected using a tandem mass spectrometer in positive selected reaction monitoring (SRM) mode. Method validation revealed good linearity over the range of 1–500 ng/mL for YH-8 with a lower limit of quantification (LLOQ) of 1 ng/mL. Intra- and inter-day precision of YH-8 assay in rat plasma samples were 2.0%–6.8%, with accuracy of the method being 100.69%–106.18%. Stability test showed that when spiked into rat plasma, YH-8 was stable for 12 h at room temperature, for up to 15 days at −70 °C, and after three freeze-thaw cycles. Extracted samples were found to be stable over 12 h in an auto-sampler. The method was successfully applied to the pharmacokinetic study of YH-8 in rats after oral administration at 100 mg/kg and 200 mg/kg.

Optimizing drug-target interaction prediction based on random walk on heterogeneous networks

BACKGROUND

Predicting novel drug-target associations is important not only for developing new drugs, but also for furthering biological knowledge by understanding how drugs work and their modes of action. As more data about drugs, targets, and their interactions becomes available, computational approaches have become an indispensible part of drug target association discovery. In this paper we apply random walk with restart (RWR) method to a heterogeneous network of drugs and targets compiled from DrugBank database and investigate the performance of the method under parameter variation and choice of chemical fingerprint methods.

RESULTS

We show that choice of chemical fingerprint does not affect the performance of the method when the parameters are tuned to optimal values. We use a subset of the ChEMBL15 dataset that contains 2,763 associations between 544 drugs and 467 target proteins to evaluate our method, and we extracted datasets of bioactivity ≤1 and ≤10 μM activity cutoff. For 1 μM bioactivity cutoff, we find that our method can correctly predict nearly 47, 55, 60% of the given drug-target interactions in the test dataset having more than 0, 1, 2 drug target relations for ChEMBL 1 μM dataset in top 50 rank positions. For 10 μM bioactivity cutoff, we find that our method can correctly predict nearly 32.4, 34.8, 35.3% of the given drug-target interactions in the test dataset having more than 0, 1, 2 drug target relations for ChEMBL 1 μM dataset in top 50 rank positions. We further examine the associations between 110 popular top selling drugs in 2012 and 3,519 targets and find the top ten targets for each drug.

CONCLUSIONS

We demonstrate the effectiveness and promise of the approach-RWR on heterogeneous networks using chemical features-for identifying novel drug target interactions and investigate the performance.

Application of Shape Similarity in Pose Selection and Virtual Screening in CSARdock2014 Exercise

To evaluate the applicability of shape similarity in docking-based pose selection and virtual screening, we participated in the CSARdock2014 benchmark exercise for identifying the correct docking pose of inhibitors targeting factor XA, spleen tyrosine kinase, and tRNA methyltransferase. This exercise provides a valuable opportunity for researchers to test their docking programs, methods, and protocols in a blind testing environment. In the CSARdock2014 benchmark exercise, we have implemented an approach that uses ligand 3D shape similarity to facilitate docking-based pose selection and virtual screening. We showed here that ligand 3D shape similarity between bound poses could be used to identify the native-like pose from an ensemble of docking-generated poses. Our method correctly identified the native pose as the top-ranking pose for 73% of test cases in a blind testing environment. Moreover, the pose selection results also revealed an excellent correlation between ligand 3D shape similarity scores and RMSD to X-ray crystal structure ligand. In the virtual screening exercise, the average RMSD for our pose prediction was found to be 1.02 Å, and it was one of the top performances achieved in CSARdock2014 benchmark exercise. Furthermore, the inclusion of shape similarity improved virtual screening performance of docking-based scoring and ranking. The coefficient of determination (r(2)) between experimental activities and docking scores for 276 spleen tyrosine kinase inhibitors was found to be 0.365 but reached 0.614 when the ligand 3D shape similarity was included.

Selective pharmacologic inhibition of a PASTA kinase increases Listeria monocytogenes susceptibility to β-lactam antibiotics

While β-lactam antibiotics are a critical part of the antimicrobial arsenal, they are frequently compromised by various resistance mechanisms, including changes in penicillin binding proteins of the bacterial cell wall. Genetic deletion of the penicillin binding protein and serine/threonine kinase-associated protein (PASTA) kinase in methicillin-resistant Staphylococcus aureus (MRSA) has been shown to restore β-lactam susceptibility. However, the mechanism remains unclear, and whether pharmacologic inhibition would have the same effect is unknown. In this study, we found that deletion or pharmacologic inhibition of the PASTA kinase in Listeria monocytogenes by the nonselective kinase inhibitor staurosporine results in enhanced susceptibility to both aminopenicillin and cephalosporin antibiotics. Resistance to vancomycin, another class of cell wall synthesis inhibitors, or antibiotics that inhibit protein synthesis was unaffected by staurosporine treatment. Phosphorylation assays with purified kinases revealed that staurosporine selectively inhibited the PASTA kinase of L. monocytogenes (PrkA). Importantly, staurosporine did not inhibit a L. monocytogenes kinase without a PASTA domain (Lmo0618) or the PASTA kinase from MRSA (Stk1). Finally, inhibition of PrkA with a more selective kinase inhibitor, AZD5438, similarly led to sensitization of L. monocytogenes to β-lactam antibiotics. Overall, these results suggest that pharmacologic targeting of PASTA kinases can increase the efficacy of β-lactam antibiotics.

Using cheminformatics to predict cross reactivity of "designer drugs" to their currently available immunoassays

Background

A challenge for drug of abuse testing is presented by ‘designer drugs’, compounds typically discovered by modifications of existing clinical drug classes such as amphetamines and cannabinoids. Drug of abuse screening immunoassays directed at amphetamine or methamphetamine only detect a small subset of designer amphetamine-like drugs, and those immunoassays designed for tetrahydrocannabinol metabolites generally do not cross-react with synthetic cannabinoids lacking the classic cannabinoid chemical backbone. This suggests complexity in understanding how to detect and identify whether a patient has taken a molecule of one class or another, impacting clinical care.

Methods

Cross-reactivity data from immunoassays specifically targeting designer amphetamine-like and synthetic cannabinoid drugs was collected from multiple published sources, and virtual chemical libraries for molecular similarity analysis were built. The virtual library for synthetic cannabinoid analysis contained a total of 169 structures, while the virtual library for amphetamine-type stimulants contained 288 compounds. Two-dimensional (2D) similarity for each test compound was compared to the target molecule of the immunoassay undergoing analysis.

Results

2D similarity differentiated between cross-reactive and non-cross-reactive compounds for immunoassays targeting mephedrone/methcathinone, 3,4-methylenedioxypyrovalerone, benzylpiperazine, mephentermine, and synthetic cannabinoids.

Conclusions

In this study, we applied 2D molecular similarity analysis to the designer amphetamine-type stimulants and synthetic cannabinoids. Similarity calculations can be used to more efficiently decide which drugs and metabolites should be tested in cross-reactivity studies, as well as to design experiments and potentially predict antigens that would lead to immunoassays with cross reactivity for a broader array of designer drugs.

Condorcet and borda count fusion method for ligand-based virtual screening

Background

It is known that any individual similarity measure will not always give the best recall of active molecule structure for all types of activity classes. Recently, the effectiveness of ligand-based virtual screening approaches can be enhanced by using data fusion. Data fusion can be implemented using two different approaches: group fusion and similarity fusion. Similarity fusion involves searching using multiple similarity measures. The similarity scores, or ranking, for each similarity measure are combined to obtain the final ranking of the compounds in the database.

Results

The Condorcet fusion method was examined. This approach combines the outputs of similarity searches from eleven association and distance similarity coefficients, and then the winner measure for each class of molecules, based on Condorcet fusion, was chosen to be the best method of searching. The recall of retrieved active molecules at top 5% and significant test are used to evaluate our proposed method. The MDL drug data report (MDDR), maximum unbiased validation (MUV) and Directory of Useful Decoys (DUD) data sets were used for experiments and were represented by 2D fingerprints.

Conclusions

Simulated virtual screening experiments with the standard two data sets show that the use of Condorcet fusion provides a very simple way of improving the ligand-based virtual screening, especially when the active molecules being sought have a lowest degree of structural heterogeneity. However, the effectiveness of the Condorcet fusion was increased slightly when structural sets of high diversity activities were being sought.

Fusing dual-event data sets for Mycobacterium tuberculosis machine learning models and their evaluation

The search for new tuberculosis treatments continues as we need to find molecules that can act more quickly, be accommodated in multidrug regimens, and overcome ever increasing levels of drug resistance. Multiple large scale phenotypic high-throughput screens against Mycobacterium tuberculosis (Mtb) have generated dose response data, enabling the generation of machine learning models. These models also incorporated cytotoxicity data and were recently validated with a large external data set. A cheminformatics data-fusion approach followed by Bayesian machine learning, Support Vector Machine, or Recursive Partitioning model development (based on publicly available Mtb screening data) was used to compare individual data sets and subsequent combined models. A set of 1924 commercially available molecules with promising antitubercular activity (and lack of relative cytotoxicity to Vero cells) were used to evaluate the predictive nature of the models. We demonstrate that combining three data sets incorporating antitubercular and cytotoxicity data in Vero cells from our previous screens results in external validation receiver operator curve (ROC) of 0.83 (Bayesian or RP Forest). Models that do not have the highest 5-fold cross-validation ROC scores can outperform other models in a test set dependent manner. We demonstrate with predictions for a recently published set of Mtb leads from GlaxoSmithKline that no single machine learning model may be enough to identify compounds of interest. Data set fusion represents a further useful strategy for machine learning construction as illustrated with Mtb. Coverage of chemistry and Mtb target spaces may also be limiting factors for the whole-cell screening data generated to date.