Search

The theoretical prediction of drug-decorated nanoparticles (DDNPs) has become a very important task in medical applications. For the current paper, Perturbation Theory Machine Learning (PTML) models were built to predict the probability of different pairs of drugs and nanoparticles creating DDNP complexes with anti-glioblastoma activity. PTML models use the perturbations of molecular descriptors of drugs and nanoparticles as inputs in experimental conditions. The raw dataset was obtained by mixing the nanoparticle experimental data with drug assays from the ChEMBL database. Ten types of machine learning methods have been tested. Only 41 features have been selected for 855,129 drug-nanoparticle complexes. The best model was obtained with the Bagging classifier, an ensemble meta-estimator based on 20 decision trees, with an area under the receiver operating characteristic curve (AUROC) of 0.96, and an accuracy of 87% (test subset). This model could be useful for the virtual screening of nanoparticle-drug complexes in glioblastoma. All the calculations can be reproduced with the datasets and python scripts, which are freely available as a GitHub repository from authors.

Drug-decorated nanoparticles (DDNPs) have important medical applications. The current work combined Perturbation Theory with Machine Learning and Information Fusion (PTMLIF). Thus, PTMLIF models were proposed to predict the probability of nanoparticle–compound/drug complexes having antimalarial activity (against Plasmodium). The aim is to save experimental resources and time by using a virtual screening for DDNPs. The raw data was obtained by the fusion of experimental data for nanoparticles with compound chemical assays from the ChEMBL database. The inputs for the eight Machine Learning classifiers were transformed features of drugs/compounds and nanoparticles as perturbations of molecular descriptors in specific experimental conditions (experiment-centered features). The resulting dataset contains 107 input features and 249,992 examples. The best classification model was provided by Random Forest, with 27 selected features of drugs/compounds and nanoparticles in all experimental conditions considered. The high performance of the model was demonstrated by the mean Area Under the Receiver Operating Characteristics (AUC) in a test subset with a value of 0.9921 ± 0.000244 (10-fold cross-validation). The results demonstrated the power of information fusion of the experimental-centered features of drugs/compounds and nanoparticles for the prediction of nanoparticle–compound antimalarial activity. The scripts and dataset for this project are available in the open GitHub repository.

Metal-oxide nanoparticles are regarded as favorable candidates for different device applications including gas sensors. Decoration of nanoparticles with smaller ones of different types enables taking advantage of the physical and chemical characteristics of both core and decorate nanoparticles. Fe 3 O 4 nanoparticles decorated with CuO are produced in this work by a coprecipitation method and investigated for their application for H 2 S gas sensor devices. The average size of Fe 3 O 4 nanoparticles is 33.33 ∓ 5.55 n m while the average grain size of the CuO nanoparticles is 9.72 ∓ 1.39 n m. Gas sensors are fabricated by depositing dispersed nanoparticles on substrates with pre-printed interdigitated electrodes. Impedance spectroscopy is utilized to investigate the electrical characteristics of fabricated devices, where their activation energy is evaluated to 0.386 ± 0.076 e V. The fabricated sensors are found to be selective to H 2 S and sensitive to low concentrations, as low as 1.0 ppm, with minimum response time of 1.0 min. The produced sensors indicate potential for field applications due to their various features that include simplified and practical fabrication procedure, low power needs, high sensitivity, reasonable response time, and magnetic properties of nanoparticles that facilitate their recycling. • H 2 S gas sensors were produced based on nanoparticles of Fe 3 O 4 decorated with CuO. • The nanoparticles were synthesized by a coprecipitation method. • The sensors were sensitive at room temperature for H 2 S concentration of 1.0 ppm. • The minimum response times was 1.0 min. • The sensors were stable for multiple application cycles. [ABSTRACT FROM AUTHOR]

The theoretical prediction of drug-decorated nanoparticles (DDNPs) has become a very important task in medical applications. For the current paper, Perturbation Theory Machine Learning (PTML) models were built to predict the probability of different pairs of drugs and nanoparticles creating DDNP complexes with anti-glioblastoma activity. PTML models use the perturbations of molecular descriptors of drugs and nanoparticles as inputs in experimental conditions. The raw dataset was obtained by mixing the nanoparticle experimental data with drug assays from the ChEMBL database. Ten types of machine learning methods have been tested. Only 41 features have been selected for 855,129 drug-nanoparticle complexes. The best model was obtained with the Bagging classifier, an ensemble meta-estimator based on 20 decision trees, with an area under the receiver operating characteristic curve (AUROC) of 0.96, and an accuracy of 87% (test subset). This model could be useful for the virtual screening of nanoparticle-drug complexes in glioblastoma. All the calculations can be reproduced with the datasets and python scripts, which are freely available as a GitHub repository from authors. [ABSTRACT FROM AUTHOR]

Drug-decorated nanoparticles (DDNPs) have important medical applications. The current work combined Perturbation Theory with Machine Learning and Information Fusion (PTMLIF). Thus, PTMLIF models were proposed to predict the probability of nanoparticle-compound/drug complexes having antimalarial activity (against Plasmodium). The aim is to save experimental resources and time by using a virtual screening for DDNPs. The raw data was obtained by the fusion of experimental data for nanoparticles with compound chemical assays from the ChEMBL database. The inputs for the eight Machine Learning classifiers were transformed features of drugs/compounds and nanoparticles as perturbations of molecular descriptors in specific experimental conditions (experiment-centered features). The resulting dataset contains 107 input features and 249,992 examples. The best classification model was provided by Random Forest, with 27 selected features of drugs/compounds and nanoparticles in all experimental conditions considered. The high performance of the model was demonstrated by the mean Area Under the Receiver Operating Characteristics (AUC) in a test subset with a value of 0.9921 ± 0.000244 (10-fold cross-validation). The results demonstrated the power of information fusion of the experimental-centered features of drugs/compounds and nanoparticles for the prediction of nanoparticle-compound antimalarial activity. The scripts and dataset for this project are available in the open GitHub repository.

This article presents the synthesis of poly(methacrylic acid)‐b‐poly(methyl methacrylate) diblock copolymer via polymerization‐induced self‐assembly in the presence of iron‐oxide nanoparticles. Detailed phase diagrams with and without inorganic nanoparticles were constructed. Scanning transmission electron microscopy and energy dispersive X‐ray photometry studies confirme the decoration of the polymeric nanoparticles with the iron‐oxide nanoparticles. These hybrid nanoparticles were used to prepare porous thin film membranes by spin coating. Finally, the magneto‐responsive properties of the membranes were assessed using water filtration tests in the presence and absence of a magnetic field. Iron‐oxide‐decorated PMAA‐b‐PMMA nanoparticles are prepared via polymerization‐induced self‐assembly and the influence of presence of magnetic iron‐oxide nanoparticles on the phase diagram is investigated. Thin‐film membranes made from these decorated nanoparticles show magnetic character. [ABSTRACT FROM AUTHOR]

Regimen adherence, systemic toxicities, and limited drug penetrance to viral reservoirs are obstacles limiting the effectiveness of antiretroviral therapy (ART). Our laboratory's development of the monocyte-macrophage-targeted long-acting nanoformulated ART (nanoART) carriage provides a novel opportunity to simplify drug-dosing regimens. Progress has nonetheless been slowed by cumbersome, but required, pharmacokinetic (PK), pharmacodynamics, and biodistribution testing. To this end, we developed a small magnetite ART (SMART) nanoparticle platform to assess antiretroviral drug tissue biodistribution and PK using magnetic resonance imaging (MRI) scans. Herein, we have taken this technique a significant step further by determining nanoART PK with folic acid (FA) decorated magnetite (ultrasmall superparamagnetic iron oxide [USPIO]) particles and by using SMART particles. FA nanoparticles enhanced the entry and particle retention to the reticuloendothelial system over nondecorated polymers after systemic administration into mice. These data were seen by MRI testing and validated by comparison with SMART particles and direct evaluation of tissue drug levels after nanoART. The development of alendronate (ALN)-coated magnetite thus serves as a rapid initial screen for the ability of targeting ligands to enhance nanoparticle-antiretroviral drug biodistribution, underscoring the value of decorated magnetite particles as a theranostic tool for improved drug delivery.