Browse
Submit Data
Databases
API
Help

Dataset Information

29 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Prediction of Methylene Blue Removal by Nano TiO₂ Using Deep Neural Network.

ABSTRACT: This paper deals with the prediction of methylene blue (MB) dye removal under the influence of titanium dioxide nanoparticles (TiO2 NPs) through deep neural network (DNN). In the first step, TiO2 NPs were prepared and their morphological properties were analysed by scanning electron microscopy. Later, the influence of as synthesized TiO2 NPs was tested against MB dye removal and in the final step, DNN was used for the prediction. DNN is an efficient machine learning tools and widely used model for the prediction of highly complex problems. However, it has never been used for the prediction of MB dye removal. Therefore, this paper investigates the prediction accuracy of MB dye removal under the influence of TiO2 NPs using DNN. Furthermore, the proposed DNN model was used to map out the complex input-output conditions for the prediction of optimal results. The amount of chemicals, i.e., amount of TiO2 NPs, amount of ehylene glycol and reaction time were chosen as input variables and MB dye removal percentage was evaluated as a response. DNN model provides significantly high performance accuracy for the prediction of MB dye removal and can be used as a powerful tool for the prediction of other functional properties of nanocomposites.

SUBMITTER: Amor N

PROVIDER: S-EPMC8473325 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Solar Light-Induced Methylene Blue Removal over TiO2/AC Composites and Photocatalytic Regeneration.

Project description:TiO2-containing photocatalysts, which combine TiO2 with carbon-based materials, are promising materials for wastewater treatment due to synergistic photodegradation and adsorption phenomena. In this work, TiO2/AC composites were produced by the in situ immobilization of TiO2 nanoparticles over activated carbon (AC) derived from spent coffee grains, using different TiO2/AC proportions. The TiO2/AC composites were tested as adsorbents (dark) and as photocatalysts in a combined adsorption+photocatalytic process (solar irradiation) for methylene blue (MB) removal from ultrapure water, and from a secondary effluent (SecEf) of an urban wastewater treatment plant. All the materials were characterized by XRD (X-ray powder diffraction), N2 adsorption-desorption isotherms at -196 °C, SEM (scanning electron microscopy), UV-Vis diffuse reflectance, FTIR (Fourier-transform infrared spectroscopy), TPD (temperature programmed desorption), XPS (X-ray photoelectron spectroscopy) and TGA (thermogravimetric analysis). The TiAC60 (60% C) composite presented the lowest band gap (1.84 eV), while, for TiAC29 (29% C), the value was close to that of bare TiO2 (3.18 vs. 3.17 eV). Regardless of the material, the solar irradiation improved the percentage of MB discolouration when compared to adsorption in dark conditions. In the case of simultaneous adsorption+photocatalytic assays performed in ultrapure water, TiAC29 presented the fastest MB removal. Nevertheless, both TiAC29 and TiAC60 led to excellent MB removal percentages (96.1-98.1%). UV-induced photoregeneration was a promising strategy to recover the adsorption capacity of the materials, especially for TiAC60 and AC (>95%). When the assays were performed in SecEf, all the materials promoted discolouration percentages close to those obtained in ultrapure water. The bulk water parameters revealed that TiAC60 allowed the removal of a higher amount of MB, associated with the overall improvement of the SecEf quality.

| S-EPMC8625254 | biostudies-literature

Ultra-Highly Efficient Removal of Methylene Blue Based on Graphene Oxide/TiO2/Bentonite Sponge.

Project description:An ultra-highly efficient Graphene Oxide/TiO2/Bentonite (GO/TiO2/Bent) sponge was synthesized using an in situ hydrothermal method. GO/TiO2/Bent sponge with a GO mass concentration of 10% exhibited the highest treatment efficiency of methylene blue (MB), combining adsorption and photocatalytic degradation, and achieved a maximum removal efficiency of 100% within about 70 min. To further prove the ultra-high removal capacity of the sponge, the concentration of MB in water increased to ten times the original concentration. At so high a MB concentration, the removal rate was still as high as 80% in 90 min. The photocatalytic mechanism of GO/TiO2/Bent sponge was discussed through XPS, PL and radicals quenching experiments. Here Bent can immobilize TiO2 and react with a photo-generated hole to increase the amount of hydroxyl radical; effectively enhancing the degradation of MB.GO sponge enlarges the sensitivity range of TiO2 to visible light by increasing the charge separation of TiO2 and reducing the recombination of photo-generated electron-hole pairs. Additionally, GO sponge with an interconnected porous structure provides an effective platform to immobilize TiO2/bent and makes them be easily recovered. The as-prepared sponge develops a simple and cost-effective strategy to realize the ultra-highly efficient treatment of dyes in wastewater.

| S-EPMC7078707 | biostudies-literature

Molecular Geometry Prediction using a Deep Generative Graph Neural Network.

Project description:A molecule's geometry, also known as conformation, is one of a molecule's most important properties, determining the reactions it participates in, the bonds it forms, and the interactions it has with other molecules. Conventional conformation generation methods minimize hand-designed molecular force field energy functions that are often not well correlated with the true energy function of a molecule observed in nature. They generate geometrically diverse sets of conformations, some of which are very similar to the lowest-energy conformations and others of which are very different. In this paper, we propose a conditional deep generative graph neural network that learns an energy function by directly learning to generate molecular conformations that are energetically favorable and more likely to be observed experimentally in data-driven manner. On three large-scale datasets containing small molecules, we show that our method generates a set of conformations that on average is far more likely to be close to the corresponding reference conformations than are those obtained from conventional force field methods. Our method maintains geometrical diversity by generating conformations that are not too similar to each other, and is also computationally faster. We also show that our method can be used to provide initial coordinates for conventional force field methods. On one of the evaluated datasets we show that this combination allows us to combine the best of both methods, yielding generated conformations that are on average close to reference conformations with some very similar to reference conformations.

| S-EPMC6938476 | biostudies-literature

HumDLoc: Human Protein Subcellular Localization Prediction Using Deep Neural Network.

Project description:AimsTo develop a tool that can annotate subcellular localization of human proteins.BackgroundWith the progression of high throughput human proteomics projects, an enormous amount of protein sequence data has been discovered in the recent past. All these raw sequence data require precise mapping and annotation for their respective biological role and functional attributes. The functional characteristics of protein molecules are highly dependent on the subcellular localization/compartment. Therefore, a fully automated and reliable protein subcellular localization prediction system would be very useful for current proteomic research.ObjectiveTo develop a machine learning-based predictive model that can annotate the subcellular localization of human proteins with high accuracy and precision.MethodsIn this study, we used the PSI-CD-HIT homology criterion and utilized the sequence-based features of protein sequences to develop a powerful subcellular localization predictive model. The dataset used to train the HumDLoc model was extracted from a reliable data source, Uniprot knowledge base, which helps the model to generalize on the unseen dataset.ResultsThe proposed model, HumDLoc, was compared with two of the most widely used techniques: CELLO and DeepLoc, and other machine learning-based tools. The result demonstrated promising predictive performance of HumDLoc model based on various machine learning parameters such as accuracy (≥97.00%), precision (≥0.86), recall (≥0.89), MCC score (≥0.86), ROC curve (0.98 square unit), and precision-recall curve (0.93 square unit).ConclusionIn conclusion, HumDLoc was able to outperform several alternative tools for correctly predicting subcellular localization of human proteins. The HumDLoc has been hosted as a web-based tool at https://bioserver.iiita.ac.in/HumDLoc/.

| S-EPMC7604748 | biostudies-literature

Prediction of Thermo-Physical Properties of TiO2-Al2O3/Water Nanoparticles by Using Artificial Neural Network.

Project description:In this paper, an artificial neural network is implemented for the sake of predicting the thermal conductivity ratio of TiO2-Al2O3/water nanofluid. TiO2-Al2O3/water in the role of an innovative type of nanofluid was synthesized by the sol-gel method. The results indicated that 1.5 vol.% of nanofluids enhanced the thermal conductivity by up to 25%. It was shown that the heat transfer coefficient was linearly augmented with increasing nanoparticle concentration, but its variation with temperature was nonlinear. It should be noted that the increase in concentration may cause the particles to agglomerate, and then the thermal conductivity is reduced. The increase in temperature also increases the thermal conductivity, due to an increase in the Brownian motion and collision of particles. In this research, for the sake of predicting the thermal conductivity of TiO2-Al2O3/water nanofluid based on volumetric concentration and temperature functions, an artificial neural network is implemented. In this way, for predicting thermal conductivity, SOM (self-organizing map) and BP-LM (Back Propagation-Levenberq-Marquardt) algorithms were used. Based on the results obtained, these algorithms can be considered as an exceptional tool for predicting thermal conductivity. Additionally, the correlation coefficient values were equal to 0.938 and 0.98 when implementing the SOM and BP-LM algorithms, respectively, which is highly acceptable.

| S-EPMC7221607 | biostudies-literature

DFT Study of Methylene Blue Adsorption on ZnTiO3 and TiO2 Surfaces (101).

Project description:The search for alternative materials with high dye adsorption capacity, such as methylene blue (MB), remains the focus of current studies. This computational study focuses on oxides ZnTiO3 and TiO2 (anatase phase) and on their adsorptive properties. Computational calculations based on DFT methods were performed using the Viena Ab initio Simulation Package (VASP) code to study the electronic properties of these oxides. The bandgap energy values calculated by the Hubbard U (GGA + U) method for ZnTiO3 and TiO2 were 3.17 and 3.21 eV, respectively, which are consistent with the experimental data. The most favorable orientation of the MB adsorbed on the surface (101) of both oxides is semi-perpendicular. Stronger adsorption was observed on the ZnTiO3 surface (-282.05 kJ/mol) than on TiO2 (-10.95 kJ/mol). Anchoring of the MB molecule on both surfaces was carried out by means of two protons in a bidentate chelating (BC) adsorption model. The high adsorption energy of the MB dye on the ZnTiO3 surface shows the potential value of using this mixed oxide as a dye adsorbent for several technological and environmental applications.

| S-EPMC8270277 | biostudies-literature

Synthesis of TiO2NWS@AuNPS Composite Catalyst for Methylene Blue Removal.

Project description:In this article, HBP-NH?-modified titania nanowire (TiO2NWS)-decorated Au nanoparticles (TiO2NWS@AuNPS) were synthesized by one-step method. The role of HBP-NH? concentration in the formation of TiO2NWS was investigated. The fineness and uniformity of pure TiO2NWS were enhanced by absorbed amino groups from amino-terminated hyperbranched polymer (HBP-NH?). The morphology and crystal structure of TiO2NWS and TiO2NWS@AuNPS were examined by transmission electron microscopy (TEM), X-ray diffraction (XRD), and Fournier transform infrared (FTIR) spectroscopy. The chemical states of gold, titanium and oxygen were analyzed by X-ray photoelectron spectroscopy (XPS). The results showed that at the concentration of HBP-NH? 100 g/L, the mean diameter of TiO2NWS was nearly 72 nm and Au nanoparticles were uniformly distributed on the surface of TiO2NWS. The presence of AuNPS improved the photocatalytic properties of TiO2NWS under UV light irradiation. The Au load was believed to improve the utilization rate of the photoelectron and activated the adsorbed oxygen. The obtained TiO2NWS@AuNPS decomposed 99.6% methylene blue (MB) after 300 min when subjected to UV light irradiation. After five cycles of the catalyzing process, the TiO2NWS@AuNPS still retained over 90% of its catalytic ability for MB. The Au deposition was found responsible for the high catalytic activity of TiO2NWS@AuNPS.

| S-EPMC6025176 | biostudies-literature

Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network.

Project description:The ability to predict tandem mass (MS/MS) spectra from peptide sequences can significantly enhance our understanding of the peptide fragmentation process and could improve peptide identification in proteomics. However, current approaches for predicting high-energy collisional dissociation (HCD) spectra are limited to predict the intensities of expected ion types, that is, the a/b/c/x/y/z ions and their neutral loss derivatives (referred to as backbone ions). In practice, backbone ions only account for <70% of total ion intensities in HCD spectra, indicating many intense ions are ignored by current predictors. In this paper, we present a deep learning approach that can predict the complete spectra (both backbone and nonbackbone ions) directly from peptide sequences. We made no assumptions or expectations on which kind of ions to predict but instead predicting the intensities for all possible m/z. Training this model needs no annotations of fragment ion nor any prior knowledge of the fragmentation rules. Our analyses show that the predicted 2+ and 3+ HCD spectra are highly similar to the experimental spectra, with average full-spectrum cosine similarities of 0.820 (±0.088) and 0.786 (±0.085), respectively, very close to the similarities between the experimental replicated spectra. In contrast, the best-performed backbone only models can only achieve an average similarity below 0.75 and 0.70 for 2+ and 3+ spectra, respectively. Furthermore, we developed a multitask learning (MTL) approach for predicting spectra of insufficient training samples, which allows our model to make accurate predictions for electron transfer dissociation (ETD) spectra and HCD spectra of less abundant charges (1+ and 4+).

| S-EPMC8057055 | biostudies-literature

PUResNet: prediction of protein-ligand binding sites using deep residual neural network.

Project description:BackgroundPredicting protein-ligand binding sites is a fundamental step in understanding the functional characteristics of proteins, which plays a vital role in elucidating different biological functions and is a crucial step in drug discovery. A protein exhibits its true nature after binding to its interacting molecule known as a ligand that binds only in the favorable binding site of the protein structure. Different computational methods exploiting the features of proteins have been developed to identify the binding sites in the protein structure, but none seems to provide promising results, and therefore, further investigation is required.ResultsIn this study, we present a deep learning model PUResNet and a novel data cleaning process based on structural similarity for predicting protein-ligand binding sites. From the whole scPDB (an annotated database of druggable binding sites extracted from the Protein DataBank) database, 5020 protein structures were selected to address this problem, which were used to train PUResNet. With this, we achieved better and justifiable performance than the existing methods while evaluating two independent sets using distance, volume and proportion metrics.

| S-EPMC8424938 | biostudies-literature

Novel approach for effective removal of methylene blue dye from water using fava bean peel waste.

Project description:Fava bean peels, Vicia faba (FBP) are investigated as biosorbents for the removal of Methylene Blue (MB) dye from aqueous solutions through a novel and efficient sorption process utilizing ultrasonic-assisted (US) shaking. Ultrasonication remarkably enhanced sorption rate relative to conventional (CV) shaking, while maintaining the same sorption capacity. Ultrasonic sorption rate amounted to four times higher than its conventional counterpart at 3.6 mg/L initial dye concentration, 5 g/L adsorbent dose, and pH 5.8. Under the same adsorbent dose and pH conditions, percent removal ranged between 70-80% at the low dye concentration range (3.6-25 mg/L) and reached about 90% at 50 mg/L of the initial dye concentration. According to the Langmuir model, maximum sorption capacity was estimated to be 140 mg/g. A multiple linear regression statistical model revealed that adsorption was significantly affected by initial concentration, adsorbent dose and time. FBP could be successfully utilized as a low-cost biosorbent for the removal of MB from wastewater via US biosorption as an alternative to CV sorption. US biosorption yields the same sorption capacities as CV biosorption, but with significant reduction in operational times.

| S-EPMC7210991 | biostudies-literature