Ranitidine hydrochloride X-ray assay using a neural network

Crystal Structure Assignment for Unknown Compounds from X-ray Diffraction Patterns with Deep Learning

Determining the structures of previously unseen compounds from experimental characterizations is a crucial part of materials science. It requires a step of searching for the structure type that conforms to the lattice of the unknown compound, which enables the pattern matching process for characterization data, such as X-ray diffraction (XRD) patterns. However, this procedure typically places a high demand on domain expertise, thus creating an obstacle for computer-driven automation. Here, we address this challenge by leveraging a deep-learning model composed of a union of convolutional residual neural networks. The accuracy of the model is demonstrated on a dataset of over 60,000 different compounds for 100 structure types, and additional categories can be integrated without the need to retrain the existing networks. We also unravel the operation of the deep-learning black box and highlight the way in which the resemblance between the unknown compound and a structure type is quantified based on both local and global characteristics in XRD patterns. This computational tool opens new avenues for automating structure analysis on materials unearthed in high-throughput experimentation.

A deep-learning technique for phase identification in multiphase inorganic compounds using synthetic XRD powder patterns

Here we report a facile, prompt protocol based on deep-learning techniques to sort out intricate phase identification and quantification problems in complex multiphase inorganic compounds. We simulate plausible powder X-ray powder diffraction (XRD) patterns for 170 inorganic compounds in the Sr-Li-Al-O quaternary compositional pool, wherein promising LED phosphors have been recently discovered. Finally, 1,785,405 synthetic XRD patterns are prepared by combinatorically mixing the simulated powder XRD patterns of 170 inorganic compounds. Convolutional neural network (CNN) models are built and eventually trained using this large prepared dataset. The fully trained CNN model promptly and accurately identifies the constituent phases in complex multiphase inorganic compounds. Although the CNN is trained using the simulated XRD data, a test with real experimental XRD data returns an accuracy of nearly 100% for phase identification and 86% for three-step-phase-fraction quantification.

Identifying the composition of multiphase inorganic compounds from XRD patterns is challenging. Here the authors use a convolutional neural network to identify phases in unknown multiphase mixed inorganic powder samples with an accuracy of nearly 90%.

The significance of artificial intelligence in drug delivery system design

Over the last decade, increasing interest has been attracted towards the application of artificial intelligence (AI) technology for analyzing and interpreting the biological or genetic information, accelerated drug discovery, and identification of the selective small-molecule modulators or rare molecules and prediction of their behavior. Application of the automated workflows and databases for rapid analysis of the huge amounts of data and artificial neural networks (ANNs) for development of the novel hypotheses and treatment strategies, prediction of disease progression, and evaluation of the pharmacological profiles of drug candidates may significantly improve treatment outcomes. Target fishing (TF) by rapid prediction or identification of the biological targets might be of great help for linking targets to the novel compounds. AI and TF methods in association with human expertise may indeed revolutionize the current theranostic strategies, meanwhile, validation approaches are necessary to overcome the potential challenges and ensure higher accuracy. In this review, the significance of AI and TF in the development of drugs and delivery systems and the potential challenging issues have been highlighted.

Classification of crystal structure using a convolutional neural network

A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.

Determination of factors controlling the particle size and entrapment efficiency of noscapine in PEG/PLA nanoparticles using artificial neural networks

In this study, di- and triblock copolymers based on polyethylene glycol and polylactide were synthesized by ring-opening polymerization and characterized by proton nuclear magnetic resonance and gel permeation chromatography. Nanoparticles containing noscapine were prepared from these biodegradable and biocompatible copolymers using the nanoprecipitation method. The prepared nanoparticles were characterized for size and drug entrapment efficiency, and their morphology and size were checked by transmission electron microscopy imaging. Artificial neural networks were constructed and tested for their ability to predict particle size and entrapment efficiency of noscapine within the formed nanoparticles using different factors utilized in the preparation step, namely polymer molecular weight, ratio of polymer to drug, and number of blocks that make up the polymer. Using these networks, it was found that the polymer molecular weight has the greatest effect on particle size. On the other hand, polymer to drug ratio was found to be the most influential factor on drug entrapment efficiency. This study demonstrated the ability of artificial neural networks to predict not only the particle size of the formed nanoparticles but also the drug entrapment efficiency. This may have a great impact on the design of polyethylene glycol and polylactide-based copolymers, and can be used to customize the required target formulations.

An accurate quantitative analysis of polymorphs based on artificial neural networks

Measurement precision based on homogeneous and accurate standard samples has been reported to result in significant improvement in the sensitivity and accuracy of the quantitative analysis of polymorphic mixtures. The purpose of this study was to further improve the accuracy of the quantitation based on data processing by artificial neural networks (ANNs), using such high quality standard samples. Homogeneous powder mixtures of alpha- and gamma-forms of indomethacin (IMC) at various ratios (0-50% alpha-form content) were subjected to X-ray powder diffractometry. The two diffraction peaks selected as the best combination in multiple linear regression (MLR) were used in the ANN with an extended Kalman filter as a training algorithm. The results obtained by ANN had better predictive accuracy at lower contents (0-5%) compared to those of MLR. ANNs for the diffraction data based on high quality standard samples provide an extremely precise and accurate quantification for polymorphic mixtures.

Conductimetric determination of phenylpropanolamine HCl, ranitidine HCl, hyoscyamine HBr and betaine HCl in their pure state and pharmaceutical preparations

Sodium tetraphenylborate and phosphotungstic acid were used as titrants for the conductimetric determination of phenylpropanolamine HCl (PPA.Cl), ranitidine HCl (Ra.Cl), hyoscyamine HBr (Hy.Br) and betaine HCl (Be.Cl) through ion-associate complex formation. The molar combining ratio and the solubility products of the formed ion-associates were studied and calculated. The suggested method has been applied to the determination of the mentioned drugs in their pure state and pharmaceutical preparations with mean recovery values of 97.71-102.97% and relative standard deviations 0.25-0.85%. The accuracy of the method is indicated by excellent recovery and low standard deviation. The results are compared with the pharmacopoeial or the official methods.

Solubility, dissolution rate and phase transition studies of ranitidine hydrochloride tautomeric forms

Understanding the polymorphic behavior of pharmaceutical solids during the crystallization process and further in post-processing units is crucial to meet medical and legal requirements. In this study, an analytical technique was developed for determining the composition of two solid forms of ranitidine hydrochloride using two peaks of Fourier transform infrared (FTIR) spectra without the need to grind the samples. Solubility studies of ranitidine hydrochloride showed that Form 2 has a higher solubility than Form 1. Solution-mediated transformation is very slow and occurs from Form 2 to Form 1 and not the reverse. No solid-solid transformation was observed due to grinding or compressing the pure samples of either forms and of a 50/50 wt.% mixture. Grinding was found to be a proper technique for increasing the bulk solid density of the ranitidine hydrochloride without the risk of solid-solid transformation. Dissolution rate found to be equally fast for both forms. The solubility data were modeled using the group contribution parameters and UNIversal QUAsi-Chemical (UNIQUAC) theory. There was a good agreement between the experimental solubility data of ranitidine hydrochloride and the results of UNIQUAC equation.

Quantitative analysis of polymorphic mixtures of ranitidine hydrochloride by Raman spectroscopy and principal components analysis

Ranitidine hydrochloride exists as two polymorphs, forms I and II, both of which are used to manufacture commercial tablets. Raman spectroscopy can be used to differentiate the two forms but univariate methods of quantitative analysis of one polymorph as an impurity in the other lack sensitivity. We have applied principal components analysis (PCA) of Raman spectra to binary mixtures of the two polymorphs and to binary mixtures prepared by adding one polymorph to powdered tablets of the other. Based on absorption measurements of seven spectral regions, it was found that >97% of the spectral variation was accounted for by three principal components. Quantitative calibration models generated by multiple linear regression predicted a detection limit and quantitation limit for either forms I or II in mixtures of the two of 0.6 and 1.8%, respectively. This study demonstrates that PCA of Raman spectroscopic data provides a sensitive method for the quantitative analysis of polymorphic impurities of drugs in commercial tablets with a quantitation limit of less than 2%.

The effect of experimental design on the modeling of a tablet coating formulation using artificial neural networks

The aim of this study was to investigate the effect of experimental design strategy on the modeling of a film coating formulation by artificial neural networks (ANNs). Box-Behnken, central composite and pseudo-random designs of 102, 90 and 100 simulated records, respectively were used to train a multilayer perceptron (MLP) ANN comprising six input and two output nodes separated by a single hidden layer of five nodes. Network over-training was limited by using a test set of 40 pseudo-randomly distributed records. The models were validated using a set of 60 pseudo-randomly distributed records. Crack velocity was highly curved with respect to pigment particle size and size distribution. Similarly, film opacity was highly curved in response to pigment concentration and film thickness. The Box-Behnken and central composite designs generated models that were unable to predict crack velocity and showed extensive bias in prediction of film opacity. The pseudo-random design was unable to predict crack velocity of the test data set but yielded acceptable predictions for the validation set. Film opacity was well predicted by the pseudo-random design model. The poor predictive ability of the Box-Behnken and central composite models was attributed to poor interpolation of the high curvature of the response surfaces. In contrast, the pseudo-random design mapped the interior of the design space allowing improved interpolation and predictive ability. It is concluded that Box-Behnken and central composite experimental designs are inappropriate for ANN modeling of highly curved responses and that extensive internal mapping of the design space is essential to generate predictive ANN models.

Predictive non-linear modeling of complex data by artificial neural networks

An artificial neural network (ANN) is an artificial intelligence tool that identifies arbitrary nonlinear multiparametric discriminant functions directly from experimental data. The use of ANNs has gained increasing popularity for applications where a mechanistic description of the dependency between dependent and independent variables is either unknown or very complex. This machine learning technique can be roughly described as a universal algebraic function that will distinguish signal from noise directly from experimental data. The application of ANNs to complex relationships makes them highly attractive for the study of biological systems. Recent applications include the analysis of expression profiles and genomic and proteomic sequences.

Kinetic spectrophotometric determination of nizatidine and ranitidine in pharmaceutical preparations

A new simple and sensitive kinetic spectrophotometric method is described for analysis of nizatidine (I) and ranitidine (II). The method involves the reaction of the drugs with alkaline potassium permanganate, whereby a green color peaking at 610 nm is produced. The reaction is monitored spectrophotometrically by measuring the rate of change of absorbance of the resulting manganate species at 610 nm. Calibration graphs are linear over the concentration range 0.8-4.0 microg/ml and the precision (% RSD 1.80, 1.53 for I and II, respectively) is quite acceptable. The method is satisfactorily applied for direct analysis of pharmaceutical preparations containing I and II. A proposal of the reaction pathway is postulated.