Application of Machine Learning Algorithms to the Discretization Problem in Wearable Electrical Tomography Imaging for Bladder Tracking.

The article presents the implementation of artificial intelligence algorithms for the problem of discretization in Electrical Impedance Tomography (EIT) adapted for urinary tract monitoring. The primary objective of discretization is to create a finite element mesh (FEM) classifier that will separate the inclusion elements from the background. In general, the classifier is designed to detect the area of elements belonging to an inclusion revealing the shape of that object. We show the adaptation of supervised learning methods such as logistic regression, decision trees, linear and quadratic discriminant analysis to the problem of tracking the urinary bladder using EIT. Our study focuses on developing and comparing various algorithms for discretization, which perfectly supplement methods for an inverse problem. The innovation of the presented solutions lies in the originally adapted algorithms for EIT allowing for the tracking of the bladder. We claim that a robust measurement solution with sensors and statistical methods can track the placement and shape change of the bladder, leading to effective information about the studied object. This article also shows the developed device, its functions and working principle. The development of such a device and accompanying information technology came about in response to particularly strong market demand for modern technical solutions for urinary tract rehabilitation.

Logistic Regression for Machine Learning in Process Tomography.

The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images.

Comparison of Selected Machine Learning Algorithms for Industrial Electrical Tomography.

The main goal of this work was to compare the selected machine learning methods with the classic deterministic method in the industrial field of electrical impedance tomography. The research focused on the development and comparison of algorithms and models for the analysis and reconstruction of data using electrical tomography. The novelty was the use of original machine learning algorithms. Their characteristic feature is the use of many separately trained subsystems, each of which generates a single pixel of the output image. Artificial Neural Network (ANN), LARS and Elastic net methods were used to solve the inverse problem. These algorithms have been modified by a corresponding increase in equations (multiply) for electrical impedance tomography using the finite element method grid. The Gauss-Newton method was used as a reference to machine learning methods. The algorithms were trained using learning data obtained through computer simulation based on real models. The results of the experiments showed that in the considered cases the best quality of reconstructions was achieved by ANN. At the same time, ANN was the slowest in terms of both the training process and the speed of image generation. Other machine learning methods were comparable with the deterministic Gauss-Newton method and with each other.

A Non-Destructive System Based on Electrical Tomography and Machine Learning to Analyze the Moisture of Buildings.

This article presents the results of research on a new method of spatial analysis of walls and buildings moisture. Due to the fact that destructive methods are not suitable for historical buildings of great architectural significance, a non-destructive method based on electrical tomography has been adopted. A hybrid tomograph with special sensors was developed for the measurements. This device enables the acquisition of data, which are then reconstructed by appropriately developed methods enabling spatial analysis of wet buildings. Special electrodes that ensure good contact with the surface of porous building materials such as bricks and cement were introduced. During the research, a group of algorithms enabling supervised machine learning was analyzed. They have been used in the process of converting input electrical values into conductance depicted by the output image pixels. The conductance values of individual pixels of the output vector made it possible to obtain images of the interior of building walls as both flat intersections (2D) and spatial (3D) images. The presented group of algorithms has a high application value. The main advantages of the new methods are: high accuracy of imaging, low costs, high processing speed, ease of application to walls of various thickness and irregular surface. By comparing the results of tomographic reconstructions, the most efficient algorithms were identified.

Tiered analytics for purity assessment of macrocyclic peptides in drug discovery: Analytical consideration and method development.

Synthetic macrocyclic peptides with natural and unnatural amino acids have gained considerable attention from a number of pharmaceutical/biopharmaceutical companies in recent years as a promising approach to drug discovery, particularly for targets involving protein-protein or protein-peptide interactions. Analytical scientists charged with characterizing these leads face multiple challenges including dealing with a class of complex molecules with the potential for multiple isomers and variable charge states and no established standards for acceptable analytical characterization of materials used in drug discovery. In addition, due to the lack of intermediate purification during solid phase peptide synthesis, the final products usually contain a complex profile of impurities. In this paper, practical analytical strategies and methodologies were developed to address these challenges, including a tiered approach to assessing the purity of macrocyclic peptides at different stages of drug discovery. Our results also showed that successful progression and characterization of a new drug discovery modality benefited from active analytical engagement, focusing on fit-for-purpose analyses and leveraging a broad palette of analytical technologies and resources.

Serendipitous oxidation product of BIBN4096BS: a potent CGRP receptor antagonist.

An oxidation product (5) formed during the synthesis of BIBN-4096BS (1) was found to be a potent CGRP antagonist (IC50=0.11nM). While 5 was found to be ten-fold less potent than 1, another analog 8 with lower molecular weight containing the oxidized fragment demonstrated twenty-fold higher activity than its parent 7. Alternative conditions which preclude the formation of the oxidation product are described. The activities of 1, 5, 7 and 8 in functional cAMP assay are also discussed.

Potential CRF1R PET imaging agents: 1-fluoroalkylsubstituted 5-halo-3-(arylamino)pyrazin-2(1H)-ones.

A series of pyrazinones were prepared and evaluated as potential CRF(1)R PET imaging agents. Optimization of their CRF(1)R binding potencies and octanol-phosphate buffer phase distribution coefficients are discussed herein.

Potential CRF1R PET imaging agents: N-fluoroalkyl-8-(6-methoxy-2-methylpyridin-3-yl)-2,7-dimethyl-N-alkylpyrazolo[1,5-a][1,3,5]triazin-4-amines.

A series of N-fluoroalkyl-8-(6-methoxy-2-methylpyridin-3-yl)-2,7-dimethyl-N-alkylpyrazolo[1,5-a][1,3,5]triazin-4-amines were prepared and evaluated as potential CRF(1)R PET imaging agents. Optimization of their CRF(1)R binding potencies and octanol-phosphate buffer phase distribution coefficients resulted in discovery of analog 7e (IC(50)=6.5 nM, logD=3.5).

Conformationally restricted homotryptamines. Part 7: 3-cis-(3-aminocyclopentyl)indoles as potent selective serotonin reuptake inhibitors.

A series of conformationally restricted homotryptamines has been synthesized and shown to be potent inhibitors of hSERT. Conformational restriction of the homotryptamine side chain was attained by the insertion of a cyclopentyl ring, with the indole ring and the terminal dialkylamino group occupying the 1- and 3-positions, respectively. Nitrile and fluoro substitutions at the indole 5-position gave highest hSERT potency. Preferred cyclopentane ring stereochemistry in both series was cis (1S,3R for 5-CN compound 8a, 1R,3S for 5-F compound 9a). High hSERT binding affinity was observed for 8a and 9a (0.22 and 0.63 nM, respectively). The corresponding trans isomers were 4-9 times less potent. 8a, dosed at 1 and 3 mg/kg po, produced a robust, dose-dependent increase in extracellular serotonin in the frontal cortex of rats, similar to that induced by paroxetine at 5 mg/kg, po. By contrast, 9a did not produce a significant increase in extracellular serotonin in rat frontal cortex at 3 mg/kg po due to relatively low brain and plasma levels.

Conformationally restricted homotryptamines. Part 5: 3-(trans-2-aminomethylcyclopentyl)indoles as potent selective serotonin reuptake inhibitors.

A series of racemic 3-(trans-2-aminomethylcyclopentyl)indoles was synthesized and found to have potent binding to the human serotonin transporter (hSERT). The most active analog was synthesized stereospecifically and the active enantiomer was shown to have high affinity binding to hSERT.

Separation of maxi-K channel opening 3-substituted-4-arylquinolinone atropisomers by enantioselective supercritical fluid chromatography.

Many 3-substituted-4-arylquinolinones containing an ortho substituent on the aryl ring were known as a class of compounds with maxi-K opening activity. These quinolinones, which contained a stereogenic axis in their structures due to their bulky ortho substituents on the two aryl rings, exhibited atropisomerism. The rotationally hindered atropisomers could have differential biological and pharmacological activity, and it was highly desirable to separate them and test the individual atropisomers in biological assays. To explore the potential of supercritical fluid chromatography (SFC) to separate the atropisomers of this class of compounds, six 3-substituted-4-arylquinolinones with various hydrophilic and hydrophobic substituents in various positions were screened using three alcoholic modifiers (methanol, ethanol and 2-propanol) with four polysaccharide-based chiral stationary phases (Chiralpak AD-H and AS-H, Chiralcel OD-H and OJ-H). Our results showed that all six compounds studied were successfully resolved under multiple SFC conditions regardless of their structural differences and polarity. The majority of the separations were completed within 10 min. The Chiralpak AD-H column appeared to be superior to the other three chiral columns, and methanol and ethanol showed higher successful rate than 2-propanol in separating atropisomers of this class of compounds. These SFC methods were efficient and easily scalable for preparative separation. Thus, SFC was found to be the methodology of choice for resolving the atropisomers of this class of compounds.

Analyte solvent and injection volume as variables affecting method development in semipreparative reversed-phase liquid chromatography.

Analyte solvent and injection volume were examined as parameters that affect peak elution during method development for semipreparative RP HPLC purification. Analytical and semipreparative scale HPLC with gradient elution were used to analyze a mixture of three standard compounds with significantly different retention factors (k). This mixture was analyzed after (i) dissolution in solvents of varied compositions, and (ii) with progressively larger injection volumes. As analyte solvent composition and injection volume were changed, the most notable effects on peak shape were observed for the compounds with the smallest k values. Overall changes in peak shape were less pronounced when analyte solvent composition was similar to the starting mobile phase regardless of injection volume. Scale-up to semipreparative conditions yielded results consistent with those observed at the analytical scale. These data show that peak shape is greatly affected by analyte solvent composition and injection volume, and that these effects can be ameliorated by the dissolution of analytes in solvent that closely resembles that of the mobile phase used for initial run conditions. The following study addresses the concepts of peak elution in RP HPLC and how they factor into semipreparative purification.

Atropisomeric 3-(beta-hydroxyethyl)-4-arylquinolin-2-ones as Maxi-K potassium channel openers.

The synthesis of a series of 3-beta-hydroxyethyl-4-arylquinolin-2-ones is described. These compounds contain hydrophilic and hydrophobic substituents ortho to the phenolic OH in the C ring of the quinolinone. Electrophysiological evaluation of the panel of compounds revealed that 11 and 16 with an unbranched ortho substituent retain activity as maxi-K ion channel openers. Members of this series of compounds can exist as stable atropisomers. Calculated estimates of the energy barrier for rotation around the aryl-aryl single bond in 3 is 31 kcal/mol. The atropisomers of (+/-)-3, (+/-)-4, and (+/-)-11 were separated by chiral HPLC and tested for their effect on maxi-K mediated outward current in hSlo injected X. laevis oocytes. The (-) isomer in each case was found to be more active than the corresponding (+) isomer, suggesting that the ion channel exhibits stereoselective activation. X-ray crystallographic structures of (+)-3 and (+)-11 were determined. Evaluation of the stability of (-)-3 at 80 degrees C in n-butanol indicated a 19.6% conversion to (+)-3 over 72 h. In human serum at 37 degrees C (-)-3 did not racemize over the course of the 30 h study.