Antiepileptic drug concentration detection based on Raman spectroscopy and an improved snake optimization-convolutional neural network algorithm.

A method for measurement of antiepileptic drug concentrations based on Raman spectroscopy and an optimization algorithm for mathematical models are proposed and investigated. This study uses Raman spectroscopy to measure mixed antiepileptic drugs, and an Improved Snake Optimization (ISO)-Convolutional Neural Network (CNN) algorithm is proposed. Raman spectroscopy is widely used in the identification of pharmaceutical ingredients due to its sharp peaks, no pre-treatment of samples and non-destructive detection. To analyze the spectral data precisely, a machine learning method is used in this paper. The ISO algorithm is an improved intelligent swarm algorithm in which the method of generating random solutions is improved, which can ensure that a comprehensive local search of the model is performed, the global search capability is maintained at a later stage, and the convergence speed is accelerated. In this study, 360 groups of oxcarbazepine, carbamazepine, and lamotrigine drug mixtures are measured using Raman spectroscopy, and the raw spectral data after pre-processing are trained and evaluated using ISO-CNN algorithms, and the results are compared and analyzed with those obtained from other algorithms such as the Northern Goshawk Optimization algorithm, Chameleon Swarm Algorithm, and White Shark Optimizer algorithm. The results show that the best ISO-CNN algorithm training is achieved for oxcarbazepine, with a determination coefficient and root mean square error of 0.99378 and 0.0295 for the validation set, and 0.99627 and 0.0278 for the test set. The overall results suggest that Raman spectroscopy combined with machine learning algorithms can be a potential tool for drug concentration prediction.

Enhancement of membrane stability on magnetic responsive hydrogel microcapsules for potential on-demand cell separation.

It is of high interest to obtain hydrogel membranes with optimum mechanical stability, which is a prerequisite to the successful fabrication of hydrogel microcapsules for cell separation. In this work, we developed magnetic responsive alginate/chitosan (MAC) hydrogel microcapsules by co-encapsulation of microbial cells and superparamagnetic iron oxide nanoparticles (SPIONs) reacting under a high voltage electrostatic field. We investigated the influence of the molecular weight of chitosan, microcapsules size, and membrane crosslinking time on the swelling behavior of microcapsules as an indicator of stability of the membranes. The results demonstrated that the suitable membrane stability conditions were obtained by a crosslinking of the microspheres with a chitosan presenting a molecular weight of 70kDa for 15-30min resulting in a membrane thickness of approximately 30mm. Considering the need of maintaining the cells inside the microcapsules, fermentation at 37°C and at neutral pH was favorable. Moreover, the MAC microcapsules sizing between 300 and 380µm were suitable for immobilizing Bacillus licheniformis in a 286h multiple fed-bath operation with no leakage of the SPIONs and cells. Overall, the results of this study provided strategies for the rational design of magnetic microcapsules exhibiting suitable mechanical stable membranes.

Molecular data and ecological niche modeling reveal population dynamics of widespread shrub Forsythia suspensa (Oleaceae) in China's warm-temperate zone in response to climate change during the Pleistocene.

BACKGROUND: Despite its high number of endemic deciduous broad-leaved species in China's warm-temperate zone, far less attention has been paid to phylogeographic studies in this region. In this work, the phylogeographic history of Forsythia suspensa endemic to China's warm-temperate zone was investigated to explore the effect of climate change during the Pleistocene on the distribution of this deciduous broad-leaved species in China. RESULTS: The cpDNA data revealed seven phylogeographical groups corresponding to geographical regions. By contrast, the nrDNA data supported the samples clustered into three groups, which was inconsistent with separate geographical regions supported by cpDNA data. Ecological niche modeling showed that the climatically suitable area during the cold period was larger than that during the warm period. CONCLUSIONS: Both molecular data and ecological niche modeling indicated that F. suspensa expanded to nearby low-elevation plains in the glacial periods, and retreated to mountaintops during interglacial warmer stages. This study thus supported that F. suspensa persisted in situ during the glacial of the Pleistocene with enlarged distribution area, contrary to the hypothesis of long distance southward migration or large-scale range contraction.