Search

Puerariae Thomsonii Radix (PTR) is not only widely used in disease prevention and treatment but is also an important raw material as a source of starch and other food. The growth years of PTR are closely related to its quality. The rapid and nondestructive identification of growth year is essential for the quality control of PTR and other traditional Chinese medicines. In this study, we proposed a convolutional neural network (CNN)-based classification framework in conjunction with hyperspectral imaging (HSI) technology for the rapid identification of the growth years of PTRs. Traditional treatment methods (i.e., multiplicative scatter correction, standard normal variate, and Savitzky-Golay smoothing) combined with machine learning algorithms (i.e., random forest, logistic regression, naive Bayes, and eXtreme gradient boost) were used as baseline models. Among them, the F1-score of CNN-based models based on PTRs' outer surfaces was over 90%, outperforming all the other baseline models. These results showed that it was feasible to use a deep learning algorithm in conjunction with HSI technology to identify the growth years of PTR. This method provides a fast, nondestructive, and simple method of identifying the growth years of PTR. It can be easily applied to other scenarios, such as for the identification of the locality or years of growth for other traditional Chinese herbs. [ABSTRACT FROM AUTHOR]

Puerariae Thomsonii Radix (PTR) is not only widely used in disease prevention and treatment but is also an important raw material as a source of starch and other food. The growth years of PTR are closely related to its quality. The rapid and nondestructive identification of growth year is essential for the quality control of PTR and other traditional Chinese medicines. In this study, we proposed a convolutional neural network (CNN)-based classification framework in conjunction with hyperspectral imaging (HSI) technology for the rapid identification of the growth years of PTRs. Traditional treatment methods (i.e., multiplicative scatter correction, standard normal variate, and Savitzky-Golay smoothing) combined with machine learning algorithms (i.e., random forest, logistic regression, naive Bayes, and eXtreme gradient boost) were used as baseline models. Among them, the F1-score of CNN-based models based on PTRs' outer surfaces was over 90%, outperforming all the other baseline models. These results showed that it was feasible to use a deep learning algorithm in conjunction with HSI technology to identify the growth years of PTR. This method provides a fast, nondestructive, and simple method of identifying the growth years of PTR. It can be easily applied to other scenarios, such as for the identification of the locality or years of growth for other traditional Chinese herbs. [ABSTRACT FROM AUTHOR]

The insulin-like growth factor (IGF) axis has been implicated in the progression of malignant disease and identified as a clinically important therapeutic target. Several IGF-1 receptor (IGF-1R) targeting drugs including humanized monoclonal antibodies have advanced to phase II/III clinical trials, but to date, have not progressed to clinical use, due, at least in part, to interference with insulin receptor signalling. We previously reported on the production of a soluble fusion protein consisting of the extracellular domain of human IGF-1R fused to the Fc portion of human IgG1 (first generation IGF-TRAP) that bound human IGF-1 and IGF-2 with a 3 log higher affinity than insulin. We showed that the IGF-TRAP had potent anti-cancer activity in several pre-clinical models of aggressive carcinomas. Here we report on the re-engineering of the IGF-TRAP with the aim of improving physicochemical properties and suitability for clinical applications. We show that cysteine-serine substitutions in the Fc hinge region of IGF-TRAP eliminated high-molecular-weight oligomerized species, while a further addition of a flexible linker, not only improved the pharmacokinetic profile, but also enhanced the therapeutic profile of the IGF-TRAP, as evaluated in an experimental colon carcinoma metastasis model. Dose-response profiles of the modified IGF-TRAPs correlated with their bio-availability profiles, as measured by the IGF kinase-receptor-activation (KIRA) assay, providing a novel, surrogate biomarker for drug efficacy. This study provides a compelling example of structure-based re-engineering of Fc-fusion-based biologics for better manufacturability that also significantly improved pharmacological parameters. It identifies the re-engineered IGF-TRAP as a potent anti-cancer therapeutic. [ABSTRACT FROM AUTHOR]