Visible particle identification is a crucial prerequisite step for process improvement and control during the manufacturing of injectable biotherapeutic drug products. Raman spectroscopy is a technology with several advantages for particle identification including high chemical sensitivity, minimal sample manipulation, and applicability to aqueous solutions. However, considerable effort and experience are required to extract and interpret Raman spectral data. In this study, we applied machine learning algorithms to analyze Raman spectral data for visible particle identification in order to minimize expert support and improve data analysis accuracy. We manually prepared ten types of particle standard solutions to simulate the particle types typically observed during manufacturing and established a Raman spectral library with accurate peak assignments for the visible particles. Five classification algorithms were trained using visible particle Raman spectral data. All models had high prediction accuracy of >98% for all types of visible particles. Our results demonstrate that the combination of Raman spectroscopy and machine learning can provide a simple and accurate data analysis approach for visible particle identification. Graphical abstract
Xiangan Long,Chongjun Ma,Han Sheng,Liwen Chen,Yiyan Fei,Lan Mi,Dongmei Han,Jiong Ma
Subvisible particles are an ongoing problem in biotherapeutic injectable pharmaceutical formulations, and their identification is an important prerequisite for tracing them back to their source and optimizing the process. Flow imaging microscopy (FIM) is a favored imaging technique, mainly because of its ability to achieve rapid batch imaging of subvisible particles in solution with excellent imaging quality. This study used VGG16 after transfer learning to identify subvisible particle images acquired using FlowCam. We manually prepared standards for seven classes of particles, acquired the image information through FlowCam, and fed the images over 5 µm into VGG16 consisting of a convolutional base of VGG16 pre-trained with ImageNet data and a custom classifier for training. An accuracy of 97.51% was obtained for the test set data. The study also demonstrated that the recognition method using transfer learning outperforms machine learning methods based on morphological parameters in terms of accuracy, and has a significant training speed advantage over scratch-trained CNN. The combination of transfer learning and FIM images is expected to provide a general and accurate data-analysis method for identifying subvisible particles.Keywords:image analysis;protein formulation;convolutional neural network;particle identification;machine learning
Shuting Chen,Weijia Wang,Shaohua Xu,Caili Fu,Shuyi Ji,Fang Luo,Cuiying Lin,Bin Qiu,Zhenyu Lin
In this work, an auto-identify sensor was constructed for rapid and high-precision detection of L-histidine. The proposed strategy is based on the auto-identify algorithm and the aggregation of alkynyl and azide functionalized gold nanoparticles induced by the Cu + catalyzed azides and alkynes cycloaddition (CuAAC) reaction. Specially, the color of scattering light spots for the aggregated gold nanoparticle (AuNPs) caused by CuAAC reaction was quite different from that of the monomers . However, L-histidine can bind to Cu 2+ and inhibits the production of Cu + , hence preventing the aggregation of AuNPs. Therefore, there is a distinct change of color as the addition of L-histidine under dark-field microscopy. Then, L-histidine can be quantitatively detected by combining the color change with the Meanshift algorithm accurately and automatically. Such proposed method has been successfully applied for the detection of L-histidine in serum sample with satisfying result.
危险品化学品经营许可证（带存储）