基于拉曼光谱法进行细胞培养过程监测的变异性自编码器与即时学习的整合
Mohammad Rashedi1, Hamid Khodabandehlou1, Tony Wang2
1Digital Integration & Predictive Technologies, Amgen Inc., Thousand Oaks, California, USA.
Biotechnology and bioengineering
|April 24, 2024
概括
本研究介绍了一种基于变异自编码器的即时学习 (VAE-JITL) 方法,用于使用拉曼光谱实时监测生物过程. 与传统方法相比,VAE-JITL方法在预测关键过程变量方面提高了准确性.
科学领域:
- 生物制药制造业 生物制药制造业
- 过程分析技术 (PAT) 是一种分析技术.
- 化学测量 化学测量 化学测量
背景情况:
- 确保生物制药蛋白生产的安全性和一致性需要强大的分析技术和控制策略.
- 拉曼光谱是一种过程分析技术 (PAT),通过将光谱数据与关键变量相关联,可以实时监测细胞培养过程.
- 传统的基于Raman的即时学习 (JITL) 使用K-最近邻居 (KNN) 与数据不确定性作斗争.
研究的目的:
- 开发一种先进的软传感器建模技术,用于增强生物制药细胞培养过程的实时监测.
- 将即时学习 (JITL) 与变量自编码器 (VAE) 集成,以解决拉曼光谱数据中的数据不确定性和非线性.
- 评估拟议的VAE-JITL方法的性能与预测关键过程变量的既有技术相比.
主要方法:
- 开发一种新的VAE-JITL算法,以提取非线性拉曼特征作为多变量高斯分布.
- 化学测量模型的应用,以确定拉曼信号和过程变量之间的相关性.
- 对VAE-JITL与部分最小平方 (PLS),卷积神经网络 (CNN) 和传统的JITL-KNN方法进行比较分析,使用来自三个细胞线路运行的实验数据.
主要成果:
- 在不同的实验运行中,VAE-JITL方法在准确预测关键过程变量方面表现出卓越的表现.
- 拟议的方法有效地以非线性方式提取主导拉曼特征,提高模型的稳定性.
- 在关键过程参数的预测准确性方面,VAE-JITL始终优于PLS,CNN和JITL-KNN.
结论:
- 变化自编码器与即时学习的集成提供了一个强大而准确的工具,用于生物制药制造业的实时监控.
- VAE-JITL有效地处理来自细胞培养的拉曼光谱数据中固有的数据不确定性和非线性.
- 这种先进的软传感器建模技术为生物制药生产过程控制和一致性提供了显著的改进.
更多相关视频
相关概念视频
Raman Spectroscopy Instrumentation: Overview
332
A conventional Raman spectrophotometer includes a laser source, a sample holding system, a wavelength selector, and a detector.
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
332
Raman Spectroscopy: Overview
372
The underlying principle of Raman spectroscopy is based on the interaction between light and matter, specifically molecules' inelastic scattering of photons. When a monochromatic beam of light, typically from a laser source, interacts with a sample, most scattered light has the same frequency as the incident light. This is known as Rayleigh scattering.
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
372


