计算生物学
基因组
重组DNA
计算机科学
载体(分子生物学)
生物
人工智能
遗传学
算法
基因
作者
Sofia Ostellino,Raffaele Fronza,Alfredo Benso
标识
DOI:10.1109/icet59753.2023.10374991
摘要
This article proposes the development of a novel tool for analyzing the structure and characteristics of recombinant adeno-associated virus (rAAV) vectors during vector production and quality assessment. The tool utilizes dotplots, a graphical method for comparing sequences, and a deep learning-based image classification approach. The focus is on the inverted terminal repeats (ITRs) sequences, which play a critical role in identifying and differentiating AAV types. The tool aims to infer the ITR origin, and improve vector analysis and quality control. The dataset creation process involves generating dotplots of wild-type AAV ITRs and introducing small mutations to simulate biological noise. Future work includes addressing the impact of mutations on vector characteristics to detect major structural anomalies, as well as further analyzing pair-dotplots for vector characterization.
科研通智能强力驱动
Strongly Powered by AbleSci AI