Nakano Ryota, Iwano Natsuki, Ichinose Akiko, Hamada Michiaki
Graduate School of Advanced Science and Engineering, Waseda University, Tokyo, 169-8555, Japan.
Cellular and Molecular Biotechnology Research Institute (CMB), National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, 135-0064, Japan.
Bioinform Adv. 2025 May 23;5(1):vbaf120. doi: 10.1093/bioadv/vbaf120. eCollection 2025.
RaptGen-UI provides intuitive graphical user-interface of the system exploring and analyzing the sequence landscape of high-throughput (HT)-SELEX (Systematic Evolution of Ligands by EXponential enrichment) experiments through machine learning-driven visualization with optimization capabilities. This software enables wet-lab researchers to efficiently analyze HT-SELEX dataset and optimize RNA aptamers without requiring extensive computational expertise. The containerized architecture ensures secure local deployment and supports both of high-performance Graphics Processing Unit (GPU) acceleration and CPU-only environments, making it suitable for various research settings.
This software is a web-based application running locally on the user's PC. The frontend is constructed using Next.js and Plotly.js with TypeScript, while the backend is developed using FastAPI, Celery, PostgreSQL RDBMS, and Redis with Python. Each module is encapsulated within Docker containers and deployed via Docker Compose. The system supports both CUDA GPU and CPU-only environments. Source code and documentation are freely available at https://github.com/hmdlab/RaptGen-UI.
RaptGen-UI提供了直观的系统图形用户界面,通过机器学习驱动的可视化和优化功能,探索和分析高通量(HT)-SELEX(指数富集的配体系统进化)实验的序列景观。该软件使湿实验室研究人员能够高效分析HT-SELEX数据集并优化RNA适配体,而无需广泛的计算专业知识。容器化架构确保安全的本地部署,并支持高性能图形处理单元(GPU)加速和仅使用CPU的环境,使其适用于各种研究场景。
该软件是一个在用户个人电脑上本地运行的基于网络的应用程序。前端使用Next.js和带有TypeScript的Plotly.js构建,而后端则使用FastAPI、Celery、PostgreSQL关系数据库管理系统和带有Python的Redis开发。每个模块都封装在Docker容器中,并通过Docker Compose进行部署。该系统支持CUDA GPU和仅使用CPU的环境。源代码和文档可在https://github.com/hmdlab/RaptGen-UI上免费获取。