On May 26, Jinan Microecological Biomedicine Shandong Laboratory held a training session on Big Data and Artificial Intelligence Platform in Room 18F. The training covered the basic functions of the platform, statistics and visualisation in R language, service deployment and task delivery, aiming at helping users to make efficient use of the platform resources and improve their data analysis ability. Assistant experimenters of Big Data and Artificial Intelligence Platform, Yang Long and Li Tongtong, gave the training lectures, and a number of scientific research backbones of the laboratory attended the meeting.
At the training session, Yang Long systematically explained the core functional modules of the platform such as sandbox environment construction, file management system operation, mirror repository application and resource optimization configuration of Poros, a task scheduling platform, by combining theoretical analysis with on-site demonstration. He also analysed the technical key points of constructing a safe experimental environment and efficient management of computational tasks through example demonstration, and demonstrated abstract technical concepts in scientific research scenarios so that they can be presented in the scientific research scene. The abstract technical concepts were presented in the scientific research scenarios, enabling everyone to quickly understand and master the use of the platform.
Titled ‘Statistical Analysis and Visualisation in R’, Tongtong Li systematically explained the core functions of ggplot2, pheatmap and other toolkits, and how to adapt them to scientific research scenarios. She also demonstrated in detail the whole process of data pre-processing to visualisation and chart generation, and the deployment of the software environment based on Docker and Singularity through the case study of micro-ecology field. The training also covered the operation of WDL workflow and qsub task delivery system, which helped the trainees to master the complete research workflow from environment deployment to task scheduling, and thus significantly improved the execution efficiency of complex analysis tasks.
During the Q&A session, the trainees actively asked questions and held in-depth discussions on issues such as mirror authority management and R code optimisation, and unanimously expressed that the training not only provided rich theoretical knowledge, but also paid more attention to the cultivation of practical operation ability, which enabled the users to get started quickly and apply it to their own scientific research work. Big Data and Artificial Intelligence Platform said that colleagues are welcome to put forward technical needs and suggestions at any time, so that we can carry out follow-up training and communication in a targeted manner, continue to improve the technical service system, and provide solid support for the laboratory's scientific research and innovation.
