📋 Tender Overview
The AI-based data analysis tool used for this purpose could be created without any prior programming knowledge. “The results demonstrate how powerful AI-powered tools can be in everyday research. They not only make complex analyses accessible but also improve the reliability of scientific data,” explains Christmann. Advanced large language models such as ChatGPT (OpenAI), Gemini (Google), and Claude (Anthropic) now allow natural language to be translated directly into computer languages like Python. This enables researchers without coding backgrounds to create applications that, for instance, search through large datasets for specific text components or measurement values. The data obtained in this way can then be automatically processed further and checked for plausibility.
Christmann’s study, “What I Learned from Analyzing Accurate Mass Data of 3000 Supporting Information Files,” used an AI-powered data analysis tool to uncover previously unknown systematic errors. It also identified instances where miscalculated values appeared to be validated by measurements. “These observations raise the question of whether some measurements may have been fabricated,” the researcher emphasizes.
This study, published as an open-access paper, demonstrates how AI tools can enhance scientific integrity through automated quality control and systematic error detection. As part of an “AI in Education” initiative, Freie Universität Berlin’s Department of Biology, Chemistry, Pharmacy plans to integrate these and similar tools into its curriculum. “They will help students develop strong data analysis skills and critical thinking abilities,” says Christmann. “AI tools will be valuable in preparing students for their research careers."
