From Prompt to Pipeline: Large Language Models for Scientific Workflow Development in Bioinformatics

Abstract: The increasing complexity of bioinformatics data analysis has made Scientific Workflow Systems (SWSs) like Galaxy and Nextflow essential for enabling scalable, reproducible, and automated workflows. However, creating and understanding these workflows remains challenging, particularly for domain experts without programming expertise. This study investigates whether modern LLMs, GPT-4o, Gemini 2.5 Flash, and DeepSeek-V3, can support the generation of accurate, complete, and usable bioinformatics workflows, and examines which prompting strategies most effectively guide this process. We evaluate these models using diverse tasks such as SNP analysis, RNA-seq, DNA methylation, and data retrieval, spanning both graphical (Galaxy) and script-based (Nextflow) platforms. Expert reviewers assess the generated workflows against community-curated baselines from the Galaxy Training Network and nf-core repositories. The results show that Gemini 2.5 Flash excels in generating Galaxy workflows, while DeepSeek-V3 performs strongly in Nextflow. Prompting strategies significantly impact quality, with role-based and chain-of-thought prompts improving completeness and correctness. While GPT-4o benefits from structured inputs, DeepSeek-V3 offers rich technical detail, albeit with some verbosity. Overall, the findings highlight the potential of LLMs to lower the barrier for workflow development, improve reproducibility, and democratize access to computational tools in bioinformatics, especially when combined with thoughtful prompt engineering.