C-P.05: LLM-Assisted Development of Large-Scale Proteomics Infrastructure: An Empirical Study from PRIDE Reanalysis
In data-intensive fields such as proteomics, the primary bottleneck is not only algorithm development but also the construction and operation of scalable data infrastructure. Building such systems, including pipelines, data layers, and validation frameworks, typically requires large and specialized teams.
We present a case study based on a fully operational pipeline for the systematic reanalysis of public timsTOF datasets from the PRIDE repository. The system integrates multiple search engines, performs raw signal extraction, and produces a versioned, bias-documented reference layer for downstream analysis and model training. The pipeline was developed by a single researcher using LLM-assisted software development and evolved under real data constraints, providing a unique setting to study infrastructure construction at scale.
We analyze the development process through version history and code evolution and investigate system behavior under increasing data volume to identify characteristic failure modes and validation challenges. Our observations indicate that while LLM-assisted development enables rapid construction of complex systems, it introduces new classes of errors and shifts the primary challenge from implementation to validation and system-level consistency.
These results highlight the need for systematic validation strategies for LLM-assisted scientific software and suggest that such methods may allow individual researchers to build infrastructure that previously required dedicated teams.
Co-authors: Stefan Tenzer, David Gomez-Zepeda, Tim Maier, Andreas Hildebrandt, Thomas Kemmer, Maximilian Sprang, Asis Asis Hallab
Contact Attendee
Warning: Attempt to read property "user_email" on string in /home/1276969.cloudwaysapps.com/ydbgzhdjeq/public_html/wp-content/plugins/my-conference-now/functions.php on line 2826