Use Cases

End-to-end walkthroughs for representative scientific and data-readiness scenarios are located in use_cases/. Each covers data acquisition, code registration, pipeline construction, and agent-driven execution against a real dataset.

Use case	Domain	Summary
Microbial Isolates	Genomics — short-read QC and assembly with fastp + megahit	Register short-read QC and assembly tools, ingest genomics best-practice knowledge, and build a reproducible isolate-processing pipeline against real sequencing reads.
Cryo-EM	Structural biology — EMPIAR-10017 β-galactosidase micrographs via CryoPPP	DSAgt-assisted curation of cryo-EM data from the EMPIAR public archive (EMPIAR-10017 β-galactosidase micrographs via CryoPPP) — register curation tools, ingest cryo-EM quality knowledge, and build a micrograph-preprocessing pipeline.
VASP / ISAAC	Materials science — DFT input/output handling with VASP	Convert VASP DFT input/output into an AI-ready ISAAC record — register the conversion tooling and build the pipeline against bundled NEB fixture data (no DFT run, no HPC).
AIDRIN Readiness Gate (Cryo-EM)	AI data readiness — aidrin quality metrics before/after cryo-EM curation	Use AIDRIN as a readiness gate around a cryo-EM curation step — run the applicable data-quality and class-balance metrics before and after particle curation, with full provenance, to measure how much the pipeline improved AI-readiness.
AIDRIN Full Feature Tour	AI data readiness — all 15 aidrin metrics (quality, fairness, privacy) on UCI Adult	Drive every AIDRIN metric through DSAgt on a single tabular dataset (UCI Adult) — all 15 metrics across data-quality, impact-on-AI, fairness-and-bias, and data-governance, each recorded with full provenance.
Genesis Skills for Data Curation	Skill management — external skill catalog (Genesis / OSTI GitLab) driving a data-curation pipeline	Sync the Genesis skill catalog, install data-curation skills (datacard generation, Croissant validation), ground them in KB-ingested domain docs, and produce a datacard for a small curated dataset.
Skill-Driven VASP → ISAAC Conversion	Skill management — external skill catalog (K-Dense) authoring a VASP → ISAAC converter	A lightweight mock of the isaac_vasp workflow where the agent itself discovers, syncs, installs, and authors skills (pymatgen, skill-creator) to convert mock VASP output into an ISAAC record, vetting the skill-management feature end-to-end.
Fusion Foundation Model (XGC)	Plasma physics — gyrokinetic turbulence simulation (XGC) training-data prep	Preprocess HPC-scale XGC ADIOS2 BP5 simulation output into GNN-ready npz files and a PyTorch Dataset for training a plasma foundation model, via a bundled skill that registers the scripts as DSAgt codes with provenance. Advanced, bring-your-own-data.
Tokamak Stability	Fusion energy - explore finite-element simulation data	Register tools for reading, analyzing, and visualizing data from the M3D-C1 finite-element code. Use DSAgt to explore an example dataset, produce a range of plots, and generate and repackage secondary data products. Save the pipeline as a script that can be rerun across other similar datasets.

Adding a use case

Drop a README.md with frontmatter (title, domain, summary) into a use_cases/<name>/ folder — it is auto-added to this table, gets its own page, and appears in the nav. Folders without frontmatter are left out entirely. See hooks/gen_use_cases.py.