Appendix C — Case Studies
Case 1: Structure Prediction as a Research Input
A team without an experimental structure uses AlphaFold DB to generate hypotheses about a protein domain. The correct use is hypothesis generation, followed by confidence review, domain inspection, and assay planning (AlphaFold Protein Structure Database, 2026).
Case 2: Protein Binder Design
A protein engineering group uses RFdiffusion for backbone proposals and ProteinMPNN for sequence design. The design is not a success until expression, binding, specificity, and stability data support it (Watson et al., 2023; Dauparas et al., 2022).
Case 3: Docking Benchmark Failure
A docking method looks strong by RMSD but generates physically implausible poses. PoseBusters shows why chemical validity checks belong beside geometric metrics (Buttenschoen et al., 2024).
Case 4: Single-Cell Perturbation Forecasting
A group uses GEARS to rank perturbations for a follow-up experiment. The result supports prioritization, not general causal certainty (Roohani et al., 2024).
Case 5: Closed-Loop Experimentation
A self-driving lab chooses the next experiment based on prior measurements. The system needs protocol versioning, instrument logs, objective functions, and stopping rules (Abolhasani and Kumacheva, 2023; Mehr et al., 2024).
Case 6: Agentic Research Planning
A research agent drafts hypotheses and suggests protocols. The output requires source verification, human review, and authorization before any biological action (ARPA-H IGoR, 2026).