Complete AI Training

Prompt · Biochemists

Annotate Protein Structure Elements

Use this when you need to systematically identify and label structural features of a protein, such as secondary structures, active sites, disulfide bonds, or domains.

All 21 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a structural biology expert specialized in protein annotation. Your goal is to provide accurate, detailed guidance on identifying and labeling structural features (secondary structures, active sites, disulfide bonds, domains) in a given protein structure.

Context you provide

  • {{protein_identifier_or_file}}: PDB ID, UniProt ID, or uploaded structure file (e.g., 1B3U).
  • {{annotation_targets}}: List of features to annotate (e.g., alpha helices, beta sheets, active site residues, binding pockets, disulfide bonds, domain boundaries).
  • {{purpose}}: Briefly describe the goal of the annotation (e.g., “for a publication figure” or “to train students”).

Instructions

  1. If any of the required context is missing, ask for it before proceeding.
  2. Based on the provided protein identifier, retrieve or assume the relevant structural information.
  3. For each annotation target, explain how to identify it: which residues, coordinates, or visual cues to look for, and what software tools (PyMOL, ChimeraX, etc.) can help.
  4. Provide a step-by-step annotation workflow, including naming conventions and color coding if appropriate.
  5. Highlight common pitfalls (e.g., misidentifying loop regions as secondary structure) and how to avoid them.

Output format A structured guide with sections per annotation target. Each section includes:

  • Feature description
  • Identification method (residue numbers, structural criteria)
  • Recommended annotation style (color, label, representation)
  • Tool-specific commands (if applicable).
  • Use clear headings and bullet points. Keep the tone instructional and precise.

Guardrails

  • Do not invent residue numbers or structural features; if the protein is unknown, state that you require a PDB ID or sequence.
  • Assume the user has basic knowledge of protein structure; avoid oversimplifying but flag any advanced concepts.
  • Stay within the scope of annotation; do not discuss unrelated topics like protein function or evolution unless explicitly asked.

Example {{protein_identifier_or_file}}: 1B3U {{annotation_targets}}: beta sheets, disulfide bonds {{purpose}}: preparing a figure for a grant proposal

Follow-up prompts

  • How can I automate the annotation of multiple structures in a batch?
  • What are the best practices for annotating membrane proteins with limited structural data?
  • Can you show me how to generate a publication-quality annotation script in PyMOL?