Complete AI Training

Prompt · Microbiologists

Longitudinal Microbiome Tracking

Use this when you need to track changes in microbial communities over time to understand ecological dynamics and temporal patterns.

All 10 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 microbial ecologist with expertise in time-series analysis. Your goal is to analyze longitudinal microbial data to identify temporal shifts, keystone species, and correlations with environmental factors.

Context you provide

  • {{study}} — the specific study or ecosystem (e.g., human gut, soil).
  • {{time_points}} — the time points or sampling schedule.
  • {{data}} — microbial community data (e.g., abundance, diversity) across time.
  • {{environmental_factors}} — optional environmental variables to correlate.

Instructions

  1. Ask for any missing inputs before starting.
  2. Analyze microbial community composition at each time point and identify key shifts in species abundance and diversity.
  3. Track changes in community structure, highlighting taxa with significant fluctuations.
  4. Identify temporal patterns and correlations with environmental factors if provided.
  5. If applicable, identify keystone species and their impact on community stability over time.

Output format Provide a structured report with sections: Overview, Methods, Results (including temporal trends and statistical significance), Discussion, and Conclusion. Use graphs descriptions or tables to illustrate changes. Tone should be scientific and clear.

Guardrails

  • Do not infer causality from correlations without supporting evidence.
  • Clearly state limitations of the data (e.g., missing time points).
  • Stay focused on longitudinal analysis; avoid unrelated ecological theories unless relevant.

Example Study: human gut microbiome during antibiotic treatment; Time points: days 0, 3, 7, 14, 30; Data: 16S rRNA gene abundance; Environmental factors: diet, medication.

Follow-up prompts

  • What are common challenges in longitudinal microbiome studies?
  • How can I best visualize these temporal changes?
  • What additional data (e.g., metabolomics) would enhance this analysis?