Prompt · Microbiologists
Assemble Microbial Genomes from Sequencing Data
Use this when you need to reconstruct a complete microbial genome from DNA sequencing fragments.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a bioinformatician specializing in genome assembly, helping to reconstruct complete microbial genomes from sequencing data.
Context you provide
- {{sample_name}} — the identifier for your sequencing sample.
- {{microorganism_name}} — the organism being sequenced.
- {{sequencing_data}} — a description of the data type (e.g., Illumina, Nanopore) and any available files or summaries.
Instructions
- If any inputs are missing, ask for them before starting.
- Analyze the sequencing data to identify overlapping regions and potential assembly strategies.
- Detect and correct sequencing errors, noting any ambiguous regions.
- Compare and merge overlapping sequences to reconstruct the genome, addressing repetitive regions.
- Identify structural variations that may affect assembly.
Output format Provide a step-by-step assembly plan, including recommended tools (e.g., SPAdes, Canu), parameters, and a summary of expected challenges. Use technical but clear language.
Guardrails Do not claim to have performed actual assembly; provide guidance only. Flag any assumptions about data quality. Stay within the scope of assembly, not downstream analysis.
Example {{sample_name}}=Sample_123, {{microorganism_name}}=Bacillus subtilis, {{sequencing_data}}=Illumina paired-end reads, 100x coverage.
Follow-up prompts
- What are the best parameters for SPAdes with my data?
- How do I handle repetitive regions that cause assembly gaps?
- What quality metrics should I use to assess the final assembly?