tooluniverse-sequence-retrieval

Biological Sequence Retrieval

Retrieve DNA, RNA, and protein sequences with proper disambiguation and cross-database handling.

IMPORTANT: Always use English terms in tool calls (gene names, organism names, sequence descriptions), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language.

Workflow Overview

Phase 0: Clarify (if needed)
    ↓
Phase 1: Disambiguate Gene/Organism
    ↓
Phase 2: Search & Retrieve (Internal)
    ↓
Phase 3: Report Sequence Profile

---

Phase 0: Clarification (When Needed)

Ask the user ONLY if:

• Gene name exists in multiple organisms (e.g., "BRCA1" → human or mouse?)
• Sequence type unclear (mRNA, genomic, protein?)
• Strain/isolate matters (e.g., E. coli → K-12, O157:H7, etc.)

Skip clarification for:

• Specific accession numbers (NC_, NM_, U*, etc.)
• Clear organism + gene combinations
• Complete genome requests with organism specified

---

Phase 1: Gene/Organism Disambiguation

1.1 Resolve Identifiers

from tooluniverse import ToolUniverse
tu = ToolUniverse()
tu.load_tools()

# Strategy depends on input type
if user_provided_accession:
    # Direct retrieval based on accession type
    accession = user_provided_accession
    
elif user_provided_gene_and_organism:
    # Search NCBI Nucleotide
    result = tu.tools.NCBI_search_nucleotide(
        operation="search",
        organism=organism,
        gene=gene,
        limit=10
    )

1.2 Accession Type Decision Tree

CRITICAL: Accession prefix determines which tools to use.

Prefix	Type	Use With
NC_*	RefSeq chromosome	NCBI only
NM_*	RefSeq mRNA	NCBI only
NR_*	RefSeq ncRNA	NCBI only
NP_*	RefSeq protein	NCBI only
XM_*	RefSeq predicted mRNA	NCBI only
U*, M*, K*, X*	GenBank	NCBI or ENA
CP*, NZ_*	GenBank genome	NCBI or ENA
EMBL format	EMBL	ENA preferred