84 lines
3.2 KiB
Python
84 lines
3.2 KiB
Python
|
"""Utility-task catalog separate from formal analysis pipelines.
|
||
|
|
|
||
|
|
Utility tasks are TBtools-like one-off operations for file preparation,
|
||
|
|
sequence extraction, ID cleanup and external sequence fetching. They remain
|
||
|
|
executable, but they must not be expanded into gene-family or RNA-seq pipeline
|
||
|
|
dependencies from natural-language planning.
|
||
|
|
"""
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from typing import Any
|
||
|
|
|
||
|
|
|
||
|
|
UTILITY_TASKS: dict[str, dict[str, Any]] = {
|
||
|
|
"fasta_header_clean": {
|
||
|
|
"stage": "sequence_extract_by_id",
|
||
|
|
"name": "清理FASTA序列ID/header",
|
||
|
|
"description": "Remove long FASTA header annotations and keep the first ID token.",
|
||
|
|
},
|
||
|
|
"sequence_extract_by_id": {
|
||
|
|
"stage": "sequence_extract_by_id",
|
||
|
|
"name": "按ID从FASTA提取序列",
|
||
|
|
"description": "Extract protein/CDS/FASTA records from local files using an ID list or inline IDs.",
|
||
|
|
},
|
||
|
|
"ncbi_fetch_sequences": {
|
||
|
|
"stage": "ncbi_fetch_sequences",
|
||
|
|
"name": "NCBI序列下载",
|
||
|
|
"description": "Fetch protein/CDS sequences from NCBI by GeneID, gene symbol, locus tag or ID list.",
|
||
|
|
},
|
||
|
|
"prepare_organize": {
|
||
|
|
"stage": "prepare_organize",
|
||
|
|
"name": "整理输入文件",
|
||
|
|
"description": "Organize uploaded files by config.xlsx without starting a gene-family pipeline.",
|
||
|
|
},
|
||
|
|
"prepare_normalize_gff": {
|
||
|
|
"stage": "prepare_normalize_gff",
|
||
|
|
"name": "规范化GFF ID",
|
||
|
|
"description": "Normalize GFF/GTF attributes and IDs as a standalone file-preparation task.",
|
||
|
|
},
|
||
|
|
"prepare_longest_transcript": {
|
||
|
|
"stage": "prepare_longest_transcript",
|
||
|
|
"name": "提取最长转录本",
|
||
|
|
"description": "Select the longest transcript/CDS per gene as a standalone preparation task.",
|
||
|
|
},
|
||
|
|
"prepare_extract_pep": {
|
||
|
|
"stage": "prepare_extract_pep",
|
||
|
|
"name": "从Genome+GFF提取全蛋白组",
|
||
|
|
"description": "Run gffread peptide extraction from genome FASTA and GFF/GTF.",
|
||
|
|
},
|
||
|
|
"prepare_extract_cds": {
|
||
|
|
"stage": "prepare_extract_cds",
|
||
|
|
"name": "从Genome+GFF提取全CDS",
|
||
|
|
"description": "Run gffread CDS extraction from genome FASTA and GFF/GTF.",
|
||
|
|
},
|
||
|
|
"prepare_filter_fasta": {
|
||
|
|
"stage": "prepare_filter_fasta",
|
||
|
|
"name": "按ID筛选FASTA",
|
||
|
|
"description": "Filter FASTA records using an ID list as a standalone task.",
|
||
|
|
},
|
||
|
|
"prepare_simplify_ncbi": {
|
||
|
|
"stage": "prepare_simplify_ncbi",
|
||
|
|
"name": "简化NCBI注释/序列ID",
|
||
|
|
"description": "Simplify NCBI GFF attributes and normalize NCBI CDS headers.",
|
||
|
|
},
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
STAGE_TO_DEFAULT_TOOL = {
|
||
|
|
value["stage"]: key for key, value in UTILITY_TASKS.items()
|
||
|
|
}
|
||
|
|
STAGE_TO_DEFAULT_TOOL["sequence_extract_by_id"] = "sequence_extract_by_id"
|
||
|
|
|
||
|
|
|
||
|
|
def utility_tool_for_stage(stage: str, params: dict[str, Any] | None = None) -> str:
|
||
|
|
params = params or {}
|
||
|
|
if stage == "sequence_extract_by_id" and params.get("sequenceExtractCleanHeaders"):
|
||
|
|
return "fasta_header_clean"
|
||
|
|
return STAGE_TO_DEFAULT_TOOL.get(stage, stage)
|
||
|
|
|
||
|
|
|
||
|
|
def utility_display_name(stage: str, params: dict[str, Any] | None = None) -> str:
|
||
|
|
tool = utility_tool_for_stage(stage, params)
|
||
|
|
return UTILITY_TASKS.get(tool, {}).get("name", stage)
|
||
|
|
|