Files

243 lines
4.5 KiB
YAML
Raw Permalink Normal View History

2026-08-03 18:42:47 +08:00
# bbav20311 Skill 契约定义
# 基于 ClawBio SKILL.md 格式
name: gene-family-plant
description: 植物学基因家族分析专业助手 - 支持11个分析阶段的标准化基因家族分析流程
version: 1.0.0
author: xialab
metadata:
openclaw:
requires:
bins:
- python3
- conda
env:
- test4py311
config: []
always: false
emoji: "🧬"
homepage: https://github.com/xialab/bbav20311
os: [linux]
min_python: "3.11"
install:
- kind: conda
environment: environment.yml
system_dependencies:
- hmmer>=3.4
- blast>=2.17.0
- mafft
- iqtree
- meme>=4.11.2
- r-base>=4.4.3
- seqkit>=2.12.0
# 分析阶段定义
stages:
- name: identify
description: 基因家族鉴定
order: 1
required: true
inputs:
- protein_fasta
- hmm_file
outputs:
- final_members
- identify_report
- name: phylogeny
description: 系统发育分析
order: 2
required: false
depends_on:
- identify
inputs:
- final_proteins
outputs:
- phylogenetic_tree
- msa_alignment
- phylogeny_report
- name: motif
description: Motif分析
order: 3
required: false
depends_on:
- identify
inputs:
- final_proteins
outputs:
- meme_xml
- motif_report
- name: domain
description: Domain分析
order: 4
required: false
depends_on:
- identify
inputs:
- final_proteins
outputs:
- domtblout
- domain_report
- name: structure
description: 基因结构分析
order: 5
required: false
depends_on:
- identify
- phylogeny
inputs:
- gff3_file
- final_members
outputs:
- structure_gff3
- structure_report
- name: promoter
description: Promoter分析
order: 6
required: false
depends_on:
- identify
- phylogeny
inputs:
- genome_fasta
- gff3_file
outputs:
- promoter_sequences
- promoter_report
- name: synteny
description: 种内共线性分析(MCScanX / Circos)
order: 7
required: false
depends_on:
- identify
inputs:
- genome_fasta
- gff3_file
outputs:
- synteny_results
- synteny_report
- name: karyotype
description: 核型分析
order: 8
required: false
depends_on:
- identify
- synteny
inputs:
- genome_fasta
- gff3_file
outputs:
- karyotype_plot
- karyotype_report
- name: interspecies
description: 物种间共线性分析(跨物种 / JCVI-MCScan 流程,区别于种内 synteny)
order: 9
required: false
depends_on:
- identify
inputs:
- reference_genome
- reference_gff3
outputs:
- interspecies_synteny
- interspecies_report
- name: combo
description: 综合分析可视化
order: 10
required: false
depends_on:
- phylogeny
- motif
- domain
- structure
inputs:
- tree_nwk
- meme_xml
- domtblout
- structure_gff3
outputs:
- combo_plot
- combo_report
# 输入文件定义
inputs:
protein_fasta:
type: fasta
description: 蛋白质序列文件
required: true
extensions: [.fa, .fasta, .faa, .pep]
genome_fasta:
type: fasta
description: 基因组序列文件
required: false
extensions: [.fa, .fasta, .fna]
gff3_file:
type: gff3
description: 基因注释文件
required: false
extensions: [.gff, .gff3]
hmm_file:
type: hmm
description: HMM模型文件
required: true
extensions: [.hmm]
reference_fasta:
type: fasta
description: 参考序列文件
required: false
extensions: [.fa, .fasta]
subfamily_file:
type: tsv
description: 亚家族分类文件
required: false
extensions: [.tsv, .txt]
# 输出文件定义
outputs:
figures:
type: image
description: 分析结果图片
formats: [png, pdf, svg]
directory: final/figures/
tables:
type: table
description: 数据表格
formats: [csv, tsv, fa, nwk]
directory: final/tables/
reports:
type: markdown
description: 分析报告
formats: [md, json]
directory: final/reports/
logs:
type: text
description: 分析日志
formats: [log]
directory: logs/
# 可复现性配置
reproducibility:
enabled: true
generate:
- commands.sh
- environment.yml
- checksums.sha256
- manifest.json
copy_to_project: true