外部基因组分析与 MCP¶
通过统一 Python API 检索已登记功能、调用外部分析软件和连接第三方 MCP。安装、完整参数与运行约定见参数 FAQ，作者、论文和许可证见来源 FAQ。
希望通过 pip 一并安装计算依赖，可先使用基因组教程中的 genomics 安装选项。它提供进程内的基因型 PCA、ANI、原核 CDS 预测等接口；本页 run_analysis() 继续使用所登记的外部可执行程序，二者的输入和算法范围分别说明。43 项功能的逐项迁移策略见FAQ。
1) 检索项目与可执行功能¶
- 作用： 查找相关项目与 DNAKit 已登记的分析接口，读取所需输入和后端。
- 计算方法： 对本地目录记录进行关键词匹配，并按领域筛选；
describe_analysis根据分析 ID 返回接口定义。检索过程不运行分析。 - API：
dnakit.integrations.search_projects(query[可选], domain[可选], verbose[可选])；dnakit.integrations.list_analyses(query[可选], domain[可选], verbose[可选])；dnakit.integrations.describe_analysis(analysis[必须], verbose[可选])。 - 输入： 项目关键词、领域名称或分析 ID，例如
plink2、population、plink2-pca。 - 输出： 返回项目列表、可用分析列表和分析定义字典。
- 示例代码：
from dnakit.integrations import search_projects, list_analyses, describe_analysis
projects = search_projects("plink2", verbose=False)
analyses = list_analyses("plink2", verbose=False)
definition = describe_analysis("plink2-pca", verbose=False)
print([project["id"] for project in projects["projects"]])
print([analysis["id"] for analysis in analyses])
print(definition["backend"], sorted(definition["inputs"]))
- 示例结果： 当前目录的离线查询结果。
2) 外部软件调用¶
- 作用： 根据已登记的分析定义生成运行计划，并在准备好后端和输入后执行分析。
- 计算方法： 校验输入文件、参数和输出目录，按登记模板构造命令参数。
plan_analysis返回计划；run_analysis调用后端并检查输出文件，保存运行记录。 - API：
dnakit.integrations.plan_analysis(analysis[必须], inputs[必须], output_directory[必须], parameters[可选], threads[可选], executable_paths[可选], verbose[可选])；dnakit.integrations.run_analysis(analysis[必须], inputs[必须], output_directory[必须], parameters[可选], threads[可选], executable_paths[可选], timeout_seconds[可选], max_artifact_bytes[可选], verbose[可选])。 - 输入： 分析 ID、输入文件映射和尚不存在的输出目录。以下示例需已有
data/cohort.bed、data/cohort.bim、data/cohort.fam。 - 输出：
plan_analysis返回执行计划；实际调用返回状态、步骤和产物路径。 - 示例代码：
from dnakit.integrations import plan_analysis, run_analysis
inputs = {"genotypes": "data/cohort"}
plan = plan_analysis(
"plink2-pca", inputs, "results/cohort-pca",
parameters={"components": 3}, threads=4, verbose=False,
)
print(plan["analysis"], plan["status"])
print(plan["parameters"])
print(plan["steps"][0]["expected_outputs"])
# 已安装 PLINK 2，并确认输入与计划后执行：
# result = run_analysis(
# "plink2-pca", inputs, "results/cohort-pca",
# parameters={"components": 3}, threads=4,
# )
- 示例结果： 输入文件就绪时的计划输出；此步骤不执行 PLINK，也不写结果文件。
已登记分析与后端
| Analysis ID / 分析 ID | Capability / 功能 | Backend / 后端 | Validation / 验证 |
|---|---|---|---|
plink2-pca |
群体结构主成分 | plink2 | passed_synthetic_fixture |
plink2-king |
样本亲缘系数 | plink2 | passed_synthetic_fixture |
plink2-ld-prune |
连锁不平衡剪枝 | plink2 | passed_synthetic_fixture |
plink2-gwas |
带协变量的全基因组关联分析 | plink2 | passed_synthetic_fixture |
gcta-grm |
基因组关系矩阵文件 | gcta64 | not_run |
gcta-reml |
遗传力估计 | gcta64 | not_run |
minigraph-pangenome |
参考基因组与组装图构建 | minigraph | not_run |
hifiasm-assembly |
HiFi 单样本组装 | hifiasm | not_run |
flye-assembly |
Nanopore 长读长组装 | flye | not_run |
sniffles-sv |
长读长结构变异检测 | sniffles | not_run |
modkit-pileup |
修饰碱基覆盖统计 | modkit | not_run |
mosdepth-coverage |
测序深度统计 | mosdepth | not_run |
fastani |
微生物平均核苷酸一致性 | fastANI | not_run |
kraken2-classify |
微生物读段分类 | kraken2 | not_run |
amrfinder-nucleotide |
组装序列耐药基因注释 | amrfinder | not_run |
prokka-annotation |
原核基因组注释 | prokka | not_run |
barrnap-rrna |
基因组核糖体 RNA 位点识别 | barrnap | not_run |
fimo-motifs |
DNA 模体位点搜索 | fimo | not_run |
cas-offinder |
CRISPR 脱靶候选枚举 | cas-offinder | not_run |
bakta-annotation |
细菌、MAG与质粒标准化注释 | bakta | not_run |
busco-proteins |
蛋白集完整性评估 | busco | not_run |
busco-genome |
基因组完整性评估 | busco | not_run |
augustus-genes |
真核基因结构预测 | augustus | not_run |
diamond-blastp |
蛋白相似性搜索 | diamond | passed_synthetic_smoke |
diamond-blastx |
翻译核酸相似性搜索 | diamond | passed_synthetic_smoke |
eggnog-proteins |
直系同源支持的蛋白功能注释 | emapper.py | not_run |
miniprot-align |
含剪接和移码的蛋白到基因组比对 | miniprot | passed_synthetic_smoke |
liftoff-annotation |
组装之间的基因注释迁移 | liftoff | not_run |
checkm2-predict |
MAG完整性与污染度预测 | checkm2 | not_run |
quast-assembly |
参考支持的组装质量评估 | quast.py | not_run |
vsearch-dereplicate |
核酸序列去重复 | vsearch | passed_synthetic_smoke |
vsearch-cluster |
核酸相似性聚类 | vsearch | passed_synthetic_smoke |
mmseqs-protein-search |
蛋白序列快速搜索 | mmseqs | passed_synthetic_smoke |
mmseqs-protein-cluster |
蛋白序列聚类 | mmseqs | passed_synthetic_smoke |
abricate-screen |
组装序列耐药与毒力标记筛查 | abricate | not_run |
mlst-typing |
PubMLST方案多位点序列分型 | mlst | not_run |
genomad-mobile-elements |
病毒和质粒等移动元件识别 | genomad | not_run |
repeatmasker-library |
指定重复序列库的核酸屏蔽 | RepeatMasker | not_run |
mageck-test |
CRISPR筛选基因效应排序 | mageck | not_run |
mageck-count |
CRISPR筛选sgRNA读数统计 | mageck | not_run |
crispresso2-amplicon |
单扩增子编辑结果定量 | CRISPResso | not_run |
drugz-unpaired |
非配对CRISPR药物交互筛选 | drugz.py | passed_synthetic_smoke |
gemma-lmm |
亲缘校正的混合模型关联检验 | gemma | not_run |
3) 第三方 MCP 连接¶
- 作用： 查看已登记服务，并通过实时工具清单选择和调用第三方能力。
- 计算方法：
list_mcp_servers读取本地目录；list_mcp_tools连接指定服务并获取工具 schema；call_mcp_tool校验参数后调用一个工具。 - API：
dnakit.integrations.list_mcp_servers(verbose[可选])；dnakit.integrations.list_mcp_tools(server_id[必须], transport[可选], executable_path[可选], workdir[可选])；dnakit.integrations.call_mcp_tool(server_id[必须], tool_name[必须], arguments[必须], transport[可选], executable_path[可选], workdir[可选])。连接超时、环境变量和响应限制见参数 FAQ。 - 输入： 目录中的服务 ID；实际调用还需已配置的服务，以及实时 schema 中的工具名称和参数。
- 输出： 返回 MCP 服务和工具列表；每项包含服务 ID、命令或工具定义。
- 示例代码：
from dnakit.integrations import list_mcp_servers, list_mcp_tools, call_mcp_tool
server = next(
item for item in list_mcp_servers(verbose=False) if item["id"] == "biomcp"
)
print(server["id"], server["command"])
print(server["arguments"])
# 配置好 BioMCP 后，查询实时工具；这一步会启动服务：
# tools = list_mcp_tools("biomcp")
# 按 tools 返回的工具名称和 inputSchema 准备参数，再调用：
# result = call_mcp_tool("biomcp", tool_name, arguments)
- 示例结果： 离线服务目录结果；未启动服务或调用远端工具。
已登记 MCP 服务与上游配置
| Server ID / 服务 ID | Upstream / 上游 | Configuration / 配置 |
|---|---|---|
gigwa-mcp |
Gigwa MCP | Install gigwa-mcp separately into a Python >=3.10 environment; configure GIGWA_URL and optional paired GIGWA_USER/GIGWA_PASS. |
chorus |
Chorus | Install the pinellolab/chorus source project and provision its oracle environments, model weights and references separately. The PyPI package named chorus is unrelated. Set executable_path to the installed chorus-mcp. |
mavedb-link |
MaveDB-Link | For stdio, install the source project's dependencies in Python >=3.12 and set workdir to that checkout and executable_path to its Python. The author-documented HTTP service is available with transport='http'. |
biomcp |
BioMCP | Install genomoncology/biomcp separately; its PyPI distribution is biomcp-cli, not the unrelated biomcp distribution. The installed executable is biomcp. |
juicebox |
Juicebox MCP | Prepare the official source checkout and npm dependencies separately, then set workdir to the checkout and executable_path to Node if necessary. |
genechat |
GeneChat MCP | Install and initialize GeneChat and its local genome/annotation databases separately. GENECHAT_CONFIG optionally selects an existing TOML configuration. |
genepattern |
GenePattern MCP | Install the official source checkout requirements separately with Python >=3.11. Set workdir to the checkout, executable_path to that Python, and GENEPATTERN_KEY to an existing API token. |
brapi |
BrAPI MCP | Separately prepare the pinned @cyanheads/brapi-mcp-server release/source with its dist build and dependencies; set workdir to the package root and executable_path to Node >=24. The bridge never runs npm, npx, bunx or an installer. |
ensembl |
Ensembl MCP (cyanheads) | Separately prepare the pinned @cyanheads/ensembl-mcp-server build and dependencies; set workdir to the package root and executable_path to Node >=24. |
biothings |
BioThings MCP | Install the pinned longevity-genie/biothings-mcp project separately in Python >=3.10; use its installed biothings-mcp entry point. |
gget |
gget MCP | Install gget-mcp and its separately specified gget dependencies in Python >=3.10; the verified command is gget-mcp stdio. |
ucsc-genome |
UCSC Genome MCP | Prepare the pinned source checkout and its requirements in Python >=3.10, set workdir to the checkout and executable_path to that Python. Use the existing hyphenated ucsc-genome-mcp.py script; upstream README/packaging also mention nonexistent underscore filenames. |
opentargets |
Open Targets MCP | Install nickzren/opentargets-mcp separately in Python >=3.10; set executable_path to its interpreter. Uses the verified Python module entry point with explicit stdio. |
plant-genomics |
Plant Genomics MCP | Install the pinned plant-genomics-mcp Python distribution and dependencies separately. The plant-genomics-mcp entry point selects stdio; no HTTP token is needed for this local transport. |
biocontext-kb |
BioContextAI Knowledgebase MCP | Install biocontext_kb separately in Python >=3.12. DNAKit fixes MCP_ENVIRONMENT=DEVELOPMENT for the verified stdio entry point. |
grebi |
GrEBI | Select transport='http' for the author-documented development service. Local deployment is a separate Java/API plus graph-database and HPC data-pipeline task; no local startup recipe is claimed here. |
ebi-tools |
EBI Tools MCP (QuentinCody) | Select transport='http' for the repository author's published Cloudflare Worker MCP service. No standalone Node stdio entry point is present; no mcp-remote/npx helper is required by DNAKit. |
gwas-mcp |
GWAS MCP (muslus) | Prepare the pinned muslus/gwas-mcp source and its dependencies in an isolated Python >=3.10 environment, then point executable_path at that interpreter. Avoid assuming that the separately published gwas-mcp distribution has identical code. |
ncbi-database |
NCBI Database MCP (hpend2373) | Prepare the pinned NCBI-Database-MCP checkout and its requirements, set workdir to the checkout and executable_path to its Python. Uses the README-supported standard MCP script rather than executing its shell installer/launcher. |
pubmed |
PubMed MCP (cyanheads) | Prepare the pinned @cyanheads/pubmed-mcp-server build and dependencies separately, then set workdir to the package root and executable_path to Node >=24. |
encode-toolkit |
ENCODE Toolkit | Install the Python encode-toolkit distribution separately and set executable_path to its interpreter. DNAKit invokes the verified Python module directly; it does not use the npm shim which can bootstrap uv/Python. |
tooluniverse |
ToolUniverse | Install the pinned ToolUniverse distribution and required provider dependencies separately. Use the installed tooluniverse console script; unlike the README uvx --refresh example, this bridge does not refresh or install anything. |
kiro-genomics |
AWS Kiro Life Sciences: genomics | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-genomics component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-genomics console script. No uvx or automatic install is used. |
kiro-model-organisms |
AWS Kiro Life Sciences: model-organisms | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-model-organisms component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-model-organisms console script. No uvx or automatic install is used. |
kiro-epigenomics |
AWS Kiro Life Sciences: epigenomics | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-epigenomics component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-epigenomics console script. No uvx or automatic install is used. |
kiro-agriculture |
AWS Kiro Life Sciences: agriculture | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-agriculture component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-agriculture console script. No uvx or automatic install is used. |
kiro-ecology |
AWS Kiro Life Sciences: ecology | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-ecology component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-ecology console script. No uvx or automatic install is used. |
kiro-clinical |
AWS Kiro Life Sciences: clinical | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-clinical component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-clinical console script. No uvx or automatic install is used. |
kiro-pipelines |
AWS Kiro Life Sciences: pipelines | Prepare the pinned aws-samples/sample-kiro-power-life-sciences source. Separately install life-sciences-common and the life-sciences-pipelines component in its Python >=3.10 environment, then set executable_path to the installed life-sciences-pipelines console script. No uvx or automatic install is used. |
pubmed-anthropic |
PubMed (Anthropic Life Sciences hosted connector) | Select transport=http. The provider-published endpoint supports anonymous MCP initialization and tools/list as verified on 2026-09-20. No local installer is run. |
opentargets-platform |
Open Targets Platform official MCP | Select transport=http. The provider-published endpoint supports anonymous MCP initialization and tools/list as verified on 2026-09-20. No local installer is run. |
10x-genomics |
10x Genomics Cloud MCP | Separately prepare and unpack the upstream 10x Genomics MCP bundle, including its server/, node_modules/ and platform bin/ files. Set workdir to that unpacked bundle, executable_path to installed Node.js >=18, and the named TXG_CLI_ACCESS_TOKEN environment variable. DNAKit does not download a bundle or TXG binary. |
4) 同一会话连续调用¶
- 作用： 在同一 MCP 会话内依次执行多个工具，保留模型加载等服务内状态。
- 计算方法： 每步重新读取 schema、校验显式参数并按顺序调用；遇到远端错误即停止，返回已执行步骤及错误状态。
- API：
dnakit.integrations.call_mcp_workflow(server_id[必须], calls[必须], transport[可选], executable_path[可选], workdir[可选], timeout_seconds[可选])；其余连接参数见参数 FAQ。 - 输入： 服务 ID 和调用列表；每项包含实时 schema 中的
tool_name与arguments。下例的加载和预测工具名称、参数需由调用者传入。 - 输出： 返回同一会话中各工具调用的结果字典。
- 示例代码：
from dnakit.integrations import call_mcp_workflow
def load_then_predict(load_tool, load_arguments, predict_tool, predict_arguments):
calls = [
{"tool_name": load_tool, "arguments": load_arguments},
{"tool_name": predict_tool, "arguments": predict_arguments},
]
result = call_mcp_workflow("chorus", calls, timeout_seconds=300)
print(result["status"], result["requested_steps"], result["executed_steps"])
return result
- 示例结果： 两步均成功时的输出形式；此处未连接 Chorus，实际结果取决于服务返回。
5) 通过 DNAKit MCP 暴露¶
- 作用： 将基因组分析和外部工具接口提供给支持 MCP 的客户端，并在调用前查询其输入与执行类型。
- 计算方法： DNAKit 从公开函数生成工具目录、签名和 JSON schema；客户端检索目录后调用指定工具。下面离线查看同一工具目录中的运行类型。
- API： 启动入口
dnakit-mcp；MCP 工具search_dnakit_tools(query[必须], category[可选], limit[可选])、describe_dnakit_tool(tool_name[必须])；本地目录入口dnakit.tools.default_tool_registry(verbose[可选])。 - 输入： 检索词
genomics或integrations，以及工具完整名称，如dnakit.integrations.run_analysis。 - 输出： 返回 DNAKit MCP 工具说明或执行结果。
- 示例代码：
from dnakit.tools import default_tool_registry
registry = default_tool_registry(verbose=False)
info = registry.describe("dnakit.integrations.run_analysis")
print(info["name"])
print(info["effect"])
- 示例结果： 离线读取工具信息；未执行分析。