Skip to main content

CLI for MERGE variant pathogenicity prediction

Project description

MERGE CLI

MERGE 变异致病性预测命令行工具。所有计算在服务器端完成,本地只需 Python 3.9+。

安装

pip install merge-cli

快速开始

# 1. 配置服务器地址(只需配置一次)
merge config set-url https://your-server.com
merge config set-token YOUR_API_TOKEN

# 2. 单变异预测
merge predict --chrom chr17 --pos 43092919 --ref A --alt G

# 3. 批量预测(上传 VCF,结果发邮件)
merge batch my_variants.vcf --email you@example.com

命令详解

merge predict — 单变异预测

选项:
  --chrom     染色体(chr17 或 17 均可)   [必填]
  --pos       变异位置(1-based)           [必填]
  --ref       参考碱基                      [必填]
  --alt       突变碱基                      [必填]
  --genome    hg38 / hg19                  [默认: hg38]
  --format    table / json / tsv           [默认: table]
  --no-ensemble   跳过 MERGE 集成打分
  --no-alphagenome / --no-hyenadna / --no-nt
  --no-alphamissense / --no-esm1b / --no-gpn-msa
  --no-popeve / --no-evo2 / --no-evo1

输出示例(table 模式):

╭──────────────────────────────────────────╮
│          MERGE 预测结果                   │
├──────────────────┬───────────────────────┤
│ 变异位点         │ chr17:43092919 A → G  │
│ 基因 / 转录本    │ BRCA1 / ENST00000357654│
├──────────────────┼───────────────────────┤
│ MERGE 致病性     │ 87.3%  Likely Pathogenic│
│ 使用模型         │ ClinVar               │
├──────────────────┼───────────────────────┤
│ AlphaMissense    │ 0.9341                │
│ ESM1b            │ -3.2180               │
│ GPN-MSA          │ -1.4420               │
│ popEVE           │ 0.8812                │
│ AlphaGenome      │ 0.0234                │
│ HyenaDNA         │ -2.1100               │
│ NT               │ -1.8830               │
│ Evo2 LLR         │ -4.2210               │
│ Evo1 Delta       │ -3.9910               │
╰──────────────────┴───────────────────────╯

管道输出(TSV 模式,方便写脚本):

merge predict --chrom chr17 --pos 43092919 --ref A --alt G --format tsv >> results.tsv

脚本批量调用单变异(小于 20 个时比上传 VCF 更快):

while IFS=$'\t' read -r chrom pos ref alt; do
    merge predict --chrom "$chrom" --pos "$pos" --ref "$ref" --alt "$alt" --format tsv
done < variants.tsv >> results.tsv

merge batch — 批量 VCF 预测

merge batch variants.vcf --email you@example.com
merge batch variants.vcf.gz --email you@example.com --genome hg19 --no-evo2

任务提交成功后返回 Job ID,结果通过邮件发送,附件包含:

  • batch_predictions.csv — 所有模型分数汇总(可直接用 Excel 打开)
  • batch_predictions.vcf — 标准 VCF 格式,含 MERGE 及各模型分数
  • imputation_details.csv — MERGE 各特征缺失填补情况

服务端限制:每 IP 每日 5 次,同一邮箱间隔 1 小时,单次最多 2000 个变异。


merge status — 查询批量任务

merge status A3F2C1B0          # 查看一次
merge status A3F2C1B0 --watch  # 每 30 秒轮询

环境变量(适合 CI / 服务器环境)

export MERGE_API_URL=https://your-server.com
export MERGE_API_TOKEN=your-token
merge predict --chrom chr1 --pos 100000 --ref C --alt T

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

merge_cli-1.0.1.tar.gz (12.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

merge_cli-1.0.1-py3-none-any.whl (12.9 kB view details)

Uploaded Python 3

File details

Details for the file merge_cli-1.0.1.tar.gz.

File metadata

  • Download URL: merge_cli-1.0.1.tar.gz
  • Upload date:
  • Size: 12.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for merge_cli-1.0.1.tar.gz
Algorithm Hash digest
SHA256 2bda6e0da90379793f18f9988adbef382214c35ee417eff6ca0a0ac148e608bf
MD5 02010506fbcab36d4bbef8d9676cd1d2
BLAKE2b-256 2f03a9e96b824ffa1dab7315b83f61bb65f12dd26ea93e5cfa9bd4405dc09032

See more details on using hashes here.

File details

Details for the file merge_cli-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: merge_cli-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 12.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for merge_cli-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ac8d84829020ebcc0f69ea183940e4ec034372ffbc5e6906de2b5810adf02493
MD5 42916583cc9a0779dd7ded3141d3971b
BLAKE2b-256 5613308a94bfe06b4dda0229503f2b034e2100437ed9351d9dc8c29cbefdaa9e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page