About MERGE Project

Project Overview

The MERGE (Model Ensemble for Ranking Genomic Effect) framework is a pipeline for variant pathogenicity prediction. By avoiding reliance on clinical databases that cause "data circularity," MERGE uses a Dynamic Shunting Architecture that routes every variant to a dedicated panel rather than scoring everything with one general-purpose model.

There are four panelscoding, splice, non-coding and non-SNV (indel / MNV / delins) — each with its own feature set and its own classifier, trained separately. The panel is chosen automatically: a variant whose REF or ALT is not a single base goes to the non-SNV panel; otherwise ANNOVAR annotation decides between coding, splice and non-coding.

PanelClassifierFeatures
CodingLogistic regression (L1)6
SpliceCatBoost10
Non-codingLogistic regression (L2)10
Non-SNVCatBoost10

The panels draw on up to 14 model features from genomic foundation models and protein language models: AlphaGenome, Enformer, Evo2 (7B, 7B-base and 1B-base), Carbon-3B, GENERATOR and GENERATOR-v2, Nucleotide Transformer and NT-v2, HyenaDNA, AlphaMissense, ESM-1b and GPN-MSA. Any feature that cannot be computed for a given variant is median-imputed by the ensemble, and every prediction reports which features were computed and which were imputed.

OPEN SOURCE · NOT FOR CLINICAL USE

Terms of Use

The MERGE software is open source under the MIT licence. The web server is provided free of charge for research use. By using this website or the merge-cli command-line tool, you agree to the following.

Required AlphaGenome notice.
The AlphaGenome API is provided for non-commercial use only and is subject to the AlphaGenome Terms of Service. Outputs generated by AlphaGenome should not be used for the training of other machine learning models.

Predictions are for theoretical modelling and research purposes only; they should not be used for clinical decision-making or relied upon for medical or other professional advice.

For collaboration or any question about these terms, contact the team using the addresses below.

Command-line Tool (merge-cli)

merge-cli is the professional-user counterpart to this website: the same models and the same ensemble, scriptable and runnable on your own machine. It is published on PyPI and, is published under the MIT licence — the source carries no field-of-use restriction. The four bundled ensemble model files are CC BY-NC 4.0; see the terms above.

It covers all four variant panels — coding, splice, non-coding and non-SNV (indel / MNV / delins) — and up to 14 model features (AlphaGenome, Enformer, Evo2-7B / 7B-base / 1B-base, Carbon-3B, GENERATOR, GENERATOR-v2, Nucleotide Transformer, NT-v2, HyenaDNA, AlphaMissense, ESM-1b, GPN-MSA).

1. Install

# Core install — remote mode, no GPU required
pip install merge-cli

# Optional extras
pip install "merge-cli[mcp]"   # ask for predictions inside an AI assistant
pip install "merge-cli[local]" # local GPU mode (adds pysam)
pip install "merge-cli[all]"   # everything

merge --help

Requires Python 3.11 or newer.

2. Remote mode (default) — nothing to configure

Scores are computed by this server; the MERGE ensemble runs locally on your CPU. The variant panel (coding / splice / non-coding / non-SNV) is chosen automatically.

# Single variant (BRCA1 p.Pro871Leu, hg38)
merge predict --chrom chr17 --pos 43092919 --ref G --alt A --genome hg38

# Force a panel, or emit machine-readable output
merge predict --chrom chr1 --pos 1040819 --ref G --alt GC --ensemble-type nonsnv
merge predict --chrom chr1 --pos 69428 --ref T --alt G --format json > result.json

# Batch VCF — runs asynchronously, results are emailed to you
merge batch variants.vcf --email you@example.org
merge status <job_id>

3. Local mode (optional, GPU)

Local mode runs every model on your own hardware — no rate limits and no variant ever leaves your machine. Each model is deployed into its own conda environment and served over HTTP; deploy only the ones you need.

merge doctor                      # check GPU, files and services
merge local setup                 # paths, incl. reference FASTA (recommended)
merge local env setup --model evo2 # deploy one model (or --model all)
merge local env start --model evo2
merge local env status
merge local predict --chrom chr17 --pos 43092919 --ref G --alt A

Scoring windows and conventions are fixed to the values the ensemble was trained on, so results match the published model. A model you do not run is simply median-imputed by the ensemble, and the CLI always reports which features were computed and which were imputed.

4. Use it from an AI assistant (MCP)

merge-cli ships an MCP server, so assistants such as Claude Desktop, Claude Code and Codex can call MERGE directly. Both steps are needed: the first registers the tools, the second makes the assistant reach for them.

pip install "merge-cli[mcp]"
merge mcp install    # register the tools
merge skill install  # make the assistant discover them
merge mcp status

The MCP server always runs in remote mode, so no GPU is required. Full documentation ships with the package (TUTORIAL.md) and on the PyPI project page.

The Research Team

Chen Yang
Lead Developer & Researcher
Zhongshan School of Medicine, SYSU
📧 chenyanggza01@163.com
Dr. Fang Li
Project Supervisor & Academic Mentor
Zhongshan School of Medicine, SYSU
📧 fangli9@mail.sysu.edu.cn