GenoMAS

A code-driven multi-agent framework for automated gene expression analysis workflows.

Source repo
Liu-Hy/GenoMAS
Stars
★ 134
Last updated
5mo ago
License
MIT
Primary language
Python

At a glance

Works with
Universal · cross-platformOpenAI API · Claude API
You'll need
Python 3.10condapipShell / CLINetwork accessLocal filesystem
Typical use
A computational genomics researcher needs repeatable preprocessing and regression runs across many GenoTEX trait-condition pairs.
Main limitation
The full GenoTEX benchmark requires roughly 42 GB of input data; the documented estimate is 3–5 continuous days and more than $300 for all pairs.

What does this agent do, and when should you use it?

GenoMAS combines a minimal multi-agent framework for scientific workflow automation with a specialized implementation for gene expression analysis. Its typed messaging and notebook-style workflow let agents plan, write code, execute it, debug, and backtrack across multi-step tasks. The specialized system analyzes transcriptomic datasets from GEO and TCGA to identify trait-related significant genes while accounting for confounders. Experiments run from the command line and write GenoTEX-structured preprocessing data, regression results, and logs under output/. Adoption requires local input data, a Python environment, and at least one provider credential, although local models can be run through Ollama.

Experiments are launched with python main.py, with configuration such as --version, --model, --api, and --data-root. The system reads GenoTEX input data, performs cohort preprocessing and regression analysis, and writes preprocessed cohort datasets to output/preprocess/{trait_name}/ and regression results to output/regress/{trait_name}/. Separate model and API-index settings are available for the Code Review, Domain Expert, Data Engineer, Statistician, and planning roles, while --parallel-mode cohorts can process cohorts concurrently. With --generate-action-units, it generates Action Unit prompts from agent guidelines, pauses for optional manual editing by default, and can proceed automatically with --non-interactive. It records activity in ./output/log_{version}.txt and supports checkpoint resume when the same interrupted command is rerun.

  1. A computational genomics researcher needs repeatable preprocessing and regression runs across many GenoTEX trait-condition pairs.
  2. A bioinformatics team working with GEO or TCGA transcriptomic data wants to identify trait-associated genes while accounting for confounders.
  3. A research engineer wants to evaluate heterogeneous model assignments for code review, domain expertise, data engineering, statistics, and planning.
  4. A team wants to validate cohort preprocessing on a few datasets before committing to the full statistical workflow, using --quick-test.
  5. A user constrained by API rate limits wants to reduce wall-clock time by processing a controlled number of cohorts with --parallel-mode cohorts.

How do you install or deploy this agent?

Create the documented environment and install dependencies:

conda create -n genomas python=3.10
conda activate genomas
pip install -r requirements.txt

Copy the configuration template and provide at least one model-provider API key:

cp env.example .env

OpenAI models also require an organization ID. Download the input data separately and place it under the data root; the documented default is ../data.

How do you use this agent?

Validate downloaded data first:

cd download
python validator.py --data-dir /path/to/data --validate

Then run a basic experiment from the project root:

python main.py --version exp1 --model gpt-5-mini-2025-08-07 --api 1

Add --data-root /path/to/data when the data is elsewhere. Use --quick-test for a small preprocessing-focused run. A local Ollama model can be selected with, for example, --model llama3.1.

What are this agent's strengths and limitations?

Pros
  • It pairs a general multi-agent scientific-workflow framework with a concrete implementation for GEO and TCGA transcriptomic analysis.
  • Its notebook-style execution model explicitly includes planning, code writing, execution, debugging, and backtracking instead of only producing recommendations.
  • It supports both global model selection and role-level overrides for Code Review, Domain Expert, Data Engineer, Statistician, and planning.
  • Its documented output layout, human-readable logs, and checkpoint resume make lengthy benchmark runs easier to inspect and continue.
Limitations
  • The full GenoTEX benchmark requires roughly 42 GB of input data; the documented estimate is 3–5 continuous days and more than $300 for all pairs.
  • Cloud use requires at least one provider API key, OpenAI use additionally requires an organization ID, and parallel runs can stress API rate limits.
  • Local deployment of large models has substantial GPU-memory and latency demands; the README states that DeepSeek-R1 671B requires multiple high-end GPUs.
  • Full regression requires all related datasets to be preprocessed, so the documented quick-test path validates preprocessing rather than the complete analysis workflow.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Stars Updated Language Full support on
GenoMAS This agent 51 · Major gaps ★ 134 5mo ago Python OpenAI API · Claude API
GenoTEX Gene Expression Benchmark 36 · Major gaps ★ 65 4mo ago Jupyter Notebook
BambooAI Data Analyst 85 · Good ★ 790 7d ago Python OpenAI API · Claude API
MiroFish Offline 30 · Major gaps ★ 2.5k 6mo ago Python OpenAI API · Claude API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
51/ 100 5-point scale 2.6 / 5
Trust 8/29
Reliability 8/14
Adaptability 12/18
Convention 10/18
Effectiveness 9/13
Verifiability 4/8
Why each dimension lost points
Trust8 / 29 · 1.4/5

Evidence: README requires users to configure API keys (.env), no hardcoded keys or excessive permissions found; --generate-action-units interactive mode pauses for manual editing and confirmation; output structure clear, logs traceable; no sensitive data handling details; dependencies not pinned, no security audit; external effects mainly API calls and local file writes, no malicious behavior; checkpoint resume mechanism provides rollback support; author identity clear in README and LICENSE. Deductions: dependencies not pinned, no security audit; sensitive data handling not specified; external effects not explicitly limited.

Reliability8 / 14 · 2.9/5

Evidence: README consistent with code structure, detailed parameter descriptions; dependency list exists but not pinned, may affect reproducibility; error handling has hints (e.g., model name errors list supported models), but no complete error message examples. Deductions: dependency versions not pinned, error message coverage limited.

Adaptability12 / 18 · 3.3/5

Evidence: Targeted at scientific users, provides multiple usage scenarios (basic, heterogeneous models, open-source, parallel, AU generation); capability boundaries explained via parameters and role configuration; triggers clear (command-line arguments); environment requirements (Python 3.10, conda, API keys) clear. Deductions: no detailed system requirements (e.g., memory, GPU), limited environment fit.

Convention10 / 18 · 2.8/5

Evidence: README structure complete, includes TOC, usage, output structure, troubleshooting; installation steps clear; naming stable (parameter names consistent); multiple examples and troubleshooting provided; known limitations (memory, timeout) documented; MIT license complete; no version number or changelog; maintenance responsibility not clear (no maintainer or contribution guidelines). Deductions: no version/changelog, maintenance responsibility unclear.

Effectiveness9 / 13 · 3.5/5

Evidence: Output structure follows GenoTEX convention, easy to use; benchmark results (F1 score) and cost estimates provided, showing marginal value; cost-benefit estimated ($300+ full run), but no detailed comparison. Deductions: cost-benefit analysis rough.

Verifiability4 / 8 · 2.5/5

Evidence: README cites arXiv paper and benchmark, traceable; but no independent verification data; facts and inferences not clearly separated (e.g., performance claims without detailed experimental data). Deductions: insufficient cross-validation, facts and inferences mixed.

Risks and how to mitigate them
  • Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
  • Dependencies are not pinned, which may introduce security vulnerabilities or compatibility issues.
  • API key management relies on user configuration; ensure .env file security.
  • Full run cost is high ($300+), evaluate resources carefully.
  • No version number or changelog provided, making updates hard to track.
Evidence confidence: Low Reviewed Aug 09, 2026 Reviewed revision d6365a700794
See the full review method →

FAQ

What does a full run cost and how long does it take?
For all 1,384 GenoTEX trait-condition pairs, the documented estimate is 3–5 days of continuous execution and more than $300, varying by model choice and API pricing.
Is a cloud API mandatory?
No. The documented local path uses Ollama with open-source models. API-based use requires at least one provider key in .env.
Can an interrupted experiment resume?
Yes. The repository documents checkpoint resume: rerunning the same command continues from the interruption point and clears half-finished task output automatically.
What data and outputs are in scope?
The specialized implementation analyzes GEO and TCGA transcriptomic datasets and produces trait-organized preprocessed cohorts, regression analysis results, and detailed execution logs.
View on GitHub ↗ Install ↓

Related agents