GenoTEX Gene Expression Benchmark
An expert-curated benchmark for evaluating automated gene-expression and gene–trait association analysis workflows.
- Source repo
- Liu-Hy/GenoTEX
- Stars
- ★ 65
- Last updated
- 5mo ago
- License
- NOASSERTION
- Primary language
- Jupyter Notebook
- FA score
- 54/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free, no paid service needed
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- An agent-development team that needs a common GTA benchmark to measure dataset filtering, preprocessing, and significant-gene identification.
- Not a fit if
- Users who want a quick start without downloading tens of GB of data
- Teams with limited disk space or no access to Google Drive, Baidu, Kaggle, or Hugging Face
- Users wanting a hosted service or chat UI instead of a local conda setup
- Source review
- 54/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
GenoTEX is a benchmark dataset for automated gene-expression analysis, with particular emphasis on evaluating LLM-based agents. It contains 1,384 gene–trait association (GTA) problems, 911 datasets, and bioinformatician-curated analysis code and results. Dataset-specific Jupyter notebooks perform cohort preprocessing, while code/regress.py centralizes association analysis and model selection. Large input, output, and metadata directories are obtained separately from cloud storage; bundled code-and-data versions are also available through Kaggle and Hugging Face. Evaluation is local through eval.py, which compares dataset selection, preprocessing, and statistical-analysis outputs rather than exposing a hosted service or chat interface.
The preprocessing notebooks read GEO and TCGA inputs organized by trait, clean and standardize them, and link clinical and gene-expression data. They produce clinical_data, gene_data, linked CSV files, and cohort_info.json under output/preprocess/. code/regress.py selects suitable preprocessed cohorts for each trait-condition problem, applies statistical models and hyperparameter tuning, and writes significant_genes_condition_{condition name}.json files under output/regress/. These result files include importance-ranked genes, coefficients, absolute coefficients, and cv_performance. A candidate method must emit the same output structure, then can be evaluated with python eval.py -p {prediction_directory} -r {reference_directory} -t selection preprocessing analysis -s gene clinical linked.
- An agent-development team that needs a common GTA benchmark to measure dataset filtering, preprocessing, and significant-gene identification.
- A bioinformatician who wants to inspect cohort-specific preprocessing notebooks and reproduce the documented association-analysis workflow.
- A team building automated GEO and TCGA processing that needs to produce CSV and JSON outputs comparable with benchmark references.
- An evaluator who needs separate scores for selection, preprocessing, and analysis, or for gene, clinical, and linked preprocessing subtasks.
- A computational-genomics researcher studying gene associations with a trait while accounting for age, gender, or a co-existing trait.
How do you install or deploy this agent?
Clone the repository and enter it: git clone https://github.com/Liu-Hy/GenoTEX.git && cd GenoTEX. Download the metadata, input, and output directories and place them at the repository root; the README lists Google Drive and Baidu Cloud Disk, while complete code-and-data bundles are available on Kaggle and Hugging Face. Create the documented environment and install dependencies: conda create -n genotex python=3.10, conda activate genotex, pip install -r requirements.txt. For the Kaggle version, run python recompress_files.py first to recompress required files.
How do you use this agent?
Run the applicable cohort notebooks in ./code/{trait_name}/ to create preprocessed data, then run python code/regress.py from the repository root for GTA association analysis. To evaluate a custom method, make its outputs match the documented output CSV/JSON structure and run: python eval.py -p {prediction_directory} -r {reference_directory} -t selection preprocessing analysis -s gene clinical linked. -p is required; -r defaults to ./output. Omit -t or -s to evaluate all tasks or all preprocessing subtasks.
What are this agent's strengths and limitations?
- It separates evaluation into 1,384 unconditional and conditional GTA problems across dataset selection, preprocessing, and statistical analysis.
- It supplies 911 datasets, 237,907 lines of expert-curated analysis code, and cohort-level Jupyter notebooks with step outputs.
- Its reference outputs specify concrete clinical, gene-expression, linked-data, and significant-gene file formats for offline comparison.
- It covers both GEO and TCGA data and includes gene_synonym.json for gene-symbol normalization.
- The documented download total is 82.0 GB, so full use requires substantial local disk space; the README also states 41.5 GB of input data, leaving a size-definition difference to resolve.
- The complete workflow depends on externally hosted data or Kaggle/Hugging Face bundles, plus local conda, Python 3.10, and filesystem access.
- Preprocessing is primarily distributed across many cohort-specific notebooks; the documentation does not describe one command that batch-runs all preprocessing.
- The supplied repository metadata says NOASSERTION while the README says the dataset is CC BY 4.0, so the applicable license should be verified before adoption.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| GenoTEX Gene Expression Benchmark This agent | 54 · Major gaps | CLIFree | ★ 65 | 5mo ago | Jupyter Notebook | — |
| GenoMAS | 50 · Major gaps | CLIFree + model costs | ★ 130 | 15d ago | Python | OpenAI API · Claude API |
| Open Science Workbench | 81 · Good | Desktop appFree + model costs | ★ 5.5k | today | TypeScript | Codex · Claude Code |
| Scientific Agent Skills | 75 · Some gaps | CLIFree + model costs | ★ 56k | 6d ago | Python | Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The README explains data directories, public sources, cloud distribution, and analysis output formats, providing some data-flow transparency. The packet does not show access controls, sensitive-data handling, or pre-run confirmation; download and recompression operations have no recovery guidance, so those criteria lose credit. Dependencies are listed without versions or security notes. Dataset and knowledge sources are attributed, but publisher identity and maintenance path are unclear.
The README describes preprocessing and regression responsibilities, input/output structures, and evaluation tasks in a broadly consistent way. Availability support is thin because dependencies are unpinned and include several model-service clients. It says format errors are reported but gives little detail on diagnosis or recovery.
The intended scenario is clear: a research benchmark for gene-expression analysis methods covering dataset selection, preprocessing, and statistical analysis. The documentation distinguishes the reference pipeline from evaluation of a user's own method. Task boundaries and output conventions are fairly clear, but no trigger rules or environment-specific adaptation guidance are shown.
The README has clear sections for repository structure, installation, usage, data formats, and citation. It gives conda/Python setup, dependency installation, and a Kaggle recompression note, but limited environment troubleshooting beyond the storage requirement. Naming conventions and examples are concrete; limitations are lightly documented, and no version history or named maintainer is shown. LICENSE.md states CC BY 4.0, while license metadata is NOASSERTION, so scope should be checked.
Directory conventions, JSON examples, and an evaluation command make outputs comparatively easy to integrate. The benchmark covers three tasks and explains its evaluation, supporting research value. The roughly 82 GB dataset and per-dataset preprocessing impose substantial storage and time costs; hardware and runtime needs are not quantified.
The README ties claims about scale, formats, sources, and metrics to concrete structure descriptions and distinguishes benchmark facts from intended use. LICENSE.md and the README corroborate the CC BY 4.0 statement, but the packet has no code, tests, or data samples for broader cross-checking; execution correctness is not inferred.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- The dataset is about 82 GB and requires a separate download; confirm storage and compute capacity before setup.
- Dependency versions are unpinned and license metadata differs from the repository declaration; verify dependency compatibility and the rights covering data and code before use or redistribution.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/genotex)<a href="https://followagents.com/en/agents/genotex"><img src="https://followagents.com/badge/genotex.svg" alt="FARS review"></a>FAQ
Is this a deployable analysis service or chat agent?
What data is required for a full run?
How do I evaluate my automated method?
Does it support conditional association analysis?
Is the license unambiguous?
Thanks — we use this to improve the page.