ams-meta-analysis 0.1.0

Installable Streamlit GUI for R-backed Python meta-analysis runners.

Meta-Analysis Streamlit App

An installable Streamlit GUI for the R-backed Python meta-analysis runners in /Volumes/Firecuda-4TB/R-code_to-python.

The original source directory is treated as read-only. The runner files were copied into this package under meta_analysis_streamlit/runners/ so the app can be installed and launched without editing the source folder.

What It Runs

• Workbook-level auto routing through the original main.py
• Binary pairwise meta-analysis
• Continuous pairwise meta-analysis
• Single-arm proportion and mean meta-analysis
• Diagnostic accuracy meta-analysis
• Frequentist and Bayesian network meta-analysis
• LM Studio model detection, with manual study-characteristic controls when LM Studio is not reachable

Install

From PyPI after the first release:

python3 -m pip install ams-meta_analysis
ams-meta-analysis

From this folder:

python3 -m pip install -e ".[dev]"

For a normal local wheel install:

python3 -m pip install .

Launch the GUI:

ams-meta-analysis

Run the original workbook orchestrator from the installed package:

meta-analysis-runner "/path/to/workbook.xlsx" --yes

Check the local environment:

meta-analysis-doctor

External Requirements

Python dependencies are installed by pip, but the statistical analyses still need R and the R packages used by the original generated scripts.

Install R, make sure Rscript is on PATH, then install the common R packages:

install.packages(c(
  "meta",
  "metafor",
  "readxl",
  "dplyr",
  "ggplot2",
  "netmeta",
  "gemtc",
  "rjags",
  "RTSA"
))

Bayesian network meta-analysis also needs JAGS installed on the system.

Trial sequential analysis can use the external TSA engine expected by the original code. If needed, point to it with:

export TSA_ANALYSIS_PY="/path/to/tsa_analysis.py"

LLM Provider Behavior

By default, the app checks http://localhost:1234/v1 for LM Studio. If LM Studio is not available, it can use OpenAI-compatible hosted APIs instead.

Supported GUI options:

• LM Studio: http://localhost:1234/v1
• OpenAI: https://api.openai.com/v1
• Gemini through Google's OpenAI-compatible endpoint: https://generativelanguage.googleapis.com/v1beta/openai
• Custom OpenAI-compatible endpoint
• Manual/no LLM

The app auto-selects the first available option in this order: LM Studio, OPENAI_API_KEY, GEMINI_API_KEY or GOOGLE_API_KEY, META_ANALYSIS_LLM_API_KEY, then manual mode.

For command-line runs, hosted APIs can also be used with the original --lmstudio-url option because the packaged runners now support OpenAI-compatible authentication headers:

export META_ANALYSIS_LLM_API_KEY="$OPENAI_API_KEY"
meta-analysis-runner "/path/to/workbook.xlsx" \
  --lmstudio-url "https://api.openai.com/v1" \
  --model "your-model" \
  --yes

For Gemini:

export META_ANALYSIS_LLM_API_KEY="$GEMINI_API_KEY"
meta-analysis-runner "/path/to/workbook.xlsx" \
  --lmstudio-url "https://generativelanguage.googleapis.com/v1beta/openai" \
  --model "your-gemini-model" \
  --yes

When no provider is reachable, the GUI still works: it passes --no-lmstudio and asks you to choose basic study characteristics such as analysis route, binary effect size, single-arm outcome type, diagnostic mode, and network model settings.

Output Location

Uploaded workbooks and generated outputs are staged under:

~/.meta_analysis_streamlit/runs/

The app writes a run log and offers a zip download for completed outputs.

Development

Run the tests:

pytest

Build a wheel:

python3 -m build
python3 -m twine check dist/*

See PUBLISHING.md for PyPI release steps, including Trusted Publishing through GitHub Actions.

The project is ready to commit and push from /Volumes/Firecuda-4TB/meta-streamlit-app.