Magi

B+ 89 completed
Cli Tool
cli / python · small
56
Files
2,662
LOC
1
Frameworks
4
Languages

Pipeline State

completed
Run ID
#339796
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
31.24
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47626
Member of a group with 2 similar repo(s) — canonical #93576 view group →
Top concepts (2)
Project DescriptionTesting
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/

AI Prompt

Create a command-line tool in Python for multi-kingdom metagenomic interaction analysis, similar to MAGI. The tool should automate the process from raw long-read data to generating publication-ready cross-kingdom interaction networks. Key features to include are quality control (like adapter trimming and host depletion), multi-kingdom taxonomic profiling (bacteria, fungi, viruses), assembly, binning, and functional annotation. Finally, it must be able to infer cross-kingdom interactions and generate integrated, interactive HTML reports. The tool should use a configuration file, perhaps YAML, for setup.
python cli metagenomics bioinformatics genomics analysis snakemake command-line
Generated by gemma4:latest

Catalog Information

A command-line tool that performs multi-kingdom metagenomic interaction analysis and visualizes the results.

Description

Magi-Metagenomics is a Python-based CLI application that ingests raw metagenomic abundance tables and metadata, normalizes the data, and applies statistical and machine‑learning techniques to uncover interactions between organisms from different kingdoms. It constructs correlation and co‑occurrence networks, clusters taxa into functional groups, and generates both static and interactive visualizations using Matplotlib and Plotly. The tool is designed for researchers who need to explore complex ecological relationships without writing extensive code, providing a streamlined workflow from data import to publication‑ready figures. It supports common file formats such as CSV, TSV, and BIOM, and outputs results in easily shareable formats like PNG, HTML, and JSON. By integrating scikit‑learn and SciPy, the application offers robust statistical testing and dimensionality reduction to highlight significant patterns in large datasets.

الوصف

تُعدّ أداة ماغي‑ميتاجينومكس تطبيقاً سطر أوامر مبنيًا بلغة بايثون يتيح للباحثين استيراد جداول الكثافة الجينية للميتاجينوم والبيانات الميتاداتية، ثم يُعالجها عبر عمليات تطبيع وتحليل إحصائي وتعلم آلي لاستخلاص التفاعلات بين الكائنات من ممالك مختلفة. تقوم الأداة ببناء شبكات الترابط والتواجد المشترك، وتُقسِّم الكائنات إلى مجموعات وظيفية، وتُنتج رسومات إحصائية وتفاعلية باستخدام مكتبات ماتبلوتليب وبلاوتلي. صُممت لتلبية احتياجات علماء الأحياء الدقيقة والبيولوجيا الحاسوبية الذين يرغبون في استكشاف العلاقات البيئية المعقدة دون الحاجة لكتابة كود برمجي معقد، مقدمةً سير عمل مبسّط من استيراد البيانات إلى إنتاج رسومات جاهزة للنشر. تدعم الأداة صيغ ملفات شائعة مثل CSV وTSV وBIOM، وتصدر النتائج بصيغ قابلة للمشاركة مثل PNG وHTML وJSON. بدمجها لمكتبات سكيت‑ليرن وسكيب‑إي، توفر أداة ماغي‑ميتاجينومكس اختبارات إحصائية قوية وتقليل أبعاد لتسليط الضوء على الأنماط الهامة في مجموعات البيانات الكبيرة.

Novelty

7/10

Tags

metagenomic-analysis interaction-network-construction interactive-visualization statistical-correlation machine-learning-clustering cross-kingdom-comparison data-preprocessing

Technologies

click matplotlib numpy pandas plotly scikit-learn scipy

Claude Models

claude-opus-4.6

Quality Score

B+
88.8/100
Structure
90
Code Quality
100
Documentation
80
Testing
75
Practices
83
Security
100
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (40% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Low average code complexity \u2014 well-structured code
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Security & Health

4.8h
Tech Debt (D)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (4)
All rows above produced by Repobility · https://repobility.com
Apache-2.0
License
5.8%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
85.8%
yaml
6.8%
markdown
5.5%
toml
1.9%

Frameworks

pytest

Concepts (2)

Same analyzer free for public repos: https://repobility.com
CategoryNameDescriptionConfidence
Citation: Repobility (2026). State of AI-Generated Code. https://repobility.com/research/
auto_descriptionProject DescriptionMAGI integrates bacterial, fungal, and viral communities from long-read metagenomic data into a unified multi-kingdom analysis framework. It automates the journey from raw reads to publication-ready cross-kingdom interaction networks.80%
auto_categoryTestingtesting70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/63822.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV