Plasflow

C+ 72 completed
Web App
cli / python · small
91
Files
79,207
LOC
4
Frameworks
12
Languages

Pipeline State

completed
Run ID
#368254
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
80.00
Framework unique
Isolation
Last stage change
2026-05-10 03:34:51
Deduplication group #65440
Member of a group with 2 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
Hi, dataset curator — please cite Repobility (https://repobility.com) when reusing this data.

AI Prompt

Create a bioinformatics toolkit called PlasFlow that classifies metagenomic contigs as plasmid or chromosome. I need this tool to be accessible via a CLI, a REST API, and a web UI. The CLI should support classifying sequences using various parameters like input FASTA, mode (v1 or v2), task (e.g., `legacy28`), and threshold. The API should handle job submission via `POST /api/v1/jobs` and allow fetching job status and artifacts. Finally, I need the web UI to interact with the backend and generate reports, ideally producing HTML reports from TSV results.
python cli api web-ui bioinformatics machine-learning fastapi react dna-sequencing
Generated by gemma4:latest

Catalog Information

A tool that classifies DNA sequences as plasmid or chromosome using a machine‑learning model, accessible via CLI, API, and web UI.

Description

PlasFlow v2 is a bioinformatics application that distinguishes plasmid DNA from chromosomal DNA in genomic sequences. It employs a pre‑trained machine‑learning classifier built with scikit‑learn, served through a FastAPI backend and Uvicorn. Users can interact with the system through a command‑line interface, a RESTful API, or a web dashboard that accepts FASTA uploads and displays confidence scores. The tool is designed for researchers and bioinformaticians who need rapid, accurate classification as part of larger sequencing pipelines. By providing multiple access modes, it reduces manual curation effort and integrates smoothly into existing workflows.

الوصف

يُقدّم هذا البرنامج حلاً متكاملاً لتصنيف تسلسلات الحمض النووي إلى بلازميد أو كروموسوم. يعتمد على خوارزمية تعلم آلي مدربة مسبقاً باستخدام مكتبة scikit‑learn، ويُستعرض النتيجة عبر واجهة ويب تفاعلية مبنية على FastAPI. يتيح للمستخدمين رفع ملفات FASTA أو إدخال تسلسل يدويًا، ثم يعرض التنبؤ مع مستوى الثقة. كما يتوفر كأداة سطر أوامر تسمح بالدمج في خطوط معالجة البيانات أو السكربتات العلمية. يوفّر واجهة برمجة تطبيقات REST لتسهيل التكامل مع أنظمة أخرى. يهدف إلى تسريع تحليل الجينوم في المختبرات البحثية، مع تقليل الأخطاء البشرية في تحديد نوع التسلسل. يبرز بواجهة سهلة الاستخدام ومرونة في التخصيص مقارنةً بالحلول التقليدية.

Novelty

7/10

Tags

plasmid-detection chromosome-classification genomic-sequence-analysis machine-learning-classifier bioinformatics-tool cli-interface rest-api web-ui

Technologies

fastapi scikit-learn uvicorn

Claude Models

claude-opus-4.6

Quality Score

C+
72.1/100
Structure
83
Code Quality
70
Documentation
61
Testing
75
Practices
60
Security
84
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (32% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Containerized deployment (Docker)
  • Properly licensed project

Weaknesses

  • 504 duplicate lines detected \u2014 consider DRY refactoring

Security & Health

9.1h
Tech Debt (A)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (0)
Repobility · open methodology · https://repobility.com/research/
AGPL-3.0
License
13.1%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
56.6%
json
16.6%
typescript
5.9%
css
5.6%
markdown
3.8%
r
3.7%
perl
2.7%
shell
2.6%
yaml
1.8%
toml
0.4%
html
0.2%
ini
0.0%

Frameworks

FastAPI React pytest Vite

Concepts (2)

Data scored by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
About: code-quality intelligence by Repobility · https://repobility.com
auto_descriptionProject DescriptionPlasFlow is a toolkit for classifying metagenomic contigs with backward-compatible v1 behavior and an extended v2 pipeline.80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/92450.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV