Metapathpredict

C+ 73 completed
Api
infrastructure / python · small
134
Files
32,505
LOC
5
Frameworks
12
Languages

Pipeline State

completed
Run ID
#365267
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
77.67
Framework unique
Isolation
Last stage change
2026-05-10 03:35:34
Deduplication group #60506
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
All rows above produced by Repobility · https://repobility.com

AI Prompt

Create a full-stack service for classifying metagenomic DNA sequences. I need a RESTful API built with FastAPI that handles the classification logic, which involves a pipeline using contrastive learning and deep reinforcement learning. The service should allow users to upload FASTA files for prediction. On the frontend, use React and Tailwind CSS to provide a clean interface for uploading files and viewing the classification results (bacteria, eukaryotic, virus). Please structure the project to include necessary configuration files and testing setup using pytest.
python fastapi react tailwindcss deep-learning dna-classification restful-api pytorch reinforcement-learning
Generated by gemma4:latest

Catalog Information

A RESTful service that classifies DNA sequences using contrastive learning and deep reinforcement learning.

Description

This project exposes a high‑performance API that accepts raw DNA sequences and returns functional or disease‑associated predictions. It employs contrastive learning to generate robust sequence embeddings, then refines classification through a deep reinforcement learning policy that optimizes decision boundaries. The backend is built on FastAPI and PyTorch, with optional integration to Prometheus and Grafana for real‑time monitoring. Target users include computational biologists and genomics data scientists who need accurate, scalable sequence analysis without extensive labeled data. The service can be embedded into existing bioinformatics pipelines or used as a standalone microservice for rapid inference.

الوصف

يقدم هذا المشروع واجهة برمجة تطبيقات عالية الأداء تستقبل تسلسلات DNA خام وتعيد تنبؤات حول وظائفها أو ارتباطها بأمراض معينة. يستخدم التعلم التبايني لتوليد تمثيلات قوية للتسلسلات، ثم يُحسّن التصنيف عبر سياسة تعلم تعزيزي عميق تقوم بتحسين حدود القرار. يعتمد البنية التحتية على FastAPI وPyTorch، مع إمكانية التكامل مع Prometheus وGrafana لمراقبة الأداء في الوقت الحقيقي. يستهدف الباحثين في علم الأحياء الحاسوبي وعلماء بيانات الجينوم الذين يحتاجون إلى تحليل تسلسلي دقيق وقابل للتوسع دون الاعتماد على بيانات معنونة كبيرة. يمكن دمج الخدمة في خطوط أنابيب تحليل الجينوم الحالية أو استخدامها كخدمة ميكرو سرفيس مستقلة لتقديم استدلال سريع.

Novelty

8/10

Tags

dna-sequence-classification contrastive-learning deep-reinforcement-learning bioinformatics machine-learning predictive-modeling sequence-analysis data-science

Technologies

aws-sdk fastapi grafana matplotlib numpy plotly prometheus pydantic pytorch scikit-learn uvicorn

Claude Models

claude-opus-4.6

Quality Score

C+
73.0/100
Structure
86
Code Quality
72
Documentation
86
Testing
65
Practices
64
Security
55
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Code linting configured (ruff (possible))
  • Containerized deployment (Docker)
  • Properly licensed project

Weaknesses

  • 1 files with critical complexity need refactoring
  • 1549 duplicate lines detected \u2014 consider DRY refactoring
  • 3 'god files' with >500 LOC need decomposition

Security & Health

8.3h
Tech Debt (A)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (1)
Generated by Repobility's multi-pass static-analysis pipeline (https://repobility.com)
MIT
License
4.1%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
46.2%
json
27.1%
markdown
18.9%
typescript
4.2%
yaml
2.5%
toml
0.6%
javascript
0.1%
sql
0.1%
css
0.1%
html
0.0%
ini
0.0%
text
0.0%

Frameworks

FastAPI React pytest Tailwind CSS Vite

Concepts (2)

Repobility analysis · methodology at https://repobility.com/research/
CategoryNameDescriptionConfidence
Methodology: Repobility · https://repobility.com/research/state-of-ai-code-2026/
auto_descriptionProject DescriptionDeep learning framework for metagenomic DNA sequence classification using Contrastive Learning and Deep Reinforcement Learning.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/89441.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV