How ayazxdev/aquadex works
AQUADEX is a web platform for analyzing environmental DNA sequencing data, classifying taxa, and exploring biodiversity and novelty results. Users upload sequence files, start a run, follow its status, then inspect summaries, visualizations, sequences, and downloadable artifacts. The FastAPI service coordinates run storage and pipeline execution; the real pipeline includes quality control, denoising, classification, embedding, novelty scoring, clustering, phylogeny, and reports. The tree also documents additional pipeline stages. Their exact runtime wiring is not established by the sampled excerpts, so those links are omitted.
Main entry points: pipeline_runner.py Pipeline runner · routes.py API routes · App.jsx Page navigation · pipeline.py Pipeline service
Components 22
Web interface
- Page navigation
frontend/src/App.jsx - Run submission
frontend/src/pages/Run.jsx - Results explorer
frontend/src/pages/Results.jsx
API and run services
- FastAPI app
backend/app/main.py - API routes
backend/app/api/routes.py - Run storage
backend/app/services/storage.py - Pipeline service
backend/app/services/pipeline.py
Bioinformatics analysis
- Pipeline runner
backend/app/pipeline/pipeline_runner.py - Quality control
backend/app/pipeline/pipeline_runner.py - Denoising
backend/app/pipeline/pipeline_runner.py - Taxonomic classification
backend/app/pipeline/pipeline_runner.py - Sequence embeddings
backend/app/pipeline/step_embeddings.py - Novelty scoring
backend/app/pipeline/pipeline_runner.py - Clustering
backend/app/pipeline/pipeline_runner.py - Phylogeny
backend/app/pipeline/pipeline_runner.py - Report generation
backend/app/pipeline/pipeline_runner.py
Results and artifacts
- Result aggregation
backend/app/results_aggregator.py - Results service
backend/app/services/results.py - Run files
Other components
- Research user
- Bioinformatics tools
- DNABERT-S model
Connections 27
- Research user → Page navigation: uses
- Page navigation → Run submission: navigates
- Page navigation → Results explorer: navigates
- Run submission → API routes: uploads and starts
- Results explorer → API routes: requests results
- FastAPI app → API routes: mounts
- API routes → Run storage: creates run directories
- API routes → Pipeline service: starts pipeline
- Pipeline service → Run storage: reads run files
- Pipeline service → Pipeline runner: runs analysis
- Pipeline runner → Quality control: runs
- Pipeline runner → Denoising: runs
- Pipeline runner → Taxonomic classification: runs
- Pipeline runner → Sequence embeddings: runs
- Pipeline runner → Novelty scoring: runs
- Pipeline runner → Clustering: runs
- Pipeline runner → Phylogeny: runs
- Pipeline runner → Report generation: runs
- Quality control → Bioinformatics tools: invokes
- Denoising → Bioinformatics tools: invokes
- Taxonomic classification → Bioinformatics tools: invokes
- Sequence embeddings → DNABERT-S model: loads
- Pipeline runner → Run files: writes outputs
- API routes → Results service: reads summaries
- Results service → Result aggregation: aggregates
- Result aggregation → Run files: reads run outputs
- API routes → Run files: serves artifacts