RAPTOR v2.2.1 — Dashboard Verified & Enhanced

What's New in v2.2.1

Dashboard (fully verified)

• All 9 Streamlit pages tested with real data
• 16 bugs fixed across Import DE, Ensemble, Optimization, Reports
• Quality page: 7 visualization tabs (PCA 2D/3D, RLE, dendrogram, BCV)
• Optimization: 4 scientific methods (FDR Control, Ground Truth, Stability, Reproducibility)
• Visualization: complete rewrite with 12 plot types, 7 gene expression styles
• Professional styling across all pages

Core

• 413 tests passing, 0 failures
• CLI: 55 commands tested, version reporting fixed
• Column name mapping between Module 7 and Modules 8/9

Install

pip install raptor-rnaseq==2.2.1

RAPTOR v2.2.0 - Ensemble Analysis + Enhanced Optimization

RAPTOR v2.2.0

RNA-seq Analysis Pipeline Testing and Optimization Resource

Highlights

NEW: Module 9 - Ensemble Analysis
Combine DE results from multiple methods (DESeq2, edgeR, limma) for robust consensus gene lists.

• Fisher's Method
• Brown's Method (correlation-aware)
• Robust Rank Aggregation (RRA)
• Voting Consensus
• Weighted Ensemble

EXPANDED: Module 8 - Parameter Optimization
Four optimization approaches (previously just one):

• Ground Truth optimization
• FDR Control optimization
• Stability-based optimization
• Reproducibility-based optimization

ENHANCED: Module 3 - Data Profiler
32-feature profiling with key BCV metric for ML-based pipeline recommendations.

---

Documentation

• User Guide - Complete tutorial
• API Docs - Python reference
• Quick Reference - Command cheat sheet
• Migration Guide - Upgrade from v2.1.x

---

Breaking Changes

Module 8 renamed and expanded. Pipeline structure reorganized.

See CHANGELOG and Migration Guide for details.

---

Installation

PyPI:

pip install raptor-rnaseq==2.2.0

Conda:

# Core environment
conda env create -f environment.yml

# Full environment (includes STAR, Salmon, R packages)
conda env create -f environment-full.yml

---

Full Changelog

See CHANGELOG.md for complete details.

---

Acknowledgments

Thanks to the bioinformatics community for feedback and suggestions!

Citation: See CITATION.cff
DOI: 10.5281/zenodo.17607161

RAPTOR v2.1.2 - Hotfix

RAPTOR v2.1.2 - Hotfix

Release Date: December 30, 2025

Fixed

• Python 3.8-3.11 compatibility: removed backslash in f-string expression in automated_reporting.py

Details

The v2.1.1 release contained Python 3.12+ syntax (\n inside f-string {} expression) that caused SyntaxError on Python 3.8-3.11.

Thanks to @ulbivin for reporting this issue.

Upgrade

pip install raptor-rnaseq --upgrade

Full Changelog

See CHANGELOG.md

RAPTOR v2.1.1 - Adaptive Threshold Optimizer

RAPTOR v2.1.1 - Adaptive Threshold Optimizer

Release Date: December 15, 2025

New Feature: Adaptive Threshold Optimizer (ATO)

Stop using arbitrary thresholds! ATO provides data-driven significance cutoffs for DE analysis.

Features:

• Data-driven logFC threshold selection
• Multiple p-value adjustment methods (BH, BY, Storey q-value, Holm, Bonferroni)
• π₀ estimation for true null proportion
• Three analysis goals: discovery, balanced, validation
• Auto-generated publication methods text
• New dashboard page

Quick Start

from raptor.threshold_optimizer import optimize_thresholds
result = optimize_thresholds(de_results, goal='discovery')
print(result.methods_text)  # Copy to paper!

Install

pip install raptor-rnaseq --upgrade

Full Changelog: See CHANGELOG.md

🦖 RAPTOR v2.1.0 - ML Intelligence & Interactive Dashboard

This release represents a major evolution of RAPTOR, introducing artificial intelligence, interactive visualization, and cloud computing capabilities while maintaining full backward compatibility with v2.0.0.

8 New Features

1. ML-Based Pipeline Recommendations - 87% accuracy
2. Interactive Web Dashboard - Zero-coding Streamlit interface
3. Advanced Quality Assessment - Batch effect detection
4. Ensemble Analysis - Combine multiple pipelines
5. Real-Time Resource Monitoring - CPU/memory tracking
6. Parameter Optimization - Bayesian & grid search
7. Automated Reporting - Publication-ready reports
8. Cloud Integration - AWS, GCP, Azure support

Installation

pip install git+https://github.com/AyehBlk/RAPTOR.git@v2.1.0

Links

• DOI: 10.5281/zenodo.17607162
• Docs: See docs/ folder

---

✅ Full backward compatibility with v2.0.0

# RAPTOR v2.0.0 - Official Release

🎉 First Official Release

We're excited to announce the first official release of RAPTOR (RNA-seq Analysis Pipeline Testing and Optimization Resource) - an intelligent framework for RNA-seq pipeline selection and benchmarking!

---

🆕 What's New in v2.0.0

Core Features

Intelligent Pipeline Recommendation

• Automatic data profiling (BCV, depth, library size, zero-inflation)
• Multi-criteria scoring algorithm
• Recommendations in seconds
• Clear explanatory reasoning

Comprehensive Benchmarking Framework

• Systematic comparison of 8 production-ready pipelines
• Accuracy, runtime, and memory metrics
• Interactive reports with visualizations
• Concordance analysis

Eight Complete Pipelines

1. STAR-RSEM-DESeq2 (Gold standard)
2. HISAT2-StringTie-Ballgown (Novel transcript discovery)
3. Salmon-edgeR (Recommended balance)
4. Kallisto-Sleuth (Ultra-fast)
5. STAR-HTSeq-limma-voom (Complex designs)
6. STAR-featureCounts-NOISeq (Small samples)
7. Bowtie2-RSEM-EBSeq (Memory-efficient)
8. HISAT2-Cufflinks-Cuffdiff (Legacy)

Data Simulation

• Generate synthetic RNA-seq data with known ground truth
• Validate pipeline performance
• Support benchmarking studies

---

✨ Key Highlights

• 84% agreement with expert recommendations across 50 diverse datasets
• 97% of expert choices in top-3 recommendations
• Up to 23% difference in DE genes detected between pipelines
• Up to 6.7× runtime differences between methods
• Fully open source under MIT License

---

📦 Installation

Via pip (Recommended)

pip install raptor-rnaseq

Via conda

conda env create -f environment.yml
conda activate raptor

From source

git clone https://github.com/AyehBlk/RAPTOR.git
cd RAPTOR
pip install -e .

---

🚀 Quick Start

Get a Pipeline Recommendation

# Command line
raptor profile --counts data.csv --metadata samples.csv

# Python API
from raptor import RNAseqDataProfiler, PipelineRecommender

profiler = RNAseqDataProfiler(counts, metadata)
profile = profiler.profile()

recommender = PipelineRecommender()
recommendations = recommender.recommend(profile)

Run Comprehensive Benchmarking

raptor benchmark --data fastq/ --pipelines 1,3,4,5 --output results/

---

📚 Documentation

Complete documentation available at:

• User Guide
• API Reference
• Tutorial
• Pipeline Specifications

Example workflows:

• Basic Usage
• Benchmarking
• Custom Pipelines

---

🎓 Citation

If you use RAPTOR in your research, please cite:

@software{bolouki_2025_raptor,
  author       = {Bolouki, Ayeh},
  title        = {RAPTOR: RNA-seq Analysis Pipeline Testing and Optimization Resource},
  year         = 2025,
  publisher    = {Zenodo},
  version      = {v2.0.0},
  doi          = {10.5281/zenodo.17607161},
  url          = {https://doi.org/10.5281/zenodo.17607161}
}

Plain text citation:

Bolouki, A. (2025). RAPTOR: RNA-seq Analysis Pipeline Testing and Optimization Resource (Version 2.0.0) [Software]. Zenodo. https://doi.org/10.5281/zenodo.17607161

---

🛠️ System Requirements

Minimum:

• Python 3.8+
• 8 GB RAM
• 4 CPU cores

Recommended:

• Python 3.10+
• 32 GB RAM
• 8+ CPU cores

Operating Systems:

• Linux (Ubuntu 20.04+, CentOS 7+)
• macOS (10.14+)
• Windows (via WSL2)

---

📊 Validation Results

Tested on 50 diverse RNA-seq datasets:

• Sample sizes: 3-100 per group
• BCV range: 0.12-0.95
• Sequencing depths: 8M-50M reads
• Multiple organisms and tissue types

Performance:

• 84% agreement with expert recommendations
• 97% of expert choices in top-3 recommendations
• High concordance with published benchmarks

---

🔗 Links

• GitHub Repository: https://github.com/AyehBlk/RAPTOR
• Zenodo Archive: https://doi.org/10.5281/zenodo.17607161
• Documentation: https://github.com/AyehBlk/RAPTOR/tree/main/docs
• Issue Tracker: https://github.com/AyehBlk/RAPTOR/issues
• PyPI Package: https://pypi.org/project/raptor-rnaseq/

---

🤝 Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Ways to contribute:

• Report bugs or request features (GitHub Issues)
• Submit pull requests
• Improve documentation
• Share your use cases
• Add new pipeline implementations

---

📄 License

RAPTOR is released under the MIT License. See LICENSE for details.

---

👥 Authors

Ayeh Bolouki

• NARILIS, University of Namur, Belgium
• Email: ayehbolouki1988@gmail.com
• GitHub: @AyehBlk

---

🙏 Acknowledgments

We thank:

• The developers of all integrated tools (STAR, Salmon, DESeq2, edgeR, etc.)
• The open-source bioinformatics community
• Early users and testers for valuable feedback

---

📈 What's Next?

Planned for v2.1.0:

• Single-cell RNA-seq support
• Additional pipeline implementations
• Cloud/HPC integration
• Web interface
• Enhanced visualization

Stay tuned! Star/Watch this repository for updates.

---

🐛 Known Issues

See GitHub Issues for current known issues and workarounds.

---

📞 Support

Need help?

• Check documentation
• Search existing issues
• Open a new issue
• Email: ayehbolouki1988@gmail.com

---

⭐ Show Your Support

If RAPTOR helps your research:

• ⭐ Star this repository
• 📢 Share with colleagues
• 📝 Cite in your papers
• 🐛 Report bugs or suggest features
• 🤝 Contribute code or documentation

---

Thank you for using RAPTOR! 🎉

We hope RAPTOR makes your RNA-seq analyses more informed, reproducible, and efficient.

---

Release Date: 2025
Version: 2.0.0
DOI: 10.5281/zenodo.17607161
License: MIT

---

Stop guessing. Start benchmarking. Choose wisely. 🚀