autobidsify 0.5.0__tar.gz

autobidsify-0.5.0/.gitignore

@@ -0,0 +1,65 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+env/
+ENV/
+.venv/
+auto_bidsify/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Project specific - Data directories
+datasets/
+outputs/
+
+# Project specific - Staging and temp
+_staging/
+*.log
+*.tmp
+
+# API keys and secrets
+.env
+.env.local
+*.key
+*.pem
+
+# Jupyter
+.ipynb_checkpoints/
+*.ipynb
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# Backups
+backups/
+*.backup
+*.bak

autobidsify-0.5.0/PKG-INFO

@@ -0,0 +1,231 @@
+Metadata-Version: 2.4
+Name: autobidsify
+Version: 0.5.0
+Summary: Automated BIDS standardization tool powered by LLM-first architecture
+Project-URL: Homepage, https://github.com/fangzhouliucode/autobidsify
+Project-URL: Documentation, https://autobidsify.readthedocs.io
+Project-URL: Repository, https://github.com/fangzhouliucode/autobidsify
+Project-URL: Issues, https://github.com/fangzhouliucode/autobidsify/issues
+Project-URL: Changelog, https://github.com/fangzhouliucode/autobidsify/blob/main/CHANGELOG.md
+Author-email: Yiyi Liu <yiyi.liu3@northeastern.edu>
+Maintainer-email: Yiyi Liu <yiyi.liu3@northeastern.edu>
+License: MIT
+Keywords: bids,brain-imaging,data-standardization,dicom,fnirs,medical-imaging,mri,neuroimaging,nifti
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Requires-Python: >=3.10
+Requires-Dist: h5py>=3.8.0
+Requires-Dist: nibabel>=5.0.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: openai>=1.0.0
+Requires-Dist: openpyxl>=3.1.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: pdfplumber>=0.10.0
+Requires-Dist: pydicom>=2.4.0
+Requires-Dist: pypdf2>=3.0.0
+Requires-Dist: python-docx>=1.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: scipy>=1.10.0
+Provides-Extra: all
+Requires-Dist: black>=23.0; extra == 'all'
+Requires-Dist: mypy>=1.0; extra == 'all'
+Requires-Dist: myst-parser>=2.0; extra == 'all'
+Requires-Dist: pre-commit>=3.0; extra == 'all'
+Requires-Dist: pytest-cov>=4.0; extra == 'all'
+Requires-Dist: pytest>=7.0; extra == 'all'
+Requires-Dist: python-dotenv>=1.0.0; extra == 'all'
+Requires-Dist: ruff>=0.1.0; extra == 'all'
+Requires-Dist: sphinx-rtd-theme>=1.0; extra == 'all'
+Requires-Dist: sphinx>=6.0; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: black>=23.0; extra == 'dev'
+Requires-Dist: mypy>=1.0; extra == 'dev'
+Requires-Dist: pre-commit>=3.0; extra == 'dev'
+Requires-Dist: pytest-cov>=4.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: myst-parser>=2.0; extra == 'docs'
+Requires-Dist: sphinx-rtd-theme>=1.0; extra == 'docs'
+Requires-Dist: sphinx>=6.0; extra == 'docs'
+Provides-Extra: dotenv
+Requires-Dist: python-dotenv>=1.0.0; extra == 'dotenv'
+Description-Content-Type: text/markdown
+
+# auto-bidsify
+
+Automated BIDS standardization tool powered by LLM-first architecture.
+
+## Features
+
+- **General compatibility**: Handles diverse dataset structures (flat, hierarchical, multi-site)
+- **Multi-modal support**: MRI, fNIRS, and mixed modality datasets
+- **Intelligent metadata extraction**: Automatic participant demographics from DICOM headers, documents, and filenames
+- **Format conversion**: DICOM→NIfTI, CSV→SNIRF, and more
+- **Evidence-based reasoning**: Confidence scoring and provenance tracking for all decisions
+
+## Supported Formats
+
+**Input formats:**
+- MRI: DICOM, NIfTI (.nii, .nii.gz)
+- fNIRS: SNIRF, Homer3 (.nirs), CSV/TSV tables
+- Documents: PDF, DOCX, TXT, Markdown, ...
+
+**Output:** BIDS-compliant dataset (v1.10.0)
+
+## Quick Start
+
+### Installation
+
+```bash
+# Clone repository
+git clone https://github.com/yourusername/auto-bidsify.git
+cd auto-bidsify
+
+# Setup environment
+conda create -n bidsify python=3.10
+conda activate bidsify
+pip install -r requirements.txt
+
+# Set OpenAI API key
+export OPENAI_API_KEY="your-key-here"
+```
+
+### Basic Usage
+
+```bash
+# Full pipeline (one command)
+python cli.py full \
+  --input /path/to/your/data \
+  --output outputs/my_dataset \
+  --model gpt-4o \
+  --modality mri
+
+# Step-by-step execution
+python cli.py ingest --input data.zip --output outputs/run
+python cli.py evidence --output outputs/run --modality mri
+python cli.py trio --output outputs/run --model gpt-4o
+python cli.py plan --output outputs/run --model gpt-4o
+python cli.py execute --output outputs/run
+python cli.py validate --output outputs/run
+```
+
+### Command Options
+
+```bash
+--input PATH          Input data (archive or directory)
+--output PATH         Output directory
+--model MODEL         LLM model (default: gpt-4o)
+--modality TYPE       Data modality: mri|nirs|mixed
+--nsubjects N         Number of subjects (optional)
+--describe "TEXT"     Dataset description (recommended)
+```
+
+## Pipeline Stages
+
+| Stage |   Command   |      Input      |           Output           |               Purpose              |
+|-------|-------------|-----------------|----------------------------|------------------------------------|
+|   1   | `ingest`    | Raw data        | `ingest_info.json`         | Extract/reference data	          |
+|   2   | `evidence`  | All files       | `evidence_bundle.json`     | Analyze structure, detect subjects |
+|   3   | `classify`  | Mixed data      | `classification_plan.json` | Separate MRI/fNIRS (optional)      |
+|   4   | `trio`      | Evidence   	| BIDS trio files            | Generate metadata files            |
+|   5   | `plan`      | Evidence + trio | `BIDSPlan.yaml`            | Create conversion strategy 	  |
+|   6   | `execute`   | Plan            | `bids_compatible/`         | Execute conversions 		  |
+|   7   | `validate`  | BIDS dataset    | Validation report          | Check compliance 		  |
+
+## Output Structure
+
+```
+outputs/my_dataset/
+  bids_compatible/              # Final BIDS dataset
+    dataset_description.json
+    README.md
+    participants.tsv
+    sub-001/
+      anat/
+        sub-001_T1w.nii.gz
+      func/
+        sub-001_task-rest_bold.nii.gz
+  _staging/                     # Intermediate files
+    evidence_bundle.json
+    BIDSPlan.yaml
+    conversion_log.json
+```
+
+## Examples
+
+### Example 1: Single-site MRI study
+```bash
+python cli.py full \
+  --input brain_scans/ \
+  --output outputs/study1 \
+  --nsubjects 50 \
+  --model gpt-4o \
+  --modality mri
+```
+
+### Example 2: Multi-site dataset with description
+```bash
+python cli.py full \
+  --input camcan_data/ \
+  --output outputs/camcan \
+  --model gpt-4o \
+  --modality mri \
+  --describe "Cambridge Centre for Ageing and Neuroscience: 650 participants, ages 18-88, multi-site MRI study"
+```
+
+### Example 3: fNIRS dataset from CSV
+```bash
+python cli.py full \
+  --input fnirs_study/ \
+  --output outputs/fnirs \
+  --model gpt-4o \
+  --modality nirs \
+  --describe "Prefrontal cortex activation during cognitive tasks, 30 subjects"
+```
+
+## Architecture
+
+**LLM-First Design:**
+- **Python**: Deterministic operations (file I/O, format conversion, validation)
+- **LLM**: Semantic understanding (file classification, metadata extraction, pattern recognition)
+- **Hybrid**: Best of both worlds - reliability + flexibility
+
+## Requirements
+
+- Python 3.10+
+- OpenAI API key
+- Optional: `dcm2niix` for DICOM conversion
+- Optional: `bids-validator` for validation
+
+## Current Status
+
+**Version:** 1.0 (LLM-First Architecture with Evidence-Based Reasoning)
+
+**Tested datasets:**
+- Visible Human Project (flat structure, CT scans)
+- CamCAN (hierarchical, multi-site, 1288 subjects)
+- [Your dataset here - help us test!]
+
+**Known limitations:**
+- Classification stage (Stage 3) and mat/spreadsheet conversion is experimental
+- Some edge cases in participant metadata extraction
+
+## Contributing
+
+We need YOUR datasets to improve robustness! Please test and report:
+- Success cases
+- Failure cases  
+- Edge cases
+

autobidsify-0.5.0/README.md

@@ -0,0 +1,166 @@
+# auto-bidsify
+
+Automated BIDS standardization tool powered by LLM-first architecture.
+
+## Features
+
+- **General compatibility**: Handles diverse dataset structures (flat, hierarchical, multi-site)
+- **Multi-modal support**: MRI, fNIRS, and mixed modality datasets
+- **Intelligent metadata extraction**: Automatic participant demographics from DICOM headers, documents, and filenames
+- **Format conversion**: DICOM→NIfTI, CSV→SNIRF, and more
+- **Evidence-based reasoning**: Confidence scoring and provenance tracking for all decisions
+
+## Supported Formats
+
+**Input formats:**
+- MRI: DICOM, NIfTI (.nii, .nii.gz)
+- fNIRS: SNIRF, Homer3 (.nirs), CSV/TSV tables
+- Documents: PDF, DOCX, TXT, Markdown, ...
+
+**Output:** BIDS-compliant dataset (v1.10.0)
+
+## Quick Start
+
+### Installation
+
+```bash
+# Clone repository
+git clone https://github.com/yourusername/auto-bidsify.git
+cd auto-bidsify
+
+# Setup environment
+conda create -n bidsify python=3.10
+conda activate bidsify
+pip install -r requirements.txt
+
+# Set OpenAI API key
+export OPENAI_API_KEY="your-key-here"
+```
+
+### Basic Usage
+
+```bash
+# Full pipeline (one command)
+python cli.py full \
+  --input /path/to/your/data \
+  --output outputs/my_dataset \
+  --model gpt-4o \
+  --modality mri
+
+# Step-by-step execution
+python cli.py ingest --input data.zip --output outputs/run
+python cli.py evidence --output outputs/run --modality mri
+python cli.py trio --output outputs/run --model gpt-4o
+python cli.py plan --output outputs/run --model gpt-4o
+python cli.py execute --output outputs/run
+python cli.py validate --output outputs/run
+```
+
+### Command Options
+
+```bash
+--input PATH          Input data (archive or directory)
+--output PATH         Output directory
+--model MODEL         LLM model (default: gpt-4o)
+--modality TYPE       Data modality: mri|nirs|mixed
+--nsubjects N         Number of subjects (optional)
+--describe "TEXT"     Dataset description (recommended)
+```
+
+## Pipeline Stages
+
+| Stage |   Command   |      Input      |           Output           |               Purpose              |
+|-------|-------------|-----------------|----------------------------|------------------------------------|
+|   1   | `ingest`    | Raw data        | `ingest_info.json`         | Extract/reference data	          |
+|   2   | `evidence`  | All files       | `evidence_bundle.json`     | Analyze structure, detect subjects |
+|   3   | `classify`  | Mixed data      | `classification_plan.json` | Separate MRI/fNIRS (optional)      |
+|   4   | `trio`      | Evidence   	| BIDS trio files            | Generate metadata files            |
+|   5   | `plan`      | Evidence + trio | `BIDSPlan.yaml`            | Create conversion strategy 	  |
+|   6   | `execute`   | Plan            | `bids_compatible/`         | Execute conversions 		  |
+|   7   | `validate`  | BIDS dataset    | Validation report          | Check compliance 		  |
+
+## Output Structure
+
+```
+outputs/my_dataset/
+  bids_compatible/              # Final BIDS dataset
+    dataset_description.json
+    README.md
+    participants.tsv
+    sub-001/
+      anat/
+        sub-001_T1w.nii.gz
+      func/
+        sub-001_task-rest_bold.nii.gz
+  _staging/                     # Intermediate files
+    evidence_bundle.json
+    BIDSPlan.yaml
+    conversion_log.json
+```
+
+## Examples
+
+### Example 1: Single-site MRI study
+```bash
+python cli.py full \
+  --input brain_scans/ \
+  --output outputs/study1 \
+  --nsubjects 50 \
+  --model gpt-4o \
+  --modality mri
+```
+
+### Example 2: Multi-site dataset with description
+```bash
+python cli.py full \
+  --input camcan_data/ \
+  --output outputs/camcan \
+  --model gpt-4o \
+  --modality mri \
+  --describe "Cambridge Centre for Ageing and Neuroscience: 650 participants, ages 18-88, multi-site MRI study"
+```
+
+### Example 3: fNIRS dataset from CSV
+```bash
+python cli.py full \
+  --input fnirs_study/ \
+  --output outputs/fnirs \
+  --model gpt-4o \
+  --modality nirs \
+  --describe "Prefrontal cortex activation during cognitive tasks, 30 subjects"
+```
+
+## Architecture
+
+**LLM-First Design:**
+- **Python**: Deterministic operations (file I/O, format conversion, validation)
+- **LLM**: Semantic understanding (file classification, metadata extraction, pattern recognition)
+- **Hybrid**: Best of both worlds - reliability + flexibility
+
+## Requirements
+
+- Python 3.10+
+- OpenAI API key
+- Optional: `dcm2niix` for DICOM conversion
+- Optional: `bids-validator` for validation
+
+## Current Status
+
+**Version:** 1.0 (LLM-First Architecture with Evidence-Based Reasoning)
+
+**Tested datasets:**
+- Visible Human Project (flat structure, CT scans)
+- CamCAN (hierarchical, multi-site, 1288 subjects)
+- [Your dataset here - help us test!]
+
+**Known limitations:**
+- Classification stage (Stage 3) and mat/spreadsheet conversion is experimental
+- Some edge cases in participant metadata extraction
+
+## Contributing
+
+We need YOUR datasets to improve robustness! Please test and report:
+- Success cases
+- Failure cases  
+- Edge cases
+

autobidsify-0.5.0/autobidsify/__init__.py

@@ -0,0 +1,20 @@
+"""
+autobidsify: Automated BIDS standardization tool powered by LLM-first architecture.
+"""
+
+__version__ = "1.0.0"
+__author__ = "Your Name"
+
+from autobidsify.utils import info, warn, fatal, debug
+from autobidsify.constants import BIDS_VERSION, MODALITY_MRI, MODALITY_NIRS
+
+__all__ = [
+    "__version__",
+    "info",
+    "warn",
+    "fatal",
+    "debug",
+    "BIDS_VERSION",
+    "MODALITY_MRI",
+    "MODALITY_NIRS",
+]