ppmi-skill

Orchestrates BIDS validation and multimodal processing of PPMI Parkinson's disease neuroimaging data.

89|5|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill ppmi-skill-cuhk-aim-group
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ppmi-skill
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/ppmi-skill
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill ppmi-skill-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, and includes scripts (resource) components.

What problem does it solve? Processing the Parkinson's Progression Markers Initiative (PPMI) dataset requires coordinating BIDS validation, structural MRI, resting-state fMRI, diffusion MRI, phenotype extraction, and quality control across a controlled-access multi-site cohort, which is error-prone when done manually. ## Core Features & Use Cases - BIDS Validation: Validates PPMI BIDS directory structure, diagnostic group completeness, and modality presence, producing a compliance report via scripts/validate_ppmi.py. - Multimodal Delegation: Delegates sMRI, rs-fMRI, and dMRI processing to dedicated modality skills (smri-skill, fmri-skill, dwi-skill) through a confirmed, numbered execution plan. - Phenotype Extraction & QC: Merges clinical measures (MDS-UPDRS, MoCA, UPSIT, DAT binding, CSF biomarkers) into a single CSV and generates per-subject QC summaries with framewise-displacement exclusion lists. - Use Case: A researcher with approved PPMI access asks to process the local BIDS export; the skill validates the dataset, runs all three imaging pipelines, merges phenotype tables, and outputs a QC summary with an exclusion list under ppmi_output/. ## Quick Start Ask the agent to run the end-to-end PPMI multimodal pipeline on your local BIDS dataset, including validation, sMRI, rs-fMRI, dMRI processing, phenotype extraction, and QC.

Frequently Asked Questions about ppmi-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I process PPMI neuroimaging data end to end?

Request the PPMI workflow and the skill generates a numbered plan covering BIDS validation, sMRI, rs-fMRI, and dMRI processing, then phenotype extraction and QC. After you confirm the plan, each step is delegated to the corresponding modality skill and outputs are saved under ppmi_output/.

How do I validate a PPMI BIDS dataset?

Run scripts/validate_ppmi.py with --input pointing to the BIDS directory and --output for the report path. It checks T1w, rs-fMRI, task-fMRI, dMRI, and DaTscan presence per subject and writes a CSV compliance report with a summary.

How do I access and download PPMI data?

PPMI data requires a signed Data Use Agreement and an online application through ppmi-info.org, typically reviewed within one week. After approval, download via the PPMI project in LONI IDA and record export date, filters, modalities, and checksums.

What clinical measures can be extracted from PPMI phenotype files?

The phenotype extraction script merges MDS-UPDRS motor scores, Hoehn and Yahr staging, MoCA cognition, UPSIT olfaction, RBDSQ sleep screening, DAT striatal binding ratios, and CSF biomarkers. It aligns these measures with the imaging subject list into one CSV.

Why are subjects excluded in PPMI quality control?

Subjects are excluded when mean framewise displacement from fMRIPrep confounds exceeds the 0.3 mm threshold, indicating excessive head motion. The QC script writes a per-subject summary and a separate exclusion list with reasons.

What are the limitations of the PPMI dataset for analysis?

PPMI is controlled data that cannot be redistributed and is governed by its DUA. It is a multi-site study so site effects should be modeled, and DaTscan SPECT may not follow standard BIDS conventions.