skills.rest
CUHK-AIM-Group
CUHK-AIM-GroupOFFICIAL
Explore all skills by this author →
WebsiteGitHub

connectome-discovery

Compares aligned connectome maps, computes permutation significance, and ranks neuromodulation targets.

89|5|Updated Mar 25, 2026
Search Tags:#neuroimaging#connectome#fmri#neuromodulation#permutation test#map similarity#target ranking
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill connectome-discovery-cuhk-aim-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: connectome-discovery
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/connectome-discovery
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill connectome-discovery-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, scipy, pandas.

What problem does it solve? Turning fitted connectome model outputs into interpretable network discoveries requires map alignment, statistical significance testing, and target ranking, which are tedious and error-prone to do by hand. ## Core Features & Use Cases - Map Similarity Scoring: Computes cosine similarity between aligned ROI or network maps sharing the same atlas and node ordering. - Permutation Significance Testing: Generates empirical P values from null distributions with recorded permutation counts and random seeds. - Target Ranking: Ranks candidate neuromodulation targets with atlas and coordinate-space metadata for downstream visualization. - Use Case: After training a CPM model on fMRI data, compare its edge-weight map against a reference network map, obtain a permutation P value, and produce a ranked list of candidate stimulation targets for a publication-ready figure. ## Quick Start Ask the assistant to compare two aligned connectome maps, compute the permutation P value, and rank the top neuromodulation targets using the connectome discovery workflow.

Frequently Asked Questions about connectome-discovery

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

FAQPage Schema
How do I compute a permutation P value for connectome map similarity?▼

Use the permutation_pvalue function in models/connectome_discovery/mapping.py after aligning both maps to the same atlas and node order. Record the observed score, null distribution settings, permutation count, and random seed for reproducibility.

How do I rank neuromodulation targets from connectome model outputs?▼

Use the rank_targets function in mapping.py, which returns target identifiers with similarity scores, ranks, and atlas/space metadata. Inputs must be aligned ROI or network maps derived from a fitted model such as CPM.

Does connectome-discovery train connectome predictive models?▼

No, it is an interpretation workflow, not a model implementation. Model training is handled by the cpm skill or other connectome model skills; this skill consumes their fitted outputs for similarity, significance, and ranking analysis.

What alignment is required before comparing two brain network maps?▼

Both maps must share the same atlas, node order, hemisphere convention, and value orientation. Any resampling or atlas mapping must be recorded, and atlas or space validation can be done with fmri-skill or nibabel-skill.

Can I visualize the ranked connectome targets on a brain surface?▼

Yes, route the final ROI or network values to the brain-visualization skill for surface or network rendering. Do not infer an anatomical target from an unlabeled edge vector before visualization.

Related Skills

Explore More Education & Research Skills→
sports-data-hqsports-data-hq
1

model-building

Build and validate sports prediction models with walk-forward validation and held-out evaluation.

Official
Advanced
hiyenwonghiyenwong
2

seizure-suppression-hub-stimulation

Identify epileptic brain network hubs and compute optimal electrical stimulation parameters.

Community
Advanced
ZK-TheoryZK-Theory
1

markov-null-design

Scaffolds Markov null model permutation tests for trajectory TDA pipelines.

Official
Intermediate
hiyenwonghiyenwong
2

bridge-neurodivergence-detection

Quantify neural divergence from typical developmental trajectories using graph-regularized modeling and deep generative networks.

Community
Advanced