Home / cuhk-aim-group / neurodiscovery · GitHub

braingnn SKILL.md skillA

braingnn from cuhk-aim-group/neurodiscovery is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add cuhk-aim-group/neurodiscovery/braingnn@git:20261023.f74c2bd

Pins git:20261023.f74c2bd in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: cuhk-aim-group/neurodiscovery
Path: skills/brain_gnn/SKILL.md
Versions recorded: 4
Latest version: git:20261023.f74c2bd, committed Oct 23, 2026
First version recorded: May 5, 2026
Size: 6,655 bytes
Repository stars: 93
License: MIT

Use this model doc whenever the user wants to run BrainGNN for fMRI phenotype prediction, including graph construction, training, and evaluation. This document focuses on model-level usage and delegates upstream preprocessing to fmri-skill (and optionally hcpya-skill for HCP data).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# BrainGNN Model Doc

## Overview
BrainGNN is an interpretable graph neural network for fMRI analysis and phenotype prediction.

- Paper: Li et al., 2020, BrainGNN
- Official code: https://github.com/xxlya/BrainGNN_Pytorch/tree/main
- NeuroRuntime reimplementation: `models/braingnn/` (Windows-compatible, 无需 torch_sparse)
- Primary input: ROI-level fMRI connectivity matrices (per-subject .pt files)
- Primary output: phenotype prediction (classification/regression) + interpretable pooling scores

**Research use only.**

---

## NeuroRuntime 实现要点

NeuroRuntime 版本对原始 BrainGNN 做了以下关键改动：

1. **去除 torch_sparse 依赖**：`augment_adj` 不再使用 `spspmm` 做邻接矩阵平方，改用 `add_self_loops + remove_self_loops`，在 Windows 上可直接运行。
2. **全连接输入图**：data_adapter 构建 FULL graph（所有 i!=j 对），edge_attr = |Pearson r|。TopKPooling 负责选择，不在输入端做稀疏化。
3. **Fisher-z 反变换**：存储的 fc_matrix 是 Fisher-z，加载时用 `torch.tanh()` 还原为 Pearson r，对角线置零。
4. **支持 classification + regression 双任务**：通过 `--task` 参数切换，regression 时 nclass=1，输出 raw scalar，用 MSELoss。
5. **PyG >=2.3 兼容**：TopKPooling.weight 可能在 `pool.select.weight`，forward 中做了兼容处理。
6. **可选 T1 GM volume 融合**：`--include-t1` 将 z-scored GM volume 作为额外 1 维 node feature 拼接。

---
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cuhk-aim-group/neurodiscovery/braingnn@sha256:798acd3f2d4b08b0

The line at the top of this page pins the label git:20261023.f74c2bd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_a3aytmrh2653vk3p.svg)](https://markdownregistry.com/a/art_a3aytmrh2653vk3p)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between May 5, 2026 and Oct 23, 2026, about one every 57 days.

version	committed	commit	size	audit
git:20261023.f74c2bd latest	2026-10-23	f74c2bd	6,655 B	A	view · diff
git:20260515.bfd8dae	2026-05-15	bfd8dae	6,637 B	A	view · diff
git:20260506.f8d0216	2026-05-06	f8d0216	5,326 B	A	view · diff
git:20260505.e9ddd22	2026-05-05	e9ddd22	5,223 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (6655 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

cuhk-aim-group/neurodiscovery · 93 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_a3aytmrh2653vk3p
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/braingnn
GET https://markdownregistry.com/api/v1/blob/798acd3f2d4b08b03568a454787980e2851d2d0a0fa2096f0c8d255b018194ec

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.