braingnn skillA
braingnn is agent-read markdown (skill) from cuhk-aim-group/neurodiscovery: 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)..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns 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 - NeuroClaw 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.** --- ## NeuroClaw 实现要点 NeuroClaw 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
mdr add cuhk-aim-group/neurodiscovery/braingnn@git:20260515.bfd8daemdr add cuhk-aim-group/neurodiscovery/braingnn@sha256:19a92bfd04590713Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_a3aytmrh2653vk3p)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260515.bfd8dae latest | 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
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6637 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
cuhk-aim-group/neurodiscovery · 91 stars · license MIT · pushed 2026-09-22 · 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/19a92bfd04590713549e82856f857365a1e9160872d6a78d2713704c99a6d325
Your agent 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.