MCP App StoreMCP App Store
from neuroclaw73
PyG-based interpretable graph neural network for connectome (fMRI) phenotype prediction, with MPConv message MLP and support for post-hoc edge-mask explanation.
IBGNN (Interpretable Brain Graph Neural Network) provides a PyTorch-Geometric implementation for connectome-based phenotype prediction. It replaces standard GCN message passing with an MLP-based MPConv that computes messages from [x_i, x_j, edge_attr], enabling richer edge-aware representation and supporting downstream edge-mask explanation workflows. NeuroClaw's reimplementation focuses on the encoder and training pipelines for classification and regression tasks on fMRI connectomes.
Use IBGNN when you need to predict subjects' phenotypes (e.g., diagnosis, age, gender) from brain connectivity graphs and want interpretable edge-level insights. Appropriate for research experiments, model comparisons, or when you need a GNN that natively supports attention/edge importance analysis on connectome-style inputs.
Likely used in research or model-execution agents that support Python and PyTorch (OpenClaw/ClawShell, Python-capable agent runtimes).
IBGNN is an interpretable brain GNN skill for fMRI connectome phenotype prediction, part of the NeuroClaw project. Both bundled scripts (data adapter and training reference) are well-structured with argparse CLIs and docstrings, but fail at import due to missing PyTorch/PyG dependencies — expected for domain-specific ML tools. SKILL.md is thorough with architecture diagrams, parameter tables, and debugging notes (written in Chinese). No security concerns whatsoever.
torchtorch_geometricsklearnDomain-specific neuroscience ML skill. Clean code, no security issues. Scripts are reference implementations meant to run within the NeuroClaw project ecosystem, not standalone. Useful for a narrow research audience.
ASL Skill (Arterial Spin Labeling)
Modality-layer skill for Arterial Spin Labeling (ASL) perfusion MRI processing: preprocessing, M0 normalization, CBF quantification, PVC, and QC.
fMRI ICA Network Decomposition
Unsupervised resting-state network decomposition using Independent Component Analysis (ICA) for fMRI data.
ToolUniverse — Neuroscience Research
A neuroscience research skill that directs agents to verify facts via PubMed/Allen/WormBase, perform computational neuroscience calculations in Python, and reas
PyTorch Geometric (PyG) Guide
Authoritative guide for building and scaling Graph Neural Networks using PyTorch Geometric: data, layers, training patterns, and common pitfalls.
fMRI ICA Network Decomposition
Unsupervised resting-state network decomposition using Independent Component Analysis (ICA) for fMRI data.