Minerva(Multi-target Interactive Network for Explainable Research and Visualization in Alzheimer’s Disease): a public web-based platform designed to support multi-target drug discovery in Alzheimer’s Disease through Explainable Artificial Intelligence (XAI) methodologies.
In the notebook, we provide a workflow similar to that provided in the final platform, to be soon published.

MINERVA brings together a large, high-quality, Alzheimer-focused dataset that includes:

• 70,960 small molecules
• annotated across 33 AD-relevant biological targets
• with data integrated from ChEMBL and the CADRO framework.

To enable flexible exploration of ligand activity and pharmacological relevance, the platform defines four activity thresholds, the relevant labels are provided
in the attached csv files:

• 10 μM (dataset_10micro.csv)
• 1 μM (dataset_1micro.csv)
• 100 nM (dataset_100nano.csv)
• 10 nM (dataset_10nano.csv)

These thresholds allow users to investigate ligand spaces ranging from weak binders to high-affinity compounds, supporting comparative analyses and multi-target profiling.