MIND-updated: Mechanistic Repositioning Network with Indications (6,761 indication edges, 5-fold CV splits)

Extended version of the MIND (Mechanistic Repositioning Network with Indications) knowledge graph with 1,391 new FDA-approved drug indication edges sourced from DrugCentral, remapped via a DrugCentral→MeSH→DOID pipeline. Contents: mind_updated.tsv — Full updated knowledge graph (9,652,116 edges, 250,035 nodes, 22 relation types)splits_updated.zip — 5-fold stratified cross-validation splits (676 test/valid indication edges per fold)drug_indications_with_ids.tsv — The 6,761 indication edges with CHEBI/DOID identifiersmapping_report.csv — DrugCentral→MeSH→DOID remapping provenanceKey statistics: 6,761 total indication edges (up from 5,370 in original MIND), 9,652,116 total edges, 250,035 nodes, 9 node types, 22 relation types. Used in WeightedKgBlend (doi:10.1101/2024.07.16.603664) and NeuralPathReasoning-MIND for drug repurposing benchmarks. Original MIND dataset: doi:10.5281/zenodo.8117748 Zenodo record 20184623, published 2026-05-14, 4 file(s) totalling 639.4 MB (3 tabular, 1 archive).

Category
Drug Discovery
Provider
Meghamala Sinha and 3 others
License
CC-BY-4.0
DOI
10.5281/zenodo.20184623
Hosted on
Zenodo
Access
Free and public. No account with the data provider is needed.
Source
https://doi.org/10.5281/zenodo.20184623
Data structure and loading code

Fields

UNII:BTY153760Ostring
inhibits_CinGstring
NCBIGene:3605string

Files

Example file: https://zenodo.org/api/records/20184623/files/mind_updated.tsv/content

Path pattern: Flat Zenodo record: every file hangs directly off the record, no directory tree.

Load the data

import pandas as pd

# mind_updated.tsv is 429.9 MB. Preview the first rows over HTTPS; Zenodo supports
# Range requests, so this reads a slice rather than the whole file.
url = "https://zenodo.org/api/records/20184623/files/mind_updated.tsv/content"
df = pd.read_csv(url, sep="\t", nrows=5_000, low_memory=False)
print(df.shape, "(preview)")
# Full read, 429.9 MB into memory - uncomment when you mean it:
# df = pd.read_csv(url, sep="\t", low_memory=False)
df.head()

Written for a Scigantic notebook, where /mnt/archive is the mounted dataset.

Analyze this dataset without downloading it

On Scigantic, MIND-updated: Mechanistic Repositioning Network with Indications (6,761 indication edges, 5-fold CV splits) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

Related Drug Discovery datasets