What is the difference between curated and text-mined data?

When you compare DISGENET plans, you may notice two distinct data sources: curated and text-mined.

In this article, we’ll share the key differences between these types of data.

What is curated data?

Curated data is information that has been carefully selected and organized by experts in the field. This data is typically well-established and has been thoroughly validated.

Which curated databases are integrated into DISGENET?

For gene–disease associations (GDAs), curated data comes from these expert resources:

• Clin Gen
• ClinPGX
• ClinVar
• GenCC
• MGD (human)
• Orphanet
• PsyGeNET
• RGD (human)
• UniProt/SwissProt

For variant-disease associations (VDAs), curated data comes from:

• UniProt/SwissProt
• ClinVar
• PheWAS Catalog
• NHGRI-EBI GWAS Catalog
• ClinPGX
• ClinGen Evidence Respiratory for Variants (ClinGen Variants)

What is text-mined data? 

Text-mined data is information that has been extracted from scientific literature using our high-performance Natural Language Processing (NLP) tool. This data may be less well-established than curated data, but it can be a very valuable source of novel insights.

Which DISGENET plans include text-mined data?

• Text-Mined Data: Available on Standard, Advanced, and Premium plans.
• Curated Data: Available on all plans (Free Academic License, Standard, Advanced, and Premium).