CancerMine: Cancer Gene Roles and Supporting Sentences from Literature

CancerMine provides structured data on cancer gene roles extracted from biomedical literature. The dataset includes collated gene-cancer relationships with citation counts and a separate file with supporting sentences from publications. It was created by Jake Lever at Stanford University.

Use Cases

• Training relation extraction models based on annotated cancer-gene-sentence triples.
• Validating cancer gene hypotheses based on citation counts from the collated file.
• Exploring the literature evidence for specific gene-disease links using the supporting sentences.

Strengths

• Data includes normalized identifiers from HUGO, Entrez Gene, and the Disease Ontology.
• Separate filtered and unfiltered files allow users to balance precision and recall.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Stanford University

Collection Method

Text mining of PubMed, PubMed Central Open Access, and PubMed Central Author Manuscript Collection.