GenoNet: Functional Scores for Non-Coding Variants Across 127 Tissues

GenoNet scores predict the functional consequences of non-coding genetic variants. The dataset provides scores for genomic regions across 127 Roadmap Epigenomics tissues, based on the GRCh37 human genome assembly. It was created by researchers at Columbia University and published in Nature Communications in 2018.

Use Cases

• Prioritizing disease-associated non-coding variants based on predicted tissue-specific functional effects.
• Training models for regulatory variant prediction using semi-supervised scores across 127 epigenomes.
• Analyzing tissue-specific regulatory activity across genomic regions defined by the GRCh37 assembly.

Strengths

• Scores are provided for 127 distinct Roadmap Epigenomics tissues, offering broad cell-type specificity.
• The method utilizes a semi-supervised approach combining labeled regulatory variants with millions of unlabeled variants.

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

Columbia University

Collection Method

Semi-supervised computational prediction utilizing epigenetic annotations and labeled variants.