Mechanistic explanation of genetic variant pathogenicity

Using genomic foundation model internals to generate disruption profiles that explain variant effects mechanistically, achieving 0.997 AUROC on ClinVar pathogenicity prediction.

9 members. Each node is clickable.

Loading graph…

Drawn from 1 source

The papers/notes whose extracted claims & findings make up this cluster.

Explaining 4.2 million genetic variants with state-of-the-art, interpretable predictions9 members

Bridges (3)

Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.

Mechanistic interpretability & model evaluation9 shared
Mechanistic variant pathogenicity prediction3 shared
Disruption profile explanation quality2 shared

Claims (5)

Disruption profiles are higher quality explanations than metadata-only descriptionsClaim supported by the 3.8 vs 2.8 human rating finding.
Evee outperforms existing methods for variant pathogenicity predictionInterpretive claim supported by the high AUROC findings.
EVEE provides mechanistic explanations for variant effects derived from model internals, not just pathogenicity calls.Core interpretability claim distinguishing EVEE from black-box prediction tools; applies interpretability for science.
Evee provides predictions and mechanistic explanations for 4.2 million genetic variants across the whole human genomeScale claim, demonstrating whole-genome applicability.
Model internals of genomic foundation models can yield mechanistic explanations for variant effectsFoundational interpretability claim that the paper exemplifies.

Findings (4)

0.991 AUROC zero-shot on insertions/deletionsEVEE demonstrates strong generalization to indels without explicit training, indicating learned mechanistic principles.
0.997 AUROC on pathogenicity prediction for 839k ClinVar variantsEVEE achieves state-of-the-art performance on variant pathogenicity classification, outperforming existing methods.
Disruption profiles scored 3.8/5 for explanation quality vs 2.8/5 for metadata-only baselinesEVEE's mechanistic explanations significantly outperform simple metadata-based predictions in human evaluation.
Mechanistic explanations provided for ~2M variants of uncertain significanceScale of interpretability output, addressing a major clinical need for VUS resolution.