claim

active

claim:evee-provides-mechanistic-explanations-for-variant-effects-derived-from-model-internals-not-just-pathogenicity-calls

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.

Source paper

extracted_from

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

(2026) · Pearce, Michael · Dooms, Thomas · Yamamoto, Ryo · Meehl, Joshua +18

Neighborhood — ranked by edge-count

Papers (1)

paper

Explaining 4.2 million genetic variants with state-of-the-art, interpretable predictions
mentions

Findings (2)

finding

Disruption profiles scored 3.8/5 for explanation quality vs 2.8/5 for metadata-only baselines
supports
EVEE's mechanistic explanations significantly outperform simple metadata-based predictions in human evaluation.
0.997 AUROC on pathogenicity prediction for 839k ClinVar variants
supports
EVEE achieves state-of-the-art performance on variant pathogenicity classification, outperforming existing methods.

Communities (3)

community

Mechanistic interpretability & model evaluation
members_of
Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
Mechanistic explanation of genetic variant pathogenicity
members_of
Using genomic foundation model internals to generate disruption profiles that explain variant effects mechanistically, achieving 0.997 AUROC on ClinVar pathogenicity prediction.
Mechanistic variant pathogenicity prediction
members_of
EVEE tool predicts and mechanistically explains effects of 4.2M human genome variants using model internals.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Evee outperforms existing methods for variant pathogenicity predictionclaim0.839
Interpretive claim supported by the high AUROC findings.
Evee provides predictions and mechanistic explanations for 4.2 million genetic variants across the whole human genomeclaim0.827
Scale claim, demonstrating whole-genome applicability.
Evee variant effect prediction methodmethod0.804
The method that predicts and explains variant pathogenicity using Evo 2, producing disruption profiles.
Model internals of genomic foundation models can yield mechanistic explanations for variant effectsclaim0.778
Foundational interpretability claim that the paper exemplifies.
Causal emergence is widespread across measures of causation, not just EI.claim0.728
Claim by Comolatti & Hoel (2022) endorsed by this survey.
When a model discovers that its outputs produce effects, it accelerates learning through in-context learning, analogous to lucid dreaming.claim0.728
Describes scaffolding method and the model's meta-learning loop.
Biology's robustness, open-endedness, evolvability, and unique complexity likely depend on the fact that evolution works with an agential material.claim0.727
Central claim linking life's properties to the inherent competencies of its material substrate.
The evil-vector recovery is not proof of a uniquely identifiable harmfulness coordinate but evidence that fine-tuned variants can expose hard-to-estimate directionsclaim0.726
Cautions against over-interpreting the transfer result given non-identifiability of steering vectors