alphagenome
Agent skill fromK-Dense-AI/scientific-agent-skills
Looks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), scores variants or scans windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and builds Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.
How to install alphagenome
npx skills add K-Dense-AI/scientific-agent-skills# or add only this skill to Claude Code: copy the folder
skills/alphagenome/
# into
~/.claude/skills/alphagenome/ (all projects)
.claude/skills/alphagenome/ (one project)
1# AlphaGenome and the AlphaGenome Atlas23AlphaGenome is DeepMind's sequence-to-function model: 1 Mb of DNA in,4predictions at modality-specific resolutions for eleven assay types across5thousands of human and mouse tracks out. The **AlphaGenome Atlas** (released 2026-09-08) is that model run once over6every possible single-nucleotide change in GRCh38, about 9 billion variants,7stored with a single ranking number, the **AlphaGenome Variant Impact (AVI)**8score, its genome-wide percentile, and an 18-way attribution of what drives it.9Both are reached through one `pip install alphagenome` and one API key.1011> Research and theoretical modelling only. API outputs must not be used to train12> other models, and are not for diagnostic procedures or medical decisions.13> Permissive-use downloads have separate terms; check the artifact licence.1415## When to use which1617| You have | Use | Why |18| --- | --- | --- |19| hg38 SNVs (a VCF, a credible set, a region up to ~1 kb) | **Atlas** via `scripts/atlas_query.py` | precomputed, higher quota, includes AVI and attributions |20| indels, mouse variants, a non-reference background, a custom scorer or window | **model** via `scripts/score_variants.py` or Python | the Atlas is SNV-only and hg38-only |21| a hypothesis to explain (which motif, which tissue, REF vs ALT tracks) | model `predict_variant` + plots, Atlas track scores, portal link | mechanism, not just rank |22…
Excerpt shown under the repository's MIT license.
