alphagenome
Looks up precomputed genomic effects for genetic variants. It provides scores and explanations to understand the impact of variants on the genome.
What it does
AlphaGenome is a tool that predicts the impact of small changes in human and mouse DNA. It analyzes these changes and indicates how likely they are to affect important functions, such as gene expression.
When to use it
- ✓To check the impact of a known genetic mutation.
- ✓To understand how a DNA variation might affect health.
- ✓To research effects of genetic variants in scientific studies.
Example of what to ask your AI
“What is the impact of the variant chr22:36201698:A>C?”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
AlphaGenome uses an AI model trained on extensive genetic data. It analyzes the DNA sequence and predicts the effects of specific changes across various biological assay types.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add K-Dense-AI/scientific-agent-skills --skill alphagenomeOr download just the file:
curl -L https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/main/skills/alphagenome/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
AlphaGenome and the AlphaGenome Atlas
AlphaGenome is DeepMind's sequence-to-function model: 1 Mb of DNA in,
predictions at modality-specific resolutions for eleven assay types across
thousands of human and mouse tracks out. The AlphaGenome Atlas (released 2026-09-08) is that model run once over
every possible single-nucleotide change in GRCh38, about 9 billion variants,
stored with a single ranking number, the AlphaGenome Variant Impact (AVI)
score, its genome-wide percentile, and an 18-way attribution of what drives it.
Both are reached through one pip install alphagenome and one API key.
Research and theoretical modelling only. API outputs must not be used to train other models, and are not for diagnostic procedures or medical decisions. Permissive-use downloads have separate terms; check the artifact licence.
When to use which
| You have | Use | Why |
|---|---|---|
| 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 |
| 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 |
| 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 |
| GRCh37 coordinates, rsIDs, unnormalised indels | genomic-coordinates first, then come back |
wrong build or swapped REF gives a plausible wrong answer |
| ClinVar assertions, gene-disease validity, ACMG framing | folklore-variant-evidence, database-lookup |
AlphaGenome is one evidence line, never the verdict |
| promoter/enhancer/expression predictions without a DeepMind key | genomic-intelligence |
different provider, keyless demo tier |
Setup
uv pip install alphagenome # PyPI; tested on Python 3.12 and 3.13, alphagenome 0.9.0
export ALPHAGENOME_API_KEY="..." # https://deepmind.google.com/science/alphagenome
cd skills/alphagenome/scripts
python atlas_query.py scorers # proves key + network in one call
Shell examples quote variant strings because > otherwise redirects output.
Network examples below are illustrative and were checked against SDK 0.9.0
contracts, without authenticated prediction/Atlas calls during this review.
Never put the key on a command line or in a file you commit; the scripts only
read it from the environment. Authentication failures may surface as
ValueError or PermissionError,
depending on the gRPC status returned by the service.
The coordinate contract
- A variant is 1-based
chr:pos:ref>alt(chr22:36201698:A>C). gnomAD (22-36201698-A-C), GTEx (chr22_36201698_A_C_b38), and Open Targets spellings are autodetected by the scripts. In the SDK, pass the matchingvariant_format=genome.VariantFormat.GNOMAD(orGTEX,OPEN_TARGETS,OPEN_TARGETS_BIGQUERY);from_strdefaults tochr:pos:ref>alt. - An interval on the command line is 1-based closed
chr:start-end; the SDK'sgenome.Intervalis 0-based half-open. The scripts convert. - Human is GRCh38 only. The Atlas key is
chr:pos:alt; REF is implied by the reference. Swapping REF/ALT can cause a miss; a wrong REF or build can misidentify a record. The scripts reject a returned variant that differs from the request, but cannot validate the build. Check REF against GRCh38 FASTA. - rsIDs are not accepted by the API or the portal. Resolve them to coordinates.
- Use the
chrprefix;MTbecomeschrM.
Atlas workflow
1. Rank with AVI
python atlas_query.py avi --variant "chr22:36201698:A>C" "chr9:128225994:G>A"
python atlas_query.py avi --input candidates.vcf --min-phred 20 -o avi.tsv
python atlas_query.py avi --interval chr11:5225727-5226575 --top-k 25 -o hbb_window.tsv
python atlas_query.py avi --input credible_set.tsv --with-tracks -o avi_tracks.tsv
Output, one row per variant:
| Column | Meaning |
|---|---|
avi_raw |
composite model output (the 18 attributions sum to it) |
avi_cdf_quantile |
cumulative quantile against all genome-wide SNVs, as served |
avi_tail_quantile, avi_phred, avi_top_percent |
tail = 1 - cdf, phred = -10 log10(tail); Phred 20 = top 1 %, 30 = top 0.1 % |
top_feature, top_feature_value |
largest absolute SHAP attribution and its value |
…
FAQ
What is the AlphaGenome Atlas?
It's a collection of pre-computed predictions for almost every possible single-nucleotide change in the human GRCh38 reference genome. It provides an impact score (AVI) and details about what drives that impact.
Can I use this for medical diagnosis?
No. AlphaGenome is for research and theoretical modeling only. Outputs must not be used for diagnostic procedures or medical decisions.
Does it work for genomes of animals other than humans and mice?
Currently, AlphaGenome only supports human (GRCh38) and mouse genomes.
Details
Original description by the author
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 s
Popularity
- GitHub stars
- 51k
- Ranking position
- #1830
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
13c-metabolic-flux
Estimates metabolic fluxes using carbon-13 isotope tracing data. It is useful for analyzing cellular metabolism and biochemical pathways.
K-Dense-AI/scientific-agent-skills
adaptyv
Designs protein characterization experiments using the Adaptyv API. It helps estimate costs, submit sequences, and monitor lab results.
K-Dense-AI/scientific-agent-skills
aeon
Performs machine learning tasks on time series data. It is useful for classifying, forecasting, detecting anomalies, and finding patterns in sequential data.
K-Dense-AI/scientific-agent-skills
analytical-method-validation
Helps your agent validate scientific analysis methods. This ensures tests and results are reliable and accurate for lab use.
K-Dense-AI/scientific-agent-skills
Similar skills
pytorch-patterns
Helps your agent use PyTorch for machine learning models. It applies best practices for efficient model training and ensures reproducible results.
affaan-m/ECC
evm-token-decimals
Helps your agent avoid errors with decimal numbers across different blockchain networks. It ensures token values are accurate in transactions and calculations.
affaan-m/ECC
knowledge-agent
Creates and queries knowledge bases using AI. It allows asking questions about past work or compiling expertise on a topic.
thedotmack/claude-mem