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.
kortix marketplace install K-Dense-AI/scientific-agent-skills:alphagenomepip 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.
| 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 |
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
> 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.ValueError or PermissionError,
depending on the gRPC status returned by the service.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 matching
variant_format=genome.VariantFormat.GNOMAD (or GTEX, OPEN_TARGETS,
OPEN_TARGETS_BIGQUERY); from_str defaults to chr:pos:ref>alt.chr:start-end; the
SDK's genome.Interval is 0-based half-open. The scripts convert.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.chr prefix; MT becomes chrM.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
| 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 |
fi_MERGED_SPLICING ... fi_IS_DELETION | all 18 attributions (keys in references/atlas.md) |
top_track_* (with --with-tracks) | the strongest track behind the top feature: scorer, track, biosample, ontology CURIE, gene, raw score |
atlas_url | deep link to the variant on the portal |
error | per-variant lookup failure or mismatched returned allele instead of a crash |
MERGED_SPLICING or ALPHAMISSENSE
on top means a splice or coding mechanism; MAX_ABS_DNASE, MAX_ABS_CHIP_TF,
MAX_ABS_RNA_SEQ mean a regulatory mechanism you can resolve by track;
CACTUS_241_WAY or PHASTCONS_470_WAY on top means conservation is carrying
the score and the molecular mechanism is not resolved.python atlas_query.py scorers # what the server serves right now
python atlas_query.py tracks --scorer RNA_SEQ --query colon # find ontology CURIEs
python atlas_query.py scores --variant "chr22:36201698:A>C" \
--scorers RNA_SEQ DNASE SPLICE_SITE_USAGE --ontology UBERON:0001157 -o colon.tsv
python atlas_query.py scores --interval chr11:5225727-5226575 --scorers CHIP_TF -o hbb_tf.tsv
raw_score and, where served, quantile_score. Track-level
scorer names: ATAC, DNASE, CHIP_TF, CHIP_HISTONE, CAGE, PROCAP,
RNA_SEQ, POLYADENYLATION, SPLICE_SITES, SPLICE_SITE_USAGE,
SPLICE_JUNCTIONS, CONTACT_MAPS, plus *_ACTIVE variants; scorers is the
authority on the live list. Filter by the tissue the question is about, not
by the genome-wide maximum: 9,440 scorer-track entries mean something may be extreme
somewhere.python atlas_link.py variant "chr22:36201698:A>C" --biosample "colon" --modalities RNA_SEQ,DNASE,CHIP_TF
python atlas_link.py locus chr11:5225727-5226575 --tf GATA1
python atlas_link.py gene HBB --markdown
import os
from alphagenome.atlas import atlas
from alphagenome.data import genome
client = atlas.create(os.environ["ALPHAGENOME_API_KEY"], timeout=30)
scores = client.query_variant(
genome.Variant.from_str("chr22:36201698:A>C"),
requested_scorers=["AVI_SCORE", "AVI_SCORE_FEATURE_IMPORTANCE", "RNA_SEQ"],
ontology_terms=["UBERON:0001157"], # optional; ignored for scorers without ontology metadata
)
avi = scores["AVI_SCORE"] # AnnData: X (1,1) raw; layers['quantiles'] (1,1) cdf
fi = scores["AVI_SCORE_FEATURE_IMPORTANCE"] # AnnData: X (1,18); var['name'] = feature keys
rna = scores["RNA_SEQ"] # AnnData: obs = variant x gene, var = tracks, X = natural-log FC
client.query_interval(genome.Interval("chr11", 5225726, 5226575), requested_scorers=["AVI_SCORE"])
query_interval returns up to 3 SNVs per non-N base, in 32 bp chunks. Keep windows
to about 1 kb (3,000 variants); atlas_query.py refuses more unless
--max-window is raised. query_variants raises if any submitted lookup fails;
completion order is not input order;
the script makes separate variant requests so misses become error cells.python score_variants.py --variant "chr22:36201698:A>C" -o scores.tsv # 12 recommended scorers, 1 Mb
python score_variants.py --input indels.vcf --scorers RNA_SEQ SPLICE_SITE_USAGE \
--ontology UBERON:0001157 --min-abs-quantile 0.99 -o colon.tsv
python score_variants.py --organism mouse --variant "chr7:45000000:A>G" --scorers RNA_SEQ --sequence-length 500KB -o mouse.tsv
python score_variants.py --list-scorers
python score_variants.py --list-tracks --output-type RNA_SEQ --query liver -o tracks.tsv
variant_scorers.tidy_scores: one row
per variant x scorer x track (x gene) with raw_score and quantile_score,
sorted by |raw|. Default scorers are the 12 recommended difference scorers;
--include-active adds the seven *_ACTIVE activity scorers. At most 20
scorers per request. Mouse has no calibrated quantiles; use raw scores there.
--min-abs-quantile uses the supplied signed quantile magnitude (unsigned
scorers use their upper-tail quantile); it never treats zero as an extreme.from alphagenome.models import dna_client, variant_scorers
model = dna_client.create(os.environ["ALPHAGENOME_API_KEY"])
variant = genome.Variant.from_str("chr22:36201698:A>C")
interval = variant.reference_interval.resize(dna_client.SEQUENCE_LENGTH_1MB)
adatas = model.score_variant(interval, variant, variant_scorers=[variant_scorers.RECOMMENDED_VARIANT_SCORERS["RNA_SEQ"]])
df = variant_scorers.tidy_scores(adatas) # filter df.ontology_curie afterwards; score_variant takes no ontology_terms
vo = model.predict_variant(interval, variant,
requested_outputs=[dna_client.OutputType.RNA_SEQ, dna_client.OutputType.DNASE],
ontology_terms=["UBERON:0001157"])
vo.reference.rna_seq.values, vo.alternate.rna_seq.values # (1048576, n_tracks)
window = genome.Interval("chr20", 3_753_000, 3_753_400).resize(dna_client.SEQUENCE_LENGTH_16KB)
ism = model.score_ism_variants(interval=window, ism_interval=window.resize(256),
variant_scorers=[variant_scorers.CenterMaskScorer(
requested_output=dna_client.OutputType.DNASE, width=501,
aggregation_type=variant_scorers.AggregationType.DIFF_MEAN)])
2**14 to 2**20); 1 Mb is
the recommended default for full context; the recommended contact-map scorer
uses a 1 Mb mask. Shorter windows lose distal sequence context. Ontology
terms are CURIEs (UBERON:0002048 lung, CL:0000084 T cell); discover them
with --list-tracks or model.output_metadata(...).concatenate(). Plotting,
gene annotation (GENCODE v46 Feather on GCS), splicing and haplotype recipes:
references/model-api.md.raw_score is the effect size on the scorer's scale
(RNA_SEQ is ln(mean ALT + 0.001) - ln(mean REF + 0.001):
-1 is about 0.37x the pseudocount-adjusted REF signal). quantile_score ranks against
common variants: signed scorers use [-1, 1], unsigned scorers [0, 1],
with finite calibration limits near 1. AVI instead uses a genome-wide SNV CDF.
A quantile above 0.99 with |raw| < 0.1 can reflect a narrow background in a quiet region; inspect REF/ALT tracks and
report the small predicted change without declaring biological absence of effect.
Raw-score thresholds are scorer-specific; quantiles are ranks, not p-values. Unsigned
scorers (SPLICE_*, POLYADENYLATION, CONTACT_MAPS, *_ACTIVE) have no
direction. "AlphaGenome predicts no appreciable change in the queried tracks"
is a complete answer, and a variant inside a peak whose REF and ALT tracks are
identical is not "disrupting" anything. Full rules, tissue matching, and the
reporting checklist: references/interpretation.md.N bases were never scored.RESOURCE_EXHAUSTED
and UNAVAILABLE are retried. Atlas also retries DEADLINE_EXCEEDED
(up to 5 attempts, 60 s call deadline); model streaming RPCs use a separate
retry policy. --timeout controls channel setup only, not total query time.alphagenome client is Apache-2.0; model weights and outputs carry
DeepMind's terms. Cite Avsec et al., Nature 649:1206 (2026) and the Atlas
report (Cheng et al., medRxiv, 2026, doi:10.64898/2026.09.16.26363192).references/atlas.md - what the Atlas contains, the 19 scorer
configurations with track counts, AVI training and the 18 features, quantile
to Phred, the client API and AnnData layout, error mapping, access tiers,
portal URL grammar, GTF and download locations.references/model-api.md - dna_client cheat sheet: coordinates, sequence
lengths, output types and track counts, ontology metadata, predict and score
calls, recommended scorer configurations, ISM, gene annotation, plotting.references/interpretation.md - raw versus quantile, AVI thresholds,
tissue matching, negative results, model blind spots, coordinate hygiene,
reporting checklist.scripts/atlas_query.py (Atlas: avi, scores, scorers,
tracks), scripts/score_variants.py (model scoring, --list-scorers,
--list-tracks), scripts/atlas_link.py (portal deep links, offline).Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065. https://doi.org/10.48550/arXiv.2609.00065
v1. When network access is
available, fetch https://arxiv.org/abs/2609.00065 (or
http://export.arxiv.org/api/query?id_list=2609.00065)) before writing the reference and take
the author list, year, and version from that record. If the record lists a journal reference
or publisher DOI, cite the published version instead.Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrained multistart fitting, and flux-profile diagnostics. Use for 13C-MFA, carbon tracing, mass isotopomer distributions (MDVs/MIDs), positional isotopomers, parallel tracer experiments, and determining whether labeling data constrain a pathway flux. Distinguishes measured-label inference from COBRA flux balance analysis and flags experiments requiring nonstationary MFA.
Uses the Adaptyv Bio Foundry API and Python SDK to design protein characterization experiments, estimate costs, submit sequences, monitor laboratory progress, and retrieve results. Applies to Adaptyv Foundry, its target catalog, binding screening and affinity assays, thermostability, expression, fluorescence, epitope binning, and enzyme activity workflows, including code using adaptyv or FoundryClient.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Plans, executes, and documents validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include "method validation", "analytical method validation", "AMV", "validation protocol", "acceptance criteria", "linearity", "reportable range", "accuracy and precision", "repeatability", "intermediate precision", "recovery", "LOD", "LOQ", "detection limit", "quantitation limit", "specificity", "robustness", "method transfer", "method comparison", "Deming", "Passing-Bablok", "Bland-Altman", "equivalence testing", "OOS investigation", "ICH Q2", "Q2(R2)", "Q14", "USP 1225", "ICH M10", "incurred sample reanalysis", "ISR", "CLSI EP", and any request to show that an assay works.
Handles annotated matrices in single-cell analysis, .h5ad and Zarr files, and integration with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.