gwaslab-alphagenome 0.1.0

AlphaGenome data extraction for GWASLab panel plots

gwaslab-alphagenome

Data-only bridge between AlphaGenome and GWASLab. Fetches predictions and converts them to GWASLab track bundles. No plotting — use gl.plot_panels in GWASLab.

Install

pip install gwaslab gwaslab-alphagenome
export ALPHA_GENOME_API_KEY=your_key

Usage

import gwaslab as gl
import gwaslab_alphagenome as glag

region = (1, 156538803, 157538803)  # hg38

panels = [
    gl.Panel(
        "ag_tracks",
        region=region,
        ag_spec=glag.Spec("RNA_SEQ", ontology_terms=["UBERON:0002048"]),
        filled=True,
    ),
    gl.Panel(
        "ag_tracks",
        region=region,
        ag_spec=glag.Spec("ATAC", ontology_terms=["UBERON:0002048"]),
    ),
]

fig, axes = gl.plot_panels(panels, region=region, save="locus.png")

gl.plot_panels calls glag.extract_batch() automatically when panels use ag_spec=.

LD reference + variant effect (linked SNP)

ctx = glag.resolve_variant(mysumstats.data, region_ref="rs429358", build="38")

panels = [
    gl.Panel("ag_overlay", region=region, variant_context=ctx,
             ag_spec=glag.Spec("RNA_SEQ", mode="overlay", ontology_terms=["UBERON:0002107"])),
    mysumstats.Panel("region", region=region, region_ref=ctx.region_ref,
                     vcf_path="ld.vcf.gz", build="38"),
]
gl.plot_panels(panels, region=region, variant_positions=[ctx.pos])

API

Function	Role
glag.Spec(...)	Describe output type, mode, ontology
glag.resolve_variant(sumstats, region_ref)	Link GWAS lead SNP to overlay fetch
glag.extract_batch(region, specs, ...)	Batched fetch + bundle conversion
glag.extract(region, spec, ...)	Single-spec extract

Requirements

• hg38 harmonized sumstats for variant-linked plots
• ALPHA_GENOME_API_KEY environment variable