AlphaGenome

# Download the whl file using - 
wget -q https://github.com/GoogleCloudPlatform/vertex-ai-samples/raw/main/notebooks/community/alphagenome/whl/alphagenome_cloud_sdk-0.4.2.11-py3-none-any.whl

# Install the whl file
pip install alphagenome_cloud_sdk-0.4.2.11-py3-none-any.whl

from alphagenome.models import dna_client
from alphagenome_cloud_sdk.models import dna_client_http

# Create the HTTP client pointing to the Agent Platform endpoint.
# The `service_account` parameter is optional and only required if you are 
# choosing to authenticate via service account impersonation.
dna_model = dna_client_http.create_http_client(
    vertex_ai_url=vertex_ai_url,
    # service_account=service_account  # Uncomment to use service account impersonation
)

# Pad a synthetic sequence to 1 MB using 'N' for unknown/padding bases
padded_sequence = 'GATTACA'.center(dna_client.SEQUENCE_LENGTH_1MB, 'N')

output = dna_model.predict_sequence(
    sequence=padded_sequence,
    requested_outputs=[
        dna_client.OutputType.CAGE,   # Transcription Start Sites
        dna_client.OutputType.DNASE,  # Chromatin Accessibility
    ],
    ontology_terms=[
        'UBERON:0002048',             # Lung tissue ontology term
    ]
)

# Access prediction values (shape: sequence_length, num_tracks)
dnase_signals = output.dnase.values
dnase_metadata = output.dnase.metadata

from alphagenome.data.genome import Interval

# Define a genomic interval and resize it to the 1Mb context window
interval = Interval(
    chromosome='chr19',
    start=40991281,
    end=41018398,
    strand='.',
    name='CYP2B6'
).resize(dna_client.SEQUENCE_LENGTH_1MB)

output = dna_model.predict_interval(
    interval=interval,
    requested_outputs=[dna_client.OutputType.RNA_SEQ],
    ontology_terms=['UBERON:0001114']  # Right liver lobe
)

from alphagenome.data import genome
from alphagenome.models import variant_scorers

# Define the genetic variant
variant = genome.Variant(
    chromosome='chr22',
    position=36201698,
    reference_bases='A',
    alternate_bases='C',
)

# Select the variant scoring method for RNA-Seq
variant_scorer = variant_scorers.RECOMMENDED_VARIANT_SCORERS['RNA_SEQ']

# Execute the scoring
variant_scores = dna_model.score_variant(
    interval=variant.reference_interval.resize(dna_client.SEQUENCE_LENGTH_1MB),
    variant=variant,
    variant_scorers=[variant_scorer],
    fix_negative_strand=True
)

# Output is returned as an AnnData object containing raw and quantile scores
print("Scores shape:", variant_scores[0].X.shape)

# Set your base endpoint URL
export ENDPOINT_URL="https://<your-endpoint-url>"

# (Optional) If you choose to impersonate a service account, set this variable
# export SERVICE_ACCOUNT="your-service-account-email@your-project.iam.gserviceaccount.com"

# Generate an OAuth2 access token using your current credentials
# If using service account impersonation, append: --impersonate-service-account=$SERVICE_ACCOUNT
export TOKEN=$(gcloud auth print-access-token)

curl -X POST \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/alphagenome-003",
    "instances": [
      {
        "request_type": "predict_interval",
        "data": {
          "interval": {
            "chromosome": "chr19",
            "start": "40480552",
            "end": "41529128",
            "strand": "STRAND_UNSTRANDED"
          },
          "organism": "ORGANISM_HOMO_SAPIENS",
          "requestedOutputs": ["OUTPUT_TYPE_ATAC"]
        }
      }
    ]
  }' \
  ${ENDPOINT_URL}:streamRawPredict