Follow the steps below to download and run the NVIDIA NIM inference microservice for this model on your infrastructure of choice.
NGC_API_KEY
variable.export NGC_API_KEY=<your personal NGC key>
export LOCAL_NIM_CACHE=~/.cache/nim mkdir -p $LOCAL_NIM_CACHE
docker run -it \ --runtime=nvidia \ -p 8000:8000 \ -e NGC_API_KEY \ -v $LOCAL_NIM_CACHE:/opt/nim/.cache \ nvcr.io/nim/deepmind/alphafold2:2.0.0
This command will start the NIM container and expose port 8000 for the user to interact with the NIM.
{"status":"ready"}
before proceeding. This may take a couple of minutes. You can use the following command to query the health check.curl http://localhost:8000/v1/health/ready
nim_client.py
.import requests import json url = "http://localhost:8000/protein-structure/alphafold2/predict-structure-from-sequence" # Replace with the actual URL sequence = "MNVIDIAIAMAI" # Replace with the actual sequence value headers = { "content-type": "application/json" } data = { "sequence": sequence, "databases": ["small_bfd"], "e_value": 0.000001, "algorithm": "mmseqs2", "relax_prediction": False, } response = requests.post(url, headers=headers, data=json.dumps(data)) # Check if the request was successful if response.ok: with open("output.pdb", "w") as ofi: ofi.write(json.dumps(response.json())) print("Request succeeded:", response.json()) else: print("Request failed:", response.status_code, response.text)
python nim_client.py
output.pdb
.cat output.pdb
nim_client.sh
.#!/usr/bin/env bash set -e URL=http://localhost:8000/protein-structure/alphafold2/predict-structure-from-sequence request='{ "sequence": "MNVIDIAIAMAI" }' curl -H 'Content-Type: application/json' \ -d "$request" "$URL"
chmod +x nim_client.sh ./nim_client.sh