AntibodiesGPU8 credits

ImmuneBuilder — Antibody Structure

Predict 3D antibody structure from heavy + light chain sequences

ImmuneBuilder predicts antibody Fv structures with high CDR loop accuracy, running 100x faster than AlphaFold2. Supports paired heavy-light chain prediction and nanobody structures with per-residue confidence scores.

$0.08

per API call

credits per call

/v1/antibodies/fold

API endpoint

Features

Paired Fv structure prediction

Nanobody (VHH) support

High-accuracy CDR loop prediction

100x faster than AlphaFold2

Per-residue pLDDT confidence scores

GPU-accelerated inference

Quick Start

ImmuneBuilder — Python Examplepython

import requests
import time

API_KEY = "sk-sci-your-key-here"
url = "https://scirouter.ai/v1/antibodies/fold"

response = requests.post(url, json={
    "heavy_chain": "EVQLVESGGGLVQPGGSLRLSCAASGFTFS...",
    "light_chain": "DIQMTQSPSSLSASVGDRVTITCRASQSIS..."
}, headers={"Authorization": f"Bearer {API_KEY}"})

job = response.json()

# Poll for results
while True:
    result = requests.get(f"{url}/{job['job_id']}",
        headers={"Authorization": f"Bearer {API_KEY}"})
    data = result.json()
    if data["status"] == "completed":
        print(f"PDB: {len(data['pdb'])} bytes")
        print(f"Mean pLDDT: {data['mean_plddt']:.1f}")
        break
    time.sleep(2)