Tools · Cheminformatics & Structure

Image to Structure (OCSR)

Read chemical structures and reaction schemes from images of papers, slides and whiteboards as SMILES, with each reading checked by a second model

On this page

Prices, workflows, and method papers Open in the app

Run it from the API

Submit with Submit a job and the job_type below. Price it first with Estimate job reservation cost: submitting reserves that amount from your wallet, and the charge settles at the actual runtime.

Image to Structure (OCSR) `image-to-structure`

Job type: image-to-structure
Hardware: cput4 (default)
Typical runtime: 10 min on Nvidia T4

Payload

Payload fields
Field	Type	Description
`image`required	`imageFile \| artifactRef`	One PNG or JPEG, at most 10 MB and 25 megapixels.
`reactions`	`boolean`	Also parse reaction schemes into reaction SMILES. Default: `true`
`max_structures`	`integer`	Most structures to read from the image. Default: `50`Limits: `≥ 1, ≤ 200`

Example

from cognichem_client import CogniChem

client = CogniChem.from_env()  # reads COGNICHEM_API_KEY
payload = {
    "image": {"name": "scheme.png", "content_b64": "<file contents, base64>"},
    "reactions": True,
    "max_structures": 10,
}

estimate = client.jobs.estimate(job_type="image-to-structure", payload=payload, resource="t4")
print(f"Reserves ${estimate.cost:.2f}")

job = client.jobs.submit(
    job_name="my-image-to-structure-run",
    job_type="image-to-structure",
    payload=payload,
    resource="t4",
)
status = client.jobs.wait(job.process_id)
if status.status == "completed":
    client.jobs.result(job.process_id, save_path=".")

curl -X POST "https://api.cognichem.com/api/v1/jobs/submit" \
  -H "X-Api-Key: $COGNICHEM_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{
  "job_name": "my-image-to-structure-run",
  "job_type": "image-to-structure",
  "payload": {
    "image": {
      "name": "scheme.png",
      "content_b64": "<file contents, base64>"
    },
    "reactions": true,
    "max_structures": 10
  },
  "resource": "t4"
}'

{
  "image": {
    "name": "scheme.png",
    "content_b64": "<file contents, base64>"
  },
  "reactions": true,
  "max_structures": 10
}

Sample data from the job catalog; long values are shortened here. Each job_name must be unique among your jobs.

Workflow inputs

ImagePNG, JPEG

Workflow outputs

ArchiveZIP
ImagePNG
MoleculesSMILES
TableCSV
TableCSV

Run it from the API

Image to Structure (OCSR) image-to-structure

Image to Structure (OCSR) `image-to-structure`