Skip to main content
All tools

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

Hardware and price

Price per run

What a typical run reserves from your wallet: the catalog's expected runtime on each piece of hardware × your plan's per-second rate. Larger inputs reserve more, and you're charged only for the seconds the job actually runs.

Image to Structure (OCSR): reservation per run, USD
HardwareTypical runtimeBasicStarterProEnterprise
CPU30 min$0.25$0.14$0.09$0.054
Nvidia T4Default10 min$0.34$0.25$0.20$0.15

In workflows

Chain it with other steps.

Each input and output has a data kind, so the builder only connects steps that fit.

Inputs

  • ImagePNG, JPEG

Outputs

  • ArchiveZIP
  • ImagePNG
  • MoleculesSMILES
  • TableCSV
  • TableCSV

References

The method behind it.

  1. Yujie Qian, Jiang Guo, Zhengkai Tu et al. (2023). MolScribe: Robust Molecular Structure Recognition with Image-to-Graph Generation. Journal of Chemical Information and Modeling. doi:10.1021/acs.jcim.2c01480 (opens in a new tab)
  2. Yufan Chen, Ching Ting Leung, Yong Huang et al. (2024). MolNexTR: a generalized deep learning model for molecular image recognition. Journal of Cheminformatics. doi:10.1186/s13321-024-00926-w (opens in a new tab)
  3. Yujie Qian, Jiang Guo, Zhengkai Tu et al. (2023). RxnScribe: A Sequence Generation Model for Reaction Diagram Parsing. Journal of Chemical Information and Modeling. doi:10.1021/acs.jcim.3c00439 (opens in a new tab)
  4. Kohulan Rajan, Henning Otto Brinkhaus, Maria Sorokina et al. (2021). DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature. Journal of Cheminformatics. doi:10.1186/s13321-021-00496-1 (opens in a new tab)

Run via API

Submit it from your own code.

Use an API key from your account. The estimate uses your plan's rates; submitting reserves that amount from your wallet.

# Estimate the reservation for your plan (payload fields: see the API reference)
curl -X POST https://api.cognichem.com/api/v1/jobs/estimate \
  -H "X-Api-Key: $COGNICHEM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"job_type": "image-to-structure", "resource": "t4", "payload": {}}'

# Submit (retrying with the same Idempotency-Key never submits twice)
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": "image-to-structure-1", "job_type": "image-to-structure", "resource": "t4", "payload": { ... }}'
Payload fields and examples in the docs

Cheminformatics & Structure

  • Fingerprint Similarity & Clustering

    Tanimoto nearest neighbors, Butina clustering, MaxMin diversity, and Scanpy PCA/UMAP/Leiden clustering from molecular fingerprints

  • 3D Shape Similarity

    3D shape and pharmacophore virtual screening: rank libraries against a query conformer with USRCAT and Gaussian shape + color overlay to find scaffold hops

  • ChEMBL Target Activities

    Pull measured IC50, Ki, Kd and EC50 values for your targets from ChEMBL into one table, ready to curate and train on

  • Bioactivity Dataset Curator & Splitter

    Normalize assay units, censoring, and replicates into SAR/QSAR datasets with scaffold, random, or time splits

  • Free Wilson Analysis

    Quantify R-group SAR contributions and predict unsynthesized molecules from activity data

  • Matched Molecular Pairs

    Hussain–Rea matched pairs: chemical transforms and activity deltas from a SMILES library

All tools