Demo

Click here to open and try the demo now:

Google Colabcolab.research.google.com

Pending AI Demo Notebook — An end-to-end walkthrough of the Pending AI platform in Google Colab, covering:

1. Molecule Generation — sample novel molecules from Pending AI's generative models, with lightweight post-filtering on Lipinski's Rule of 5.

2. Similarity Search — build an in-memory usearch index over Morgan fingerprints and run a Tanimoto similarity search against a reference compound (Imatinib).

3. Property Analysis — visualize QED, cLogP, and molecular weight distributions across the generated set, with a target molecule overlaid for comparison.

4. Diversity Analysis — assess sample diversity via pairwise property-distance distributions.

5. Synthesizability Screening — submit single and batch jobs to the Retrosynthesis Prediction service, poll for completion, and export/download interactive HTML reports depicting the resulting synthetic routes.

6. TwinOracle — try Pending AI's next-generation retrosynthesis engine, including a tunable full-parameter example (search depth, time budget, building-block cost/lead-time/region constraints).

Requires a registered Pending AI account (the notebook walks through login via the pendingai Python package) — reach out here to trial the platform.