Chemistry and materials science
Screen thousands of compositions before you make one.
Antinuous ranks candidate materials from databases and papers and runs atomistic simulations across many structures in parallel. Predictions are labeled, and each value links to its paper or run.
Use cases
Plan your next experiment from past results
Temperature, solvent and ratios interact, so picking the next run by hand often wastes experiments.
You ask
Here are 40 runs of our coupling reaction as a spreadsheet. Suggest the next 8 conditions most likely to raise yield, and explain why.
What it does
- Antinuous reads your spreadsheet of past runs and checks it for gaps and inconsistent units.
- It installs an open-source Bayesian optimization package in its workspace and fits a model of yield versus conditions.
- It proposes the next batch of conditions, balancing likely gains against unexplored settings.
- It writes an analysis notebook that explains the model and why it chose each condition.
You get
A notebook with a proposed batch of conditions and a chart of predictions.
Each round of lab results updates the model that picks the next round.
Who it's for
Materials scientistsScreen candidate materials before you make them.
Synthetic chemistsCompare published synthesis routes with each value linked to its paper.
Process chemistsFind safer solvent replacements with cited hazard data.
R&D leadsPlan your next experiment from past results.
Works with
PubChem
ChEMBL
RCSB PDB
arXiv
GitHub
Google Slides
PowerPoint