Molecular Photophysics AI
Seven optical properties from SMILES in seconds.
TD-DFT takes 24–72 hours per molecule, so millions of virtual candidates get narrowed to a few hundred that anyone actually evaluates. Our graph isomorphism network predicts absorption, emission, bandwidths, extinction, quantum yield, and lifetime straight from a SMILES string.
The problem
Every molecule's optical behaviour is a question quantum chemistry answers slowly.
Before anyone synthesises a candidate, someone needs to know how it absorbs, emits, and decays. Today that means TD-DFT - accurate, and slow enough that only a sliver of any real virtual library ever gets checked. The rest is guesswork, or it never gets screened at all.
Try the model
Pick a molecule. Watch the properties land.
This is a scripted preview of the live API using four reference fluorophores - the production model accepts any valid SMILES string.
How it fits your workflow
We don't replace TD-DFT. We decide what's worth running it on.
A two-stage pipeline: cheap, fast pre-screening across the full virtual library, then TD-DFT validation only on the candidates that clear the bar.
GIN pre-screen
SMILES in, seven properties out, in under a second per molecule. Rank a virtual library that would take decades to touch with TD-DFT.
TD-DFT validation
Spend your quantum-chemistry budget on the survivors. Complementary to the tools you already run, not a replacement for them.
Synthesise
At $5–20K and weeks of lab time per candidate, the cost of the pipeline is decided long before anyone touches a flask.
Test-set performance
Accuracy, property by property.
Held-out R² across all seven predicted properties. We publish all seven, not just the best ones.
Where we point it first
Major industries, one bottleneck.
Different molecules, same problem: optical properties gate every downstream decision, and today they're found out too late.
Pharma R&D & CDMO
Analytical method planning, impurity profiling, ADC payload analytics, batch QC pre-screening.
OLED / TADF
Emitter screening for next-generation displays - absorption, emission, and lifetime before synthesis.
Solar Dyes
DSSC sensitiser screening - matching absorption to the solar spectrum before a single synthesis run.
Bioimaging
Fluorescent probe design and repurposing, turn-on response prediction, target-affinity co-screening.
Bring us your hardest scaffold.
Send a library and a target window. We return the ranked shortlist and the seven predicted properties behind it, so you can check the model against molecules you already measured.