Skip to content
Materials Science · OLED & Emitter Screening

Find viable OLED emitters without running DFT

Screening 400 emitter candidates used to mean 400 DFT jobs. Now provide SMILES and get emission wavelength, TADF suitability, and device role classification - in minutes. S1 accuracy within 0.05 eV of experiment. Identify top candidates for synthesis or device testing without running full quantum workflows.

“Find me a blue OLED emitter from this library of 400 candidates, ranked by singlet-triplet gap for TADF suitability.”

0.05 eV
S1 error vs experiment
0.005 eV
T1 error vs experiment
14
OLED motifs detected
6 min
For 400 candidates
The funnel

How it works

01

Provide SMILES

Geometry optimizes via ANI-2x or MACE in milliseconds. No conformer setup, no input file preparation.

02

Frontier orbitals and device classification

predict_frontier_orbitals returns HOMO, LUMO, gap, S1/T1 energies, oscillator strength, and device role - emitter, charge transport, host, or not emissive. 14 OLED-relevant functional-group motifs detected automatically (carbazole, triphenylamine, anthracene, pyrene, oxadiazole, triazine, Ir/Pt complexes).

03

Excited-state ladder for top candidates

run_excited_states returns the full singlet/triplet ladder via sTDA-xTB with oscillator strengths. Screen for TADF suitability (small singlet-triplet gap) or phosphorescent emitters.

Proof

Anthracene S1: 3.249 eV computed vs 3.3 eV experimental (0.05 eV error). T1: 1.805 eV vs 1.8 eV (0.005 eV error).

Carbazole: correctly classified as UV emission / charge transport. Ethanol: correctly returns not_emissive (no OLED motifs).

14 detected motifs: carbazole, triphenylamine, anthracene, pyrene, oxadiazole, triazine, Ir/Pt complexes, and others.

Tool chain: optimize_geometry_nnppredict_frontier_orbitalsrun_excited_states.

Use this when you need to

Screen emitter libraries for emission wavelength and TADF suitability

Rank candidates by singlet-triplet gap before expensive validation

Classify device roles (emitter, host, charge transport) automatically

Guide early-stage selection with accuracy sufficient to prioritize synthesis

Research preview

Screen 400 candidates in minutes - not days

S1 within 0.05 eV. Accurate enough to guide selection before expensive validation.