BTD
BTD-EmisPred
Solvent-aware emission wavelength prediction

NIR-II Emission Prediction Model

Explanation

How to prepare SMILES, choose solvent, obtain prediction results, and interpret possible prediction errors.

How to use BTD-EmisPred

1

Convert molecule structure to SMILES

Draw the molecule in ChemDraw, select the structure, then click Edit - Copy As - SMILES, or use Alt+Ctrl+C.

2

Paste SMILES into the prediction box

Use one valid molecule SMILES for each prediction.

3

Input or select solvent

Common solvents are available from the solvent list. The abbreviation table below can be used as a reference.

4

Click Predict and read the result

The predicted emission wavelength will be displayed in nanometers under the result panel.

Draw a molecule in ChemDraw

Draw the molecule structure in ChemDraw.

Copy structure as SMILES in ChemDraw

Select the molecule and copy it as SMILES.

Select solvent in BTD-EmisPred

Input or choose a solvent label from common solvents.

Prediction result in BTD-EmisPred

After prediction, the emission wavelength is shown in nm.

Solvent abbreviations

Please note that only the following solvents use abbreviations:

AbbreviationFull Name
THFTetrahydrofuran
DCMDichloromethane
TOL (PHME)Toluene
H2OWater
DMSODimethyl sulfoxide
MEOHMethanol
ACNAcetonitrile
CFM (TCM)Chloroform
HEXn-Hexane
ETOHEthanol
VACVinyl acetate
ACOETEthyl acetate
CHXCyclohexane
DMFN,N-Dimethylformamide
DIOX1,4-Dioxane
ACAcetone
IPROPOH (IPA)Isopropanol
CBZNChlorobenzene
BZNBenzene
SOLIDSolid state
THF/H2OTHF-Water mixture
PBSPhosphate buffered saline
BZNITBenzonitrile
DCE1,2-Dichloroethane
BLUMEButyl methyl ether
DEEDiethyl ether
MXYLENEm-Xylene

Why are predicted results different from experimental results?

The discrepancy between the predicted and experimental results can arise from two main aspects. First, from the data perspective, the molecule under investigation may contain novel structural motifs that are underrepresented or absent in the training set of BTD-EmisPred. Second, from the model perspective, all empirical models have intrinsic prediction errors. Our model learns statistical correlations from experimental data, which inevitably contain measurement uncertainties. Therefore, predicting a perfect match for a new query molecule is challenging. We are actively expanding the training database and exploring strategies to quantify prediction confidence to better address these limitations.

Please let us know your molecule, solvent, and optical properties by sending an email to gaowen@sdnu.edu.cn. We will add your molecules to our database as soon as possible.