BTD
BTD-EmisPred
Current mainline NIR-II emission predictor

Current Mainline Model

Method

Current mainline model workflow and practical input guidance.

Current mainline workflow

1

Data and feature construction

The user-provided molecule-solvent table is cleaned and converted into Morgan fingerprints, RDKit fragment-count features, and solvent one-hot features.

2

Training-set feature screening

The data are split into training and held-out test subsets. Feature filtering and recursive feature elimination are performed only on the training set, producing the fixed feature table used by the retrained model.

3

Candidate model comparison

Eight regressors are compared by 10-fold cross-validation on the training set: CatBoost, XGBoost, LightGBM, RF, GBR, KNN, KRR, and SVR. The best-performing model can then be selected as the final base model; the template uses XGBoost.

4

Final prediction and residual correction

The default workflow trains a tuned XGBoost base model. If users add an OOF residual library, the web app applies a gated nearest-neighbor correction using the parameters supplied in NN_Residual_Correction_Config.json.

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.