Sweetener identification using transfer learning and attention mechanism

Figures & data

Figure 1. Illustration of the proposed sweetener identification method.

Table 1. Description of the collected dataset.

Source	Sweet	Non-Sweet
		Bitter	Tasteless
Rojas et al. (2016)	432	/	133
Rojas et al. (2017)	/	156	/
Tuwani et al. (2019)	653	554	130
Garg et al. (2018)	1678	437	106
Dagan-Wiener et al. (2019)	/	797	/
Total	2763	1944	369

Figure 2. Molecular images in the dataset categorized as sweet and non-sweet (bitter, tasteless) compounds.

Figure 3. Data augmentation.

Figure 4. Sweetener identification based on CBAM-SEResNet-50.

Table 2. The architecture of ResNet-50.

Layer Name	Output size	Structure
Conv1	112 × 112	7 × 7, 64, stride 2
Conv_2	56 × 56	3 × 3 max pool, stride 2 $\left[\begin{array}{c}1\times 1,64\\ 3\times 3,64\\ 1\times 1,256\end{array}\right]\times 3$
Conv_3	28 × 28	$\left[\begin{array}{c}1\times 1,128\\ 3\times 3,128\\ 1\times 1,512\end{array}\mathit{\hspace{0.17em}}\right]\times 4$
Conv_4	14 × 14	$\left[\begin{array}{c}1\times 1,256\\ 3\times 3,256\\ 1\times 1,1024\end{array}\right]\times 6$
Conv_5	7 × 7	$\left[\begin{array}{c}1\times 1,512\\ 3\times 3,512\\ 1\times 1,2048\end{array}\right]\times 3$
	1 × 1	Average pool, 1000-d fc, Softmax

Figure 5. The network structure of SE attention module.

Figure 6. The network structure of CBAM attention module.

Table 3. Parameter setting.

Parameters	Value
Input size	224 × 224
Optimizer	SGD
Learning Rate	1.0 × 10^−3
Batch size	36
Classes	2
Training epochs	100

Figure 7. Comparing the AUROC values of the transfer learning model ResNet-50 with different attention mechanisms.

Table 4. Comparison of the transfer learning model ResNet-50 with different attention mechanisms.

Model	Validation Method	Accuracy	Precision	Recall	Specificity	F1	AUROC
ResNet-50	CV	0.930 ± 0.015	0.930 ± 0.019	0.930 ± 0.022	0.923 ± 0.015	0.930 ± 0.017	0.948 ± 0.015
	Hold-out	0.939 ± 0.022	0.942 ± 0.017	0.939 ± 0.02	0.944 ± 0.016	0.939 ± 0.0015	0.952 ± 0.017
CBAM-ResNet-50	CV	0.938 ± 0.012	0.938 ± 0.015	0.937 ± 0.019	0.937 ± 0.012	0.937 ± 0.02	0.959 ± 0.013
	Hold-out	0.946 ± 0.011	0.946 ± 0.017	0.946 ± 0.018	0.946 ± 0.012	0.946 ± 0.015	0.963 ± 0.019
SE-ResNet-50	CV	0.941 ± 0.008	0.941 ± 0.01	0.941 ± 0.009	0.938 ± 0.009	0.941 ± 0.01	0.965 ± 0.011
	Hold-out	0.949 ± 0.008	0.949 ± 0.009	0.955 ± 0.009	0.949 ± 0.01	0.948 ± 0.012	0.969 ± 0.006
CBAM-SEResNet-50	CV	0.944 ± 0.009	0.943 ± 0.01	0.944 ± 0.008	0.944 ± 0.009	0.943 ± 0.007	0.971 ± 0.007
	Hold-out	0.956 ± 0.008	0.956 ± 0.007	0.956 ± 0.009	0.956 ± 0.006	0.956 ± 0.01	0.972 ± 0.007

Figure 8. Confusion matrices of different sweetener identification models.

Figure 9. Comparison of AUROC values for different transfer learning driven sweetener identification algorithms.

Table 5. Comparison of different transfer learning driven sweetener identification models.

Model	Validation Method	Accuracy	Precision	Recall	Specificity	F1	AUROC
CBAM-SEResNet-50	CV	0.944 ± 0.009	0.943 ± 0.01	0.944 ± 0.008	0.944 ± 0.009	0.943 ± 0.007	0.971 ± 0.007
	Hold-out	0.956 ± 0.008	0.956 ± 0.007	0.956 ± 0.009	0.956 ± 0.006	0.956 ± 0.01	0.972 ± 0.007
AlexNet	CV	0.879 ± 0.023	0.883 ± 0.03	0.879 ± 0.021	0.869 ± 0.022	0.878 ± 0.019	0.899 ± 0.02
	Hold-out	0.883 ± 0.021	0.889 ± 0.03	0.883 ± 0.022	0.890 ± 0.025	0.883 ± 0.031	0.909 ± 0.021
GoogleNet	CV	0.911 ± 0.018	0.911 ± 0.015	0.910 ± 0.019	0.909 ± 0.02	0.910 ± 0.021	0.932 ± 0.015
	Hold-out	0.922 ± 0.02	0.940 ± 0.018	0.940 ± 0.015	0.937 ± 0.012	0.940 ± 0.017	0.937 ± 0.02
VGG-16	CV	0.921 ± 0.018	0.921 ± 0.02	0.921 ± 0.015	0.919 ± 0.01	0.915 ± 0.015	0.944 ± 0.021
	Hold-out	0.929 ± 0.015	0.937 ± 0.018	0.933 ± 0.012	0.939 ± 0.01	0.934 ± 0.013	0.948 ± 0.015
DenseNet-121	CV	0.933 ± 0.02	0.933 ± 0.015	0.933 ± 0.019	0.934 ± 0.017	0.933 ± 0.022	0.953 ± 0.013
	Hold-out	0.940 ± 0.012	0.941 ± 0.019	0.941 ± 0.023	0.941 ± 0.02	0.941 ± 0.019	0.955 ± 0.017

Table 6. Comparison with previous sweetener identification methods.

Research	Feature	Model	Accuracy	Recall	Specificity	AUROC
Lee et al. (2022)	Descriptor, Fingerprint	Ensemble learning	/	0.907	0.891	0.961
Fritz et al. (2021)	Fingerprint	RF	0.890	0.860	0.920	0.950
Zheng et al. (2019)	Fingerprint	Ensemble learning	0.910	0.860	0.940	0.910
Rojas et al. (2017)	Descriptor, Fingerprint	PLS-DA, KNN	/	/	0.880	0.816
Tuwani et al. (2019)	Descriptor, Fingerprint	AdaBoost, RF	/	/	0.790	0.878
Bo et al. (2022)	2D image	CNN	0.840	0.850	0.850	0.900
This paper	2D image	CBAM-SEResNet-50	0.956	0.956	0.956	0.972

Figure 10. Visualization of the convolutional layers, maximum-pooling layers, and residual layers in the CBAM-SEResNet-50 model.

Figure 11. Visualizing the regions of interest (ROI) of sweet molecule images with hydroxyl groups.

Figure 12. Visualizing the ROI of sweet molecule images with carbonyl and amino groups.

Table 7. The similarity threshold, the number of compounds outside AD for each threshold, and the corresponding AUROC value.

Similarity metrics	Threshold value	# of Compounds outside the AD	Recalculated AUROC
Maximum similarity	0.85	0	0.967
	0.86	1	0.973
	0.87	3	0.970
	0.88	4	0.968
Mean similarity	0.79	0	0.967
	0.80	2	0.970
	0.81	6	0.965
	0.82	10	0.963

Table 8. Sweetener identification applications of CBAM-SEResNet-50 on different datasets.

Dataset	Model	Molecules in AD	The number of sweeteners
FlavorDB	CBAM-SEResNet-50	2,105	1,675
	(Tuwani et al., 2019)	2,294	1,650
FooDB	CBAM-SEResNet-50	21,756	11,485
	(Tuwani et al., 2019)	20,122	8,525
Super Natural II	CBAM-SEResNet-50	298,416	67,586
	(Tuwani et al., 2019)	280,989	59,414

Table 9. The identification results of the CBAM-SEResNet-50 model on a multi-taste molecule dataset.

Model	Validation Method	Accuracy	Precision	Recall	Specificity	F1	AUROC
CBAM-SEResNet-50	CV	0.919 ± 0.007	0.899 ± 0.012	0.901 ± 0.015	0.901 ± 0.007	0.903 ± 0.006	0.950 ± 0.009
	Hold-out	0.926 ± 0.009	0.907 ± 0.005	0.917 ± 0.012	0.917 ± 0.011	0.912 ± 0.01	0.953 ± 0.007

Rojas, C., Ballabio, D., Consonni, V., Tripaldi, P., Mauri, A., & Todeschini, R. (2016). Quantitative structure–activity relationships to predict sweet and non-sweet tastes. Theoretical Chemistry Accounts, 135(3), 1–13. https://doi.org/10.1007/s00214-016-1812-1

 Web of Science ®Google Scholar

Rojas, C., Todeschini, R., Ballabio, D., Mauri, A., Consonni, V., Tripaldi, P., & Grisoni, F. (2017). A QSTR-based expert system to predict sweetness of molecules. Frontiers in Chemistry, 5, 53. https://doi.org/10.3389/fchem.2017.00053

 PubMed Web of Science ®Google Scholar

Tuwani, R., Wadhwa, S., & Bagler, G. (2019). BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules. Scientific Reports, 9(1), 7155. https://doi.org/10.1038/s41598-019-43664-y

 PubMedGoogle Scholar

Garg, N., Sethupathy, A., Tuwani, R., Nk, R., Dokania, S., Iyer, A., Gupta, A., Agrawal, S., Singh, N., Shukla, S., Kathuria, K., Badhwar, R., Kanji, R., Jain, A., Kaur, A., Nagpal, R., & Bagler, G. (2018). FlavorDB: A database of flavor molecules. Nucleic Acids Research, 46(D1), D1210–D1216. https://doi.org/10.1093/nar/gkx957

 PubMed Web of Science ®Google Scholar

Dagan-Wiener, A., DiPizio, A., Nissim, I., Bahia, M. S., Dubovski, N., Margulis, E., & Niv, M. Y. (2019). BitterDB: Taste ligands and receptors database in 2019. Nucleic Acids Research, 47(D1), D1179–D1185. https://doi.org/10.1093/nar/gky974

 PubMed Web of Science ®Google Scholar

Lee, J., Song, S. B., Chung, Y. K., Jang, J. H., & Huh, J. (2022). BoostSweet: Learning molecular perceptual representations of sweeteners. Food Chemistry, 383, 132435. https://doi.org/10.1016/j.foodchem.2022.132435

 PubMed Web of Science ®Google Scholar

Fritz, F., Preissner, R., & Banerjee, P. (2021). VirtualTaste: A web server for the prediction of organoleptic properties of chemical compounds. Nucleic Acids Research, 49(W1), W679–W684. https://doi.org/10.1093/nar/gkab292

 PubMed Web of Science ®Google Scholar

Zheng, S., Chang, W., Xu, W., Xu, Y., & Lin, F. (2019). E-sweet: A machine-learning based platform for the prediction of sweetener and its relative sweetness. Frontiers in Chemistry, 7, 35. https://doi.org/10.3389/fchem.2019.00035

 PubMed Web of Science ®Google Scholar

Bo, W., Qin, D., Zheng, X., Wang, Y., Ding, B., Li, Y., & Liang, G. (2022). Prediction of bitterant and sweetener using structure-taste relationship models based on an artificial neural network. Food Research International, 153, 110974. https://doi.org/10.1016/j.foodres.2022.110974

 PubMed Web of Science ®Google Scholar