Table 3a.
Model descriptions.
| Name | Type | Data source | Data quantity | Goal | Model | Year |
|---|---|---|---|---|---|---|
| SMILES to Smell: Decoding the Structure–Odor Relationship of Chemical Compounds Using the Deep Neural Network Approach (Sharma et al., 2021b) | Odor | PubChem, GoodScents, Sigma-Aldrich, FlavorBase, Flavornet, SuperScent, ODORactor, AromaDB | 5185 chems | 104 odors | RF, DNN∗ (PPMF)/CNN∗ (images) | 2021 |
| Predicting odor from vibrational spectra: a data-driven approach (Ameta et al., 2024) | Odor | Leffingwell, Chemistry Webbook | 3018 chems | 109 odors | MLP | 2024 |
| Predicting natural language descriptions of mono-molecular odorants (Gutiérrez et al., 2018) | Odor | DREAM, Dravnieks, Dragon molecular descriptors | 476 chems, 19 odors | 131 odors | Elastic net regression | 2018 |
| A principal odor map unifies diverse tasks in olfactory perception (Lee et al., 2023) | Odor | GoodScents, Leffingwell | ∼5000 chems, 400 odors | 138 odors | MPNN | 2023 |
| Odor Impression Prediction from Mass Spectra (Nozaki and Nakamoto, 2016) | Odor | Chemistry WebBook, Dravnieks | 121 chems, 144 odors | 144 odors | Autoencoder for dimensionality reduction, then 9-layer NN | 2016 |
| Application of artificial intelligence to decode the relationships between smell, olfactory receptors and small molecules (Achebouche et al., 2022) | Odor | GS/LF | 5955 chem, 160 odors, 106 OR's | 160 odors/23 odor groups | CNN, GCN∗ | 2022 |
| XGBoost odor prediction model: finding the structure-odor relationship of odorant molecules using the extreme gradient boosting algorithm (Tyagi et al., 2024) | Odor | OlfactionBase | 1278 chems | 7 odors | XGBoost | 2023 |
| Predictive modeling for odor character of a chemical using machine learning combined with natural language processing (Nozaki and Nakamoto, 2018) | Odor | Chemistry Webbook, Sigma-Aldrich | 999 chems, 138 odors | Odor groups of size 6, 20, and 30 | Autoencoder for dimensionality reduction, then 4-layer NN | 2018 |
| iBitter-SCM: Identification and characterization of bitter peptides using a scoring card method with propensity scores of dipeptides (Charoenkwan et al., 2020a) | Taste | BIOPEP, literature review | 640 peptides | Bitter | Scoring card method | 2020 |
| e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-Learning Methods (Zheng et al., 2018) | Taste | BitterDB, SuperSweet, SweetenersDB, literature review | 1299 chems | Bitter | Ensemble: KNN, SVM, RF, GBM, and DNN | 2018 |
| BitterX: a tool for understanding bitter taste in humans (Huang et al., 2016) | Taste | BitterDB, literature review | 1078 chems | Bitter | SVM + GA | 2016 |
| Bitter or not? BitterPredict, a tool for predicting taste from chemical structure (Dagan-Wiener et al., 2017) | Taste | BitterDB, TOXNET, literature review | 2608 chems | Bitter | AdaBoost | 2017 |
| BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides (Charoenkwan et al., 2021a) | Taste | BTP640 | 640 peptides | Bitter/non-bitter | BERT∗, CNN, LSTM | 2021 |
| iBitter-Fuse: A Novel Sequence-Based Bitter Peptide Predictor by Fusing Multi-View Features (Charoenkwan et al., 2021c) | Taste | BTP640 | 640 peptides | Bitter/non-bitter | SVM | 2021 |
| Prediction of bitterant and sweetener using structure-taste relationship models based on an artificial neural network (Bo et al., 2022) | Taste | BitterDB, SuperSweet, FlavorDB | 4599 chems | Bitter/non-bitter, sweet/non-sweet, and bitter/sweet | CNN, MLP∗ | 2022 |
| Novel scaffold of natural compound eliciting sweet taste revealed by machine learning (Bouysset et al., 2020) | Taste | SweetenersDB | 316 chems | Relative sweetness | RF, SVM, AdaBoost∗, k-NN | 2020 |
| Sweetness prediction of natural compounds (Chéron et al., 2017b) | Taste | SweetenersDB | 316 chems | Relative sweetness | SVR∗, RF | 2017 |
| A QSTR-Based Expert System to Predict Sweetness of Molecules (Rojas et al., 2017) | Taste | TastesDB | 649 chems | Sweet | k-NN + PLSDA consensus | 2017 |
| Machine learning models to predict sweetness of molecules (Goel et al., 2023) | Taste | SweetpredDB | 671 chems | Relative sweetness | Gradient Boost Regressor∗, RF | 2023 |
| VirtualTaste: a web server for the prediction of organoleptic properties of chemical compounds (Fritz et al., 2021) | Taste | SuperSweet, BitterDB, ChEMBL, literature review | 4111 chems | Sweet, bitter, sour | RF | 2021 |
| Predicting multiple taste sensations with a multiobjective machine learning method (Androutsos et al., 2024) | Taste | BitterDB Fenaroli SuperSweet SweetenersDB UMP442 ChemTastesDB BIOPEP-UWM, literature review | 4717 chems | Sweet, bitter, umami, other | RF | 2024 |
| BitterSweetForest: A Random Forest Based Binary Classifier to Predict Bitterness and Sweetness of Chemical Compounds (Banerjee and Preissner, 2018) | Taste | SuperSweet, BitterDB | 1202 chems | Sweet/bitter | RF | 2018 |
| Informed classification of sweeteners/bitterants compounds via explainable machine learning (Maroni et al., 2022) | Taste | BitterDB, Fenaroli, SuperSweet, GoodScents, SweetenersDB, literature review | 2686 chems | Sweet/bitter | Logistic Regression, k-NN, RF, LightGBM∗, MLP | 2022 |
| BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules (Tuwani et al., 2019) | Taste | BitterDB, Fenaroli, SuperSweet, SweetenersDB, literature review | 4804 chems | Sweet/non-sweet bitter/non-bitter | RF∗ (bitter), Ridge Logistic Regression, AdaBoost∗ (Sweet) | 2019 |
| e-Sweet: A Machine-Learning Based Platform for the Prediction of Sweetener and Its Relative Sweetness (Zheng et al., 2019) | Taste | SuperSweet, SweetenersDB, literature review | 1380 chems | Sweet/non-sweet, relative sweetness | KNN, SVM, GBM, RF, and DNN consensus model | 2019 |
| A Comprehensive Comparative Analysis of Deep Learning Based Feature Representations for Molecular Taste Prediction (Song et al., 2023) | Taste | ChemTastesDB | 2601 chems | Sweet/non-sweet, bitter/non-bitter, umami/non-umami | GNN, CNN, consensus model∗ | 2023 |
| BoostSweet: Learning molecular perceptual representations of sweeteners (Lee et al., 2022) | Taste | BitterSweet | 2291 chems | Sweet/non-sweet | RF, XGB, LGBM, FCN soft vote ensemble | 2022 |
| A novel multi-layer prediction approach for sweetness evaluation based on systematic machine learning modeling (Yang et al., 2022) | Taste | Taste DB and LogSw DB | 2861 chems | Relative sweetness | Decision Tree, kNN, SVM, RF, XGBoost, GBT, PLS, SVR∗ | 2022 |
| Toward a general and interpretable umami taste predictor using a multi-objective machine learning approach (Pallante et al., 2022) | Taste | UMP442 | 442 peptides | Umami | SVM Ensemble | 2022 |
| iUmami-SCM: A Novel Sequence-Based Predictor for Prediction and Analysis of Umami Peptides Using a Scoring Card Method with Propensity Scores of Dipeptides (Charoenkwan et al., 2020b) | Taste | BIOPEP-UWM, literature review | 442 peptides | Umami | Scoring Card Method | 2020 |
| UMPred-FRL: A New Approach for Accurate Prediction of Umami Peptides Using Feature Representation Learning (Charoenkwan et al., 2021b) | Taste | UMP442 | 442 peptides | Umami | SVM | 2021 |
| Umami-BERT: An interpretable BERT-based model for umami peptides prediction (Zhang et al., 2023) | Taste | UMP789 | 789 peptides | Umami | BERT | 2023 |
| Umami-MRNN: Deep learning-based prediction of umami peptide using RNN and MLP (Qi et al., 2023) | Taste | BIOPEP-UWM, literature review | 499 peptides | Umami | MLP + RNN | 2023 |
| Artificial neural networks modeling of non-fat yogurt texture properties: effect of process conditions and food composition (Batista et al., 2021) | Texture | Self-collected | 13 samples | Firmness, cohesiveness, adhesiveness, and gumminess | ANN | 2021 |
| Predicting the Textural Properties of Plant-Based Meat Analogs with Machine Learning (Kircali Ata et al., 2023) | Texture | Literature review | 54 samples | Hardness, chewiness | Ridge∗, RF, XGBoost, KNN∗, MLP | 2023 |
| Rapid and Non-Invasive Assessment of Texture Profile Analysis of Common Carp (Cyprinus carpio L.) Using Hyperspectral Imaging and Machine Learning (Cao et al., 2023) | Texture | Self-collected | 387 samples | Gumminess, springiness, cohesiveness, resilience, hardness, brittleness, adhesiveness, chewiness | ANN, SVM, and PLSR (different models optimal for different objectives) | 2023 |
| Prediction of textural characteristics in low-fat mozzarella cheese by Hyperspectral imaging using machine learning methods (Jahani et al., 2024) | Texture | Self-collected | 36 samples | Hardness, adhesiveness, springiness, cohesiveness, gumminess, chewiness | MLR, PLSR, SVM, MLP∗, RF∗, consensus model∗ | 2024 |
| Non-destructive prediction of texture of frozen/thaw raw beef by Raman spectroscopy (Chen et al., 2020) | Texture | Self-collected | 16 samples | Tenderness, chewiness, firmness, hardness, springiness | PLSR | 2020 |
| Prediction of textural changes in grass carp fillets as affected by vacuum freeze drying using hyperspectral imaging based on integrated group wavelengths (Ma et al., 2017) | Texture | Self-collected | 112 samples | WBSF, hardness, gumminess, chewiness | PLSR | 2017 |
| Prediction of color, texture, and sensory characteristics of beef steaks by visible and near infrared reflectance spectroscopy. A feasibility study (Liu et al., 2003) | Texture | Self-collected | 113 samples | Tender/tough | SIMCA∗, PLSR | 2003 |
| Rapid determination of the textural properties of silver carp (Hypophthalmichthys molitrix) using near-infrared reflectance spectroscopy and chemometrics (Zhou et al., 2020) | Texture | Self-collected | 150 samples | WHC, hardness, resilience, springiness, chewiness, shear force | PLSR | 2020 |
| Potential of hyperspectral imaging combined with chemometric analysis for assessing and visualising tenderness distribution in raw farmed salmon fillets (He et al., 2014) | Texture | Self-collected | 164 samples | WBSF | PLSR, SVM∗ | 2014 |
A list of taste, odor, and texture predicting models with relevant information such as the type of model used, publication date, and data sources.