research-article
Authors: Yi He, Yilin Gao, Kaifeng Liu, Weiwei Han
Volume 184, Issue C
Published: 11 February 2025 Publication History
Metrics
Total Citations0Total Downloads0Last 12 Months0
Last 6 weeks0
New Citation Alert added!
This alert has been successfully added and will be sent to:
You will be notified whenever a record that you have chosen has been cited.
To manage your alert preferences, click on the button below.
Manage my Alerts
New Citation Alert!
Please log in to your account
- View Options
- References
- Figures
- Tables
- Media
- Share
Abstract
Astringency, a sensory experience causing mouth dryness, significantly impacts the taste of foods such as wine and tea, and astringent molecules may exhibit antibacterial properties. Traditional methods for predicting astringency are costly, and the connection between astringency and antibacterial activity remains largely unexplored. In this study, we present a pioneering computational approach that includes: (1) the creation of the first comprehensive astringency database comprising 238 molecules; (2) the development of a Ligand-Based Prediction (LBP) framework that combines large language models, deep learning, and traditional machine learning for enhanced molecular and peptide prediction; (3) an astringency predictor achieving 0.95 accuracy and 0.90 AUC, validated through electronic tongue measurements; (4) antibacterial predictors for molecules and peptides with accuracies of 0.92 and 0.88, respectively, revealing that 51% of astringent molecules possess antibacterial properties; (5) accessibility of these predictors via the AstringentPD and ABPD web servers. This work not only enhances the understanding of taste-related molecules but also elucidates the relationship between astringency and antibacterial properties, setting the stage for future explorations in food science and medicinal applications.
Highlights
•
Compiled 238 molecules as a large-scale astringency research resource.
•
Developed a Ligand-Based Prediction (LBP) framework to enhance prediction accuracy.
•
Achieved 95% accuracy and 0.90 AUC in astringency prediction, validated with electronic tongue experiments.
•
Created antibacterial predictors for molecules and peptides with accuracies of 92% and 88%, respectively.
•
Made prediction tools publicly available on AstringentPD and ABPD web servers.
References
[1]
W. Wu, Q.G. Zhu, W.Q. Wang, D. Grierson, X.R. Yin, Molecular basis of the formation and removal of fruit astringency, Food Chem. 372 (2022).
[2]
M.-P. Sáenz-Navajas, P. Fernández-Zurbano, V. Ferreira, Contribution of nonvolatile composition to wine flavor, Food Rev. Int. 28 (2012) 389–411.
[3]
S. Deng, G. Zhang, O. Olayemi Aluko, Z. Mo, J. Mao, H. Zhang, X. Liu, M. Ma, Q. Wang, H. Liu, Bitter and astringent substances in green tea: composition, human perception mechanisms, evaluation methods and factors influencing their formation, Food Res. Int. 157 (2022).
[4]
S. Scharbert, T. Hofmann, Molecular definition of black tea taste by means of quantitative studies, taste reconstitution, and omission experiments, J. Agric. Food Chem. 53 (2005) 5377–5384.
[5]
C. Masi, C. Dinnella, E. Monteleone, J. Prescott, The impact of individual variations in taste sensitivity on coffee perceptions and preferences, Physiol. Behav. 138 (2015) 219–226.
[6]
R. Huang, C. Xu, An overview of the perception and mitigation of astringency associated with phenolic compounds, Compr. Rev. Food Sci. Food Saf. 20 (2021) 1036–1074.
[7]
T. Stark, S. Bareuther, T. Hofmann, Molecular definition of the taste of roasted cocoa nibs (Theobroma cacao) by means of quantitative studies and sensory experiments, J. Agric. Food Chem. 54 (2006) 5530–5539.
[8]
K. Colonges, E. Seguine, A. Saltos, F. Davrieux, J. Minier, J.C. Jimenez, M.C. Lahon, D. Calderon, C. Subia, I. Sotomayor, F. Fernández, O. Fouet, B. Rhoné, X. Argout, M. Lebrun, P. Costet, C. Lanaud, R. Boulanger, R.G. Loor Solorzano, Diversity and determinants of bitterness, astringency, and fat content in cultivated Nacional and native Amazonian cocoa accessions from Ecuador, Plant Genome 15 (2022).
[9]
A. Karolkowski, C. Belloir, L. Briand, C. Salles, Non-volatile compounds involved in bitterness and astringency of pulses: a review, Molecules 28 (2023).
[10]
J.-H. Ye, Y. Ye, J.-F. Yin, J. Jin, Y.-R. Liang, R.-Y. Liu, P. Tang, Y.-Q. Xu, Bitterness and astringency of tea leaves and products: formation mechanism and reducing strategies, Trends Food Sci. Technol. 123 (2022) 130–143.
[11]
M. Kawakami, A. Kobayashi, Volatile constituents of green mate and roasted mate, J. Agric. Food Chem. 39 (1991) 1275–1279.
[12]
N. Bhumiratana, K. Adhikari, E. Chambers, Evolution of sensory aroma attributes from coffee beans to brewed coffee, LWT - Food Sci. Technol. (Lebensmittel-Wissenschaft -Technol.) 44 (2011) 2185–2192.
[13]
I. García-Estévez, A.M. Ramos-Pineda, M.T. Escribano-Bailón, Interactions between wine phenolic compounds and human saliva in astringency perception, Food Funct. 9 (2018) 1294–1309.
[14]
J. Liu, J. Xie, J. Lin, X. Xie, S. Fan, X. Han, D.-k. Zhang, L. Han, The material basis of astringency and the deastringent effect of polysaccharides: a review, Food Chem. 405 (2023).
[15]
A.M. Ramos-Pineda, I. García-Estévez, S. Soares, V. de Freitas, M. Dueñas, M.T. Escribano-Bailón, Synergistic effect of mixture of two proline-rich-protein salivary families (aPRP and bPRP) on the interaction with wine flavanols, Food Chem. 272 (2019) 210–215.
[16]
M.Y. Qi, Y.C. Huang, X.X. Song, M.Q. Ling, X.K. Zhang, C.Q. Duan, Y.B. Lan, Y. Shi, Artificial saliva precipitation index (ASPI): an efficient evaluation method of wine astringency, Food Chem. 413 (2023).
[17]
M.R. Bajec, G.J. Pickering, Astringency: mechanisms and perception, Crit. Rev. Food Sci. Nutr. 48 (2008) 858–875.
[18]
T.P. Cushnie, A.J. Lamb, Antimicrobial activity of flavonoids, Int. J. Antimicrob. Agents 26 (2005) 343–356.
[19]
C.-T. Liu, J.T.C. Tzen, Exploring the relative astringency of tea catechins and distinct astringent sensation of catechins and flavonol glycosides via an in vitro assay composed of artificial oil bodies, Molecules 27 (2022) 5679.
[20]
A.M. Ramos-Pineda, I. García-Estévez, M. Dueñas, M.T. Escribano-Bailón, Effect of the addition of mannoproteins on the interaction between wine flavonols and salivary proteins, Food Chem. 264 (2018) 226–232.
[21]
J. Kováč, L. Slobodníková, E. Trajčíková, K. Rendeková, P. Mučaji, A. Sychrová, S. Bittner Fialová, Therapeutic potential of flavonoids and tannins in management of oral infectious diseases-A review, Molecules 28 (2022).
[22]
P. Tarighi, M. Khoroushi, A review on common chemical hemostatic agents in restorative dentistry, Dent. Res. J. 11 (2014) 423–428.
[23]
Betony, Drugs and Lactation Database (LactMed®), National Institute of Child Health and Human Development, Bethesda (MD), 2006.
[24]
Dragon’s Blood, LiverTox: Clinical and Research Information on Drug-Induced Liver Injury, National Institute of Diabetes and Digestive and Kidney Diseases, Bethesda (MD), 2012.
[25]
G.E. Batiha, A.E. Al-Snafi, M.M. Thuwaini, J.O. Teibo, H.M. Shaheen, A.P. Akomolafe, T.K.A. Teibo, H.M. Al-Kuraishy, A.I. Al-Garbeeb, A. Alexiou, M. Papadakis, Morus alba: a comprehensive phytochemical and pharmacological review, Naunyn-Schmiedeberg’s Arch. Pharmacol. 396 (2023) 1399–1413.
[26]
A. Gupta, A.N. Atkinson, A.K. Pandey, A. Bishayee, Health-promoting and disease-mitigating potential of Verbascum thapsus L. (common mullein): a review, Phytother Res. 36 (2022) 1507–1522.
[27]
M. Leonti, S. Bellot, P. Zucca, A. Rescigno, Astringent drugs for bleedings and diarrhoea: the history of Cynomorium coccineum (Maltese Mushroom), J. Ethnopharmacol. 249 (2020).
[28]
G. Yuan, Y. Guan, H. Yi, S. Lai, Y. Sun, S. Cao, Antibacterial activity and mechanism of plant flavonoids to gram-positive bacteria predicted from their lipophilicities, Sci. Rep. 11 (2021).
[29]
M. Kuroyanagi, T. Arakawa, Y. Hirayama, T. Hayashi, Antibacterial and antiandrogen flavonoids from Sophora flavescens, J. Nat. Prod. 62 (1999) 1595–1599.
[30]
Y. Xie, W. Yang, F. Tang, X. Chen, L. Ren, Antibacterial activities of flavonoids: structure-activity relationship and mechanism, Curr. Med. Chem. 22 (2015) 132–149.
[31]
I. Lesschaeve, A.C. Noble, Polyphenols: factors influencing their sensory properties and their effects on food and beverage preferences, Am. J. Clin. Nutr. 81 (2005) 330s–335s.
[32]
A. Rudnitskaya, A. Legin, Sensor systems, electronic tongues and electronic noses, for the monitoring of biotechnological processes, J. Ind. Microbiol. Biotechnol. 35 (2008) 443–451.
[33]
C. Rojas, D. Ballabio, V. Consonni, D. Suárez-Estrella, R. Todeschini, Classification-based machine learning approaches to predict the taste of molecules: a review, Food Res. Int. 171 (2023).
[34]
T. Guo, F. Pan, Z. Cui, Z. Yang, Q. Chen, L. Zhao, H. Song, FAPD: an astringency threshold and astringency type prediction database for flavonoid compounds based on machine learning, J. Agric. Food Chem. 71 (2023) 4172–4183.
[35]
W. Bo, D. Qin, X. Zheng, Y. Wang, B. Ding, Y. Li, G. Liang, Prediction of bitterant and sweetener using structure-taste relationship models based on an artificial neural network, Food Res. Int. 153 (2022).
[36]
H. Li, R. Zhang, Y. Min, D. Ma, D. Zhao, J. Zeng, A knowledge-guided pre-training framework for improving molecular representation learning, Nat. Commun. 14 (2023) 7568.
[37]
V. Svetnik, A. Liaw, C. Tong, J.C. Culberson, R.P. Sheridan, B.P. Feuston, Random forest: a classification and regression tool for compound classification and QSAR modeling, J. Chem. Inf. Comput. Sci. 43 (2003) 1947–1958.
[38]
C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn. 20 (1995) 273–297.
[39]
F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain, Psychol. Rev. 65 (1958) 386–408.
[40]
S. Kearnes, K. McCloskey, M. Berndl, V. Pande, P. Riley, Molecular graph convolutions: moving beyond fingerprints, J. Comput. Aided Mol. Des. 30 (2016) 595–608.
[41]
Z. Cui, Z. Zhang, T. Zhou, X. Zhou, Y. Zhang, H. Meng, W. Wang, Y. Liu, A TastePeptides-Meta system including an umami/bitter classification model Umami_YYDS, a TastePeptidesDB database and an open-source package Auto_Taste_ML, Food Chem. 405 (2023).
[42]
J.M. Stokes, K. Yang, K. Swanson, W. Jin, A. Cubillos-Ruiz, N.M. Donghia, C.R. MacNair, S. French, L.A. Carfrae, Z. Bloom-Ackermann, V.M. Tran, A. Chiappino-Pepe, A.H. Badran, I.W. Andrews, E.J. Chory, G.M. Church, E.D. Brown, T.S. Jaakkola, R. Barzilay, J.J. Collins, A deep learning approach to antibiotic Discovery, Cell 180 (2020) 688–702.e613.
[43]
N. Bajiya, S. Choudhury, A. Dhall, G.P.S. Raghava, AntiBP3: a method for predicting antibacterial peptides against gram-positive/negative/variable bacteria, Antibiotics 13 (2024).
[44]
Y. He, K. Liu, L. Han, W. Han, Clustering analysis, structure fingerprint analysis, and quantum chemical calculations of compounds from essential oils of sunflower (helianthus annuus L.) receptacles, Int. J. Mol. Sci. 23 (2022) 10169.
[45]
Z. Du, X. Ding, W. Hsu, A. Munir, Y. Xu, Y. Li, pLM4ACE: a protein language model based predictor for antihypertensive peptide screening, Food Chem. 431 (2024).
[46]
S. Soares, E. Brandão, I. García-Estevez, F. Fonseca, C. Guerreiro, F. Ferreira-da-Silva, N. Mateus, D. Deffieux, S. Quideau, V. de Freitas, Interaction between ellagitannins and salivary proline-rich proteins, J. Agric. Food Chem. 67 (2019) 9579–9590.
[47]
Y. Lu, A. Bennick, Interaction of tannin with human salivary proline-rich proteins, Arch. Oral Biol. 43 (1998) 717–728.
[48]
F.G. Oppenheim, E. Salih, W.L. Siqueira, W. Zhang, E.J. Helmerhorst, Salivary proteome and its genetic polymorphisms, Ann. N. Y. Acad. Sci. 1098 (2007) 22–50.
[49]
A. Gambuti, A. Rinaldi, R. Pessina, L. Moio, Evaluation of aglianico grape skin and seed polyphenol astringency by SDS–PAGE electrophoresis of salivary proteins after the binding reaction, Food Chem. 97 (2006) 614–620.
[50]
M.D. Hanwell, D.E. Curtis, D.C. Lonie, T. Vandermeersch, E. Zurek, G.R. Hutchison, Avogadro: an advanced semantic chemical editor, visualization, and analysis platform, J. Cheminf. 4 (2012) 17.
[51]
M.J. Frisch, G. Trucks, H.B. Schlegel, G.E. Scuseria, M.A. Robb, J. Cheeseman, G. Scalmani, V. Barone, B. Mennucci, G.A. Petersson, H. Nakatsuji, M. Caricato, X. Li, H.P. Hratchian, A.F. Izmaylov, J. Bloino, G. Zheng, J. Sonnenberg, M. Hada, D. Fox, Gaussian 09 Revision A.1, Gaussian Inc, 2009.
[52]
J. Eberhardt, D. Santos-Martins, A.F. Tillack, S. Forli, AutoDock Vina 1.2.0: new docking methods, expanded force field, and Python bindings, J. Chem. Inf. Model. 61 (2021) 3891–3898.
[53]
S. Forli, R. Huey, M.E. Pique, M.F. Sanner, D.S. Goodsell, A.J. Olson, Computational protein-ligand docking and virtual drug screening with the AutoDock suite, Nat. Protoc. 11 (2016) 905–919.
[54]
Y.D. Gao, J.F. Huang, [An extension strategy of Discovery Studio 2.0 for non-bonded interaction energy automatic calculation at the residue level], Dongwuxue Yanjiu 32 (2011) 262–266.
[55]
S.A. Wildman, G.M. Crippen, Prediction of physicochemical parameters by atomic contributions, J. Chem. Inf. Comput. Sci. 39 (1999) 868–873.
[56]
A. Rauf, M. Imran, T. Abu-Izneid, H. Iahtisham Ul, S. Patel, X. Pan, S. Naz, A. Sanches Silva, F. Saeed, H.A. Rasul Suleria, Proanthocyanidins: a comprehensive review, Biomed. Pharmacother. 116 (2019).
[57]
X.L. Hu, X.Y. Lv, R. Wang, H. Long, J.H. Feng, B.L. Wang, W. Shen, H. Liu, F. Xiong, X.Q. Zhang, W.C. Ye, H. Wang, Optimization of N-Phenylpropenoyl-l-amino acids as potent and selective inducible nitric oxide synthase inhibitors for Parkinson's disease, J. Med. Chem. 64 (2021) 7760–7777.
[58]
A. Hensel, A.M. Deters, G. Müller, T. Stark, N. Wittschier, T. Hofmann, Occurrence of N-phenylpropenoyl-L-amino acid amides in different herbal drugs and their influence on human keratinocytes, on human liver cells and on adhesion of Helicobacter pylori to the human stomach, Planta Med. 73 (2007) 142–150.
[59]
O. Cala, N. Pinaud, C. Simon, E. Fouquet, M. Laguerre, E.J. Dufourc, I. Pianet, NMR and molecular modeling of wine tannins binding to saliva proteins: revisiting astringency from molecular and colloidal prospects, Faseb. J. 24 (2010) 4281–4290.
[60]
N.J. Baxter, T.H. Lilley, E. Haslam, M.P. Williamson, Multiple interactions between polyphenols and a salivary proline-rich protein repeat result in complexation and precipitation, Biochemistry 36 (1997) 5566–5577.
[61]
R.E.D. Rudge, P.L. Fuhrmann, R. Scheermeijer, E.M. van der Zanden, J.A. Dijksman, E. Scholten, A tribological approach to astringency perception and astringency prevention, Food Hydrocolloids 121 (2021).
[62]
H. Peleg, K.K. Bodine, A.C. Noble, The influence of acid on astringency of alum and phenolic compounds, Chem. Senses 23 (1998) 371–378.
[63]
F. Duprat, J.-L. Ploix, J.-M. Aubry, T. Gaudin, Fast and accurate prediction of refractive index of organic liquids with graph machines, Molecules 28 (2023) 6805.
[64]
P. Labute, A widely applicable set of descriptors, J. Mol. Graph. Model. 18 (2000) 464–477.
[65]
J. Xiao, T.S. Muzashvili, M.I. Georgiev, Advances in the biotechnological glycosylation of valuable flavonoids, Biotechnol. Adv. 32 (2014) 1145–1156.
[66]
G. Nenaah, Antimicrobial activity of Calotropis procera Ait. (Asclepiadaceae) and isolation of four flavonoid glycosides as the active constituents, World J. Microbiol. Biotechnol. 29 (2013) 1255–1262.
Index Terms
Database, prediction, and antibacterial research of astringency based on large language models
Applied computing
Life and medical sciences
Bioinformatics
Physical sciences and engineering
Chemistry
Computing methodologies
Machine learning
Learning paradigms
Supervised learning
Structured outputs
Human-centered computing
Visualization
Visualization application domains
Scientific visualization
Information systems
Information retrieval
Specialized information retrieval
Information systems applications
Index terms have been assigned to the content through auto-classification.
Recommendations
- Synthesis, molecular docking and comparative efficacy of various alkyl/aryl thioureas as antibacterial, antifungal and α-amylase inhibitors
Graphical abstract
Display Omitted
Highlights
- A small library of 1-alkyl/acyl-3-(2-cyano-4-nitrophenyl) thiourea was synthesized in good yields.
Abstract
Thioureas are exquisite building blocks for the construction of five and six membered heterocyclic units, and also display an extensive range of biological activities. 4-Nitro-2-cyano aniline was reacted with the various acid chlorides ...
Read More
- T5S1607 identified as a antibacterial FtsZ inhibitor：Virtual screening combined with bioactivity evaluation for the drug discovery
Abstract
Due to antibiotic overuse, many bacteria have developed resistance, creating an urgent need for novel antimicrobial agents. It has been established that the filamentous temperature-sensitive mutant Z (FtsZ) of the bacterial cell division protein ...
Graphical Abstract
Display Omitted
Highlights
- Virtual screening workflow has been established for FtsZ inhibitors.
- Three antimicrobial compounds were obtained through virtual screening.
- T5S1607 showed outstanding bactericidal efficacy against B. subtilis ATCC9732.
- ...
Read More
- Discovery of new Gyrase β inhibitors via structure based modeling
Graphical abstract
Display Omitted
Highlights
- 120 Gyrase b inhibitors were collected.
- LigandFit docking engines has been ...
Abstract
Gyrase B is an essential enzyme in the prokaryotes which became an attractive target for antibacterial agents. In our study, we implemented a wide range of docking configurations to dock 120 inhibitors into the in the ATP- binding ...
Read More
Comments
Information & Contributors
Information
Published In
Computers in Biology and Medicine Volume 184, Issue C
Jan 2025
1577 pages
Issue’s Table of Contents
Elsevier Ltd.
Publisher
Pergamon Press, Inc.
United States
Publication History
Published: 11 February 2025
Author Tags
- Astringent
- Antibacterial
- Large language model
- Webserver
Qualifiers
- Research-article
Contributors
Other Metrics
View Article Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
Total Citations
Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Feb 2025
Other Metrics
View Author Metrics
Citations
View Options
View options
Figures
Tables
Media
