Periodic Reporting for period 1 - VIRTUOUS (Virtual tongue to predIct the oRganoleptic profile of mediterranean IngredienTs and their effect on hUman hOmeostasis by means of an integrated compUtational multiphysicS platform)
Période du rapport: 2019-12-01 au 2021-11-30
The overarching objective of this RISE programme, called VIRTUOUS, is to develop a virtual tongue as an integrated computational framework to screen among selected ingredients of the Mediterranean diet (e.g. olive oil or wine) for natural ligands targeting taste receptors. More in detail, the proposed intelligent computational platform, by integrating drug discovery techniques, machine learning classifiers, algorithms for big data, cloud computing, and experimental data will predict the organoleptic profile of a selected type of food based on its chemical composition.
The outcomes of this research will shed light on the mechanisms driving the information transfer from the chemistry level, where food molecular constituents bind taste receptors, toward a cascade of molecular, supramolecular and cellular events emerging as an elaborated sensation that strongly contribute to the food organoleptic profile. Several scientific studies support the idea that taste receptors, key players in taste perception, are not only the first barrier against harmful foods but are also designed by nature to encourage the intake of those foods which contains molecular ingredients with long-term benefits to human homeostasis. By modelling molecular and multiscale phenomena related to ligand-receptor binding, we can link the predicted taste of a specific food to its possible long-term effects on body homeostasis.
The integration of molecular modelling techniques together with bioinformatics and machine learning applied to the compound search/discovery will lead to potential market opportunities in the field related to pharmaceutics, nutritional supplements as well as rational diet development.
The outcomes of this research will shed light on the mechanisms driving the information transfer from the chemistry level, where food molecular constituents bind taste receptors, toward a cascade of molecular, supramolecular and cellular events emerging as an elaborated sensation that strongly contribute to the food organoleptic profile. Several scientific studies support the idea that taste receptors, key players in taste perception, are not only the first barrier against harmful foods but are also designed by nature to encourage the intake of those foods which contains molecular ingredients with long-term benefits to human homeostasis. By modelling molecular and multiscale phenomena related to ligand-receptor binding, we can link the predicted taste of a specific food to its possible long-term effects on body homeostasis.
The integration of molecular modelling techniques together with bioinformatics and machine learning applied to the compound search/discovery will lead to potential market opportunities in the field related to pharmaceutics, nutritional supplements as well as rational diet development.
In the first phase of the project development (first two years), all the project beneficiaries have collectively worked together to design and develop the VIRTUOUS taste predicting platform from a technical point of view (models and ICT architecture):
The first crucial part of the activities concerned the definition of technical specifications of the multi-scale/multi-physics VIRTUOUS tongue ICT architecture/infrastructure. This piece of VIRTUOUS R&D activity specifically points out the major prerequisites and ICT approaches needed to store data and effectively implement every single modelling level (from atom to cell) and allow the integration of those modelling tools for the implementation of the final VIRTUOUS platform backend and frontend (Figure 1).
A second huge part of the project R&D activities has been developed on the modelling side, i.e. the research part dedicated to tailoring molecular and cellular models to predict taste with a multiscale/multiphysics approach. Partners with specific expertise in the modelling field have been supported by all the ICT partners in algorithm development for optimization and implementation into a web-based platform. Whereas experimental partners have provided information on model requirements and food chemical composition. Where needed, also experimental samples and associated chemical analysis have been furnished to modellers. Among modelling activities developed in the first two years, it is crucial to mention the definition/refinement of structural molecular models for all taste protein receptors (sweet, umami, bitter, sour, and salty) (Figure 2).
Furthermore, the project has developed and is currently testing several tools for the prediction using ML-based algorithms able to classify tastants or food ingredients based on their molecular structure. Scaling to another level of investigation, the protein-protein level was also deeply investigated by methods considering interlinked networks of proteins related to taste perception. Translational effects related to the interaction of the taste-related ligands with their relative receptors were studied by ad-hoc models/tools developed as new or tailored from existing ones.
A third important set of R&D activities, developed in the first two years of the project is related to the VIRTUOUS “trials” having the main challenge in guidance/employment/validation of the computational platform. In this context, the developed research activity concerns the investigation of relationships between food constituents, food properties and perceived taste by a combined approach made of experimental studies, organoleptic trials and AI-driven methodologies for data mining. Also, the VIRTUOUS project has contributed to the development of a low-cost approach for oil quality assessment by fluorescence spectroscopy.
All project events and results (also in terms of publications) can be easily found by exploring the VIRTUOUS official website (https://virtuoush2020.com/).
The first crucial part of the activities concerned the definition of technical specifications of the multi-scale/multi-physics VIRTUOUS tongue ICT architecture/infrastructure. This piece of VIRTUOUS R&D activity specifically points out the major prerequisites and ICT approaches needed to store data and effectively implement every single modelling level (from atom to cell) and allow the integration of those modelling tools for the implementation of the final VIRTUOUS platform backend and frontend (Figure 1).
A second huge part of the project R&D activities has been developed on the modelling side, i.e. the research part dedicated to tailoring molecular and cellular models to predict taste with a multiscale/multiphysics approach. Partners with specific expertise in the modelling field have been supported by all the ICT partners in algorithm development for optimization and implementation into a web-based platform. Whereas experimental partners have provided information on model requirements and food chemical composition. Where needed, also experimental samples and associated chemical analysis have been furnished to modellers. Among modelling activities developed in the first two years, it is crucial to mention the definition/refinement of structural molecular models for all taste protein receptors (sweet, umami, bitter, sour, and salty) (Figure 2).
Furthermore, the project has developed and is currently testing several tools for the prediction using ML-based algorithms able to classify tastants or food ingredients based on their molecular structure. Scaling to another level of investigation, the protein-protein level was also deeply investigated by methods considering interlinked networks of proteins related to taste perception. Translational effects related to the interaction of the taste-related ligands with their relative receptors were studied by ad-hoc models/tools developed as new or tailored from existing ones.
A third important set of R&D activities, developed in the first two years of the project is related to the VIRTUOUS “trials” having the main challenge in guidance/employment/validation of the computational platform. In this context, the developed research activity concerns the investigation of relationships between food constituents, food properties and perceived taste by a combined approach made of experimental studies, organoleptic trials and AI-driven methodologies for data mining. Also, the VIRTUOUS project has contributed to the development of a low-cost approach for oil quality assessment by fluorescence spectroscopy.
All project events and results (also in terms of publications) can be easily found by exploring the VIRTUOUS official website (https://virtuoush2020.com/).
The idea of conceiving a taste predictor to be applied to European food products will boost and widen the European food market at a global level, also enhancing Europe's attractiveness as a leading destination. Whereas the technology can be, in the future, reproduced by other countries, the food cannot, given that its taste depends on the geographical conditions of the area where the products are grown. A Virtual TONGUE will allow to “taste” a food even at thousands of kilometres far. In this project, the specific application cases will be focused on wine and oil, but the research can be easily extended to any other type of fresh food, such as vegetables. It is worth saying that, at the level of the virtual machine a different food is only identified by a different set of ligands. In this concern, many types of fresh foods have been already chemically analysed and their chemical ingredients are already classified in well-known freely available databases.
The VIRTUOUS tongue may be also thought to have a “food computer-aided design tool” for EU food technology. For example, based on taste prediction the VIRTUOUS platform may be used in the future to predict the results of a specific grape graft, and propose what grafting strategy to be used in order to obtain a specific taste or aftertaste. In the same way, all food processing procedures can be optimized and refined through the VIRTUOUS tongue, allowing to obtain different flavours and/or different effects on homeostasis.
The Virtuous tongue may be also combined with other technologies to enhance precision agriculture. The platform developed during the project can be a support tool for research on natural pesticides and the creation of more resistant crops better adapted to the climate changes in Europe, in developing countries and worldwide. The VIRTUOUS research also links taste receptors’ activation to the activity of nuclear receptors, by classifying food molecules on the basis of their ability to bind taste receptors and also nuclear receptors, following the paradigm of the Mediterranean Diet: “good and healthy”. Upgrade sin future virtual Tongues will allow setting personalized food therapies based on patient needing and preferences.
Finally, the project is strictly related to neuroscience, by considering biophysical and molecular mechanisms at the basis of brain elaboration of the taste sensation. The research put emphasise on the transfer of information from a physical level (architecture of taste receptors and protein network) to a non-physical level (the sense taste). The potential in neuroscience is huge, from a better comprehension of elaboration mechanisms of the brain to future therapies oriented to use food/diet to treat psychological disorders (taste/mood relationship).
The VIRTUOUS tongue may be also thought to have a “food computer-aided design tool” for EU food technology. For example, based on taste prediction the VIRTUOUS platform may be used in the future to predict the results of a specific grape graft, and propose what grafting strategy to be used in order to obtain a specific taste or aftertaste. In the same way, all food processing procedures can be optimized and refined through the VIRTUOUS tongue, allowing to obtain different flavours and/or different effects on homeostasis.
The Virtuous tongue may be also combined with other technologies to enhance precision agriculture. The platform developed during the project can be a support tool for research on natural pesticides and the creation of more resistant crops better adapted to the climate changes in Europe, in developing countries and worldwide. The VIRTUOUS research also links taste receptors’ activation to the activity of nuclear receptors, by classifying food molecules on the basis of their ability to bind taste receptors and also nuclear receptors, following the paradigm of the Mediterranean Diet: “good and healthy”. Upgrade sin future virtual Tongues will allow setting personalized food therapies based on patient needing and preferences.
Finally, the project is strictly related to neuroscience, by considering biophysical and molecular mechanisms at the basis of brain elaboration of the taste sensation. The research put emphasise on the transfer of information from a physical level (architecture of taste receptors and protein network) to a non-physical level (the sense taste). The potential in neuroscience is huge, from a better comprehension of elaboration mechanisms of the brain to future therapies oriented to use food/diet to treat psychological disorders (taste/mood relationship).