{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T03:01:26Z","timestamp":1702436486156},"posted":{"date-parts":[[2022,12,29]]},"group-title":"In Review","reference-count":20,"publisher":"Research Square Platform LLC","license":[{"start":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T00:00:00Z","timestamp":1672272000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2022,12,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n        <jats:p>In the past decades, the flavor industry's investment in research and development has increased to take innovative steps. Therefore, a new field to acknowledge the flavor industry challenges and concerns has arisen, developing innovative tools for the area of flavor engineering. Meanwhile, the lack of information and datasets regarding the flavored molecules and specific flavorings properties are obstacles to advances in this sector. In this context, this work presents the implementation of three Scientific Machine Learning techniques as an approach to specify flavoring characteristics in newly designed molecules. Therefore, this work brings an innovative methodology to design new natural flavor molecules with specific desired properties to product development. The Transfer Learning technique is presented, alongside a deep generative and a deep reinforcement learning models, to tackle the lack of data available when analyzing and studying flavor molecules and developing flavor-based products. This work brings as contributions the utilization of a web scrapper code to sample specific flavors\u2019 databases, apply a generative model as well as a reinforcement learning one in a transfer learning context, integrates three Scientific Machine Learning techniques in a complex system as a framework, and approaches the transfer learning model training one-by-one keeping the parameters constant but training the neural networks specifically for each case. The deep transfer learning implementation in this purpose presented excellent results, regarding the generation of molecules based on specific flavor descriptors. Nine flavor descriptors were studied along this work and all of them presented more than 50% of new molecules generated within the outstanding results considered for the evaluation metric, Natural Product Likeness Score and Synthetic Accessibility Score. Finally, a discussion of the results is constructed based on the data availability, the presence in nature, and the multisensorial components of flavor impact for the specific flavors\u2019 results.<\/jats:p>","DOI":"10.21203\/rs.3.rs-2393484\/v1","type":"posted-content","created":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T16:26:56Z","timestamp":1672331216000},"source":"Crossref","is-referenced-by-count":1,"title":["A Transfer Learning approach to develop natural molecules with specific flavor requirements"],"prefix":"10.21203","author":[{"given":"Luana P.","family":"Queiroz","sequence":"first","affiliation":[{"name":"LSRE-LCM- Laboratory of Separation and Reaction Engineering \u2013 Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto"}]},{"given":"Carine M.","family":"Rebello","sequence":"additional","affiliation":[{"name":"Universidade Federal da Bahia"}]},{"given":"Erbet A.","family":"Costa","sequence":"additional","affiliation":[{"name":"Universidade Federal da Bahia"}]},{"given":"Vin\u00edcius V.","family":"Santana","sequence":"additional","affiliation":[{"name":"LSRE-LCM- Laboratory of Separation and Reaction Engineering \u2013 Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto"}]},{"given":"Bruno C. L.","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"LSRE-LCM- Laboratory of Separation and Reaction Engineering \u2013 Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto"}]},{"given":"Al\u00edrio E.","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"LSRE-LCM- Laboratory of Separation and Reaction Engineering \u2013 Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto"}]},{"given":"Ana M.","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"LSRE-LCM- Laboratory of Separation and Reaction Engineering \u2013 Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto"}]},{"given":"Idelfonso B. R.","family":"Nogueira","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology"}]}],"member":"8761","reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1111\/j.1745-459X.2003.tb00393.x","article-title":"Attributes Believed to Impact Flavor: An Opinion Survey","volume":"18","author":"Delwiche JF","year":"2003","unstructured":"Delwiche JF (2003) Attributes Believed to Impact Flavor: An Opinion Survey. J Sens Stud 18:347\u2013352. doi:10.1111\/j.1745-459X.2003.tb00393.x","journal-title":"J Sens Stud"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10408398.2021.1939264","article-title":"Recent Insights in Flavor-Enhancers: Definition, Mechanism of Action, Taste-Enhancing Ingredients, Analytical Techniques and the Potential of Utilization","author":"Vasilaki A","year":"2021","unstructured":"Vasilaki A, Panagiotopoulou E, Koupantsis T, Katsanidis E, Mourtzinos I (2021) Recent Insights in Flavor-Enhancers: Definition, Mechanism of Action, Taste-Enhancing Ingredients, Analytical Techniques and the Potential of Utilization. Crit Rev Food Sci Nutr 0:1\u201317. doi:10.1080\/10408398.2021.1939264","journal-title":"Crit Rev Food Sci Nutr"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-020-00424-9","article-title":"Review on Natural Products Databases: Where to Find Data in 2020","volume":"12","author":"Sorokina M","year":"2020","unstructured":"Sorokina M, Steinbeck C (2020) Review on Natural Products Databases: Where to Find Data in 2020. J Cheminform 12:1\u201351. doi:10.1186\/s13321-020-00424-9","journal-title":"J Cheminform"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/molecules26113095","article-title":"Perfume and Flavor Engineering: A Chemical Engineering Perspective","volume":"26","author":"Rodrigues AE","year":"2021","unstructured":"Rodrigues AE, Nogueira I, Faria RPV (2021) Perfume and Flavor Engineering: A Chemical Engineering Perspective. Molecules 26. doi:10.3390\/molecules26113095","journal-title":"Molecules"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine Learning for Molecular and Materials Science","volume":"559","author":"Butler KT","year":"2018","unstructured":"Butler KT, Davies DW, Cartwright H, Isayev O, Walsh A (2018) Machine Learning for Molecular and Materials Science. Nature 559:547\u2013555. doi:10.1038\/s41586-018-0337-2","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/pr8010023","author":"Bi K","year":"2020","unstructured":"Bi K, Zhang D, Qiu T, Huang Y (2020) GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction. Processes 8, 1\u201311, doi:10.3390\/pr8010023"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.idairyj.2017.09.009","article-title":"Predicting Fishiness Off-Flavour and Identifying Compounds of Lipid Oxidation in Dairy Powders by SPME-GC\/MS and Machine Learning","volume":"77","author":"Chen C","year":"2018","unstructured":"Chen C, Husny J, Rabe S (2018) Predicting Fishiness Off-Flavour and Identifying Compounds of Lipid Oxidation in Dairy Powders by SPME-GC\/MS and Machine Learning. Int Dairy J 77:19\u201328. doi:10.1016\/j.idairyj.2017.09.009","journal-title":"Int Dairy J"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-43664-y","article-title":"Building Machine Learning Models for Predicting the Bitter and Sweet Taste of Small Molecules","volume":"9","author":"Tuwani R","year":"2019","unstructured":"Tuwani R, Wadhwa S, Bagler G, BitterSweet (2019) Building Machine Learning Models for Predicting the Bitter and Sweet Taste of Small Molecules. Sci Rep 9:1\u201313. doi:10.1038\/s41598-019-43664-y","journal-title":"Sci Rep"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-022-00612-9","article-title":"Recommendation Systems for Matching Molecules with Bitter Taste Receptors","volume":"14","author":"Margulis E","year":"2022","unstructured":"Margulis E, Slavutsky Y, Lang T, Behrens M, Benjamini Y, Niv MY, BitterMatch (2022) Recommendation Systems for Matching Molecules with Bitter Taste Receptors. J Cheminform 14:1\u201317. doi:10.1186\/s13321-022-00612-9","journal-title":"J Cheminform"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-1998750\/v1","author":"Queiroz LP","year":"2022","unstructured":"Queiroz LP, Rebello CM, Costa EA, Santana VV, Rodrigues BCL, Rodrigues AE, Ribeiro AM, Nogueira IBR (2022) Generating Flavors Using Scientific Machine Learning 0\u201320. doi:https:\/\/doi.org\/10.21203\/rs.3.rs-1998750\/v1","journal-title":"Generating Flavors Using Scientific Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.05859","author":"Queiroz LP","year":"2022","unstructured":"Queiroz LP, Rebello CM, Costa EA, Santana VV, Rodrigues BCL, Rodrigues AE, Ribeiro AM, Nogueira IBR (2022) A New Reinforcement Learning Framework to Discover Natural Flavor Molecules. doi:https:\/\/doi.org\/10.48550\/arXiv.2209.05859"},{"key":"ref12","author":"Dr","year":"2022","unstructured":"Dr (2022) Ganesh Bagler FlavorDB Available online: https:\/\/cosylab.iiitd.edu.in\/flavordb\/ (accessed on 5"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"8115","DOI":"10.1021\/acs.iecr.8b00527","article-title":"Flavor Engineering-A Methodology to Predict Sensory Qualities of Flavored Products","volume":"57","author":"Monteiro A","year":"2018","unstructured":"Monteiro A, Costa P, Loureiro JM, Rodrigues AE (2018) Flavor Engineering-A Methodology to Predict Sensory Qualities of Flavored Products. Ind Eng Chem Res 57:8115\u20138123. doi:10.1021\/acs.iecr.8b00527","journal-title":"Ind Eng Chem Res"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"Yan A Survey on Transfer Learning","volume":"22","author":"Pan SJ","year":"2010","unstructured":"Pan SJ (2010) Yan A Survey on Transfer Learning. IEEE Trans Knowl Data Eng 22:1345\u20131359. doi:10.1109\/TKDE.2009.191","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"8683","DOI":"10.1021\/acs.jmedchem.9b02147","article-title":"Transfer Learning for Drug Discovery","volume":"63","author":"Cai C","year":"2020","unstructured":"Cai C, Wang S, Xu Y, Zhang W, Tang K, Ouyang Q, Lai L, Pei J (2020) Transfer Learning for Drug Discovery. J Med Chem 63:8683\u20138694. doi:10.1021\/acs.jmedchem.9b02147","journal-title":"J Med Chem"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00045","author":"Wang T","year":"2019","unstructured":"Wang T, Huan J, Zhu M (2019) Instance-Based Deep Transfer Learning. Proc. \u2013 2019 IEEE Winter Conf. Appl. Comput. Vision, WACV 2019 367\u2013375, doi:10.1109\/WACV.2019.00045"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555","author":"Zhuang F","year":"2021","unstructured":"Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, Xiong H, He Q (2021) A Comprehensive Survey on Transfer Learning. Proc. IEEE 109, 43\u201376, doi:10.1109\/JPROC.2020.3004555"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of Synthetic Accessibility Score of Drug-like Molecules Based on Molecular Complexity and Fragment Contributions","volume":"1","author":"Ertl P","year":"2009","unstructured":"Ertl P, Schuffenhauer A (2009) Estimation of Synthetic Accessibility Score of Drug-like Molecules Based on Molecular Complexity and Fragment Contributions. J Cheminform 1:1\u201311. doi:10.1186\/1758-2946-1-8","journal-title":"J Cheminform"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1021\/ci700286x","article-title":"Natural Product-Likeness Score and Its Application for Prioritization of Compound Libraries","volume":"48","author":"Ertl P","year":"2008","unstructured":"Ertl P, Roggo S, Schuffenhauer A (2008) Natural Product-Likeness Score and Its Application for Prioritization of Compound Libraries. J Chem Inf Model 48:68\u201374. doi:10.1021\/ci700286x","journal-title":"J Chem Inf Model"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"4593","DOI":"10.1016\/j.csbj.2021.07.032","article-title":"Natural Product Scores and Fingerprints Extracted from Artificial Neural Networks","volume":"19","author":"Menke J","year":"2021","unstructured":"Menke J, Massa J, Koch O (2021) Natural Product Scores and Fingerprints Extracted from Artificial Neural Networks. Comput Struct Biotechnol J 19:4593\u20134602. doi:10.1016\/j.csbj.2021.07.032","journal-title":"Comput Struct Biotechnol J"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-2393484\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-2393484\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T07:59:41Z","timestamp":1672819181000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-2393484\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,29]]},"references-count":20,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-2393484\/v1","relation":{},"subject":[],"published":{"date-parts":[[2022,12,29]]},"subtype":"preprint"}}