Published Versions 1 Vol 3 (3) : 340-375 2021
Download
Integrated “Generate, Make, and Test” for Formulated Products using Knowledge Graphs
: 2020 - 12 - 31
: 2021 - 04 - 05
: 2021 - 04 - 30
25 0 0
Abstract & Keywords
Abstract: In the multi-billion dollar formulated product industry, state of the art continues to rely heavily on experts during the “generate, make and test” steps of formulation design. We propose automation aids to each step with a knowledge graph of relevant information as the central artifact. The generate step usually focuses on coming up with new recipes for intended formulation. We propose to aid the experts who generally carry out this step manually by providing a recommendation system and a templating system on top of the knowledge graph. Using the former, the expert can create a recipe from scratch using historical formulations and related data. With the latter, the expert starts with a recipe template created by our system and substitutes the requisite constituents to form a recipe. In the current state of practice, the three steps mentioned above operate in a fragmented manner wherein observations from one step do not aid other steps in a streamlined manner. Instead of manually operated labs for the make and test steps, we assume automated or robotic labs and in-silico testing, respectively. Using two formulations, namely face cream and an exterior coating, we show how the knowledge graph may help integrate and streamline the communication between the generate, the make, and the test steps. Our initial exploration shows considerable promise.
Keywords: Formulated product design; Formulation recommendation; Formulation template; Robotic labs; In-silico testing; Integrated generate-make-test
Acknowledgments
[1]
EU Formulation Network Deliverables 3.3 and 3.4, Common Vision and Roadmap for Formulated Products (2016). Available at: https://bit.ly/3rBs7Yg. Accessed 20 April 2021
[2]
Harper, P.M., Gani, R.: A multi-step and multi-level approach for computer aided molecular design, Computers &Chemical Engineering 24 (2-7), 677–683 (2000)
[3]
Conte, E., Gani, R., Ng, K.M.: Design of formulated products: A systematic methodology. AIChE Journal 57 (9), 2431–2449 (2011)
[4]
Gani, R., Ng, K.M.: Product design–molecules, devices, functional products, and formulated products, Computers & Chemical Engineering 81, 70–79 (2015)
[5]
Zhang, L., et al.: An integrated framework for designing formulated products. Computers & Chemical Engineering 107, 61–76 (2017)
[6]
Zhang, L., et al.: Advances in chemical product design. Reviews in Chemical Engineering 34 (3), 319–340 (2018)
[7]
Zhang, L., et al.: Chemical product design–recent advances and perspectives. Current Opinion in Chemical Engineering 27, 22–34 (2020)
[8]
Sunkle, S., et al.: Information extraction and graph representation for the design of formulated products. In: Dustdar, S., et al. (eds.) CAiSE 2020, pp. 433–448. Springer, Berlin (2020)
[9]
Hill, M.: Chemical product engineering—the third paradigm. Computers & Chemical Engineering 33(5), 947–953 (2009)
[10]
Cussler, E.L., Moggridge, G.D.: Chemical product design. Cambridge University Press, Cambridge (2011)
[11]
Mart´ın, M., Mart´ınez, A.: A methodology for simultaneous process and product design in the formulated consumer products industry: The case study of the detergent business. Chemical Engineering Research and Design 91(5), 795–809 (2013)
[12]
Lee, C., Choy, K.L., Chan, Y.: A knowledge-based ingredient formulation system for chemical product development in the personal care industry. Computers & Chemical Engineering 65, 40-53 (2014)
[13]
Sunkle, S., et al.: Generate and test for formulated product variants with information extraction and an in-silico model. In: Advanced Digital Architectures for Model-Driven Adaptive Enterprises, pp. 223–250. IGI Global, Hershey (2020)
[14]
Chatterjee, P., Alvi, M.M.: Excipients and active pharmaceutical ingredients. In: Pediatric Formulations, pp. 347–361. Springer, Berlin (2014)
[15]
Arrieta-Escobar, J.A., et al.: Incorporation of heuristic knowledge in the optimal design of formulated products: Application to a cosmetic emulsion. Computers & Chemical Engineering 122, 265–274 (2019)
[16]
Lee, C.K.H.: A knowledge-based product development system in the chemical industry. Journal of Intelligent Manufacturing 30(3), 1371–1386 (2019)
[17]
Taifouris, M., et al.: Challenges in the design of formulated products: multi-scale process and product design. Current Opinion in Chemical Engineering 27, 1-9 (2020)
[18]
Bernardo, F.P., Saraiva, P.M.: A conceptual model for chemical product design. AIChE Journal 61(3), 802-815(2015)
[19]
Picchioni, F., Broekhuis, A.: Material properties and processing in chemical product design, Current Opinion in Chemical Engineering 1 (4), 459–464 (2012)
[20]
Arrieta-Escobar, J.A., et al.: Integration of consumer preferences and heuristic knowledge in the design of formulated products: Application to a cosmetic emulsion. In: Computer Aided Chemical Engineering, 46, 433–438 (2019)
[21]
Conte, E., et al.: Design of formulated products: Experimental component. AIChE Journal 58 (1), 173–189 (2012)
[22]
Lindsey, J.S.: A retrospective on the automation of laboratory synthetic chemistry. Chemometrics and Intelligent Laboratory Systems 17 (1), 15-45 (1992)
[23]
Porte, C., et al.: Automation and optimization by simplex methods of 6-chlorohexanol synthesis. Process Control and Quality 4(8), 111-122 (1996)
[24]
Wagner, R.W., et al.: Investigation of cocatalysis conditions using an automated microscale multireactor workstation: Synthesis of m eso-tetramesitylporphyrin. Organic Process Research & Development 3 (1), 28-37 (1999)
[25]
L. Cheng, et al.: Accelerating electrolyte discovery for energy storage with high-throughput screening. The Journal of Physical Chemistry Letters 6 (2), 283–291 (2015)
[26]
Senkan, S.M.: High-throughput screening of solid-state catalyst libraries. Nature 394(6691), 50–353 (1998)
[27]
Macarron, et al.: Impact of high-throughput screening in biomedical research. Nature reviews Drug Discovery 10 (3), 188-195 (2011)
[28]
A. Dave, et al.: Autonomous discovery of battery electrolytes with robotic experimentation and machine learning. Cell Reports Physical Science, No.100264 (2020)
[29]
MacLeod, B.P., et al.: Self-driving laboratory for accelerated discovery of thin-film materials. Science Advances 6 (20), No. eaaz8867 (2020)
[30]
Shimizu, R., et al.: Autonomous materials synthesis by machine learning and robotics. APL Materials 8 (11), No. 111110 (2020)
[31]
Montoya, J.H., et al.: Autonomous intelligent agents for accelerated materials discovery Chemical Science, 11, 8517-8532 (2020)
[32]
Pendleton, I.M., et al.: Experiment specification, capture and laboratory automation technology (escalate): A software pipeline for automated chemical experimentation and data management. MRS Communications 9(3), 846–859 (2019)
[33]
Noack, M.M., et al.: A kriging-based approach to autonomous experimentation with applications to x-ray scattering, Scientific reports 9(1), 1-19 (2019)
[34]
Flores-Leonar, M.M., et al.: Materials acceleration platforms: On the way to autonomous experimentation. Current Opinion in Green and Sustainable Chemistry, No. 100370 (2020)
[35]
Cortes-Borda, D., et al.: An autonomous self-optimizing flow reactor for the synthesis of natural product carpanone. The Journal of Organic Chemistry 83 (23), 14286–14299 (2018)
[36]
Boyce, B.L., Uchic, M.D.: Progress toward autonomous experimental systems for alloy development. MRS Bulletin 44(4), 273–280 (2019)
[37]
Roch, L.M., et al.: Chemos: Orchestrating autonomous experimentation. Science Robotics 3(19), eaat5559 (2018)
[38]
Gromski, P.S., Granda, J.M., Cronin, J.: Universal chemical synthesis and discovery with the chemputer. Trends in Chemistry 2 (1), 4-12 (2020)
[39]
Steiner, S., et al.: Organic synthesis in a modular robotic system driven by a chemical programming language. Science 363(6423), eaav2211 (2019)
[40]
Jayabal, H., Dingari, N.N., Rai, B.: A linear viscoelastic model to understand skin mechanical behaviour and for cosmetic formulation design. International Journal of Cosmetic Science 41(3), 292-299 (2019)
[41]
Gupta, R., Sridhar, D. B., Rai, B.: Molecular dynamics simulation study of permeation of molecules through skin lipid bilayer. The Journal of Physical Chemistry B 120(34), 8987–8996 (2016)
[42]
Gajula, K., et al.: In-silico skin model: a multi-scale simulation study of drug transport. Journal of chemical information and modeling 57(8), 2027–2034 (2017)
[43]
Gupta, R., et al.: Effect of chemical permeation enhancers on skin permeability: In silico screening using molecular dynamics simulations. Scientific Reports 9 (1), No. 1456 (2019)
[44]
Flick, E.W.: Cosmetic and toiletry formulations. Available at: https://www.sciencedirect.com/book/9780815513063/cosmetic-and-toiletry-formulations#book-info. Accessed 20 May 2021
[45]
Flick, E.W.: Industrial water-based paint formulations. Available at: https://www.sciencedirect.com/science/article/pii/B9780815513452500204?via%3Dihub. Accessed 20 May 2021
[46]
Wibowo, C., Ng, K.M.: Product-oriented process synthesis and development: Creams and pastes, AIChE Journal 47 (12), 2746–2767 (2001)
[47]
Wibowo, C., Ng, K.M.: Product-centered processing: Manufacture of chemical-based consumer products. AIChE Journal 48(6), 1212–1230 (2002)
[48]
Mori, S., et al.: Flow graph corpus from recipe texts. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), European Language Resources Association (ELRA), pp. 2370–2377 (2014)
[49]
Maeta, H., Sasada, T., Mori, S.: A framework for procedural text understanding. In: Proceedings of the 14th International Conference on Parsing Technologies, pp. 50-60 (2015)
[50]
Jermsurawong, J., Habash, N.: Predicting the structure of cooking recipes. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 781–786 (2015)
[51]
Kiddon, C, et al.: Mise en place: Unsupervised interpretation of instructional recipes. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 982–992 (2015)
[52]
Mysore, S., et al.: Automatically extracting action graphs from materials science synthesis procedures. arXiv preprint arXiv:1711.06872 (2017).
[53]
Matsumoto, S., Yamanaka, R., Chiba, H.: Mapping RDF graphs to property graphs. arXiv preprint arXiv:1812.01801 (2018)
[54]
D. Alocci, et al.: Property graph vs RDF triple store: A comparison on glycan substructure search, PloS one 10 (12) (2015) e0144578 (2015)
[55]
Baken, N.: Linked data for smart homes: Comparing RDF and labeled property graphs. In: LDAC2020 - 8th Linked Data in Architecture and Construction Workshop, pp. 23-36 (2020)
[56]
Kim, S., et al.: Pubchem substance and compound databases, Nucleic acids research 44 (D1), D1202–D1213 (2016)
[57]
Harashima, J., Hiramatsu, M.: Cookpad parsed corpus: Linguistic annotations of Japanese recipes. In: Proceedings of the 14th Linguistic Annotation Workshop, pp. 87–92 (2020)
[58]
Majumder, B.P., et al.: Generating personalized recipes from historical user preferences. arXiv preprint arXiv:1909.00105 (2019)
[59]
Bergstra, J., et al.: Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems 24, 2546–2554 (2011)
[60]
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. The Journal of Machine Learning Research 13(1), 281–305 (2012)
[61]
Anderson, M.J., Whitcomb, P.J.: DOE simplified: Practical tools for effective experimentation. CRC press, Boca Raton (2017)
[62]
Lindauer, M., et al.: Smac v3: Algorithm configuration in python. Available at: https://github.com/automl/SMAC3. Accessed 20 May 2021
[63]
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. Advances in Neural Information Processing Systems 25, 2951–2959 (2012)
[64]
Häse, F., et al.: Phoenics: A universal deep Bayesian optimizer. arXiv ¨preprint arXiv:1801.01469 (2018)
[65]
Karande, P., et al.: Design principles of chemical penetration enhancers for transdermal drug delivery. In: Proceedings of the National Academy of Sciences 102(13), 4688–4693(2005)
[66]
Eichner, A., et al.: Influence of the penetration enhancer isopropyl myristate on stratum corneum lipid model membranes revealed by neutron diffraction and 2h nmr experiments. Biochimica et Biophysica Acta (BBA)-Biomembranes 1859(5), 745–755 (2017)
[67]
M. E. Nichols, Paint weathering tests. In: Handbook of environmental degradation of materials, Elsevier, pp. 51–67 (2018)
[68]
Akafuah, N.K., et al.: Evolution of the automotive body coating process a review, Coatings 6(2), 24 (2016)
[69]
Nichols, M., et al.: An improved accelerated weathering protocol to anticipate florida exposure behavior of coatings. Journal of Coatings Technology and Research 10(2), 153–173 (2013)
[70]
H. Makki, et al.: A simulation approach to study photo-degradation processes of polymeric coatings. Polymer Degradation and Stability 105, 68–79 (2014)
[71]
Hinderliter, B., Croll, S.: Monte carlo approach to estimating the photo-degradation of polymer coatings. Journal of Coatings Technology and Research 2(6), 483–491 (2005)
[72]
Schichtel, J.J., Chattopadhyay, A.: Modeling thermoset polymers using an improved molecular dynamics crosslinking methodology. Computational Materials Science 174, 109469 (2020)
[73]
Chaube, S., et al.: Multiscale analysis of large-strain deformation behaviour of random crosslinked elastomers. Molecular Simulation 45(2), 111–119 (2019)
Article and author information
Cite As
Citation: Sunkle, S., et al.: Integrated “generate, make, and test” for formulated products using knowledge graphs. Data Intelligence 3(3), 340-375 (2021). doi: 10.1162/dint_a_00096
Sagar Sunkle
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
Dr. Sagar Sunkle is a senior scientist at Tata Consultancy Services Research,India. Sagar received his PhD (with distinction) in Software Engineering fromOtto-von-Guericke University (OvGU) of Magdeburg, Germany. He alsohas two masters, one in Computer Science with specialization in softcomputing technologies from the University of Mumbai, India and second inData and Knowledge Engineering from OvGU, both also with distinction.Sagar has over 40 publications including conferences, journals, book chaptersand patents. His current research interests include using natural languageprocessing and machine learning to derive insights from information andtransform insights into recommendations with applications to materialinformatics, banking and financial services, and related business domains.
0000-0002-4757-6256
Deepak Jain
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
Deepak Jain received his Master’s in Thermal and Fluid Engineering fromIndian Institute of Technology Bombay (IIT Bombay) in 2015. Soon after hisMaster’s, he joined the Corporate Technology Office of Tata ConsultancyServices as a junior researcher in the Physical Sciences Group. His researchinterests include computational fluid dynamics, applied machine learningto physical sciences, 3rd generation photovoltaic materials and molecularmodelling. Deepak has filed 4 patents and has over 8 publications includingjournals, conferences and a book chapter.
0000-0001-5849-454X
Krati Saxena
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
krati.saxena@tcs.com
Krati Saxena is a Scientist at Tata Research Development and Design Center,Pune, India (TRDDC). Previously, she completed a Bachelor’s degree inSystem Science from Indian Institute of Technology Jodhpur and received aMaster’s degree in Global Advanced Assistive Robotics course from KyushuInstitute of Technology, Japan. Her current research interests include contentmining, natural language processing, textual AI, data-driven decision-making,and knowledge discovery.
0000-0001-7049-9685
Ashwini Patil
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
Ashwini Patil is a researcher at Tata Research Development and DesignCentre, Pune, India (TRDDC). She is working in the domain of NaturalLanguage Processing. She has completed a Master of Technology in ComputerScience from Visvesvaraya National Institute of Technology, Nagpur, India(VNIT Nagpur, India). Her current research interests include graph databases,semantic similarly, and deep learning for information and knowledgediscovery.
0000-0002-7948-0427
Tushita Singh
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
Tushita Singh is a Researcher at Tata Research Development and DesignCentre, Pune, India (TRDDC). She is a graduate in Computer Science fromthe Indian Institute of Information Technology (IIIT), Nagpur, India. Hercurrent areas of research interests include natural language processing, datadriven decision making, and textual AI.
0000-0002-1288-8161
Beena Rai
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
Dr. Beena Rai is the head of the Physical Sciences Research Area with over20 years of experience at Tata Consultancy Services Research, India. Beenais a PhD from India’s premier research institution—National ChemicalLaboratory, Pune. Her research focuses on the molecular modelling basedrational design and development of surfactants for various industrialapplications such as mineral processing, ceramics, paints and coatings,cements, lubricants, agrochemicals, pharmaceuticals and cosmetics. Beenahas published close to 100 research papers in reputed journals andconferences. She has 22 patent/patent applications to her credit. She hasdelivered several keynotes and invited talks at various forums. She is theeditor of the book titled Molecular Modelling for the Design of NovelPerformance Chemicals and Materials, published by Taylor & Francis, CRCPress. Beena is a recipient of the prestigious Chevening Scholarship at SaidBusiness School, University of Oxford, UK, and several other recognitionsand awards.
0000-0002-8637-7778
Vinay Kulkarni
S. Sunkle, D. Jain, B. Rai, and V. Kulkarni conceptualized and ideated the integrated formulation design. S. Sunkle and D. Jain wrote and reviewed the whole paper. K. Saxena, A. Patil, T. Singh, and S. Sunkle developed the knowledge graph, the recommender, and template generation systems.
Vinay Kulkarni is a Chief Scientist and Head of Software Systems Researchat Tata Consultancy Services, India. His research interests include modeldriven software engineering, enterprise modelling and software engineeringfor an uncertain world. His work in model-driven software engineering hasled to a tool set that has been used to deliver several large business-criticalsystems over the past 20 years. Much of this work has found a way into OMGstandards. This work also received fair mention in respected internationalprint media. He has several patents to his credit and has authored more than100 papers in scholastic journals and conferences worldwide. He has servedas the conference and program chairperson for the premier ACM and IEEEinternational conferences in the area of software engineering, and is ontechnical program committees of many international conferences. Recently,he was inducted as Fellow of Indian National Academy of Engineering. Analumnus of Indian Institute of Technology Madras, Vinay also serves as VisitingProfessor at Middlesex University, London.
0000-0003-1570-1339
Publication records
Published: Sept. 15, 2021 (Versions1
References
Data Intelligence