Application of Life Cycle Assessment and Machine Learning for High-Throughput Screening of Green Chemical Substitutes

被引:48
作者
Zhu, Xinzhe [1 ]
Ho, Chi-Hung [1 ]
Wang, Xiaonan [1 ]
机构
[1] Natl Univ Singapore, Dept Chem & Biomol Engn, Singapore 117585, Singapore
关键词
Machine learning; Life cycle assessment; Green chemistry; High-throughput screening; Pharmaceutical manufacturing process; MOLECULAR-STRUCTURE; OPTIMIZATION; CHEMISTRY; CLASSIFICATION; MIDPOINT; TOOL;
D O I
10.1021/acssuschemeng.0c02211
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The production process of many active pharmaceutical ingredients such as sitagliptin could cause severe environmental problems because of the use of toxic chemical materials and production infrastructure, energy consumption, and waste treatment. The environmental impacts of the sitagliptin production process were estimated with a life cycle assessment (LCA) method, which suggested that the use of chemical materials provided the major environmental impacts. Both methods of Eco-indicator 99 and ReCiPe endpoint confirmed that chemical feedstock accounted for 83% and 70% of life-cycle impact, respectively. Among all the chemical materials used in the sitagliptin production process, trifluoroacetic anhydride was identified as the largest influential factor in most impact categories according to the results of the ReCiPe midpoints' method. Therefore, high-throughput screening was performed to seek for greener chemical substitutes to replace the target chemical (i.e., trifluoroacetic anhydride) by the following three steps. First, the 30 most similar chemicals were obtained from 2 million candidate alternatives in the PubChem database on the basis of their molecular descriptors. Thereafter, deep learning neural network models were developed to predict life-cycle impact according to the chemicals in Ecoinvent v3.5 database with known LCA values and corresponding molecular descriptors. Finally, 1,2-ethanediyl ester was proved to be one of the potential greener substitutes after the LCA data of these similar chemicals were predicted using the well-trained machine learning models. The case study demonstrated the applicability of the novel framework to screen green chemical substitutes and optimize the pharmaceutical manufacturing process.
引用
收藏
页码:11141 / 11151
页数:11
相关论文
共 49 条
  • [1] Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
  • [2] Green chemistry tools to influence a medicinal chemistry and research chemistry based organisation
    Alfonsi, Kim
    Colberg, Juan
    Dunn, Peter J.
    Fevig, Thomas
    Jennings, Sandra
    Johnson, Timothy A.
    Kleine, H. Peter
    Knight, Craig
    Nagy, Mark A.
    Perry, David A.
    Stefaniak, Mark
    [J]. GREEN CHEMISTRY, 2008, 10 (01) : 31 - 36
  • [3] Regional Characterization of Freshwater Use in LCA: Modeling Direct Impacts on Human Health
    Boulay, Anne-Marie
    Bulle, Cecile
    Bayart, Jean-Baptiste
    Deschenes, Louise
    Margni, Manuele
    [J]. ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2011, 45 (20) : 8948 - 8957
  • [4] Environmental Sustainability Assessments of Pharmaceuticals: An Emerging Need for Simplification in Life Cycle Assessments
    De Soete, Wouter
    Debaveye, Sam
    De Meester, Steven
    Van der Vorst, Geert
    Aelterman, Wim
    Heirman, Bert
    Cappuyns, Philippe
    Dewulf, Jo
    [J]. ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2014, 48 (20) : 12247 - 12255
  • [5] Process Modeling, Simulation, and Technoeconomic Evaluation of Separation Solvents for the Continuous Pharmaceutical Manufacturing (CPM) of Diphenhydramine
    Diab, Samir
    Gerogiorgis, Dimitrios I.
    [J]. ORGANIC PROCESS RESEARCH & DEVELOPMENT, 2017, 21 (07) : 924 - 946
  • [6] Comparing the midpoint and endpoint approaches based on ReCiPe-a study of commercial buildings in Hong Kong
    Dong, Ya Hong
    Ng, S. Thomas
    [J]. INTERNATIONAL JOURNAL OF LIFE CYCLE ASSESSMENT, 2014, 19 (07) : 1409 - 1423
  • [7] The importance of Green Chemistry in Process Research and Development
    Dunn, Peter J.
    [J]. CHEMICAL SOCIETY REVIEWS, 2012, 41 (04) : 1452 - 1461
  • [8] Toxmatch-A chemical classification and activity prediction tool based on similarity measures
    Gallegos-Saliner, Ana
    Poater, Albert
    Jeliazkova, Nina
    Patlewicz, Grace
    Worth, Andrew P.
    [J]. REGULATORY TOXICOLOGY AND PHARMACOLOGY, 2008, 52 (02) : 77 - 84
  • [9] Integrated metabonomic analysis of the multiorgan effects of hydrazine toxicity in the rat
    Garrod, S
    Bollard, ME
    Nichollst, AW
    Connor, SC
    Connelly, J
    Nicholson, JK
    Holmes, E
    [J]. CHEMICAL RESEARCH IN TOXICOLOGY, 2005, 18 (02) : 115 - 122
  • [10] Life Cycle Assessment: Past, Present, and Futures
    Guinee, Jeroen B.
    Heijungs, Reinout
    Huppes, Gjalt
    Zamagni, Alessandra
    Masoni, Paolo
    Buonamici, Roberto
    Ekvall, Tomas
    Rydberg, Tomas
    [J]. ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2011, 45 (01) : 90 - 96