DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers

Abstract

Polyhydroxyalkanoate-based polymers—being ecofriendly, biosynthesizable, and economically viable and possessing a broad range of tunable properties—are currently being actively pursued as promising alternatives for petroleum-based plastics. The vast chemical complexity accessible within this class of polymers gives rise to challenges in the rational discovery of novel polymer chemistries for specific applications. Here, the burgeoning field of polymer informatics addresses this challenge via providing tools and strategies for accelerated property prediction and materials design via surrogate machine-learning models built on reliable past data. In this contribution, we use glass transition temperature Tg as an example target property to demonstrate promise of the data-enabled route to accelerated learning of accurate structure–property mappings in PHA-based polymers. Our analysis uses a data set of experimentally measured Tg values, polymer molecular weights, and a polydispersity index for PHA-based homo- and copolymers that was carefully assembled from the literature. A fingerprinting scheme that captures key properties based on topology, shape, and charge/polarity of specific chemical units or motifs forming the polymer backbone was devised to numerically represent the polymers. A validated statistical learning model is then developed to allow for a mapping of the polymer fingerprints onto the property space in a physically meaningful and reliable manner.more » Once developed, the model can not only rapidly predict the property of new PHA polymers but also provide uncertainties underlying the predictions. The model is further combined with an evolutionary-algorithm-based search strategy to efficiently identify multicomponent polymer compositions with a prespecified Tg. While the present contribution is focused specifically on Tg, the surrogate model development approach put forward here is general and can, in principle, be extended to a range of other properties.« less

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1579702
Report Number(s):
LA-UR-19-28291
Journal ID: ISSN 1549-9596
Grant/Contract Number:  
89233218CNA000001; AC52-06NA25396
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Chemical Information and Modeling
Additional Journal Information:
Journal Volume: 59; Journal Issue: 12; Journal ID: ISSN 1549-9596
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Citation Formats

Pilania, Ghanshyam, Iverson, Carl Nicholas, Lookman, Turab, and Marrone, Babetta Louise. Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers. United States: N. p., 2019. Web. doi:10.1021/acs.jcim.9b00807.
Pilania, Ghanshyam, Iverson, Carl Nicholas, Lookman, Turab, & Marrone, Babetta Louise. Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers. United States. https://doi.org/10.1021/acs.jcim.9b00807
Pilania, Ghanshyam, Iverson, Carl Nicholas, Lookman, Turab, and Marrone, Babetta Louise. Thu . "Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers". United States. https://doi.org/10.1021/acs.jcim.9b00807. https://www.osti.gov/servlets/purl/1579702.
@article{osti_1579702,
title = {Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers},
author = {Pilania, Ghanshyam and Iverson, Carl Nicholas and Lookman, Turab and Marrone, Babetta Louise},
abstractNote = {Polyhydroxyalkanoate-based polymers—being ecofriendly, biosynthesizable, and economically viable and possessing a broad range of tunable properties—are currently being actively pursued as promising alternatives for petroleum-based plastics. The vast chemical complexity accessible within this class of polymers gives rise to challenges in the rational discovery of novel polymer chemistries for specific applications. Here, the burgeoning field of polymer informatics addresses this challenge via providing tools and strategies for accelerated property prediction and materials design via surrogate machine-learning models built on reliable past data. In this contribution, we use glass transition temperature Tg as an example target property to demonstrate promise of the data-enabled route to accelerated learning of accurate structure–property mappings in PHA-based polymers. Our analysis uses a data set of experimentally measured Tg values, polymer molecular weights, and a polydispersity index for PHA-based homo- and copolymers that was carefully assembled from the literature. A fingerprinting scheme that captures key properties based on topology, shape, and charge/polarity of specific chemical units or motifs forming the polymer backbone was devised to numerically represent the polymers. A validated statistical learning model is then developed to allow for a mapping of the polymer fingerprints onto the property space in a physically meaningful and reliable manner. Once developed, the model can not only rapidly predict the property of new PHA polymers but also provide uncertainties underlying the predictions. The model is further combined with an evolutionary-algorithm-based search strategy to efficiently identify multicomponent polymer compositions with a prespecified Tg. While the present contribution is focused specifically on Tg, the surrogate model development approach put forward here is general and can, in principle, be extended to a range of other properties.},
doi = {10.1021/acs.jcim.9b00807},
journal = {Journal of Chemical Information and Modeling},
number = 12,
volume = 59,
place = {United States},
year = {2019},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 64 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Plastic debris in the open ocean
journal, June 2014

  • Cozar, A.; Echevarria, F.; Gonzalez-Gordillo, J. I.
  • Proceedings of the National Academy of Sciences, Vol. 111, Issue 28
  • DOI: 10.1073/pnas.1314705111

The promise of plastics from plants
journal, November 2017


The future of plastics recycling
journal, November 2017


Biodegradable Polyesters from Renewable Resources
journal, June 2013


Biodegradable and Bio-Based Polymers: Future Prospects of Eco-Friendly Plastics
journal, January 2015


Advances in cyanobacterial polyhydroxyalkanoates production
journal, September 2017

  • Singh, Akhilesh Kumar; Mallick, Nirupama
  • FEMS Microbiology Letters, Vol. 364, Issue 20
  • DOI: 10.1093/femsle/fnx189

Cyanobacterial Polyhydroxybutyrate (PHB): Screening, Optimization and Characterization
journal, June 2016


Polyhydroxyalkanoates: opening doors for a sustainable future
journal, April 2016

  • Li, Zibiao; Yang, Jing; Loh, Xian Jun
  • NPG Asia Materials, Vol. 8, Issue 4
  • DOI: 10.1038/am.2016.48

Accelerating materials property predictions using machine learning
journal, September 2013

  • Pilania, Ghanshyam; Wang, Chenchen; Jiang, Xun
  • Scientific Reports, Vol. 3, Issue 1
  • DOI: 10.1038/srep02810

A polymer dataset for accelerated property prediction and design
journal, March 2016

  • Huan, Tran Doan; Mannodi-Kanakkithodi, Arun; Kim, Chiho
  • Scientific Data, Vol. 3, Issue 1
  • DOI: 10.1038/sdata.2016.12

Machine Learning Strategy for Accelerated Design of Polymer Dielectrics
journal, February 2016

  • Mannodi-Kanakkithodi, Arun; Pilania, Ghanshyam; Huan, Tran Doan
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep20952

Scoping the polymer genome: A roadmap for rational polymer dielectrics design and beyond
journal, September 2018


Machine learning in materials informatics: recent applications and prospects
journal, December 2017

  • Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam
  • npj Computational Materials, Vol. 3, Issue 1
  • DOI: 10.1038/s41524-017-0056-5

Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions
journal, July 2018

  • Kim, Chiho; Chandrasekaran, Anand; Huan, Tran Doan
  • The Journal of Physical Chemistry C, Vol. 122, Issue 31
  • DOI: 10.1021/acs.jpcc.8b02913

Polymer Properties
book, December 2009


Prediction of Polymer Properties
book, July 2002


The Glass Temperature
book, January 2007


Prediction of the glass transition temperature of polymers
journal, February 1970


Prediction of Polymer Glass Transition Temperatures Using a General Quantitative Structure−Property Relationship Treatment
journal, January 1996

  • Katritzky, Alan R.; Rachwal, Peter; Law, Kam Wah
  • Journal of Chemical Information and Computer Sciences, Vol. 36, Issue 4
  • DOI: 10.1021/ci950156w

Prediction of Glass Transition Temperature (Tg) of Some Compounds in Organic Electroluminescent Devices with Their Molecular Properties
journal, January 2002

  • Kim, Yeong Suk; Kim, Jae Hyun; Kim, Jung Sup
  • Journal of Chemical Information and Computer Sciences, Vol. 42, Issue 1
  • DOI: 10.1021/ci0103018

Prediction of Glass Transition Temperatures from Monomer and Repeat Unit Structure Using Computational Neural Networks
journal, February 2002

  • Mattioni, Brian E.; Jurs, Peter C.
  • Journal of Chemical Information and Computer Sciences, Vol. 42, Issue 2
  • DOI: 10.1021/ci010062o

Prediction of glass transition temperatures: Binary blends and copolymers
journal, June 2008


Predicting Glass Transition Temperatures of Polyarylethersulphones Using QSPR Methods
journal, June 2012


A new approach for assessment of glass transition temperature of acrylic and methacrylic polymers from structure of their monomers without using any computer codes
journal, July 2016

  • Keshavarz, Mohammad Hossein; Esmaeilpour, Karim; Taghizadeh, Hedayatolah
  • Journal of Thermal Analysis and Calorimetry, Vol. 126, Issue 3
  • DOI: 10.1007/s10973-016-5701-6

QSPR modelling for prediction of glass transition temperature of diverse polymers
journal, November 2018


Impact of dataset uncertainties on machine learning model predictions: the example of polymer glass transition temperatures
journal, January 2019

  • Jha, Anurag; Chandrasekaran, Anand; Kim, Chiho
  • Modelling and Simulation in Materials Science and Engineering, Vol. 27, Issue 2
  • DOI: 10.1088/1361-651X/aaf8ca

Molecular modeling of polymers. IV. Estimation of glass transition temperatures
journal, September 1988

  • Hopfinger, A. J.; Koehler, M. G.; Pearlstein, R. A.
  • Journal of Polymer Science Part B: Polymer Physics, Vol. 26, Issue 10
  • DOI: 10.1002/polb.1988.090261001

Microbial Synthesis of Poly(β-hydroxyalkanoates) Bearing Phenyl Groups from Pseudomonas putida:  Chemical Structure and Characterization
journal, March 2001

  • Abraham, Gustavo A.; Gallardo, Alberto; San Roman, Julio
  • Biomacromolecules, Vol. 2, Issue 2
  • DOI: 10.1021/bm010018h

Production and characterization of biodegradable terpolymer poly(3-hydroxybutyrate-co-3-hydroxyvalerate-co-4-hydroxybutyrate) by Alcaligenes sp. A-04
journal, January 2006

  • Chanprateep, Suchada; Kulpreecha, Songsri
  • Journal of Bioscience and Bioengineering, Vol. 101, Issue 1
  • DOI: 10.1263/jbb.101.51

Production of targeted poly(3-hydroxyalkanoates) copolymers by glycogen accumulating organisms using acetate as sole carbon source
journal, May 2007


Biosynthesis and Characterization of Polyhydroxyalkanoates with Controlled Composition and Microstructure
journal, January 2018


Chemo-enzymatic synthesis of polyhydroxyalkanoate (PHA) incorporating 2-hydroxybutyrate by wild-type class I PHA synthase from Ralstonia eutropha
journal, June 2011

  • Han, Xuerong; Satoh, Yasuharu; Satoh, Toshifumi
  • Applied Microbiology and Biotechnology, Vol. 92, Issue 3
  • DOI: 10.1007/s00253-011-3362-8

Biosynthesis and Characterization of Polyhydroxyalkanoate Block Copolymer P3HB-b-P4HB
journal, August 2011

  • Hu, Die; Chung, Ah-Leum; Wu, Lin-Ping
  • Biomacromolecules, Vol. 12, Issue 9
  • DOI: 10.1021/bm200660k

Pilot scale production of poly(3-hydroxybutyrate- co -4-hydroxybutyrate) biopolymers with high molecular weight and elastomeric properties
journal, July 2017

  • Huong, Kai-Hee; Azuraini, Mat Junoh; Aziz, Nursolehah Abdul
  • Journal of Bioscience and Bioengineering, Vol. 124, Issue 1
  • DOI: 10.1016/j.jbiosc.2017.02.003

Biosynthesis of poly(3-hydroxybutyrate) and its copolymers by Yangia sp. ND199 from different carbon sources
journal, March 2016


Synthesis of P(3HB-co-4HB) copolymer with target-specific 4HB molar fractions using combinations of carbon substrates
journal, July 2013

  • Md. Iqbal, Nurhezreen; Amirul, A. A.
  • Journal of Chemical Technology & Biotechnology, Vol. 89, Issue 3
  • DOI: 10.1002/jctb.4133

Structure and properties of poly(3-hydroxybutyrate-co-4-hydroxybutyrate) produced by Alcaligenes latus
journal, June 1995

  • Kang, Choong-Kyung; Kusaka, Satoshi; Doi, Yoshiharu
  • Biotechnology Letters, Vol. 17, Issue 6
  • DOI: 10.1007/BF00129382

Thermal properties and crystallization behavior of fractionated blocky and random polyhydroxyalkanoate copolymers from mixed microbial cultures
journal, May 2014

  • Laycock, Bronwyn; Arcos-Hernandez, Monica V.; Langford, Alexandra
  • Journal of Applied Polymer Science, Vol. 131, Issue 19
  • DOI: 10.1002/app.40836

Biosynthesis and thermal characterization of polyhydroxyalkanoates bearing phenyl and phenylalkyl side groups
journal, November 2014


Methane or methanol-oxidation dependent synthesis of poly(3-hydroxybutyrate-co-3-hydroxyvalerate) by obligate type II methanotrophs
journal, May 2016


Polyhydroxyalkanoate biosynthesis by Hydrogenophaga pseudoflava DSM1034 from structurally unrelated carbon sources
journal, September 2013

  • Povolo, Silvana; Romanelli, Maria Giovanna; Basaglia, Marina
  • New Biotechnology, Vol. 30, Issue 6
  • DOI: 10.1016/j.nbt.2012.11.019

Microbial Synthesis and Characterization of Poly(3-hydroxybutyrate-co-3-hydroxypropionate)
journal, August 1994

  • Shimamura, Eihaku; Scandola, Mariastella; Doi, Yoshiharu
  • Macromolecules, Vol. 27, Issue 16
  • DOI: 10.1021/ma00094a003

Synthesis of high 4-hydroxybutyrate copolymer by Cupriavidus sp. transformants using one-stage cultivation and mixed precursor substrates strategy
journal, March 2017


Identification, Biosynthesis, and Characterization of Polyhydroxyalkanoate Copolymer Consisting of 3-Hydroxybutyrate and 3-Hydroxy-4-methylvalerate
journal, August 2009

  • Tanadchangsaeng, Nuttapol; Kitagawa, Asahi; Yamamoto, Tetsuya
  • Biomacromolecules, Vol. 10, Issue 10
  • DOI: 10.1021/bm900696c

Biosynthesis and Characterization of Diblock Copolymer of P(3-Hydroxypropionate)- block -P(4-hydroxybutyrate) from Recombinant Escherichia coli
journal, February 2013

  • Tripathi, Lakshmi; Wu, Lin-Ping; Meng, Dechuan
  • Biomacromolecules, Vol. 14, Issue 3
  • DOI: 10.1021/bm3019517

Pseudomonas putida KT2442 as a platform for the biosynthesis of polyhydroxyalkanoates with adjustable monomer contents and compositions
journal, August 2013


Biosynthesis of polyhydroxyalkanoate homopolymers by Pseudomonas putida
journal, November 2010

  • Wang, Hong-hui; Zhou, Xin-rong; Liu, Qian
  • Applied Microbiology and Biotechnology, Vol. 89, Issue 5
  • DOI: 10.1007/s00253-010-2964-x

Mechanical properties, structure analysis and enzymatic degradation of uniaxially cold-drawn films of poly[(R)-3-hydroxybutyrate-co-4-hydroxybutyrate]
journal, December 2011


Properties of PHA bi-, ter-, and quarter-polymers containing 4-hydroxybutyrate monomer units
journal, May 2018


General mechanism of the β transition in polymers
journal, January 1985


Statistical mechanics of chain molecules
journal, November 1969


The Molecular Connectivity Chi Indexes and Kappa Shape Indexes in Structure-Property Modeling
book, January 1991


Highly discriminating distance-based topological index
journal, July 1982


A widely applicable set of descriptors
journal, January 2000


Prediction of Physicochemical Parameters by Atomic Contributions
journal, August 1999

  • Wildman, Scott A.; Crippen, Gordon M.
  • Journal of Chemical Information and Computer Sciences, Vol. 39, Issue 5
  • DOI: 10.1021/ci990307l

Molecular Shape Diversity of Combinatorial Libraries:  A Prerequisite for Broad Bioactivity
journal, March 2003

  • Sauer, Wolfgang H. B.; Schwarz, Matthias K.
  • Journal of Chemical Information and Computer Sciences, Vol. 43, Issue 3
  • DOI: 10.1021/ci025599w

SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules
journal, February 1988

  • Weininger, David
  • Journal of Chemical Information and Modeling, Vol. 28, Issue 1
  • DOI: 10.1021/ci00057a005

SMILES. 2. Algorithm for generation of unique SMILES notation
journal, May 1989

  • Weininger, David; Weininger, Arthur; Weininger, Joseph L.
  • Journal of Chemical Information and Modeling, Vol. 29, Issue 2
  • DOI: 10.1021/ci00062a008

UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations
journal, December 1992

  • Rappe, A. K.; Casewit, C. J.; Colwell, K. S.
  • Journal of the American Chemical Society, Vol. 114, Issue 25, p. 10024-10035
  • DOI: 10.1021/ja00051a040

Open Babel: An open chemical toolbox
journal, October 2011

  • O'Boyle, Noel M.; Banck, Michael; James, Craig A.
  • Journal of Cheminformatics, Vol. 3, Issue 1
  • DOI: 10.1186/1758-2946-3-33

SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
journal, August 2018


New tolerance factor to predict the stability of perovskite oxides and halides
journal, February 2019

  • Bartel, Christopher J.; Sutton, Christopher; Goldsmith, Bryan R.
  • Science Advances, Vol. 5, Issue 2
  • DOI: 10.1126/sciadv.aav0693

Random Forests
journal, January 2001


Induction of decision trees
journal, March 1986


Simplifying decision trees
journal, September 1987


Ensemble Machine Learning
book, January 2012


The elements of statistical learning: data mining, inference and prediction
journal, March 2005

  • Franklin, James
  • The Mathematical Intelligencer, Vol. 27, Issue 2
  • DOI: 10.1007/BF02985802

Machine learning for quantum mechanics in a nutshell
journal, July 2015

  • Rupp, Matthias
  • International Journal of Quantum Chemistry, Vol. 115, Issue 16
  • DOI: 10.1002/qua.24954

Performance of genetic algorithms in search for water splitting perovskites
journal, May 2013

  • Jain, Anubhav; Castelli, Ivano E.; Hautier, Geoffroy
  • Journal of Materials Science, Vol. 48, Issue 19
  • DOI: 10.1007/s10853-013-7448-9

Works referencing / citing this record:

Potentials and challenges of polymer informatics: exploiting machine learning for polymer design
preprint, January 2020