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

Title: A Bayesian Approach to Predict Solubility Parameters

Abstract

Abstract Solubility is a ubiquitous phenomenon in many aspects of material science. While solubility can be determined by considering the cohesive forces in a liquid via the Hansen solubility parameters (HSP), quantitative structure–property relationship models are often used for prediction, notably due to their low computational cost. Here, gpHSP, an interpretable and versatile probabilistic approach to determining HSP, is reported. Our model is based on Gaussian processes, a Bayesian machine learning approach that provides uncertainty bounds to prediction. gpHSP achieves its flexibility by leveraging a variety of input data, such as SMILES strings, COSMOtherm simulations, and quantum chemistry calculations. gpHSP is built on experimentally determined HSP, including a general solvents set aggregated from the literature, and a polymer set experimentally characterized by this group of authors. In all sets, a high degree of agreement is obtained, surpassing well‐established machine learning methods. The general applicability of gpHSP to miscibility of organic semiconductors, drug compounds, and in general solvents is demonstrated, which can be further extended to other domains. gpHSP is a fast and accurate toolbox, which could be applied to molecular design for solution processing technologies.

Authors:
ORCiD logo [1]; ORCiD logo [1];  [2];  [2];  [3]; ORCiD logo [4]
  1. Department of Chemistry and Chemical Biology Harvard University Cambridge MA 02138 USA
  2. Institute of Materials for Electronics and Energy Technology (i-MEET) Friedrich‐Alexander‐Universität Erlangen‐Nürnberg Martensstrasse 7 91058 Erlangen Germany
  3. Institute of Materials for Electronics and Energy Technology (i-MEET) Friedrich‐Alexander‐Universität Erlangen‐Nürnberg Martensstrasse 7 91058 Erlangen Germany, Bavarian Center for Applied Energy Research (ZAE Bayern) Immerwahrstrasse 2 91058 Erlangen Germany
  4. Department of Chemistry and Chemical Biology Harvard University Cambridge MA 02138 USA, Canadian Institute for Advanced Research Toronto Ontario M5G 1Z8 Canada, Department of Computer Science University of Toronto Toronto Ontario M5S 3H7 Canada
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1469250
Resource Type:
Publisher's Accepted Manuscript
Journal Name:
Advanced Theory and Simulations
Additional Journal Information:
Journal Name: Advanced Theory and Simulations Journal Volume: 2 Journal Issue: 1; Journal ID: ISSN 2513-0390
Publisher:
Wiley Blackwell (John Wiley & Sons)
Country of Publication:
Germany
Language:
English

Citation Formats

Sanchez‐Lengeling, Benjamin, Roch, Loïc M., Perea, José Darío, Langner, Stefan, Brabec, Christoph J., and Aspuru‐Guzik, Alán. A Bayesian Approach to Predict Solubility Parameters. Germany: N. p., 2018. Web. doi:10.1002/adts.201800069.
Sanchez‐Lengeling, Benjamin, Roch, Loïc M., Perea, José Darío, Langner, Stefan, Brabec, Christoph J., & Aspuru‐Guzik, Alán. A Bayesian Approach to Predict Solubility Parameters. Germany. https://doi.org/10.1002/adts.201800069
Sanchez‐Lengeling, Benjamin, Roch, Loïc M., Perea, José Darío, Langner, Stefan, Brabec, Christoph J., and Aspuru‐Guzik, Alán. Mon . "A Bayesian Approach to Predict Solubility Parameters". Germany. https://doi.org/10.1002/adts.201800069.
@article{osti_1469250,
title = {A Bayesian Approach to Predict Solubility Parameters},
author = {Sanchez‐Lengeling, Benjamin and Roch, Loïc M. and Perea, José Darío and Langner, Stefan and Brabec, Christoph J. and Aspuru‐Guzik, Alán},
abstractNote = {Abstract Solubility is a ubiquitous phenomenon in many aspects of material science. While solubility can be determined by considering the cohesive forces in a liquid via the Hansen solubility parameters (HSP), quantitative structure–property relationship models are often used for prediction, notably due to their low computational cost. Here, gpHSP, an interpretable and versatile probabilistic approach to determining HSP, is reported. Our model is based on Gaussian processes, a Bayesian machine learning approach that provides uncertainty bounds to prediction. gpHSP achieves its flexibility by leveraging a variety of input data, such as SMILES strings, COSMOtherm simulations, and quantum chemistry calculations. gpHSP is built on experimentally determined HSP, including a general solvents set aggregated from the literature, and a polymer set experimentally characterized by this group of authors. In all sets, a high degree of agreement is obtained, surpassing well‐established machine learning methods. The general applicability of gpHSP to miscibility of organic semiconductors, drug compounds, and in general solvents is demonstrated, which can be further extended to other domains. gpHSP is a fast and accurate toolbox, which could be applied to molecular design for solution processing technologies.},
doi = {10.1002/adts.201800069},
journal = {Advanced Theory and Simulations},
number = 1,
volume = 2,
place = {Germany},
year = {Mon Sep 10 00:00:00 EDT 2018},
month = {Mon Sep 10 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1002/adts.201800069

Citation Metrics:
Cited by: 39 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Guiding the Selection of Processing Additives for Increasing the Efficiency of Bulk Heterojunction Polymeric Solar Cells
journal, September 2013

  • Vongsaysy, Uyxing; Pavageau, Bertrand; Wantz, Guillaume
  • Advanced Energy Materials, Vol. 4, Issue 3
  • DOI: 10.1002/aenm.201300752

Determination of Solubility Parameters for Organic Semiconductor Formulations
journal, August 2011

  • Machui, Florian; Abbott, Steven; Waller, David
  • Macromolecular Chemistry and Physics, Vol. 212, Issue 19
  • DOI: 10.1002/macp.201100284

Miscibility-Function Relations in Organic Solar Cells: Significance of Optimal Miscibility in Relation to Percolation
journal, January 2018

  • Ye, Long; Collins, Brian A.; Jiao, Xuechen
  • Advanced Energy Materials, Vol. 8, Issue 28
  • DOI: 10.1002/aenm.201703058

A Systematic Approach to Solvent Selection Based on Cohesive Energy Densities in a Molecular Bulk Heterojunction System
journal, February 2011

  • Walker, Bright; Tamayo, Arnold; Duong, Duc T.
  • Advanced Energy Materials, Vol. 1, Issue 2
  • DOI: 10.1002/aenm.201000054

Nanotube–polymer composites: insights from Flory–Huggins theory and mesoscale simulations
journal, February 2005


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

Estimation of Hansen solubility parameters using multivariate nonlinear QSPR modeling with COSMO screening charge density moments
journal, October 2011


The ORCA program system: The ORCA program system
journal, June 2011

  • Neese, Frank
  • Wiley Interdisciplinary Reviews: Computational Molecular Science, Vol. 2, Issue 1
  • DOI: 10.1002/wcms.81

Extended-Connectivity Fingerprints
journal, April 2010

  • Rogers, David; Hahn, Mathew
  • Journal of Chemical Information and Modeling, Vol. 50, Issue 5
  • DOI: 10.1021/ci100050t

DFTB+, a Sparse Matrix-Based Implementation of the DFTB Method
journal, July 2007

  • Aradi, B.; Hourahine, B.; Frauenheim, Th.
  • The Journal of Physical Chemistry A, Vol. 111, Issue 26
  • DOI: 10.1021/jp070186p

Density-functional exchange-energy approximation with correct asymptotic behavior
journal, September 1988


ChemOS: Orchestrating autonomous experimentation
journal, June 2018


A Simple Representation of Three-Dimensional Molecular Structure
journal, August 2017


Solubility Challenge: Can You Predict Solubilities of 32 Molecules Using a Database of 100 Reliable Measurements?
journal, June 2008

  • Llinàs, Antonio; Glen, Robert C.; Goodman, Jonathan M.
  • Journal of Chemical Information and Modeling, Vol. 48, Issue 7
  • DOI: 10.1021/ci800058v

Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995


A review of methods for the calculation of solution free energies and the modelling of systems in solution
journal, January 2015

  • Skyner, R. E.; McDonagh, J. L.; Groom, C. R.
  • Physical Chemistry Chemical Physics, Vol. 17, Issue 9
  • DOI: 10.1039/C5CP00288E

Hansen solubility parameter as a tool to predict cocrystal formation
journal, April 2011

  • Mohammad, Mohammad Amin; Alhalaweh, Amjad; Velaga, Sitaram P.
  • International Journal of Pharmaceutics, Vol. 407, Issue 1-2
  • DOI: 10.1016/j.ijpharm.2011.01.030

COSMO: a new approach to dielectric screening in solvents with explicit expressions for the screening energy and its gradient
journal, January 1993


Solubility parameter and oral absorption
journal, November 1999

  • Martini, Luigi G.; Avontuur, Paul; George, Ashley
  • European Journal of Pharmaceutics and Biopharmaceutics, Vol. 48, Issue 3
  • DOI: 10.1016/S0939-6411(99)00055-7

Optimization and application of lithium parameters for PM3
journal, November 1993

  • Anders, Ernst; Koch, Rainer; Freunscht, Peter
  • Journal of Computational Chemistry, Vol. 14, Issue 11
  • DOI: 10.1002/jcc.540141106

Computational Prediction of Drug Solubility in Fasted Simulated and Aspirated Human Intestinal Fluid
journal, September 2014

  • Fagerberg, Jonas H.; Karlsson, Eva; Ulander, Johan
  • Pharmaceutical Research, Vol. 32, Issue 2
  • DOI: 10.1007/s11095-014-1487-z

Determination of Solvent–Polymer and Polymer–Polymer Flory–Huggins Interaction Parameters for Poly(3-hexylthiophene) via Solvent Vapor Swelling
journal, August 2013

  • Emerson, Jillian A.; Toolan, Daniel T. W.; Howse, Jonathan R.
  • Macromolecules, Vol. 46, Issue 16
  • DOI: 10.1021/ma400597j

Determination of the P3HT:PCBM solubility parameters via a binary solvent gradient method: Impact of solubility on the photovoltaic performance
journal, May 2012


Sigma-Profile Database for Using COSMO-Based Thermodynamic Methods
journal, June 2006

  • Mullins, Eric; Oldland, Richard; Liu, Y. A.
  • Industrial & Engineering Chemistry Research, Vol. 45, Issue 12
  • DOI: 10.1021/ie060370h

Application of Hansen Solubility Parameters to predict drug–nail interactions, which can assist the design of nail medicines
journal, May 2016

  • Hossin, B.; Rizi, K.; Murdan, S.
  • European Journal of Pharmaceutics and Biopharmaceutics, Vol. 102
  • DOI: 10.1016/j.ejpb.2016.02.009

Understanding the correlation and balance between the miscibility and optoelectronic properties of polymer–fullerene solar cells
journal, January 2017

  • Zhang, Chaohong; Langner, Stefan; Mumyatov, Alexander V.
  • Journal of Materials Chemistry A, Vol. 5, Issue 33
  • DOI: 10.1039/C7TA03505E

Generalizing solubility parameter theory to apply to one- and two-dimensional solutes and to incorporate dipolar interactions
journal, June 2012

  • Hughes, J. Marguerite; Aherne, Damian; Coleman, Jonathan N.
  • Journal of Applied Polymer Science, Vol. 127, Issue 6
  • DOI: 10.1002/app.38051

Polymer Crystallization of Partially Miscible Polythiophene/Fullerene Mixtures Controls Morphology
journal, July 2011

  • Kozub, Derek R.; Vakhshouri, Kiarash; Orme, Lisa M.
  • Macromolecules, Vol. 44, Issue 14
  • DOI: 10.1021/ma200855r

Learning Nonlinear Functions Using Regularized Greedy Forest
journal, May 2014

  • Johnson, Rie; Zhang, Tong
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, Issue 5
  • DOI: 10.1109/TPAMI.2013.159

Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: Design and assessment of accuracy
journal, January 2005

  • Weigend, Florian; Ahlrichs, Reinhart
  • Physical Chemistry Chemical Physics, Vol. 7, Issue 18, p. 3297-3305
  • DOI: 10.1039/b508541a

Multicomponent Solubility Parameters for Single-Walled Carbon Nanotube−Solvent Mixtures
journal, August 2009

  • Bergin, Shane D.; Sun, Zhenyu; Rickard, David
  • ACS Nano, Vol. 3, Issue 8
  • DOI: 10.1021/nn900493u

The role of miscibility in polymer:fullerene nanoparticulate organic photovoltaic devices
journal, September 2013


Suppression of Thermally Induced Fullerene Aggregation in Polyfullerene-Based Multiacceptor Organic Solar Cells
journal, March 2017

  • Dowland, Simon A.; Salvador, Michael; Perea, José Darío
  • ACS Applied Materials & Interfaces, Vol. 9, Issue 12
  • DOI: 10.1021/acsami.7b00401

Accelerating the discovery of materials for clean energy in the era of smart automation
journal, April 2018

  • Tabor, Daniel P.; Roch, Loïc M.; Saikin, Semion K.
  • Nature Reviews Materials, Vol. 3, Issue 5
  • DOI: 10.1038/s41578-018-0005-z

Influence of Molecular Shape on Solid-State Packing in Disordered PC 61 BM and PC 71 BM Fullerenes
journal, September 2014

  • Williams, Monika; Tummala, Naga Rajesh; Aziz, Saadullah G.
  • The Journal of Physical Chemistry Letters, Vol. 5, Issue 19
  • DOI: 10.1021/jz501559q

Molecular-Scale Understanding of Cohesion and Fracture in P3HT:Fullerene Blends
journal, April 2015

  • Tummala, Naga Rajesh; Bruner, Christopher; Risko, Chad
  • ACS Applied Materials & Interfaces, Vol. 7, Issue 18
  • DOI: 10.1021/acsami.5b02202

Molecular solubility and hansen solubility parameters for the analysis of phase separation in bulk heterojunctions
journal, August 2012

  • Duong, Duc T.; Walker, Bright; Lin, Jason
  • Journal of Polymer Science Part B: Polymer Physics, Vol. 50, Issue 20
  • DOI: 10.1002/polb.23153

Classification of Additives for Organic Photovoltaic Devices
journal, January 2015

  • Machui, Florian; Maisch, Philipp; Burgués-Ceballos, Ignasi
  • ChemPhysChem, Vol. 16, Issue 6
  • DOI: 10.1002/cphc.201402734

Density-functional approximation for the correlation energy of the inhomogeneous electron gas
journal, June 1986


In Situ Characterization of Polymer–Fullerene Bilayer Stability
journal, January 2015

  • Leman, Deborah; Kelly, Mary Allison; Ness, Stuart
  • Macromolecules, Vol. 48, Issue 2
  • DOI: 10.1021/ma5021227

Introducing a New Potential Figure of Merit for Evaluating Microstructure Stability in Photovoltaic Polymer-Fullerene Blends
journal, August 2017

  • Perea, José Darío; Langner, Stefan; Salvador, Michael
  • The Journal of Physical Chemistry C, Vol. 121, Issue 33
  • DOI: 10.1021/acs.jpcc.7b03228

Solubility Based Identification of Green Solvents for Small Molecule Organic Solar Cells
journal, November 2013

  • Burgués-Ceballos, Ignasi; Machui, Florian; Min, Jie
  • Advanced Functional Materials, Vol. 24, Issue 10
  • DOI: 10.1002/adfm.201301509

Application of QSPR to Binary Polymer/Solvent Mixtures: Prediction of Flory-Huggins Parameters
journal, December 2008

  • Xu, Jie; Liu, Hongtao; Li, Wenbin
  • Macromolecular Theory and Simulations, Vol. 17, Issue 9
  • DOI: 10.1002/mats.200800063

Small is Powerful: Recent Progress in Solution-Processed Small Molecule Solar Cells
journal, January 2017

  • Collins, Samuel D.; Ran, Niva A.; Heiber, Michael C.
  • Advanced Energy Materials, Vol. 7, Issue 10
  • DOI: 10.1002/aenm.201602242

Semiempirical GGA-type density functional constructed with a long-range dispersion correction
journal, January 2006

  • Grimme, Stefan
  • Journal of Computational Chemistry, Vol. 27, Issue 15, p. 1787-1799
  • DOI: 10.1002/jcc.20495

For the Bright Future-Bulk Heterojunction Polymer Solar Cells with Power Conversion Efficiency of 7.4%
journal, May 2010

  • Liang, Yongye; Xu, Zheng; Xia, Jiangbin
  • Advanced Materials, Vol. 22, Issue 20, p. E135-E138
  • DOI: 10.1002/adma.200903528

Abnormal strong burn-in degradation of highly efficient polymer solar cells caused by spinodal donor-acceptor demixing
journal, February 2017

  • Li, Ning; Perea, José Darío; Kassar, Thaer
  • Nature Communications, Vol. 8, Issue 1
  • DOI: 10.1038/ncomms14541

MultiDK: A Multiple Descriptor Multiple Kernel Approach for Molecular Discovery and Its Application to Organic Flow Battery Electrolytes
journal, April 2017

  • Kim, Sungjin; Jinich, Adrián; Aspuru-Guzik, Alán
  • Journal of Chemical Information and Modeling, Vol. 57, Issue 4
  • DOI: 10.1021/acs.jcim.6b00332

Block Copolymers for Organic Optoelectronics
journal, December 2009

  • Segalman, Rachel A.; McCulloch, Bryan; Kirmayer, Saar
  • Macromolecules, Vol. 42, Issue 23
  • DOI: 10.1021/ma901350w

Combined Computational Approach Based on Density Functional Theory and Artificial Neural Networks for Predicting The Solubility Parameters of Fullerenes
journal, May 2016

  • Perea, J. Darío; Langner, Stefan; Salvador, Michael
  • The Journal of Physical Chemistry B, Vol. 120, Issue 19
  • DOI: 10.1021/acs.jpcb.6b00787

PubChem Substance and Compound databases
journal, September 2015

  • Kim, Sunghwan; Thiessen, Paul A.; Bolton, Evan E.
  • Nucleic Acids Research, Vol. 44, Issue D1
  • DOI: 10.1093/nar/gkv951

Determination of partial solubility parameters of five benzodiazepines in individual solvents
journal, October 2001


The use of solubility parameters in pharmaceutical dosage form design
journal, March 1997