MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling

Multi-component materials/compounds and polymeric/composite systems pose structural complexity that challenges the conventional methods of molecular representation in cheminformatics, which have limited applicability in such cases. Therefore, we have introduced an innovative structural representatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Rahil Ashtari Mahini, Gerardo Casanola-Martin, Simone A. Ludwig, Bakhtiyor Rasulev
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:SoftwareX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352711024002814
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850220576662093824
author Rahil Ashtari Mahini
Gerardo Casanola-Martin
Simone A. Ludwig
Bakhtiyor Rasulev
author_facet Rahil Ashtari Mahini
Gerardo Casanola-Martin
Simone A. Ludwig
Bakhtiyor Rasulev
author_sort Rahil Ashtari Mahini
collection DOAJ
description Multi-component materials/compounds and polymeric/composite systems pose structural complexity that challenges the conventional methods of molecular representation in cheminformatics, which have limited applicability in such cases. Therefore, we have introduced an innovative structural representation technique tailored for complex materials. We implemented different mixing rules based on linear and nonlinear relationships’ additive effect of different components in composites treating each multi-component material as a mixture system. We developed and improved mixture descriptors based on 12 different mixture functions grouped into three main categories: property-based descriptors, concentration-weighted descriptors, and deviation-combination descriptors. A python package was developed for this purpose, allowing users to compute 12 different mixture-descriptors to use as input for the generation of mixture-based Quantitative Structure-Activity/Property Relationship (mxb-QSAR/QSPR) machine learning models for predicting a range of chemical and physical properties across various complex systems.
format Article
id doaj-art-9d720b437a394cf883b5b3a68d84b4ce
institution OA Journals
issn 2352-7110
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series SoftwareX
spelling doaj-art-9d720b437a394cf883b5b3a68d84b4ce2025-08-20T02:07:01ZengElsevierSoftwareX2352-71102024-12-012810191110.1016/j.softx.2024.101911MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modelingRahil Ashtari Mahini0Gerardo Casanola-Martin1Simone A. Ludwig2Bakhtiyor Rasulev3Department of Computer Science, North Dakota State University, 1320 Albrecht Boulevard, Fargo, ND 58105, United States of America; Department of Coatings and Polymeric Materials, North Dakota State University, 1735 NDSU Research Park, Drive N, Fargo, ND 58102, United States of AmericaDepartment of Coatings and Polymeric Materials, North Dakota State University, 1735 NDSU Research Park, Drive N, Fargo, ND 58102, United States of AmericaDepartment of Computer Science, North Dakota State University, 1320 Albrecht Boulevard, Fargo, ND 58105, United States of AmericaDepartment of Coatings and Polymeric Materials, North Dakota State University, 1735 NDSU Research Park, Drive N, Fargo, ND 58102, United States of America; Corresponding author.Multi-component materials/compounds and polymeric/composite systems pose structural complexity that challenges the conventional methods of molecular representation in cheminformatics, which have limited applicability in such cases. Therefore, we have introduced an innovative structural representation technique tailored for complex materials. We implemented different mixing rules based on linear and nonlinear relationships’ additive effect of different components in composites treating each multi-component material as a mixture system. We developed and improved mixture descriptors based on 12 different mixture functions grouped into three main categories: property-based descriptors, concentration-weighted descriptors, and deviation-combination descriptors. A python package was developed for this purpose, allowing users to compute 12 different mixture-descriptors to use as input for the generation of mixture-based Quantitative Structure-Activity/Property Relationship (mxb-QSAR/QSPR) machine learning models for predicting a range of chemical and physical properties across various complex systems.http://www.sciencedirect.com/science/article/pii/S2352711024002814CheminformaticsMixture-based QSARMixture-based QSPRMixture descriptorMixing ruleMixtureMetrics
spellingShingle Rahil Ashtari Mahini
Gerardo Casanola-Martin
Simone A. Ludwig
Bakhtiyor Rasulev
MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
SoftwareX
Cheminformatics
Mixture-based QSAR
Mixture-based QSPR
Mixture descriptor
Mixing rule
MixtureMetrics
title MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
title_full MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
title_fullStr MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
title_full_unstemmed MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
title_short MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
title_sort mixturemetrics a comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling
topic Cheminformatics
Mixture-based QSAR
Mixture-based QSPR
Mixture descriptor
Mixing rule
MixtureMetrics
url http://www.sciencedirect.com/science/article/pii/S2352711024002814
work_keys_str_mv AT rahilashtarimahini mixturemetricsacomprehensivepackagetodevelopadditivenumericalfeaturestodescribecomplexmaterialsformachinelearningmodeling
AT gerardocasanolamartin mixturemetricsacomprehensivepackagetodevelopadditivenumericalfeaturestodescribecomplexmaterialsformachinelearningmodeling
AT simonealudwig mixturemetricsacomprehensivepackagetodevelopadditivenumericalfeaturestodescribecomplexmaterialsformachinelearningmodeling
AT bakhtiyorrasulev mixturemetricsacomprehensivepackagetodevelopadditivenumericalfeaturestodescribecomplexmaterialsformachinelearningmodeling