Faculty of Chemistry Repository - Cherry
University of Belgrade - Faculty of Chemistry
    • English
    • Српски
    • Српски (Serbia)
  • English 
    • English
    • Serbian (Cyrillic)
    • Serbian (Latin)
  • Login
View Item 
  •   Cherry
  • Hemijski fakultet
  • Publikacije
  • View Item
  •   Cherry
  • Hemijski fakultet
  • Publikacije
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Introducing of modeling techniques in the research of POPs in breast milk – A pilot study

Authorized Users Only
2019
Authors
Jovanović, Gordana
Herceg Romanić, Snježana
Stojić, Andreja
Klinčić, Darija
Matek Sarić, Marijana
Grzunov Letinić, Judita
Popović, Aleksandar R.
Article (Published version)
Metadata
Show full item record
Abstract
This study used advanced statistical and machine learning methods to investigate organochlorine pesticides (OCPs) and polychlorinated biphenyls (PCBs) in breast milk, assuming that in a complex biological mixture, the pollutants emitted from the same source or with similar properties are statistically interrelated and possibly exhibit non-linear dynamics. The elaborated analyses such as Unmix source apportionment characterized individual source groups, while guided regularized random forest indicated the pollutant dependence on the ortho-chlorine atom attached to the congener's phenyl ring and mother's age. Mutual associations among PCBs were further discussed, but the results implied they were mostly not related to child delivery. PCB congeners −153, −180, −170, −118, −156, −105, and −138 appeared to be compounds of the outmost importance for mutual prediction with reference to their interrelations regarding chemical structure and metabolic processes in the mother's body. Finally, mac...hine learning methods, which provided prediction relative errors lower than 30% and correlation coefficients higher than 0.90, suggested a possible strong non-linear relationship among the pollutants and consequently, the complexity of their pathways in the breast milk.

Keywords:
Age / Feature selection / Machine learning / Parity / Persistent organic pollutants (POPs) / Unmix
Source:
Ecotoxicology and Environmental Safety, 2019, 172, 341-347
Publisher:
  • Elsevier
Funding / projects:
  • Croatian Science Foundation (Project OPENTOX, No. 8366)
  • Studying climate change and its influence on environment: impacts, adaptation and mitigation (RS-43007)
  • Application of low temperature plasmas in biomedicine, environmental protection and nanotechnologies (RS-41011)

DOI: 10.1016/j.ecoenv.2019.01.087

ISSN: 0147-6513

WoS: 000460196000045

Scopus: 2-s2.0-85060897792
[ Google Scholar ]
7
3
URI
https://cherry.chem.bg.ac.rs/handle/123456789/2836
Collections
  • Publikacije
Institution/Community
Hemijski fakultet
TY  - JOUR
AU  - Jovanović, Gordana
AU  - Herceg Romanić, Snježana
AU  - Stojić, Andreja
AU  - Klinčić, Darija
AU  - Matek Sarić, Marijana
AU  - Grzunov Letinić, Judita
AU  - Popović, Aleksandar R.
PY  - 2019
UR  - https://cherry.chem.bg.ac.rs/handle/123456789/2836
AB  - This study used advanced statistical and machine learning methods to investigate organochlorine pesticides (OCPs) and polychlorinated biphenyls (PCBs) in breast milk, assuming that in a complex biological mixture, the pollutants emitted from the same source or with similar properties are statistically interrelated and possibly exhibit non-linear dynamics. The elaborated analyses such as Unmix source apportionment characterized individual source groups, while guided regularized random forest indicated the pollutant dependence on the ortho-chlorine atom attached to the congener's phenyl ring and mother's age. Mutual associations among PCBs were further discussed, but the results implied they were mostly not related to child delivery. PCB congeners −153, −180, −170, −118, −156, −105, and −138 appeared to be compounds of the outmost importance for mutual prediction with reference to their interrelations regarding chemical structure and metabolic processes in the mother's body. Finally, machine learning methods, which provided prediction relative errors lower than 30% and correlation coefficients higher than 0.90, suggested a possible strong non-linear relationship among the pollutants and consequently, the complexity of their pathways in the breast milk.
PB  - Elsevier
T2  - Ecotoxicology and Environmental Safety
T1  - Introducing of modeling techniques in the research of POPs in breast milk – A pilot study
VL  - 172
SP  - 341
EP  - 347
DO  - 10.1016/j.ecoenv.2019.01.087
ER  - 
@article{
author = "Jovanović, Gordana and Herceg Romanić, Snježana and Stojić, Andreja and Klinčić, Darija and Matek Sarić, Marijana and Grzunov Letinić, Judita and Popović, Aleksandar R.",
year = "2019",
abstract = "This study used advanced statistical and machine learning methods to investigate organochlorine pesticides (OCPs) and polychlorinated biphenyls (PCBs) in breast milk, assuming that in a complex biological mixture, the pollutants emitted from the same source or with similar properties are statistically interrelated and possibly exhibit non-linear dynamics. The elaborated analyses such as Unmix source apportionment characterized individual source groups, while guided regularized random forest indicated the pollutant dependence on the ortho-chlorine atom attached to the congener's phenyl ring and mother's age. Mutual associations among PCBs were further discussed, but the results implied they were mostly not related to child delivery. PCB congeners −153, −180, −170, −118, −156, −105, and −138 appeared to be compounds of the outmost importance for mutual prediction with reference to their interrelations regarding chemical structure and metabolic processes in the mother's body. Finally, machine learning methods, which provided prediction relative errors lower than 30% and correlation coefficients higher than 0.90, suggested a possible strong non-linear relationship among the pollutants and consequently, the complexity of their pathways in the breast milk.",
publisher = "Elsevier",
journal = "Ecotoxicology and Environmental Safety",
title = "Introducing of modeling techniques in the research of POPs in breast milk – A pilot study",
volume = "172",
pages = "341-347",
doi = "10.1016/j.ecoenv.2019.01.087"
}
Jovanović, G., Herceg Romanić, S., Stojić, A., Klinčić, D., Matek Sarić, M., Grzunov Letinić, J.,& Popović, A. R.. (2019). Introducing of modeling techniques in the research of POPs in breast milk – A pilot study. in Ecotoxicology and Environmental Safety
Elsevier., 172, 341-347.
https://doi.org/10.1016/j.ecoenv.2019.01.087
Jovanović G, Herceg Romanić S, Stojić A, Klinčić D, Matek Sarić M, Grzunov Letinić J, Popović AR. Introducing of modeling techniques in the research of POPs in breast milk – A pilot study. in Ecotoxicology and Environmental Safety. 2019;172:341-347.
doi:10.1016/j.ecoenv.2019.01.087 .
Jovanović, Gordana, Herceg Romanić, Snježana, Stojić, Andreja, Klinčić, Darija, Matek Sarić, Marijana, Grzunov Letinić, Judita, Popović, Aleksandar R., "Introducing of modeling techniques in the research of POPs in breast milk – A pilot study" in Ecotoxicology and Environmental Safety, 172 (2019):341-347,
https://doi.org/10.1016/j.ecoenv.2019.01.087 . .

DSpace software copyright © 2002-2015  DuraSpace
About CHERRY - CHEmistry RepositoRY | Send Feedback

re3dataOpenAIRERCUB
 

 

All of DSpaceInstitutions/communitiesAuthorsTitlesSubjectsThis institutionAuthorsTitlesSubjects

Statistics

View Usage Statistics

DSpace software copyright © 2002-2015  DuraSpace
About CHERRY - CHEmistry RepositoRY | Send Feedback

re3dataOpenAIRERCUB