Cargando…

Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models

Death investigations often include an effort to establish the postmortem interval (PMI) in cases in which the time of death is uncertain. The postmortem interval can lead to the identification of the deceased and the validation of witness statements and suspect alibis. Recent research has demonstrat...

Descripción completa

Detalles Bibliográficos
Autores principales: Belk, Aeriel, Xu, Zhenjiang Zech, Carter, David O., Lynne, Aaron, Bucheli, Sibyl, Knight, Rob, Metcalf, Jessica L.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5852600/
https://www.ncbi.nlm.nih.gov/pubmed/29462950
http://dx.doi.org/10.3390/genes9020104
_version_ 1783306602851336192
author Belk, Aeriel
Xu, Zhenjiang Zech
Carter, David O.
Lynne, Aaron
Bucheli, Sibyl
Knight, Rob
Metcalf, Jessica L.
author_facet Belk, Aeriel
Xu, Zhenjiang Zech
Carter, David O.
Lynne, Aaron
Bucheli, Sibyl
Knight, Rob
Metcalf, Jessica L.
author_sort Belk, Aeriel
collection PubMed
description Death investigations often include an effort to establish the postmortem interval (PMI) in cases in which the time of death is uncertain. The postmortem interval can lead to the identification of the deceased and the validation of witness statements and suspect alibis. Recent research has demonstrated that microbes provide an accurate clock that starts at death and relies on ecological change in the microbial communities that normally inhabit a body and its surrounding environment. Here, we explore how to build the most robust Random Forest regression models for prediction of PMI by testing models built on different sample types (gravesoil, skin of the torso, skin of the head), gene markers (16S ribosomal RNA (rRNA), 18S rRNA, internal transcribed spacer regions (ITS)), and taxonomic levels (sequence variants, species, genus, etc.). We also tested whether particular suites of indicator microbes were informative across different datasets. Generally, results indicate that the most accurate models for predicting PMI were built using gravesoil and skin data using the 16S rRNA genetic marker at the taxonomic level of phyla. Additionally, several phyla consistently contributed highly to model accuracy and may be candidate indicators of PMI.
format Online
Article
Text
id pubmed-5852600
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-58526002018-03-19 Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models Belk, Aeriel Xu, Zhenjiang Zech Carter, David O. Lynne, Aaron Bucheli, Sibyl Knight, Rob Metcalf, Jessica L. Genes (Basel) Article Death investigations often include an effort to establish the postmortem interval (PMI) in cases in which the time of death is uncertain. The postmortem interval can lead to the identification of the deceased and the validation of witness statements and suspect alibis. Recent research has demonstrated that microbes provide an accurate clock that starts at death and relies on ecological change in the microbial communities that normally inhabit a body and its surrounding environment. Here, we explore how to build the most robust Random Forest regression models for prediction of PMI by testing models built on different sample types (gravesoil, skin of the torso, skin of the head), gene markers (16S ribosomal RNA (rRNA), 18S rRNA, internal transcribed spacer regions (ITS)), and taxonomic levels (sequence variants, species, genus, etc.). We also tested whether particular suites of indicator microbes were informative across different datasets. Generally, results indicate that the most accurate models for predicting PMI were built using gravesoil and skin data using the 16S rRNA genetic marker at the taxonomic level of phyla. Additionally, several phyla consistently contributed highly to model accuracy and may be candidate indicators of PMI. MDPI 2018-02-16 /pmc/articles/PMC5852600/ /pubmed/29462950 http://dx.doi.org/10.3390/genes9020104 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Belk, Aeriel
Xu, Zhenjiang Zech
Carter, David O.
Lynne, Aaron
Bucheli, Sibyl
Knight, Rob
Metcalf, Jessica L.
Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models
title Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models
title_full Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models
title_fullStr Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models
title_full_unstemmed Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models
title_short Microbiome Data Accurately Predicts the Postmortem Interval Using Random Forest Regression Models
title_sort microbiome data accurately predicts the postmortem interval using random forest regression models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5852600/
https://www.ncbi.nlm.nih.gov/pubmed/29462950
http://dx.doi.org/10.3390/genes9020104
work_keys_str_mv AT belkaeriel microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels
AT xuzhenjiangzech microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels
AT carterdavido microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels
AT lynneaaron microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels
AT buchelisibyl microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels
AT knightrob microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels
AT metcalfjessical microbiomedataaccuratelypredictsthepostmortemintervalusingrandomforestregressionmodels