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...
Autores principales: | , , , , , , |
---|---|
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 |