Environmental predictors impact microbial-based postmortem interval (PMI) estimation models within human decomposition soils

Abstract

Microbial succession has been suggested to supplement established postmortem interval (PMI) estimation methods for human remains. Due to limitations of entomological and morphological PMI methods, microbes are an intriguing target for forensic applications as they are present at all stages of decomposition. Previous machine learning models from soil necrobiome data have produced PMI error rates from two and a half to six days; however, these models are built solely on amplicon sequencing of biomarkers (e.g., 16S, 18S rRNA genes) and do not consider environmental factors that influence the presence and abundance of microbial decomposers. This study builds upon current research by evaluating the inclusion of environmental data on microbial-based PMI estimates from decomposition soil samples. Random forest regression models were built to predict PMI using relative taxon abundances obtained from different biological markers (bacterial 16S, fungal ITS, 16S-ITS combined) and taxonomic levels (phylum, class, order, OTU), both with and without environmental predictors (ambient temperature, soil pH, soil conductivity, and enzyme activities) from 19 deceased human individuals that decomposed on the soil surface (Tennessee, USA). Model performance was evaluated by calculating the mean absolute error (MAE). MAE ranged from 804 to 997 accumulated degree hours (ADH) across all models. 16S models outperformed ITS models (p = 0.006), while combining 16S and ITS did not improve upon 16S models alone (p = 0.47). Inclusion of environmental data in PMI prediction models had varied effects on MAE depending on the biological marker and taxonomic level conserved. Specifically, inclusion of the measured environmental features reduced MAE for all ITS models, but improved 16S models at higher taxonomic levels (phylum and class). Overall, we demonstrated some level of predictability in soil microbial succession during human decomposition, however error rates were high when considering a moderate population of donors.

Fig 1. Mean absolute error (MAE) from 100 iterations of each respective model against the testing dataset.

Data are reported by biological marker (column), while color compares models with (gold) and without (gray) environmental predictors. Error bars are the standard error of MAE values across all 100 iterations for each respective model.

Fig 2. Model predictions for the training set (A-C) and testing set (D-F) for the top performing model for each biological marker as determined by the lowest MAE.

For each biological marker, top models included the 16S phylum + environmental data (A, D, line color—red) 16-ITS order (B, E, line color—blue), and ITS order + environmental data (C, F, line color—magenta). Predictability of each model is greater for the training set (A-C) compared to the testing set (D-F). Soild (training set) and dashed (testing set) lines show the best fit linear relationship and shading indicted the 95% confidence interval between actual PMI, in ADH, and predicted ADH within each respective dataset.

Fig 3. Mean absolute error (MAE) varies as a result of biological marker (16S, 16S-ITS, or ITS) used for model construction.

Average MAE is the result of 100 iterations of the 24 respective models against the testing set. Reported p-values are the result of post-hoc t-tests adjusted for multiple comparisons with the Holm method.

Fig 4. Mean absolute error (MAE) did not vary as a result of taxonomic level (color) used for model construction for any of the biological markers assessed (column).

Mean MAE is the result of 100 iterations of the 24 respective models against the testing set. Order level models generally had the lowest MAE, compared to phylum, class, and OTU models. ANOVA p-values are the result of linear models comparing mean MAE to taxonomic level.

Fig 5. Top 25 model features determined by variance of responses in Ranger.

For each biological marker, top models included 16S phylum + environmental data (A), ITS order + environmental data (B), and 16S-ITS order (C). Bar color denotes whether the feature is a 16S taxon (green), ITS taxon (orange), or environmental feature (purple).

Fig 6. Relative abundance of the 5 most important bacterial phyla in the top 16S random forest model (16S phylum + environmental data).

Relative abundance of the phyla Firmicutes, Acidobacteria, Epsilonbacteraeota, Proteobacteria, and Nitrospirae change over time, here accumulated degree hours (ADH), within decomposition-impacted soils. Abundances for each of the 19 individuals (named “TOX###”) are delineated by color.

Fig 7. Relative abundance of the fungal order Pleosporales over time, here accumulated degree hours (ADH).

Abundances for each of the 19 individuals (named “TOX###”) are delineated by color.