Predicting provenance of forensic soil samples: Linking soil to ecological habitats by metabarcoding and supervised classification

Abstract

Environmental DNA (eDNA) is increasingly applied in ecological studies, including studies with the primary purpose of criminal investigation, in which eDNA from soil can be used to pair samples or reveal sample provenance. We collected soil eDNA samples as part of a large national biodiversity research project across 130 sites in Denmark. We investigated the potential for soil eDNA metabarcoding in predicting provenance in terms of environmental conditions, habitat type and geographic regions. We used linear regression for predicting environmental gradients of light, soil moisture, pH and nutrient status (represented by Ellenberg Indicator Values, EIVs) and Quadratic Discriminant Analysis (QDA) to predict habitat type and geographic region. eDNA data performed relatively well as a predictor of environmental gradients (R2 > 0.81). Its ability to discriminate between habitat types was variable, with high accuracy for certain forest types and low accuracy for heathland, which was poorly predicted. Geographic region was also less accurately predicted by eDNA. We demonstrated the application of provenance prediction in forensic science by evaluating and discussing two mock crime scenes. Here, we listed the plant species from annotated sequences, which can further aid in identifying the likely habitat or, in case of rare species, a geographic region. Predictions of environmental gradients and habitat types together give an overall accurate description of a crime scene, but care should be taken when interpreting annotated sequences, e.g. due to erroneous assignments in GenBank. Our approach demonstrates that important habitat properties can be derived from soil eDNA, and exemplifies a range of potential applications of eDNA in forensic ecology.

Fig 1. Interpreting Ellenberg Indicator Values.

Ellipses showing the multivariate normal distribution of vegetation types plotted along Ellenberg indicator values for light, soil moisture, pH and nutrient status. Agricultural includes rotational fields, old fields and lays. The colors of the ellipses correspond to characteristic sites depicted on the right.

Fig 2. Mock crime scene 1 and the provenance derived from soil eDNA.

Predicted location in environmental space (Ellenberg Indicator Values) based on the best linear models and GAM for light (top left). The cross marks the predicted EIV value and the length of the arms show the 95% confidence intervals. Blue dots show the actual EIVs at the sample site. The predicted probability of binary habitat types based on Quadratic Discriminant Analysis are shown as red lines on a box plot of the distribution of predicted values for each characteristic (middle part). A priori classification membership is indicated by asterisk of the 0/1 variable. The probabilities for heathland, coniferous and Atlantic are not shown. A list of plant species sequences, their frequency of sequences (FS) in the sample, and if applicable, the geographic region of their distribution in Denmark is listed bottom left. For evaluation, we provide a picture of the sample location (bottom right).

Fig 3. Mock crime scene 2 and the provenance derived from soil eDNA.

Predicted location in environmental space (Ellenberg Indicator Values) based on the best linear models and GAM for light (top left). The cross marks the predicted EIV value and the length of the arms show the 95% confidence intervals. Blue dots show the actual EIVs at the sample site. The predicted probability of binary habitat types based on Quadratic Discriminant Analysis are shown as red lines on a box plot of the distribution of predicted values for each characteristic (middle part). A priori classification membership is indicated by asterisk of the 0/1 variable. The probabilities for heathland, coniferous and Atlantic are not shown. A list of plant species sequences, their frequency of sequences (FS) in the sample, and if applicable, the geographic region of their distribution in Denmark is listed bottom left. For evaluation, we provide a picture of the sample location (bottom right).