Inference of drowning sites using bacterial composition and random forest algorithm

Diagnosing the drowning site is a major challenge in forensic practice, particularly when corpses are recovered from flowing rivers. Recently, forensic experts have focused on aquatic microorganisms, including bacteria, which can enter the bloodstream during drowning and may proliferate in corpses. The emergence of 16S ribosomal RNA gene (16S rDNA) amplicon sequencing has provided a new method for analyzing bacterial composition and has facilitated the development of forensic microbiology. We propose that 16S rDNA amplicon sequencing could be a useful tool for inferring drowning sites. Our study found significant differences in bacterial composition in different regions of the Guangzhou section of the Pearl River, which led to differences in bacteria of drowned rabbit lungs at different drowning sites. Using the genus level of bacteria in the lung tissue of drowned rabbits, we constructed a random forest model that accurately predicted the drowning site in a test set with 100% accuracy. Furthermore, we discovered that bacterial species endemic to the water were not always present in the corresponding drowned lung tissue. Our findings demonstrate the potential of a random forest model based on bacterial genus and composition in drowned lung tissues for inferring drowning sites.