EUVIMEDEUVIMED entdecken
Crossref

Bacterial profile-based body fluid identification using a machine learning approach

Sungmin Kim iD, Han Chul Lee, Jeong Eun Sim, Su Jeong Park, Hye Hyun Oh

Genes & Genomics · 2025-01 · 47 (1) · 87-98

DOI: 10.1007/s13258-024-01594-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genes & Genomics, online erschienen am 06.11.2024. Verfasst von Sungmin Kim und 4 weiteren Autor:innen. Beteiligte Einrichtung: Forensic Genetics and Chemistry Division, Supreme Prosecutors' Office, 157 Banpo daero, Seocho gu, Seoul, 06590, Republic of Korea. kandury@gmail.com. Hauptthemen laut MEDLINE: Machine Learning, Body Fluids, Bacteria. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Identifying the origins of biological traces is critical for the reconstruction of crime scenes in forensic investigations. Traditional methods for body fluid identification rely on chemical, enzymatic, immunological, and spectroscopic techniques, which can be sample-consuming and depend on simple color-change reactions. However, these methods have limitations when residual samples are insufficient after DNA extraction. OBJECTIVE: This study aimed to develop a method for body fluid identification by leveraging bacterial DNA profiling to overcome the limitations of the conventional approaches. METHODS: Bacterial profiles were determined by sequencing the hypervariable region of the 16 S rRNA gene, using DNA metabarcoding of evidence collected from criminal cases. Amplicon sequence variants (ASVs) were analyzed to identify significant microbial patterns in different body fluid samples. RESULTS: The bacterial profile-based method demonstrated high discriminatory power with a machine learning model trained using the naïve Bayes algorithm, achieving an accuracy of over 98% in classifying samples into one of four body fluid types: blood, saliva, vaginal secretion, and mixture traces of vaginal secretions and semen. CONCLUSION: Bacterial profiling enhances the accuracy and robustness of body fluid identification in forensic analysis, providing a valuable alternative to traditional methods by utilizing DNA and microbial community data despite the uncontrollable conditions. This approach offers significant improvements in the classification accuracy and practical applicability in forensic investigations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBody FluidsBacteriaHumansFemaleSalivaRNA, Ribosomal, 16SMaleForensic GeneticsDNA, Bacterial

Stichwörter der Autor:innen

Bacterial profilesBody fluid identificationDNA metabarcodingMachine learning

Substanzen

RNA, Ribosomal, 16SDNA, Bacterial

Autor:innen und Institutionen

  • Forensic Genetics and Chemistry Division, Supreme Prosecutors' Office, 157 Banpo daero, Seocho gu, Seoul, 06590, Republic of Korea. kandury@gmail.com.
  • Forensic Genetics and Chemistry Division, Supreme Prosecutors' Office, 157 Banpo daero, Seocho gu, Seoul, 06590, Republic of Korea.

ORCID-Profile: Sungmin Kim

Zitieren

APA

Kim, S., Lee, H. C., Sim, J. E., Park, S. J., & Oh, H. H. (2025). Bacterial profile-based body fluid identification using a machine learning approach. Genes & Genomics, 47(1), 87-98. https://doi.org/10.1007/s13258-024-01594-8

Vancouver

Kim S, Lee HC, Sim JE, Park SJ, Oh HH. Bacterial profile-based body fluid identification using a machine learning approach. Genes & Genomics. 2025;47(1):87-98. doi:10.1007/s13258-024-01594-8

BibTeX
@article{Kim2025,
  author = {Kim, Sungmin and Lee, Han Chul and Sim, Jeong Eun and Park, Su Jeong and Oh, Hye Hyun},
  title = {Bacterial profile-based body fluid identification using a machine learning approach},
  journal = {Genes & Genomics},
  year = {2025},
  volume = {47},
  number = {1},
  pages = {87--98},
  doi = {10.1007/s13258-024-01594-8}
}
Kostenlos starten →