52/100

Moderate evidence

GainPublished recordCrimeGood Space

Supervised machine learning enables forensic microbiome source attribution in soil and touch samples with evidence-type-specific relic DNA effects

Truvace record
TRV-2026-2997raw data (JSON)
Version
v1Published
First published
Evidence type
Benchmark or lab evaluation
Sources
1 sourcePeer-reviewed
sha256
b79c91287c11…check it

Microbial trace evidence is increasingly proposed for forensic source attribution, yet most studies lack performance benchmarks across evidence types and rarely test robustness across sample preprocessing conditions. Here, we evaluated supervised machine learning models for attributing (i) mock soil trace evidence to four source locations and (ii) human touch trace evidence to the correct donor using paired samples collected under controlled transfer conditions. 16S rRNA amplicon profiles were used to assess mic…

The gain

In a forensic lab study, machine learning classifiers trained on 16S rRNA microbiome profiles matched mock soil trace evidence to one of four source locations with accuracies above 84%, reaching 97.9%.

What this doesn’t fix

The work used mock soil traces from four locations and controlled touch transfers, and touch attribution was weaker and more condition sensitive than soil attribution.

Sources

1 on file
  1. Journal of Forensic Sciencesdoi:10.1111/1556-4029.70504
    Peer-reviewed2026-11-16

Cite this record

v1

Truvace Impact Record TRV-2026-2997, v1: “Supervised machine learning enables forensic microbiome source attribution in soil and touch samples with evidence-type-specific relic DNA effects.” Truvace, 2026-11-17. /record/TRV-2026-2997 (accessed on the day you copy it). sha256 b79c91287c11208f…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv1b79c91287c11…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2997 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.