Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study
Silvia Babolin, Roberto Enea, Mariagrazia Cicala, Daniele Di Giovanni, Luigi Mazzone, Leonardo Emberti Gialloreti · 2026
Read Machine learning model to identify gut microbiome-derived metabolites as potential biomarkers of autism spectrum disorder: a pilot study by Silvia Babolin, Roberto Enea, Mariagrazia Cicala, Daniele Di Giovanni, Luigi Mazzone, Leonardo Emberti Gialloreti (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13471347.txt.
Description
Babolin and co-authors test whether a computer model can spot autism spectrum disorder from the chemicals that gut bacteria are predicted to make. Their 2026 pilot study combined two large databases, GMRepo v2 and Agora2, to estimate each person's microbial metabolite output.
A random forest model, a machine learning method that votes across many decision trees, separated autistic participants from healthy controls with a mean accuracy of 85% in validation testing. When the team checked the most influential metabolites against published lab studies, 40% matched findings already reported in living subjects. Short-chain fatty acids, amino acid derivatives, and volatile organic compounds ranked among the strongest signals. The authors frame the work as a proof of concept for cheaper, earlier screening research.
Catalog record
| CREATOR | Silvia Babolin, Roberto Enea, Mariagrazia Cicala, Daniele Di Giovanni, Luigi Mazzone, Leonardo Emberti Gialloreti |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |