biostudies-literatureUnknownKonnaris MAMicrobiome sequencing measures relative rather than absolute abundances, providing no direct information about total microbial load. Normalization methods attempt to compensate, but rely on strong, often untestable assumptions that can bias inference. Experimental measurements of load (e.g., qPCR, flow cytometry) offer a solution, but remain costly and uncommon. A recent high-profile study proposed that machine learning could bypass this limitation by predicting microbial load from sequencing data alone. To evaluate this claim, we assembled <i>mutt</i>, the largest public database of paired sequencing and load measurements, spanning 35 studies and over 15,000 samples. Using <i>mutt</i>, we show that published machine learning models fail to generalize: on average they perform worse than a bioRxiv : the preprint server for biology2025.09.12.675956https://www.ebi.ac.uk/biostudies/studies/S-EPMC12458437biostudies-literatureUncertainty Modeling Outperforms Machine Learning for Microbiome Data Analysis.PMC12458437Lazar NKonnaris MASaxena MSilverman JDfalseUncertainty Modeling Outperforms Machine Learning for Microbiome Data Analysis.Microbiome sequencing measures relative rather than absolute abundances, providing no direct information about total microbial load. Normalization methods attempt to compensate, but rely on strong, often untestable assumptions that can bias inference. Experimental measurements of load (e.g., qPCR, flow cytometry) offer a solution, but remain costly and uncommon. A recent high-profile study proposed that machine learning could bypass this limitation by predicting microbial load from sequencing data alone. To evaluate this claim, we assembled <i>mutt</i>, the largest public database of paired sequencing and load measurements, spanning 35 studies and over 15,000 samples. Using <i>mutt</i>, we show that published machine learning models fail to generalize: on average they perform worse than a 2025-01-01T00:00:00Z2025 Sep2026-05-04T03:22:51.031Z2026-05-04T03:14:32.926ZS-EPMC124584374100081110.1101/2025.09.12.675956