Back

Scalable power analysis and effect size exploration of microbiome community differences with Evident

Rahman, G.; McDonald, D.; Gonzalez, A.; Vazquez-Baeza, Y.; Jiang, L.; Casals-Pascual, C.; Peddada, S.; Hakim, D.; Dilmore, A. H.; Nowinski, B.; Knight, R.

2022-05-20 bioinformatics
10.1101/2022.05.19.492684 bioRxiv
Show abstract

Differentiating microbial communities among samples is a major objective in biomedicine. Quantifying the effect size of these differences allows researchers to understand the factors most associated with communities and to optimize the design and clinical resources required to address particular research questions. Here, we present Evident, a package for effect size calculations and power analysis on microbiome data and show that Evident scales to large datasets with numerous metadata covariates.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.