melonnpan.predict: Model-based Genomically Informed High-dimensional Predictor...

In biobakery/melonnpan: Model-based Genomically Informed High-dimensional Predictor of Microbial Community Metabolite Profiles

Model-based Genomically Informed High-dimensional Predictor of Microbial Community Metabolite Profiles

Description

Predict metabolites from new microbiome samples.

Usage

melonnpan.predict(
  metag,
  output,
  no.transform.metab = FALSE,
  no.transform.metag = FALSE,
  weight.matrix = NULL,
  train.metag = NULL,
  criticalpoint = 0.9793,
  corr.method = "pearson"
)

Arguments

metag	Microbial sequence features' relative abundances (matrix) for which prediction is desired. The sequence features' abundances are expected to be normalized.
output	The output folder to write results.
no.transform.metab	Should back transformation be turned off for predicted metabolites? Default is FALSE. If FALSE, it is expected that the proportional data ranging from 0 to 1 was used for training.
no.transform.metag	Should rank-based inverse normal (RIN) transformation be turned off for 'metag'? Default is FALSE.
weight.matrix	The weight matrix to be used for prediction (optional). If not provided, by default, a pre-trained weight matrix based on UniRef90 gene families from the original MelonnPan paper (Mallick et al, 2019) will be used.
train.metag	Quality-controlled training metagenomes against which similarity is desired (optional). The sequence features' abundances are expected to be normalized. If not provided, a pre-processed UniRef90 gene family training table from the original MelonnPan paper (Mallick et al. 2019) will be used.
criticalpoint	A numeric value corresponding to the significance level to find the top PCs. If the significance level is 0.05, 0.01, 0.005, or 0.001, the criticalpoint should be set to be 0.9793, 2.0234, 2.4224, or 3.2724, accordingly. The default is 0.9793 (i.e. 0.05 significance level).
corr.method	Method to correlate new metagenomes and training PCs. Default is 'pearson'.

biobakery/melonnpan documentation built on March 26, 2024, 11:42 p.m.