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

Description Usage Arguments

View source: R/melonnpan_predict.R

Description

Predict metabolites from new microbiome samples.

Usage

1
2
3
4
5
6
7
8
melonnpan.predict(
  metag,
  weight.matrix = NULL,
  train.metag = NULL,
  criticalpoint = 0.9793,
  corr.method = "pearson",
  output
)

Arguments

metag

Microbial sequence features' relative abundances (matrix) for which prediction is desired. The sequence features' abundances are expected to be normalized (i.e. proportional data ranging from 0 to 1.0).

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 (i.e. proportional data ranging from 0.0 to 1.0). 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'.

output

Path to the file to write the output.


biobakery/melonnpan documentation built on May 17, 2021, 3:27 a.m.