predict_paramedic: Generate predictions based on a paramedic model fit

In statdivlab/paramedic: Predicting Absolute and Relative Abundance by Modeling Efficiency to Derive Intervals and Concentrations

Generate predictions based on a paramedic model fit

Description

Predict concentrations (and efficiencies, if applicable), absolute abundances, and relative abundances based on the posterior distributions from a previously fitted model resulting from a call to run_paramedic.

Usage

predict_paramedic(
  W,
  V,
  X = V[, 1, drop = FALSE],
  beta_0,
  beta_1 = array(0, dim = c(nrow(beta_0), ncol(X) - 1, ncol(W) - 1)),
  Sigma,
  sigma_e = matrix(0, nrow = nrow(Sigma), ncol = ncol(Sigma)),
  phi = matrix(1, nrow = nrow(Sigma), ncol = nrow(X)),
  k = 0,
  n_iter = 10500,
  n_burnin = 10000,
  n_chains = 4,
  stan_seed = 4747,
  alpha_sigma = 2,
  kappa_sigma = 1,
  alpha_phi = 0,
  beta_phi = 0,
  sigma_xi = 1,
  ...
)

Arguments

W	The new relative abundance data, e.g., from broad range 16S sequencing with "universal" primers. Expects data (e.g., matrix, data.frame, tibble) with sample identifiers in the first column. Sample identifiers must be the same between W and V, and the column must have the same name in W and V.
V	The new absolute abundance data, e.g., from taxon-specific absolute primers. Expects data (e.g., matrix, data.frame, tibble) with sample identifiers in the first column. Sample identifiers must be the same between W and V, and the column must have the same name in W and V.
X	The new covariate data. Expects data (e.g., matrix, data.frame, tibble) with sample identifiers in the first column. Sample identifiers must be the same between W, V, and X, and the column must have the same name in W, V, and X. If X only consists of the subject identifiers, then no covariates are used.
beta_0	The posterior distribution on \beta_0 (the intercept in the distribution on concentrations \mu), resulting from a call to run_paramedic.
beta_1	The posterior distribution on \beta_1 (the slope in the distribution on concentrations \mu; only used if X consists of more than just sample identifiers), resulting from a call to run_paramedic.
Sigma	The posterior distribution on \Sigma (the variance in the distribution on concentrations \mu).
sigma_e	The posterior distribution on \sigma_e (the variance of the efficiencies); only used if both alpha_sigma and kappa_sigma below are nonzero.
phi	The posterior distribution on \phi (the overdispersion parameter on V); only used if both alpha_phi and beta_phi below are nonzero.
k	the number of batches that the relative abundance data W were analyzed in. If k = 0 (the default), then batch effects are not considered. (currently not used)
n_iter	The total number of iterations per chain to be run by the Stan algorithm. Defaults to 10500.
n_burnin	The total number of warmups per chain to be run by the Stan algorithm. Defaults to 10000.
n_chains	The total number of chains to be run by the Stan algorithm. Defaults to 4.
stan_seed	The random number seed to initialize.
alpha_sigma	Hyperparameter specifying the shape parameter of the prior distribution on \sigma_e. Defaults to 2.
kappa_sigma	Hyperparameter specifying the scale parameter of the prior distribution on \sigma_e. Defaults to 1.
alpha_phi	Hyperparameter specifying the shape parameter of the prior distribution on \phi. Defaults to 0; a negative binomial model can be specified if both alpha_phi and beta_phi are nonzero.
beta_phi	Hyperparameter specifying the rate parameter of the prior distribution on \phi. Defaults to 0; a negative binomial model can be specified if both alpha_phi and beta_phi are nonzero.
sigma_xi	Hyperparameters specifying the variance of efficiencies over batches. Only used if k is greater than zero. Defaults to 1. (currently not used)
...	other arguments to pass to sampling (e.g., control).

Details

Using the posterior distributions from a call to run_paramedic, generate predicted values.

Value

An object of class stanfit.

See Also

stan and sampling for specific usage of the stan and sampling functions; run_paramedic for usage of the run_paramedic function.

Examples

# load the package, read in example data
library("paramedic")
data(example_16S_data)
data(example_qPCR_data)
# generate a train/test split
set.seed(1234)
folds <- sample(1:2, size = nrow(example_16S_data), replace = TRUE)

# run paramedic (with an extremely small number of iterations, for illustration only)
# on only the first 10 taxa, and on a subset of the data
mod <- run_paramedic(W = example_16S_data[folds == 1, 1:10], 
V = example_qPCR_data[folds == 1, ], n_iter = 30, n_burnin = 25, 
n_chains = 1, stan_seed = 4747)

# generate predictions on test data
ext_mod <- rstan::extract(mod)
beta0_post <- ext_mod$beta_0
sigma_post <- ext_mod$Sigma
sigmae_post <- ext_mod$sigma_e
pred_mod <- predict_paramedic(W = example_16S_data[folds == 2, 1:10], 
V = example_qPCR_data[folds == 2, ], n_iter = 75, n_burnin = 25,
 beta_0 = beta0_post, Sigma = sigma_post, sigma_e = sigmae_post, 
 n_chains = 1, stan_seed = 1234) 

statdivlab/paramedic documentation built on May 3, 2024, 7:08 p.m.