Fit one POWERUP model — make_xgb

Fit and evaluate one XGBoost model for a single perturbation.

Usage

make_xgb_model(
  perturbation,
  indx,
  total,
  dataset,
  response_cutoff = 0.5,
  decreasing = FALSE,
  nfolds = 3,
  nrepeats = 3,
  nrounds = 200,
  max_depth = 3,
  f_subsample = 1,
  min_score = 0.01,
  shuffle = FALSE,
  seed = 1L,
  n_threads = 4,
  xgb_params = NULL,
  cor_n_features = NULL,
  shap_top_n = 100L
)

Arguments

perturbation: Column name of the perturbation to model.
indx: Integer model index used for progress reporting.
total: Total number of models used for progress reporting.
dataset: Data frame containing the perturbation response and predictor columns. Sample names are row names.
response_cutoff: Default biological response cutoff used to define target events for classification-style summaries and downstream event probabilities.
decreasing: If TRUE, values at or below response_cutoff define the target event; otherwise values at or above the cutoff define the target event.
nfolds: Number of cross-validation folds.
nrepeats: Number of repeated cross-validation runs.
nrounds: Maximum number of XGBoost boosting rounds.
max_depth: Maximum tree depth.
f_subsample: Fraction of training rows sampled for each boosting round.
min_score: Minimum mean R-squared required to retain the fitted model.
shuffle: If TRUE, shuffle response values before model fitting.
seed: Base random seed. A deterministic perturbation-specific seed is derived from this value so model results do not depend on target order. Both values are stored in each returned model object as seed and target_seed.
n_threads: Number of threads passed to XGBoost.
xgb_params: Optional named list overriding supported XGBoost parameters.
cor_n_features: Optional number of target-correlated features to retain. When set, features are ranked by absolute correlation within each cross-validation training fold and reranked using all training samples for the final refit. NULL disables correlation filtering.
shap_top_n: Maximum number of non-intercept SHAP features retained per sample before remaining contributions are collapsed into __other__.

Value

A POWERUP model object containing fitted models, cross-validation metrics, predictions, uncertainty estimates, and SHAP values.

Examples

if (FALSE) { # \dontrun{
fit <- make_xgb_model("ko_ctnnb1", 1, 1, my_data)
} # }