neuroCombat Package

neuroCombat Package

neuroCombat Module

WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.adjust_data_final(s_data, design, gamma_star, delta_star, stand_mean, var_pooled, info_dict)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.aprior(delta_hat)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.bprior(delta_hat)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.find_non_eb_adjustments(s_data, LS, info_dict)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.find_non_parametric_adjustments(s_data, LS, info_dict, mean_only)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.find_parametric_adjustments(s_data, LS, info_dict, mean_only)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.fit_LS_model_and_find_priors(s_data, design, info_dict, mean_only)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.int_eprior(sdat, g_hat, d_hat)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.it_sol(sdat, g_hat, d_hat, g_bar, t2, a, b, conv=0.0001)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.make_design_matrix(Y, batch_col, cat_cols, num_cols)[source]
Return Matrix containing the following parts:

  • one-hot matrix of batch variable (full)

  • one-hot matrix for each categorical_cols (removing the first column)

  • column for each continuous_cols

WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.neuroCombat(dat, covars, batch_col, categorical_cols=None, continuous_cols=None, eb=True, parametric=True, mean_only=False)[source]

Run ComBat to remove scanner effects in multi-site imaging data

data pandas data frame or numpy array

neuroimaging data to correct with shape = (features, samples) e.g. cortical thickness measurements, image voxels, etc

covarsa pandas data frame w/ shape = (samples, features)

demographic/phenotypic/behavioral/batch data

batch_col : string indicating batch (scanner) variable in covars

categorical_colsstring or list of strings indicating categorical variables to adjust for

  • e.g. male or female

continuous_colsstring or list of strings indicating continuous variables to adjust for

  • e.g. age

ebshould Empirical Bayes be performed?

  • True by default

parametricshould parametric adjustements be performed?

  • True by default

mean_onlyshould only be the mean adjusted (no scaling)?

  • False by default

  • A numpy array with the same shape as dat which has now been ComBat-harmonized

WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.postmean(g_hat, g_bar, n, d_star, t2)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.postvar(sum2, n, a, b)[source]
WORC.external.ComBatHarmonization.Python.neuroCombat.neuroCombat.neuroCombat.standardize_across_features(X, design, info_dict)[source]