Skip to content

sspa_KPCA

source 

sspa_KPCA(
   pathway_df, min_entity = 2, random_state = 0
)

Kernel PCA method for single sample pathway analysis

Args

  • pathway_df (pd.DataFrame) : pandas DataFrame of pathway identifiers (keys) and corresponding list of pathway entities (values).
  • min_entity (int) : minimum number of metabolites mapping to pathways for ssPA to be performed Entity identifiers must match those in the matrix columns

Methods:

.fit

source 

.fit(
   X, y = None
)

Fit the model with X.

Args

  • X (pd.DataFrame) : pandas DataFrame omics data matrix consisting of m rows (samples) and n columns (entities). Do not include metadata columns

Returns

  • self : object

.transform

source 

.transform(
   X, y = None
)

Transform X.

Args

  • X (pd.DataFrame) : pandas DataFrame omics data matrix consisting of m rows (samples) and n columns (entities). Do not include metadata columns

Returns

pandas DataFrame of pathway scores derived using the kPCA method. Columns represent pathways and rows represent samples.

.fit_transform

source 

.fit_transform(
   X, y = None
)

Fit the model with X and transform X.

Args

  • X (pd.DataFrame) : pandas DataFrame omics data matrix consisting of m rows (samples) and n columns (entities). Do not include metadata columns

Returns

pandas DataFrame of pathway scores derived using the kPCA method. Columns represent pathways and rows represent samples.

.fit_transform_

source 

.fit_transform_(
   X, y = None
)

Fit the model with X and transform X.

Args

  • X (pd.DataFrame) : pandas DataFrame omics data matrix consisting of m rows (samples) and n columns (entities). Do not include metadata columns

Returns

pandas DataFrame of pathway scores derived using the kPCA method. Columns represent pathways and rows represent samples.