rapids_singlecell.dcg.run_mlm#
- rapids_singlecell.dcg.run_mlm(mat, net, *, source='source', target='target', weight='weight', batch_size=10000, min_n=5, verbose=False, use_raw=True)[source]#
Multivariate Linear Model (MLM). MLM fits a multivariate linear model for each sample, where the observed molecular readouts in
mat
are the response variable and the regulator weights innet
are the covariates. Target features with no associated weight are set to zero. The obtained t-values from the fitted model are the activities (mlm_estimate
) of the regulators innet
.- Parameters:
- mat
AnnData
|DataFrame
|list
List of [features, matrix], dataframe (samples x features) or an AnnData instance.
- net
DataFrame
Network in long format.
- source
str
(default:'source'
) Column name in net with source nodes.
- target
str
(default:'target'
) Column name in net with target nodes.
- weight
str
(default:'weight'
) Column name in net with weights.
- batch_size
int
(default:10000
) Size of the samples to use for each batch. Increasing this will consume more memory but it will run faster.
- min_n
int
(default:5
) Minimum of targets per source. If less, sources are removed.
- verbose
bool
(default:False
) Whether to show progress.
- use_raw
bool
(default:True
) Use raw attribute of mat if present.
- mat
- Return type:
- Returns:
Updates
adata
with the following fields.- estimateDataFrame
MLM scores. Stored in
.obsm['mlm_estimate']
ifmat
is AnnData.- pvalsDataFrame
Obtained p-values. Stored in
.obsm['mlm_pvals']
ifmat
is AnnData.