def cell_cycle_correction(data, annoFile, annoDB = 'custom'):
if not os.path.exists(annoFile):
raise Exception("Annotation file not found")
data_slalom = load_txt(df=data.T,annoFiles=annoFile,annoDBs=annoDB)
print ("Loaded {:d} cells, {:d} genes".format(data_slalom['Y'].shape[0],data_slalom['Y'].shape[1]))
print ("Annotation: {:d} terms".format(len(data_slalom['terms'])))
#I: indicator matrix that assigns genes to pathways
I = data_slalom['I'] #if loaded from the hdf file change to I = data['IMSigDB']
#Y: log expresison values
Y = data_slalom['Y']
#terms: ther names of the terms
terms = data_slalom['terms']
#gene_ids: the ids of the genes in Y
gene_ids = data_slalom['genes']
#initialize FA instance, here using a Gaussian noise model and fitting 3 dense hidden factors
FA = slalom.initFA(Y, terms,I, gene_ids=gene_ids, noise='gauss', nHidden=3, minGenes=10)
#model training
FA.train()
#print diagnostics
FA.printDiagnostics()
corrected_data = FA.regressOut(terms=['M phase', 'Dna replication', 'Chromosome segregation','M phase of mitotic cell cycle'])
full_matrix = data.copy()
annotated_genes = np.array(data_slalom['genes'])[np.sum(data_slalom['I'], axis=1) != 0]
full_matrix[annotated_genes] = corrected_data
return full_matrix
def factor_analysis(norm_df, id_to_name, tsne, annoFile, annoDB):
df_factors = None
factors = []
if not os.path.exists(annoFile):
raise Exception("Annotation file not found")
norm_df_copy = norm_df.copy()
norm_df_copy.columns = np.array(
[id_to_name[gene_id] for gene_id in norm_df_copy.columns.values])
data = load_txt_2(data=norm_df_copy.T, annoFiles=annoFile, annoDBs=annoDB)
print("Loaded {:d} cells, {:d} genes".format(data['Y'].shape[0],
data['Y'].shape[1]))
print("Annotation: {:d} terms".format(len(data['terms'])))
#I: indicator matrix that assigns genes to pathways
I = data['I'] #if loaded from the hdf file change to I = data['IMSigDB']
#Y: log expresison values
Y = data['Y']
#terms: ther names of the terms
terms = data['terms']
#gene_ids: the ids of the genes in Y
gene_ids = data['genes']
#initialize FA instance, here using a Gaussian noise model and fitting 3 dense hidden factors
FA = slalom.initFA(Y,
terms,
I,
gene_ids=gene_ids,
noise='gauss',
nHidden=3,
minGenes=15)
#model training
FA.train()
#print diagnostics
FA.printDiagnostics()
#plot results
#fig = plotRelevance(FA)
print(terms[0])
X = FA.getX(terms=[terms[0]])
if True: ## is the first factor
df_factors = pd.DataFrame(X, columns=[terms[0]])
df_factors.index = tsne.index
else:
df_factors[terms[0]] = X
factors.append(terms[0])
#print(df_factors)
plot_gene_expression(df_factors, tsne, factors)
plt.show()
# plt.savefig(os.path.join(out_dir,'factors.pdf'))
#get factors; analogous getters are implemented for relevance and weights (see docs)
#X = FA.getX(terms=['G2m checkpoint','P53 pathway'])
print(FA.getX())
print(FA.getX().shape)
import time
import slalom as sl
import numpy as np
from anndata import read_h5ad
print('reading')
ad = read_h5ad('kang_count.h5ad')
print('initializing')
t0 = time.time()
FA = sl.initFA(ad.X, ad.uns['terms'], ad.varm['I'], list(ad.var_names), noise='gauss', nHidden=3, nHiddenSparse=0,
minGenes=12, pruneGenes=True, do_preTrain=False)
print('training')
FA.train()
t1 = time.time()
print(t1 - t0)
sl.saveFA(FA, 'FA_kang_3_hidden.hdf5', saveF=True)
print ("Annotation: {:d} terms".format(len(data['terms'])))
#I: indicator matrix that assigns genes to pathways
I = data['I'] #if loaded from the hdf file change to I = data['IMSigDB']
#Y: log expresison values
Y = data['Y']
#terms: ther names of the terms
terms = data['terms']
#gene_ids: the ids of the genes in Y
# gene_ids = data['genes'] # Incorrect key
gene_ids = data['sym_names']
#initialize FA instance, here using a Gaussian noise model and fitting 3 dense hidden factors
print('Initialising')
FA = slalom.initFA(Y, terms, I, gene_ids=gene_ids, noise='gauss', nHidden=3, minGenes=15)
#model training
print('Training')
FA.train()
#print diagnostics
FA.printDiagnostics()
#plot results
fig = plotRelevance(FA)
#get factors; analogous getters are implemented for relevance and weights (see docs)
# X = FA.getX(terms=['G2m checkpoint','P53 pathway']) # Incorrect names
terms_to_plot = ['G2M_CHECKPOINT','P53_PATHWAY']
X = FA.getX(terms=terms_to_plot)