def run_edgeR(gene_expression, bio_assignment, gene_names, batch_info=None, batch=True):
if batch_info is None:
batch = False
r_counts = conversion_pydataframe(gene_expression)
r_bio_group = conversion_pydataframe(bio_assignment)
r_dge = r.DGEList(counts=r.t(r_counts), genes=gene_names)
r.assign("dge", r_dge)
r.assign("bio_group", r.factor(r_bio_group))
r("dge$samples$bio_group <- bio_group")
if batch:
r_batch_group = conversion_pydataframe(batch_info)
r.assign("batch_group", r.factor(r_batch_group))
r("dge$samples$batch_group <- batch_group")
r("""dge <- suppressWarnings(edgeR::calcNormFactors(dge))""")
if not batch:
r("""design <- model.matrix(~bio_group, data = dge$samples)""")
r("""colnames(design) <- c("Intercept", "bio")""")
if batch:
r("""design <- model.matrix(~bio_group+batch_group, data = dge$samples)""")
r("""colnames(design) <- c("Intercept", "bio", "batch")""")
r("""dge <- estimateDisp(dge, design)""")
r("""fit <- glmFit(dge, design)""")
if not batch:
r("""lrt <- glmLRT(fit)""")
if batch:
r("""lrt <- glmLRT(fit, coef="bio")""")
return r("lrt$table$PValue")
def calc_size_factors(self, method="TMM"):
# Convert pandas dataframe to R dataframe
r_dge = r.DGEList(self.count_df)
# Calculate normalization factors
r_dge = r.calcNormFactors(r_dge, method=method)
size_factors = (np.array(r_dge.rx2('samples').rx2("lib.size")) *
np.array(r_dge.rx2("samples").rx2("norm.factors")))
# convert to pandas series
size_factors = pd.Series(size_factors, index=self.count_df.columns)
# adjust size factors so that the maximum is 1.0
size_factors = size_factors / size_factors.max()
return size_factors
def norm_expr_vals(self, ref_col, method="TMM"):
"""
Normalize expression values relative to a
reference sample (using TMM normalization).
Parameters:
-----------
- ref_col: Reference column
- method: Method to use for normalization, e.g. 'TMM'
"""
# Take only numeric values from dataframe
r_counts = conversion_pydataframe(self.exp_obj.counts_df)
r_dge = r.DGEList(r_counts)
# Calculate normalization factors
r_dge = r.calcNormFactors(r_dge, refColumn=ref_col, method=method)
print r_dge[0:10]
# Get counts per million
r_cpm_result = r.cpm(r_dge)
print "Counts per million: "
print r_cpm_result[0:10]
return r_dge, r_cpm_result