Hello,
I'm learning about the one_vs_rest_dmg method. I saw a function in the source code: def _single_ovr_dmg.
Why is it set to dmg_result["fc"] < fc_cutoff here in dmg_result = dmg_result[(dmg_result["pvals_adj"] < adj_p_cutoff) & (dmg_result["fc"] < fc_cutoff)].copy(), instead of dmg_result["fc"] > fc_cutoff?
def _single_ovr_dmg(
cell_label,
mcds,
obs_dim,
var_dim,
mc_type,
top_n,
adj_p_cutoff,
fc_cutoff,
auroc_cutoff,
):
····
dmg_result["fc"] = dmg_result["names"].map(fc)
# filter
dmg_result = dmg_result[(dmg_result["pvals_adj"] < adj_p_cutoff) & (dmg_result["fc"] < fc_cutoff)].copy()
dmg_result = dmg_result.set_index("names").drop_duplicates()
······
return dmg_result
Hello,
I'm learning about the one_vs_rest_dmg method. I saw a function in the source code: def _single_ovr_dmg.
Why is it set to dmg_result["fc"] < fc_cutoff here in dmg_result = dmg_result[(dmg_result["pvals_adj"] < adj_p_cutoff) & (dmg_result["fc"] < fc_cutoff)].copy(), instead of dmg_result["fc"] > fc_cutoff?
def _single_ovr_dmg(
cell_label,
mcds,
obs_dim,
var_dim,
mc_type,
top_n,
adj_p_cutoff,
fc_cutoff,
auroc_cutoff,
):
····
dmg_result["fc"] = dmg_result["names"].map(fc)
# filter
dmg_result = dmg_result[(dmg_result["pvals_adj"] < adj_p_cutoff) & (dmg_result["fc"] < fc_cutoff)].copy()
dmg_result = dmg_result.set_index("names").drop_duplicates()
······
return dmg_result