diff --git a/bin/D3.1_recluster_genes_by_species_pair.py b/bin/D3.1_recluster_genes_by_species_pair.py --- a/bin/D3.1_recluster_genes_by_species_pair.py +++ b/bin/D3.1_recluster_genes_by_species_pair.py @@ -40,18 +40,18 @@ final_df = pd.DataFrame() for name, group in species_pair_grouped_df: recluster_ID=1 - cluster_genes_list = list(set(list(group["GeneID1"])+list(group["GeneID2"]))) + cluster_genes_list = sorted(set(list(group["GeneID1"])+list(group["GeneID2"]))) #sorted: set order depends on PYTHONHASHSEED my_cluster_counter = 1 while my_cluster_counter == 1: focus_gene = cluster_genes_list[0] subgroup = group.loc[(group.GeneID1==focus_gene) | (group.GeneID2==focus_gene)] - subgroup_genes = list(set(list(subgroup["GeneID1"])+list(subgroup["GeneID2"]))) + subgroup_genes = sorted(set(list(subgroup["GeneID1"])+list(subgroup["GeneID2"]))) my_subcluster_counter = 1 while my_subcluster_counter == 1: initial_len = len(subgroup_genes) subgroup1 = group.loc[(group.GeneID1.isin(subgroup_genes) | group.GeneID2.isin(subgroup_genes))] - subgroup1_genes = list(set(list(subgroup1["GeneID1"])+list(subgroup1["GeneID2"]))) - subgroup_genes = list(set(subgroup_genes+subgroup1_genes)) + subgroup1_genes = sorted(set(list(subgroup1["GeneID1"])+list(subgroup1["GeneID2"]))) + subgroup_genes = sorted(set(subgroup_genes+subgroup1_genes)) if len(subgroup_genes) == initial_len: my_subcluster_counter = 2 #generate subclusterID