def linage_specific_genes(taxonomy, th_max, th_min):
rank = [rnk for rnk in ranks if taxonomy in get_taxonomy_list(rnk)][0]
core_genes_true = set(list_core_gene(taxonomy, th_max, th_min))
other_taxon = get_taxonomy_list(rank)
other_taxon.remove(taxonomy)
core_genes_others = [list_core_gene(other_taxa, th_max, th_min)
for other_taxa in other_taxon]
core_genes_others = set([e for row in core_genes_others for e in row])
linage_specific_genes = core_genes_true - core_genes_others
return linage_specific_genes
def main1():
for rank in ranks:
taxonomy_list = [tax for tax in get_taxonomy_list(rank)]
taxonomy_list = [tax for tax in taxonomy_list if tax in dedup]
core_gene_num_list = [count_core_gene(
taxonomy, 1, 0.98) for taxonomy in taxonomy_list]
print(core_gene_num_list)
from Taxid_Taxonomy import get_taxonomy_list
h = open("dedup.txt")
dedup = [string.replace("\n", "") for string in h.readlines()]
h.close()
ranks = ["Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"]
dic = {el[0]: el[1] for el in [ele for ele in [(taxa, rank) * (taxa in get_taxonomy_list(rank))
for rank in ranks for taxa in dedup] if ele != ()]}
def taxon(rank):
return [k for k, v in dic.items() if v == rank]