Generate 20 random files, the file name may be duplicated because no hash name is used
There are 30-50 sequences in each file
Each sequence has a length of 70-120 base
import osimport randomimport stringprint (dir (string)) Letter = string.ascii_ Lettersos.chdir ("d:\\") Bases = {1: "A", 2: "T", 3: "C", 4: "G"}## test random module , get random dna basenth = random.randint (1,4) print ( Bases[nth]) ## create random dna sequencesfor i in range (): number_of_seq = random.randint (30,50) filename = letter [I] with open ("Sequences" +filename + str (NUMBER_OF_SEQ) + ". Fasta", "W") as file_output: for j in range (NUMBER_OF_SEQ) : each_seq= "" &nbsP; rand_len = random.randint (70,120) for k in range (Rand_len): nth = random.randint (1,4) each_seq += bases[nth] file_output.write (">seq_" +str ( NUMBER_OF_SEQ) + "_" +str (rand_ Len) + "\ n") file_output.write (each_Seq+ " \ n ")
Python generates 20 random DNA fasta format files