def main():
print("poop")
prefix_500 = "500"
prefix_1000 = "1000"
prefix_2000 = "2000"
suffix_start_count = 1
suffix_end_count = 10
design_kmer_list = kmers.get_design_kmers()
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_500 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
mapping_list = BruteForceMapping.get_brute_force_mapping(sequence_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, mapping_list)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_1000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
mapping_list = BruteForceMapping.get_brute_force_mapping(sequence_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, mapping_list)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_2000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
mapping_list = BruteForceMapping.get_brute_force_mapping(sequence_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, mapping_list)
def main():
print("poop")
prefix_500 = "500"
prefix_1000 = "1000"
prefix_2000 = "2000"
suffix_start_count = 1
suffix_end_count = 10
design_kmer_list = kmers.get_design_kmers()
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_500 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
mapping_list = BruteForceMapping.get_brute_force_mapping(
sequence_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, mapping_list)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_1000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
mapping_list = BruteForceMapping.get_brute_force_mapping(
sequence_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, mapping_list)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_2000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
mapping_list = BruteForceMapping.get_brute_force_mapping(
sequence_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, mapping_list)
def main():
prefix_500 = "500"
prefix_1000 = "1000"
prefix_2000 = "2000"
suffix_start_count = 1
suffix_end_count = 10
design_kmer_list = kmers.get_design_kmers()
use_cluster_size_hard_stop = False
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_500 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = Clustering.get_cluster_dict(sequence_kmer_list,
design_kmer_list,
use_cluster_size_hard_stop)
pickle.dump(
cluster_dict,
open("clusters_no_hard_stop" + input_file_name + ".p", "wb"))
consensus_kmer_list = cluster_dict.keys()
consensus_mapping_list = get_bipartite_matching(
consensus_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, consensus_mapping_list,
cluster_dict)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_1000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = Clustering.get_cluster_dict(sequence_kmer_list,
design_kmer_list,
use_cluster_size_hard_stop)
pickle.dump(
cluster_dict,
open("clusters_no_hard_stop" + input_file_name + ".p", "wb"))
consensus_kmer_list = cluster_dict.keys()
consensus_mapping_list = get_bipartite_matching(
consensus_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, consensus_mapping_list,
cluster_dict)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_2000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = Clustering.get_cluster_dict(sequence_kmer_list,
design_kmer_list,
use_cluster_size_hard_stop)
pickle.dump(
cluster_dict,
open("clusters_no_hard_stop" + input_file_name + ".p", "wb"))
consensus_kmer_list = cluster_dict.keys()
consensus_mapping_list = get_bipartite_matching(
consensus_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, consensus_mapping_list,
cluster_dict)
def main():
sequence_kmer_list = kmers.get_random_sequence_kmers(1000)
design_kmer_list = kmers.get_design_kmers()
mapping_list = get_bipartite_matching(sequence_kmer_list, design_kmer_list)
print(len(mapping_list))
def main():
sequence_kmer_list = kmers.get_random_sequence_kmers(1000)
design_kmer_list = kmers.get_design_kmers()
isClusterSizeHardStop = True
cluster_dict = get_cluster_dict(sequence_kmer_list, design_kmer_list, isClusterSizeHardStop)
def main():
sequence_kmer_list = kmers.get_random_sequence_kmers(1000)
design_kmer_list = kmers.get_design_kmers()
cluster_dict = get_cluster_dict(sequence_kmer_list, design_kmer_list)
pickle.dump(cluster_dict, open("cluster_dict.p", "wb"))
def main():
sequence_kmer_list = kmers.get_random_sequence_kmers(1000)
design_kmer_list = kmers.get_design_kmers()
mapping_list = get_bipartite_matching(sequence_kmer_list, design_kmer_list)
print(len(mapping_list))
def main():
sequence_kmer_list = kmers.get_random_sequence_kmers(1000)
design_kmer_list = kmers.get_design_kmers()
cluster_dict = get_cluster_dict(sequence_kmer_list, design_kmer_list)
pickle.dump(cluster_dict, open("cluster_dict.p", "wb"))
def main():
sequence_kmer_list = kmers.get_random_sequence_kmers(1000)
design_kmer_list = kmers.get_design_kmers()
isClusterSizeHardStop = True
cluster_dict = get_cluster_dict(sequence_kmer_list, design_kmer_list,
isClusterSizeHardStop)
def main():
design_kmer_list = kmers.get_design_kmers()
isClusterSizeHardStop = False
input_file_name = "500_1"
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = get_cluster_dict(sequence_kmer_list, design_kmer_list,
isClusterSizeHardStop)
def main():
design_kmer_list = kmers.get_design_kmers()
isClusterSizeHardStop = False
input_file_name = "500_1"
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = get_cluster_dict(sequence_kmer_list,
design_kmer_list,
isClusterSizeHardStop)
def main():
prefix_500 = "500"
prefix_1000 = "1000"
prefix_2000 = "2000"
suffix_start_count = 1
suffix_end_count = 10
design_kmer_list = kmers.get_design_kmers()
use_cluster_size_hard_stop = False
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_500 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = Clustering.get_cluster_dict(sequence_kmer_list,
design_kmer_list,
use_cluster_size_hard_stop)
pickle.dump(cluster_dict, open("clusters_no_hard_stop" + input_file_name + ".p", "wb"))
consensus_kmer_list = cluster_dict.keys()
consensus_mapping_list = get_bipartite_matching(consensus_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, consensus_mapping_list, cluster_dict)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_1000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = Clustering.get_cluster_dict(sequence_kmer_list,
design_kmer_list,
use_cluster_size_hard_stop)
pickle.dump(cluster_dict, open("clusters_no_hard_stop" + input_file_name + ".p", "wb"))
consensus_kmer_list = cluster_dict.keys()
consensus_mapping_list = get_bipartite_matching(consensus_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, consensus_mapping_list, cluster_dict)
for suffix_count in range(suffix_start_count, suffix_end_count + 1):
input_file_name = prefix_2000 + '_' + str(suffix_count)
sequence_kmer_list = kmers.get_sequence_kmers(input_file_name)
cluster_dict = Clustering.get_cluster_dict(sequence_kmer_list,
design_kmer_list,
use_cluster_size_hard_stop)
pickle.dump(cluster_dict, open("clusters_no_hard_stop" + input_file_name + ".p", "wb"))
consensus_kmer_list = cluster_dict.keys()
consensus_mapping_list = get_bipartite_matching(consensus_kmer_list, design_kmer_list)
output_seq_kmer_mapping_list(input_file_name, consensus_mapping_list, cluster_dict)