help="File with the genome list. Format GenomeID, FullName, ShortName", required=True)
parser.add_argument("-a", "--annotation_folder", type=str,
help="Folder with the annotation files from JGI", required=True)
parser.add_argument("-c", "--cluster_file", type=str,
help="Cluster file", required=True)
parser.add_argument("-o", "--output_directory", type=str,
help="Output folder", required=True)
args = parser.parse_args()
#Create the output directory
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
#####Read the genome list
genome_id_dictionary, genome_count = ClusterTools.read_genome_list(args.genome_list_index)
###Read the annotation information
protein_annotation, function_definitions = AnnotationTools.parse_annotation_folder(genome_id_dictionary.keys(), args.annotation_folder)
##Read the cluster information
total_clusters = ClusterTools.get_cluster_information(args.cluster_file)
##Print log file
logfile = open(args.output_directory + "/logfile.txt", 'w')
##Total number of clusters
logfile.write("Total number of analyzed clusters: %d" % len(total_clusters) + "\n")
features_to_annotate = ["COG", "KO", "PFAM", "Product"]
parser.add_argument("-c", "--cluster_file", type=str, help="Ortholog file, generated by OrthoMCL", required=True)
parser.add_argument("-f", "--fasta_aa_directory", type=str, help="Directory with the fasta files", required=True)
parser.add_argument("-g", "--group_information", type=str, help="Group file")
parser.add_argument("-o", "--output_directory", type=str, help="Output directory", required=True)
args = parser.parse_args()
#Create the output directory
if not os.path.exists(args.output_directory):
os.makedirs(args.output_directory)
#Create a log file
run_summary = open(args.output_directory + "/logfile.txt", 'w')
#####Read the genome list
genome_id_dictionary, genome_count = ClusterTools.read_genome_list(args.genome_list_index)
run_summary.write("Genomes in the genome list: %d" % genome_count + "\n")
######Read the cluster information, and check that everything is ok
#cluster_information, set_of_proteins_in_clusters, unique_cluster_count, total_clusters, removed_clusters = \
# get_orthomcl_results(args.cluster_file, [i for i in genome_id_dictionary.itervalues()])
cluster_information, set_of_proteins_in_clusters, unique_cluster_count, total_clusters, removed_clusters = \
get_orthomcl_results(args.cluster_file, genome_id_dictionary.keys())
run_summary.write("Total number of clusters: %d" % len(cluster_information) + "\n")
run_summary.write("Total number of protein in clusters: %d" % len(set_of_proteins_in_clusters) + "\n")
run_summary.write("Total number of removed clusters (not present in the genome file): %d" % removed_clusters + "\n")
#Check the counts, to see if everything is going ok
dna_aligned_folder = args.output_directory + "/dna_aligned"
protein_tree_folder = args.output_directory + "/protein_trees"
dna_tree_folder = args.output_directory + "/dna_trees"
folder_list = [
args.output_directory, protein_unaligned_folder,
protein_alignment_folder, dna_unaligned_folder, dna_aligned_folder,
protein_tree_folder, dna_tree_folder
]
for folder in folder_list:
if not os.path.exists(folder):
os.makedirs(folder)
#Get the cluster information
cluster_information = ClusterTools.get_cluster_information(
args.cluster_file)
#Create the sequence dictionary
dna_sequence_dic = create_sequence_dictionary(args.fasta_nuc_directory)
#Iterate over each cluster and generate the alignments
frameshift_cases = []
inframe_stops = []
clusters_too_short = []
nucleotide_not_found = []
for cluster in cluster_information:
protein_list = cluster_information[cluster].split(",")
curated_protein_list = {}
protein_unaligned_folder = args.output_directory + "/protein_unaligned"
protein_alignment_folder = args.output_directory + "/protein_alignment"
dna_unaligned_folder = args.output_directory + "/dna_unaligned"
dna_aligned_folder = args.output_directory + "/dna_aligned"
protein_tree_folder = args.output_directory + "/protein_trees"
dna_tree_folder = args.output_directory + "/dna_trees"
folder_list = [args.output_directory, protein_unaligned_folder, protein_alignment_folder, dna_unaligned_folder,
dna_aligned_folder, protein_tree_folder, dna_tree_folder]
for folder in folder_list:
if not os.path.exists(folder):
os.makedirs(folder)
#Get the cluster information
cluster_information = ClusterTools.get_cluster_information(args.cluster_file)
#Create the sequence dictionary
dna_sequence_dic = create_sequence_dictionary(args.fasta_nuc_directory)
#Iterate over each cluster and generate the alignments
frameshift_cases = []
inframe_stops = []
clusters_too_short = []
nucleotide_not_found = []
for cluster in cluster_information:
protein_list = cluster_information[cluster].split(",")
curated_protein_list = {}
