if (dataset == "error"):
print(
"***WARNING: No file was found in the repository with the provided name: "
+ file_name + "\nNow aborting.")
sys.exit()
# If the dataset to be reconstructed is a genome dataset. If the line size is not specified, default it to 60
if (dataset == "Genome"):
# Create index variable
index = 0
# Inform the user
print("\nNow reconstructing Genome dataset contained in file: " +
file_name + ".fa")
# Use reconstruct_dataset function to recreate the file
reconstruct_dataset(size=int(line_size),
directory=directory,
output_file="../" + file_name,
mode="Genome",
seqID="0",
region="0")
# Inform the user
print("\nReconstruction completed.")
# Otherwise the dataset to be reconstructed is a dependent file
else:
# Reconstruct the variants dataset
if (dataset == "Variants"):
# Inform the user
print("\nNow reconstructing Variants dataset contained in file: " +
file_name)
reconstruct_dataset(size=1,
directory=directory,
output_file="../" + file_name + ".temporary",
mode="Variants",
if (x == (len(commit_list) - 2)):
break
else:
#print("X: ",x)
#print(commit_list[x])
print("\n\t***Finding Alignment Pickle {}***".format(
str(datetime.datetime.now())))
print(
"\n\t Warning: If you have added any data into the repository but did not commit, these changes will be lost."
)
ShellCommand = Popen("git checkout " + commit_list[x] +
" 2> /dev/null",
shell=True).wait()
reconstruct_dataset(
size=60,
directory="./Genome",
output_file="./.git/info/temporary_directory/assembly_1.fa",
mode="Genome")
next_commit = x + 2
for y in range(next_commit, len(commit_list)):
#print("Y: ",y)
#print(commit_list[y])
# Reconstruct the second version of the assembly
ShellCommand = Popen("git checkout " + commit_list[y] +
" 2> /dev/null",
shell=True).wait()
reconstruct_dataset(
size=60,
directory="./Genome",
output_file="./.git/info/temporary_directory/assembly_2.fa",
mode="Genome")
def reconstruct_annotation_variants(ToUpdate):
"""
Reconstructs the variant and annotation dataset in the temporary directory.
Requires: ToUpdate ({dataset:[[filename.extension,directory,size],[],...]}) which contains INFORMATION
of what requires updating.
"""
for dataset in ToUpdate.keys():
# If the data are variants and annotation datasets, and there is data present, perform the following block
if (dataset != "Genome" and len(ToUpdate[dataset]) != 0):
# Loop through the files of the dataset and reconstruct the file in the temporary
# directory with the same original name
for subfile in ToUpdate[dataset]:
reconstruct_dataset(
size=1,
directory=subfile[1],
output_file="./temporary_directory/{}".format(subfile[0]),
mode=dataset,
update=True,
seqID="0",
region="0")
# Create an appropiate tabix library for the file. If it is annotation or
# alignment there are two pseudo files
if (dataset == "Annotation" or dataset == "Alignment"):
# Get all the headers (starts wiht #) for the alignment files, and all non header data,
# sort column 1 and column 2 (numerically).
# Then compress and create indexes and use tabix to create the library
Popen(
"(grep "
"^#"
" ./temporary_directory/{}_A; grep -v "
"^#"
" ./temporary_directory/{}_A | "
"sort -V -k1,1 -k2,2n) | bgzip > ./temporary_directory/{}_A.gz; "
"tabix -b 2 -e 2 ./temporary_directory/{}_A.gz;".
format(subfile[0], subfile[0], subfile[0], subfile[0]),
shell=True).wait()
# Do this for dataset B too
Popen(
"(grep "
"^#"
" ./temporary_directory/{}_B; grep -v "
"^#"
" ./temporary_directory/{}_B | "
"sort -V -k1,1 -k2,2n) | bgzip > ./temporary_directory/{}_B.gz; "
"tabix -b 2 -e 2 ./temporary_directory/{}_B.gz;".
format(subfile[0], subfile[0], subfile[0], subfile[0]),
shell=True).wait()
elif (dataset == "Variants"):
# Same as above but with variant data instead
Popen(
"(grep "
"^#"
" ./temporary_directory/{}_A; grep -v "
"^#"
" ./temporary_directory/{}_A | "
"sort -V -k1,1 -k2,2n) | bgzip > ./temporary_directory/{}_A.gz; "
"tabix -b 2 -e 2 ./temporary_directory/{}_A.gz;".
format(subfile[0], subfile[0], subfile[0], subfile[0]),
shell=True).wait()
# Otherwise there was an error
else:
print("***INTERNAL ERROR*** DATASET NOT RECOGNIZED: {}".
format(dataset))
print(
"\nNow producing a report of the data currently contained in the repository\n"
)
# Create an output file
output_file = open("../GenomeGit_Report_{}.txt".format(message), "w")
output_file.write(
"\n\nNow producing a report of the data currently contained in the repository\n"
)
# If busco option was selected
if (busco != "0"):
print('\nNow running a BUSCO analysis')
# Reconstruct the genome. can change name of file to actual fasta file?
reconstruct_dataset(size=60,
directory="./Genome",
output_file="../{}.fa".format(message),
mode="Genome",
seqID="0",
region="0")
input_file = os.path.abspath('../{}.fa'.format(message))
if (lineage != "0"):
buscoReport(input_file, lineage, message)
else:
buscoReport(input_file=input_file, output_folder=message)
# Create dictionary about the genomic sequences
# {seqKey:[seqID,lenght,contig_count,N_count,[{file:vcf},{file:gff},{file:sam}]]}
genome_report = report_repo()
# Print the information of the dictionary in form of a table
# Loop through the sequences
for seqKey in genome_report.keys():
# If the there are no files to update, inform the user
update_inform_user(ToUpdate)
###############################################
# PART 1. RECONSTRUCTION OF REPOSITORY DATA #
###############################################
# Inform the user
print("\n\t*PART I. RECONSTRUCTION OF REPOSITORY DATA.*")
print("\t {}".format(str(datetime.datetime.now())))
# Create temporary directory
os.mkdir("./temporary_directory")
# Reconstruct the necessary datasets. First the old genome.
reconstruct_dataset(size=60,
directory="./Genome",
output_file="./temporary_directory/genome_old.fa",
mode="Genome",
seqID="0",
region="0")
# Reconstruct all the files related to the variants and annotation datasets
reconstruct_annotation_variants(ToUpdate)
##############################################
# PART 2. OBTAIN THE ALIGNMENT INFORMATION #
##############################################
# Obtain the information of the alignment between both assemblies.
# Determine the alignment pickle
alignment_pickle = obtain_alignment_pickle(
"./temporary_directory/genome_old.fa", new_assembly)
variables = obtain_variables(alignment_pickle)
store_variables(variables=variables, alignment_pickle=alignment_pickle)