def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# build the dictionary of GO ontology data
go_ontology_dict = xlib.build_go_ontology_dict(args.ontology_file)
# calculate annotation statistics
if args.app == 'BLAST2GO':
calculate_blast2go_go_stats(args.annotation_file, go_ontology_dict,
args.output_dir)
elif args.app == 'ENTAP':
calculate_entap_go_stats(args.annotation_file, go_ontology_dict,
args.output_dir)
elif args.app == 'TOA':
calculate_toa_go_stats(args.annotation_file, go_ontology_dict,
args.output_dir)
elif args.app == 'TRAPID':
calculate_trapid_go_stats(args.annotation_file, go_ontology_dict,
args.output_dir)
elif args.app == 'TRINOTATE':
calculate_trinotate_go_stats(args.annotation_file, go_ontology_dict,
args.output_dir)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# get the TOA-transcriptome identification relationship dictionary
toa_transcriptome_relationship_dict = xlib.get_id_relationship_dict(args.toa_transcriptome_relationship_file)
# get the TOA-TransDecoder identification relationship dictionary
if args.toa_transdecoder_relationship_file == 'NONE':
toa_transdecoder_relationship_dict = {}
else:
toa_transdecoder_relationship_dict = xlib.get_id_relationship_dict(args.toa_transdecoder_relationship_file)
# restore transcript sequence identifications in a FASTA file
if args.file_format == 'FASTA':
restore_ids_fasta(args.input_file, toa_transcriptome_relationship_dict, toa_transdecoder_relationship_dict, args.output_file)
# restore transcript sequence identifications in a XML file
elif args.file_format == 'XML':
restore_ids_xml(args.input_file, toa_transcriptome_relationship_dict, toa_transdecoder_relationship_dict, args.output_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# delete the TOA database if exists
xlib.Message.print('verbose', 'Deleting old TOA database ...\n')
if os.path.exists(args.toa_database):
os.remove(args.toa_database)
xlib.Message.print('verbose', 'Database is deleted.\n')
# connect to the TOA database (it is create if not exists)
xlib.Message.print('verbose', 'Creating new TOA database ...\n')
conn = xsqlite.connect_database(args.toa_database)
xlib.Message.print('verbose', 'Database is created.\n')
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the TOA database
conn = xsqlite.connect_database(args.toa_database)
# check the dataset identification
if not xsqlite.is_dataset_id_found(conn, args.dataset_id):
raise xlib.ProgramException('L001', args.dataset_id)
# load table "blast" where the BLAST file format is 5 (BLAST XML)
if args.blast_file_format == '5':
load_table_blast_5(conn, args.dataset_id, args.blast_file)
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the TOA database
conn = xsqlite.connect_database(args.toa_database)
# load table "go_ontology"
load_table_go_ontology(conn, args.ontology_file)
# load table "go_cross_references"
load_table_go_cross_references(conn, args.ec2go_file, args.kegg2go_file,
args.metacyc2go_file, args.interpro2go_file)
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# get the dictionary with sequence identifications of the second FASTA file
file_2_id_dict = get_file_2_id_dict(args.fasta_file_2)
# get the TOA-transcriptome identification relationship dictionary
if args.toa_transcriptome_relationship_file == 'NONE':
toa_transcriptome_relationship_dict = {}
else:
toa_transcriptome_relationship_dict = xlib.get_id_relationship_dict(
args.toa_transcriptome_relationship_file)
# merge FASTA files with operation "1AND2" (sequences included in both files)
if args.merger_operation == '1AND2':
merge_files_operation_1and2(args.fasta_file_1, file_2_id_dict,
args.merged_file,
toa_transcriptome_relationship_dict)
# merge FASTA files with operation "1LESS2" (sequences in file 1 and not in file 2)
elif args.merger_operation == '1LESS2':
merge_files_operation_1less2(args.fasta_file_1, file_2_id_dict,
args.merged_file,
toa_transcriptome_relationship_dict)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# get the TOA-transcriptome identification relationship dictionary
if args.toa_transcriptome_relationship_file == 'NONE':
toa_transcriptome_relationship_dict = {}
else:
toa_transcriptome_relationship_dict = xlib.get_id_relationship_dict(
args.toa_transcriptome_relationship_file)
# get the TOA-TransDecoder identification relationship dictionary
if args.toa_transdecoder_relationship_file == 'NONE':
toa_transdecoder_relationship_dict = {}
else:
toa_transdecoder_relationship_dict = xlib.get_id_relationship_dict(
args.toa_transdecoder_relationship_file)
# merge XML file
merge_files(args.xml_file_list, toa_transcriptome_relationship_dict,
toa_transdecoder_relationship_dict, args.merged_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the TOA database
conn = xsqlite.connect_database(args.toa_database)
# rebuild the TOA database file
xlib.Message.print('verbose', 'Rebuilding TOA database ...\n')
OK = xsqlite.rebuild_database(conn)
if OK:
xlib.Message.print('verbose', 'The database is rebuilt.\n')
else:
xlib.Message.print(
'error', '*** WARNING: The database file can not be rebuilt.')
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the TOA database
conn = xsqlite.connect_database(args.toa_database)
# load table "datasets"
load_table_datasets(conn, args.dataset_file)
# load table "species"
load_table_species(conn, args.species_file)
# load table "ec_ids"
load_table_ec_ids(conn, args.ec_id_file)
# load table "kegg_ids"
load_table_kegg_ids(conn, args.kegg_id_file)
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the NGShelper database
conn = xsqlite.connect_database(args.ngshelper_database)
# get the NGShelper database name
file_name, file_extension = os.path.splitext(
os.path.basename(args.ngshelper_database))
# list data of variants and alleles and variant identifications to the scenario X
query_data(conn, file_name, args.sp1_id, args.sp2_id, args.hybrid_id,
args.imputed_md_id, args.max_separation, args.output_dir,
args.tsi_list)
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the TOA database
conn = xsqlite.connect_database(args.toa_database)
# get the taxonomy dictionary of the species name from taxonomy server
taxonomy_dict = xlib.get_taxonomy_dict('name', args.species_name)
if taxonomy_dict == {}:
raise xlib.ProgramException('L006', args.dataset_id)
# load genomic features depending of format of the genomic feature file
load_genomic_features(conn, args.species_name, args.gff_file,
args.gff_format)
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# connect to the TOA database
conn = xsqlite.connect_database(args.toa_database)
# get the PLAZA dataset identification list
plaza_dataset_id_list = xsqlite.get_plaza_dataset_id_list(conn)
# check the dataset identification
if args.dataset_id not in plaza_dataset_id_list:
raise xlib.ProgramException('L001', 'dataset', args.dataset_id)
# get the PLAZA species identification list
plaza_species_id_list = xsqlite.get_plaza_species_id_list(conn)
# check the PLAZA species identification
if args.species_id != 'all' and args.species_id not in plaza_species_id_list:
raise xlib.ProgramException('L003', args.species_id)
# load table "plaza_gene_description"
load_table_plaza_gene_description(conn, args.dataset_id, args.species_id,
args.gene_desc_dir,
plaza_species_id_list)
# load table "plaza_interpro"
load_table_plaza_interpro(conn, args.dataset_id, args.species_id,
args.interpro_file, plaza_species_id_list)
# load table "plaza_go"
load_table_plaza_go(conn, args.dataset_id, args.species_id, args.go_file,
plaza_species_id_list)
# load table "plaza_mapman"
load_table_plaza_mapman(conn, args.dataset_id, args.species_id,
args.mapman_file, plaza_species_id_list)
# close connection to TOA database
conn.close()
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# convert a PHASE files to Structure file
convert_phase_to_structure(args.phase_dir, args.phase_extension, args.sample_file, args.sp1_id, args.sp2_id, args.hybrid_id, args.structure_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract sequences
extract_sequences(args.vcf_file, args.id_file, args.extract_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract genotype data of every variant from a VCF file
extract_vcf_genotypes(args.input_vcf_file, args.imputed_md_id, args.output_genotype_file, args.tvi_list)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract sequences
get_exon_data(args.alignment_file, args.output_dir)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract genomic features from a GFF file
extract_ff_features(args.input_gff_file, args.gff_format, args.vcf_file, args.output_gff_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# fix sequence identifiers
fix_seq_ids(args.filenum, args.readfile)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# get Gene Ontology terms per sequence
get_go_terms(args.annotation_file, args.type, args.score_file, args.go_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# calculate haplotype statistics
calculate_haplotype_statistics(args.loci_file_path, args.stats_file_path)
def main():
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# filter SSRs
filter_ssrs(args.cos_file, args.ssr_file, args.output_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# build functional annotation data corresponding to a TRAPID run
build_trapid_annotation(args.transcripts_with_go_file, args.transcripts_with_gf_file, args.transcripts_with_ko_file, args.annotation_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract RNA sequences from a GFF file and its corresponding genome FASTA file
extract_gff_rnas(args.gff_file, args.gff_format, args.genome_file,
args.rna_file, args.tvi_list)
def main():
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# filter transcripts
filter_transcripts_bylen(args.fasta_file, args.output_file, args.minlen,
args.maxlen)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract sequences
get_flanking_regions(args.vcf_file, args.genome_file,
args.flanking_region_file, args.nucleotide_number)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# convert a SimHyb file to Structure
convert_simhyb_to_structure(args.simhyb_file, args.header_row_number,
args.structure_file)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# split annotation file
split_files(args.annotation_file, args.type, args.record_number_per_file,
args.header)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# extract annotations
extract_annotations(args.annotation_file, args.type, args.id_file,
args.extract_file, args.stats_file)
def main():
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# filter transcripts
filter_transcripts(args.assembly_software_code, args.transcriptome_file,
args.score_file, args.output_file, args.minlen,
args.maxlen, args.minFPKM, args.minTPM)
def main(argv):
'''
Main line of the program.
'''
# check the operating system
xlib.check_os()
# get and check the arguments
parser = build_parser()
args = parser.parse_args()
check_args(args)
# collapses the variant records corresponding to an indel in a VCF file
collapse_indels(args.input_vcf_file, args.sample_file, args.imputed_md_id,
args.sp1_id, args.sp2_id, args.hybrid_id,
args.output_vcf_file, args.stats_file, args.tvi_list)
