'organism': 'TcruziCLBrenerEsmeraldo-like'
}
non_emeraldo = {
'genome_filename':
'TTDB/TriTrypDB-46_TcruziCLBrenerNon-Esmeraldo-like_Genome.fasta',
'regions_filename':
'TTDB/TriTrypDB-46_TcruziCLBrenerNon-Esmeraldo-like_AnnotatedCDSs.fasta',
'organism': 'TcruziCLBrenerNon-Esmeraldo-like'
}
organism = emeraldo_like
if __name__ == "__main__":
# Load FASTA files
genome = FASTA(organism['genome_filename'])
genome.load()
regions = FASTA(organism['regions_filename'])
regions.load()
# Load database file
sqlite = sqlite3.connect(SQLite_DB)
# Create MFASeq Folder
Organism_MFASeq_folder = f"{MFASeq_folder}/MFA-Seq_{organism['organism']}"
if not os.path.isdir(Organism_MFASeq_folder):
os.mkdir(Organism_MFASeq_folder)
# Create MFASeq Files
for chromosome_id in genome.data.keys():
Chromosome_file = f"{Organism_MFASeq_folder}/{chromosome_id}.txt"
action='store_true',
help="Use base pairs instead of genome counts")
args = parser.parse_args()
protein_fasta = args.fasta or '/home/seijihariki/Documents/TCC/TTDB/TriTrypDB-46_TcruziCLBrenerEsmeraldo-like_AnnotatedTranscripts.fasta'
simulation_folder = args.simulation
search = args.search or 'DGF-1'
base_pairs = args.basepairs
simulation_cnt = args.count or 50
chromosomes_cnt = args.chromosomes or 41
print('Loading annotations:')
transcripts = FASTA(protein_fasta)
transcripts.load()
collisions = {}
print('Detecting collisions:')
for chromosome in range(chromosomes_cnt):
chromosome_name = f"TcChr{chromosome + 1}-S"
collisions[chromosome_name] = []
for simulation in range(simulation_cnt):
with open(
f"{simulation_folder}simulation_{simulation}/{chromosome_name}.cseq"
) as times:
start, end = -2, -2
current_location = 0
