def update_taxa(species_threshold=0.97, genus_threshold=0.80):
logger = generic_logger('update_taxa.csv')
run = Dir().dirname
trim_dir = Dir(BASEDIR.join('data', 'trimmed_reads', run))
assembly_dir = Dir(BASEDIR.join('data', 'assemblies', run))
ani_dir = Dir(assembly_dir.join('ANI'))
trimmed_reads = trim_dir.files(endswith="fq", dataframe=True)
assemblies = assembly_dir.files(endswith='fna', dataframe=True)
ani = ani_dir.files(endswith='.csv')
for file in ani:
try:
df = pd.read_csv(file.path).sort_values('ani')
sample_name = df.iloc[0].sample
trim1 = trimmed_reads[
(trimmed_reads.filename.str.contains(sample_name))
& (trimmed_reads.filename.str.contains('_R1'))].iloc[0].path
trim2 = trimmed_reads[
(trimmed_reads.filename.str.contains(sample_name))
& (trimmed_reads.filename.str.contains('_R2'))].iloc[0].path
assembly = assemblies[(
assemblies.filename.str.contains(sample_name))].iloc[0].path
trim1 = File(trim1)
trim2 = File(trim2)
assembly = File(assembly)
# ASSIGN TAXON
taxon = 'UNKNOWN'
possible_species = df[(df.ani >= species_threshold)]
if len(possible_species) > 0:
taxon = possible_species.iloc[0].taxon
elif len(df[(df.ani >= genus_threshold)]) > 0:
taxon = 'NTM'
trim1_filename = trim1.filename
trim2_filename = trim2.filename
assembly_filename = assembly.filename
trim1.rename(f'{sample_name}_{taxon}.fq.gz')
trim2.rename(f'{sample_name}_{taxon}.fq.gz')
assembly.rename(f'{sample_name}_{taxon}_000.fna')
logger.info(f'renamed {trim1_filename} to {trim1.filename}')
logger.info(f'renamed {trim2_filename} to {trim1.filename}')
logger.info(f'renamed {assembly_filename} to {assembly.filename}')
except Exception as e:
logger.warning(e)
CP018363.1 2334023 G A,T 0 30 30 SNP
CP018363.1 2948951 T C,G 0 6 6 SNP
CP018363.1 3621547 T C,G 0 35 35 SNP
CP018363.1 4243092 A G,C 0 33 33 SNP
CP018363.1 4562156 T C,G 0 15 15 SNP
"""
VCF_DIR = Dir("/Strong/proj/.data/alma")
FASTA_DIR = VCF_DIR.make_subdir("fasta")
MATRIX = FASTA_DIR.join("ALMA_matrix_N.fna")
CSV_OUT = FASTA_DIR.join("ALMA_stats.csv")
CSV_MUTATIONS = FASTA_DIR.join("ALMA_mutations.csv")
POSITIONS = 5626623
files = VCF_DIR.files(endswith='.cf')
records = []
multi_alleles = {}
print(f"Building Matrix: {MATRIX} from {len(files)} files.")
for i, file in enumerate(files):
print(f"\t{i:02d} | {file.filename}")
isolate = file.filename.split("_vs_")[0]
seq = ['-'] * POSITIONS
record = {'isolate': isolate, 'totalMulti': 0, 'N': 0, 'alt': 0, 'ref': 0}
options=set()
with open(file.path, 'r') as file_in, open(MATRIX, 'a+') as file_out:
for line in file_in:
# EXTRACT METADATA FROM LINE