def build_filesystem():
# DIRECTORY STRUCTURE
global SCRATCH, BASEDIR, REFERENCES, DATA, TRIM_DIR, ASSEMBLY_DIR, ANNOTATION_DIR, MAP_DIR
SCRATCH = Dir.make('/scratch/' + os.environ['USER'])
BASEDIR = Dir('/Strong/proj/.data/Project_NTM')
REFERENCES = Dir(BASEDIR.join("lib", "reference_genomes"))
DATA = BASEDIR.make_subdir("data")
# RAW_DIR = DATA.make_subdir("00_raw")
TRIM_DIR = DATA.make_subdir('trimmed_reads')
ASSEMBLY_DIR = DATA.make_subdir('assemblies')
ANNOTATION_DIR = DATA.make_subdir('annotations')
MAP_DIR = DATA.make_subdir('mapped_reads')
"""
beagles[compbio] alma: grep , E-ALMA1.MAV_vs_NJH87.cf | more
CP018363.1 83972 C T,G 0 34 34 SNP
CP018363.1 148672 A G,C 0 14 14 SNP
CP018363.1 1381815 G A,C 0 8 8 SNP
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