def subset_fasta(fasta, seqids_l):
"""
Get a subset of the fasta file with only the sequence which ids are in
ids_file.
"""
seq_d = bfas.fasta_2_dict(fasta)
seq_i = bfas.filter_by_id(seq_d, seqids_l)
bfas.write_as_fas(seq_i)
def get_chro_len(g_fas):
seq_d = bf.fasta_2_dict(g_fas)
len_d = dict()
for chro in seq_d:
len_d[chro] = len(seq_d[chro])
return sum(len_d.values())
def filterFastaByIds(fasta, idsFile):
seqs = bf.fasta_2_dict(fasta)
ids_to_keep = []
with open(idsFile, 'r') as f:
ids_to_keep = [seqid.strip() for seqid in f]
filt_seqs = bf.filter_by_id(seqs, ids_to_keep, False)
bf.write_as_fas(filt_seqs)
def loadFasta(fas_f, jid, dbName):
fas_d = bfas.fasta_2_dict(fas_f)
with sqlite3.connect(dbName) as conn:
c = conn.cursor()
for seqid in fas_d:
seq = fas_d[seqid]
c.execute(
'INSERT INTO seqs (jid, seqid, seq, len) VALUES (?,?,?,?)',
(jid, seqid, seq, len(seq)))
def fasta_stats(fasta, graphs_path=None):
seq_d = bfas.fasta_2_dict(fasta)
bfas.make_summary(seq_d, graphs_path)
def sample_fasta(fasta, nseq):
seq_d = bfas.fasta_2_dict(fasta)
seq_i = bfas.get_random_seqs(seq_d, nseq)
bfas.write_as_fas(seq_i)