def output_counts(end_function, count_file):
# if the count_file already exists, skip
outdir = os.path.join(config["dir"]["results"], stage)
safe_makedir(outdir)
count_file = os.path.join(outdir, count_file)
if os.path.exists(count_file):
return count_file
# outputs a tab file of the counts at the end
# of the fastq files kj
counts = [reduce(count_ends,
apply_seqio(x, end_function, kind="fastq"),
{}) for x in curr_files]
df = pd.DataFrame(counts,
index=map(_short_name, curr_files))
df = df.astype(float)
total = df.sum(axis=1)
df = df.div(total, axis=0)
df["total"] = total
df.to_csv(count_file, sep="\t")
def _trim(fasta_file, input_files):
# make dictionary of all sequence ids in them
# if a sequence file isnt in the dictionary add it and its begin/end/length
# if it is already and the length in the dictionary is shorter than the
d = _make_length_dict(input_files)
def trim_function(x, d):
new_seq = x
entry = d[x.id]
start = int(entry["qstart"])
end = int(entry["qend"])
new_seq.seq = x.seq[start:end]
return new_seq
out_file = append_stem(fasta_file, "trimmed")
out_handle = open(out_file, "w")
def output_writer(x):
return SeqIO.write(x, out_handle, "fasta")
map(output_writer,
fasta.apply_seqio(fasta_file, partial(trim_function, d=d), "fasta"))
return out_file
def _make_combined_csv(fasta_file, input_files, org_names, out_file=None):
"""
takes a list of output files from blastn and a fasta file and attaches
the columns jagesh wants all into one big data frame and writes it out
"""
suffixes = map(lambda x: "_" + x, org_names)
# columns to keep
TO_KEEP = list(flatten(["qseqid", map(lambda x: "sseqid" + x, suffixes),
map(lambda x: "evalue" + x, suffixes),
map(lambda x: "length" + x, suffixes),
map(lambda x: "pident" + x, suffixes),
map(lambda x: "sstart" + x, suffixes),
map(lambda x: "send" + x, suffixes)]))
# read inputs as tables and merge into one big table
inputs = zip(suffixes, map(pd.read_table, input_files))
dfs = [inp[1].rename(columns=lambda name: name + inp[0]) for inp in inputs]
d = {}
for x in suffixes:
d["qseqid" + x] = "qseqid"
renamed = [x.rename(columns=d) for x in dfs]
merged = reduce(lambda x, y: pd.merge(x, y, on="qseqid"),
renamed[1:], renamed[0])
df_subset = merged[TO_KEEP]
# add the sequence from the fasta file
seqs = pd.DataFrame(fasta.apply_seqio(
fasta_file, lambda x: {'qseqid': x.id, 'seq': str(x.seq)},
"fasta"))
merged = pd.merge(df_subset, seqs, on="qseqid")
merged.to_csv(out_file, index=False, sep="\t")
return out_file
def _make_combined_csv(fasta_file, input_files, org_names, out_file=None):
"""
takes a list of output files from blastn and a fasta file and attaches
the columns jagesh wants all into one big data frame and writes it out
"""
suffixes = map(lambda x: "_" + x, org_names)
# columns to keep
TO_KEEP = list(flatten(["qseqid", map(lambda x: "sseqid" + x, suffixes),
map(lambda x: "evalue" + x, suffixes),
map(lambda x: "length" + x, suffixes),
map(lambda x: "pident" + x, suffixes),
map(lambda x: "sstart" + x, suffixes),
map(lambda x: "send" + x, suffixes)]))
# read inputs as tables and merge into one big table
inputs = zip(suffixes, map(pd.read_table, input_files))
dfs = [inp[1].rename(columns=lambda name: name + inp[0]) for inp in inputs]
d = {}
for x in suffixes:
d["qseqid" + x] = "qseqid"
renamed = [x.rename(columns=d) for x in dfs]
merged = reduce(lambda x, y: pd.merge(x, y, on="qseqid"),
renamed[1:], renamed[0])
df_subset = merged[TO_KEEP]
# add the sequence from the fasta file
seqs = pd.DataFrame(fasta.apply_seqio(
fasta_file, lambda x: {'qseqid': x.id, 'seq': str(x.seq)},
"fasta"))
merged = pd.merge(df_subset, seqs, on="qseqid")
merged.to_csv(out_file, index=False, sep="\t")
return out_file
