with open(ogfile, 'r') as f:
cluster_id = 0
for line in f:
cluster = filter(lambda s : s.isdigit(), re.split(r'[@\s]', line))
n = len(cluster)
hist[n] = hist.get(n, 0) + 1
if n >= 4:
nseqs += n
for seq_id in cluster:
database.execute("""
INSERT INTO homology (run_id, component_id, sequence_id)
VALUES (?,?,?);""",
(_run_id, cluster_id, seq_id))
cluster_id += 1
database.execute("COMMIT")
utils.info(
"histogram of gene cluster sizes:\n",
'\n '.join("%d\t:\t%d" % (k, hist[k]) for k in sorted(hist)))
diagnostics.log('nseqs', nseqs)
diagnostics.log('histogram', hist)
if __name__ == "__main__":
# Run the pipeline.
pipe.run()
# Push the local diagnostics to the global database.
diagnostics.merge()
