def plot_dpgmm(args):
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """SELECT {0}.coverage, {0}.GC, {0}.length, {1}.cluster, {1}.probability
FROM {0}
INNER JOIN {1}
WHERE {0}.scaffold = {1}.scaffold
""".format(
db.ScaffoldsTable, db.DPGMMResultsTable
)
data = db.retrieve_data(sql_command)
db.close()
coverages = []
cgs = []
lengths = []
genera = []
for r in data:
if r["probability"] > args.dpgmm:
genera.append(r["cluster"])
else:
genera.append(defs.not_assigned)
coverages.append(r["coverage"])
cgs.append(r["GC"])
lengths.append(r["length"])
Plots.fig2(coverages, cgs, lengths, genera, args.fn_plot)
def plot_genus_assignments(args):
""" Draws a plot of the read coverage for the scaffolds vs their GC content
Each of the genera is assigned a color.
This new version assumes that the ScaffoldKmerComparisonTable
of final assignments has merged the results from ScaffoldsAssignmentsTable
(the scaffolds assigned with BLAST)
"""
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """SELECT {1}.scaffold, {1}.genus, {0}.length, {0}.GC, {0}.coverage
FROM {1}
INNER JOIN {0}
WHERE {1}.scaffold = {0}.scaffold
""".format(
db.ScaffoldsTable, db.ScaffoldKmerComparisonTable
)
data = db.retrieve_data(sql_command)
coverages = []
gcs = []
lengths = []
genera = []
for r in data:
coverages.append(r["coverage"])
gcs.append(r["GC"])
lengths.append(r["length"])
genera.append(r["genus"])
print "coverages", len(coverages), "gcs", len(gcs), "lengths", len(lengths), "genera", len(genera)
Plots.fig2(coverages, gcs, lengths, genera, args.fn_plot)
def plot_kmeans_clusters(args):
""" PLot of the genus assignments for each of the scaffolds
after performing k-means clustering
"""
log.info("Plotting the K-means clusters")
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """SELECT {0}.scaffold, {0}.coverage, {0}.GC, {0}.length, {1}.cluster
FROM {0}
INNER JOIN {1}
WHERE {0}.scaffold = {1}.scaffold
ORDER BY {0}.scaffold
""".format(
db.ScaffoldsTable, db.KmeansResultsTable
)
data = db.retrieve_data(sql_command)
db.close()
scaffolds = []
coverages = []
cgs = []
lengths = []
clusters = []
for r in data:
coverages.append(r["coverage"])
cgs.append(r["GC"])
lengths.append(r["length"])
clusters.append(r["cluster"])
Plots.fig2(coverages, cgs, lengths, clusters, args.fn_plot)
def plot_genus_assignments(args):
""" Draws a plot of the read coverage for the scaffolds vs their GC content
Each of the genera is assigned a color.
This new version assumes that the ScaffoldKmerComparisonTable
of final assignments has merged the results from ScaffoldsAssignmentsTable
(the scaffolds assigned with BLAST)
"""
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """SELECT {1}.scaffold, {1}.genus, {0}.length, {0}.GC, {0}.coverage
FROM {1}
INNER JOIN {0}
WHERE {1}.scaffold = {0}.scaffold
""".format(db.ScaffoldsTable, db.ScaffoldKmerComparisonTable)
data = db.retrieve_data(sql_command)
coverages = []
gcs = []
lengths = []
genera = []
for r in data:
coverages.append(r["coverage"])
gcs.append(r["GC"])
lengths.append(r["length"])
genera.append(r["genus"])
print "coverages", len(coverages), "gcs", len(gcs), "lengths", len(
lengths), "genera", len(genera)
Plots.fig2(coverages, gcs, lengths, genera, args.fn_plot)
def plot_kmeans_clusters(args):
""" PLot of the genus assignments for each of the scaffolds
after performing k-means clustering
"""
log.info("Plotting the K-means clusters")
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """SELECT {0}.scaffold, {0}.coverage, {0}.GC, {0}.length, {1}.cluster
FROM {0}
INNER JOIN {1}
WHERE {0}.scaffold = {1}.scaffold
ORDER BY {0}.scaffold
""".format(db.ScaffoldsTable, db.KmeansResultsTable)
data = db.retrieve_data(sql_command)
db.close()
scaffolds = []
coverages = []
cgs = []
lengths = []
clusters = []
for r in data:
coverages.append(r["coverage"])
cgs.append(r["GC"])
lengths.append(r["length"])
clusters.append(r["cluster"])
Plots.fig2(coverages, cgs, lengths, clusters, args.fn_plot)
def plot_kmeans_assignments(args):
""" PLot of the genus assignments for each of the scaffolds
after performing k-means clustering
"""
log.info("Plotting the K-means assignments")
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """ SELECT DISTINCT cluster FROM {0}
""".format(db.KmeansResultsTable)
data = db.retrieve_data(sql_command)
clusters = [r["cluster"] for r in data]
pairs_scaffold_genus = []
for cluster in clusters:
# Select the scaffolds assinged in the cluster, sum the
# bit scores of of each of the genera, and sort by the sum
sql_command = """ SELECT {0}.scaffold, {0}.genus, SUM({0}.bits)
FROM {0}
INNER JOIN {1}
WHERE cluster = {2} AND
{0}.scaffold = {1}.scaffold
GROUP BY {0}.genus
ORDER BY {0}.bits DESC
""".format(db.ScaffoldsAssignmentsTable,
db.KmeansResultsTable, cluster)
data = db.retrieve_data(sql_command)
# get the genus with the largest number of bits assigned is the
# first entry:
if len(data) == 0:
genus = defs.not_assigned
else:
genus = data[0]["genus"]
# Assign the genus to all the scaffolds in the cluster
sql_command = """ SELECT {0}.scaffold
FROM {0}
WHERE cluster = {1}
""".format(db.KmeansResultsTable, cluster)
data = db.retrieve_data(sql_command)
pairs_scaffold_genus.extend([(r["scaffold"], genus) for r in data])
pairs_scaffold_genus.sort()
sql_command = """SELECT {0}.scaffold, {0}.coverage, {0}.GC, {0}.length
FROM {0} ORDER BY scaffold
""".format(db.ScaffoldsTable)
data = db.retrieve_data(sql_command)
db.close()
if len(data) != len(pairs_scaffold_genus):
raise ValueError("The number of scaffolds in the database is not the " \
"same as the number of scaffolds assigned with k-means")
scaffolds = []
coverages = []
cgs = []
lengths = []
genera = []
for r, pair in zip(data, pairs_scaffold_genus):
coverages.append(r["coverage"])
cgs.append(r["GC"])
lengths.append(r["length"])
genera.append(pair[1])
Plots.fig2(coverages, cgs, lengths, genera, args.fn_plot)
def plot_dpgmm(args):
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """SELECT {0}.coverage, {0}.GC, {0}.length, {1}.cluster, {1}.probability
FROM {0}
INNER JOIN {1}
WHERE {0}.scaffold = {1}.scaffold
""".format(db.ScaffoldsTable, db.DPGMMResultsTable)
data = db.retrieve_data(sql_command)
db.close()
coverages = []
cgs = []
lengths = []
genera = []
for r in data:
if r["probability"] > args.dpgmm:
genera.append(r["cluster"])
else:
genera.append(defs.not_assigned)
coverages.append(r["coverage"])
cgs.append(r["GC"])
lengths.append(r["length"])
Plots.fig2(coverages, cgs, lengths, genera, args.fn_plot)
def plot_kmeans_assignments(args):
""" PLot of the genus assignments for each of the scaffolds
after performing k-means clustering
"""
log.info("Plotting the K-means assignments")
db = MetagenomeDatabase.MetagenomeDatabase(args.fn_database)
sql_command = """ SELECT DISTINCT cluster FROM {0}
""".format(
db.KmeansResultsTable
)
data = db.retrieve_data(sql_command)
clusters = [r["cluster"] for r in data]
pairs_scaffold_genus = []
for cluster in clusters:
# Select the scaffolds assinged in the cluster, sum the
# bit scores of of each of the genera, and sort by the sum
sql_command = """ SELECT {0}.scaffold, {0}.genus, SUM({0}.bits)
FROM {0}
INNER JOIN {1}
WHERE cluster = {2} AND
{0}.scaffold = {1}.scaffold
GROUP BY {0}.genus
ORDER BY {0}.bits DESC
""".format(
db.ScaffoldsAssignmentsTable, db.KmeansResultsTable, cluster
)
data = db.retrieve_data(sql_command)
# get the genus with the largest number of bits assigned is the
# first entry:
if len(data) == 0:
genus = defs.not_assigned
else:
genus = data[0]["genus"]
# Assign the genus to all the scaffolds in the cluster
sql_command = """ SELECT {0}.scaffold
FROM {0}
WHERE cluster = {1}
""".format(
db.KmeansResultsTable, cluster
)
data = db.retrieve_data(sql_command)
pairs_scaffold_genus.extend([(r["scaffold"], genus) for r in data])
pairs_scaffold_genus.sort()
sql_command = """SELECT {0}.scaffold, {0}.coverage, {0}.GC, {0}.length
FROM {0} ORDER BY scaffold
""".format(
db.ScaffoldsTable
)
data = db.retrieve_data(sql_command)
db.close()
if len(data) != len(pairs_scaffold_genus):
raise ValueError(
"The number of scaffolds in the database is not the "
"same as the number of scaffolds assigned with k-means"
)
scaffolds = []
coverages = []
cgs = []
lengths = []
genera = []
for r, pair in zip(data, pairs_scaffold_genus):
coverages.append(r["coverage"])
cgs.append(r["GC"])
lengths.append(r["length"])
genera.append(pair[1])
Plots.fig2(coverages, cgs, lengths, genera, args.fn_plot)