def test_weird_counts():
samples = {
"counts_A": "counts_A",
"counts_B": "counts_B",
"counts_C": "counts_C",
"counts_D": "counts_D",
"counts_E": "counts_E"
}
counts = pandas.read_table("./data/weird_counts.txt", sep="\t")
counts = counts.set_index("gene_id")
exp_obj = experiment.Experiment(counts, samples)
# DESeq normalization
deseq_norm = normalizers.norm_deseq(exp_obj)
# TMM normalization
tmm_norm = normalizers.norm_tmm(exp_obj)
# Compare results for one gene
g = "ENSMUSG00000020140"
print "DESeq results for %s" % (g)
print deseq_norm.ix[g]
print "=" * 10
print "TMM resutls for %s" % (g)
print tmm_norm.ix[g]
# fold difference in counts for sample C
print "Fold difference in sample C (TMM / DESeq): %.4f" \
%(tmm_norm.ix[g]["counts_C"] / deseq_norm.ix[g]["counts_C"])
# fold relative difference in counts, comparing A to C
tmm_A_vs_C = tmm_norm.ix[g]["counts_A"] / tmm_norm.ix[g]["counts_C"]
deseq_A_vs_C = deseq_norm.ix[g]["counts_A"] / deseq_norm.ix[g]["counts_C"]
print "TMM fold change A vs. C: %.2f" % (tmm_A_vs_C)
print "DESeq fold change A vs. C: %.2f" % (deseq_A_vs_C)
def test_weird_counts():
samples = {"counts_A": "counts_A",
"counts_B": "counts_B",
"counts_C": "counts_C",
"counts_D": "counts_D",
"counts_E": "counts_E"}
counts = pandas.read_table("./data/weird_counts.txt", sep="\t")
counts = counts.set_index("gene_id")
exp_obj = experiment.Experiment(counts, samples)
# DESeq normalization
deseq_norm = normalizers.norm_deseq(exp_obj)
# TMM normalization
tmm_norm = normalizers.norm_tmm(exp_obj)
# Compare results for one gene
g = "ENSMUSG00000020140"
print "DESeq results for %s" %(g)
print deseq_norm.ix[g]
print "=" * 10
print "TMM resutls for %s" %(g)
print tmm_norm.ix[g]
# fold difference in counts for sample C
print "Fold difference in sample C (TMM / DESeq): %.4f" \
%(tmm_norm.ix[g]["counts_C"] / deseq_norm.ix[g]["counts_C"])
# fold relative difference in counts, comparing A to C
tmm_A_vs_C = tmm_norm.ix[g]["counts_A"] / tmm_norm.ix[g]["counts_C"]
deseq_A_vs_C = deseq_norm.ix[g]["counts_A"] / deseq_norm.ix[g]["counts_C"]
print "TMM fold change A vs. C: %.2f" %(tmm_A_vs_C)
print "DESeq fold change A vs. C: %.2f" %(deseq_A_vs_C)
def test_tmm():
"""
Calls TMM normalization. Prints raw counts then normed counts.
"""
counts_fname = utils.load_testdata("pasilla")
# Consider only a subset of the samples
samples = OrderedDict()
samples["Untreated 1"] = "untreated1"
samples["Untreated 2"] = "untreated2"
exp_obj = experiment.Experiment(counts_fname, samples)
norm_counts_df = normalizers.norm_tmm(exp_obj)
print "\nTMM Testing:"
print "--------------"
print "Pre-normalized counts: "
print exp_obj.counts_df.head()
print "Normalized counts: "
print norm_counts_df.head()
def test_tmm():
"""
Calls TMM normalization. Prints raw counts then normed counts.
"""
counts_fname = utils.load_testdata("pasilla")
# Consider only a subset of the samples
samples = OrderedDict()
samples["Untreated 1"] = "untreated1"
samples["Untreated 2"] = "untreated2"
exp_obj = experiment.Experiment(counts_fname, samples)
norm_counts_df = normalizers.norm_tmm(exp_obj)
print("\nTMM Testing:")
print("--------------")
print("Pre-normalized counts: ")
print(exp_obj.counts_df.head())
print("Normalized counts: ")
print(norm_counts_df.head())
def test_quantile_vs_tmm():
"""
Test quantile normalization versus TMM
in rank correlation of genes.
"""
counts_fname = utils.load_testdata("pasilla")
# Consider only a subset of the samples
samples = OrderedDict()
samples["Untreated 1"] = "untreated1"
samples["Untreated 2"] = "untreated2"
exp_obj = experiment.Experiment(counts_fname, samples)
quantile_counts_df = normalizers.norm_q(exp_obj)
tmm_counts_df = normalizers.norm_tmm(exp_obj)
print("\nQuantile versus TMM Testing:")
print("--------------")
print("Normalized quantile counts: ")
print(quantile_counts_df.head())
print("Normalized TMM counts: ")
print(tmm_counts_df.head())
print("Correlating the genes.")
# Merge the dataframes together, indexing by gene
combined_df = pandas.merge(quantile_counts_df,
tmm_counts_df,
left_index=True,
right_index=True,
suffixes=["_q", "_tmm"],
how="outer")
# Get log of counts: get rid of infinite values
log_counts_df = combined_df.apply(np.log2).replace([-np.inf, np.inf],
np.nan)
print("Combined dataframe: ")
print(combined_df.head())
print("Combined log dataframe: ")
print(log_counts_df.head())
# Plot correlation
from pandas.tools.plotting import scatter_matrix
scatter_matrix(log_counts_df, alpha=0.2, figsize=(8, 7))
plot_utils.save_fig("quantile_vs_tmm_corr", ext="png")
sys.stderr.write("Test quantile vs tmm done!\n")
def test_quantile_vs_tmm():
"""
Test quantile normalization versus TMM
in rank correlation of genes.
"""
counts_fname = utils.load_testdata("pasilla")
# Consider only a subset of the samples
samples = OrderedDict()
samples["Untreated 1"] = "untreated1"
samples["Untreated 2"] = "untreated2"
exp_obj = experiment.Experiment(counts_fname, samples)
quantile_counts_df = normalizers.norm_q(exp_obj)
tmm_counts_df = normalizers.norm_tmm(exp_obj)
print "\nQuantile versus TMM Testing:"
print "--------------"
print "Normalized quantile counts: "
print quantile_counts_df.head()
print "Normalized TMM counts: "
print tmm_counts_df.head()
print "Correlating the genes."
# Merge the dataframes together, indexing by gene
combined_df = pandas.merge(quantile_counts_df, tmm_counts_df,
left_index=True,
right_index=True,
suffixes=["_q", "_tmm"],
how="outer")
# Get log of counts: get rid of infinite values
log_counts_df = combined_df.apply(np.log2).replace([-np.inf, np.inf],
np.nan)
print "Combined dataframe: "
print combined_df.head()
print "Combined log dataframe: "
print log_counts_df.head()
# Plot correlation
from pandas.tools.plotting import scatter_matrix
scatter_matrix(log_counts_df, alpha=0.2, figsize=(8, 7))
plot_utils.save_fig("quantile_vs_tmm_corr", ext="png")
